The Robot Report editorial director Eugene Demaitre recently returned from the R-24 international robotics event in Odense, Denmark. From this trip, he immediately headed out to San Jose, Calif., to attend NVIDIA GTC 2024 with senior editor Mike Oitzman.

In this episode, Gene and Mike talk about what Gene saw and learned during his latest visit to Odense. From there, the co-hosts discuss their experiences at the GTC event, and all of the interesting sessions on artificial intelligence and robotics, NVIDIA’s product announcements for robotics, and the demonstrations by vendors that exhibited on the busy show floor.

R-24: Robots, Automation, and Drones

• Odense Robotics is one of the largest robotics clusters in the world, with 350 members across Denmark, about half of which are in the Odense area.
• It employs about 18,000 people, with plans to double that over the next decade. Local leaders attributed that to a culture of collaboration.
• Among the interesting things the international delegations saw around R-24 was Odense Port, which is now building giant wind turbines in addition to maintaining container ships.
• They also visited the drone test center at the Hans Christian Andersen Airport; the Danish Technological Institute, which hosts the Odense Robotics Startup Fund; and the Maersk-McKinney Moller Institute at the University of Southern Denmark, as well as Universal Robots headquarters.
• Odense is also hosting ROSCon later this year.

Highlights from NVIDIA GTC 2024

In addition to CEO Jensen Huang’s keynote, here are some highlights from NVIDIA‘s latest GPU Technology Conference:

New foundation for humanoid robotics

The big news from the robotics side of the house was that NVIDIA launched a new general-purpose foundation model for humanoid robots called Project GR00T. This new model is designed to bring robotics and embodied AI together while enabling the robots to understand natural language and emulate movements by observing human actions.

GR00T uses the new Jetson Thor

As part of its robotics announcements, NVIDIA unveiled Jetson Thor for humanoid robots, based on the NVIDIA Thor system-on-a-chip (SoC). Significant upgrades to the NVIDIA Isaac robotics platform include generative AI foundation models and tools for simulation and AI workflow infrastructure.

The Thor SoC includes a next-generation GPU based on NVIDIA Blackwell architecture with a transformer engine delivering 800 teraflops of 8-bit floating-point AI performance. With an integrated functional safety processor, a high-performance CPU cluster, and 100GB of Ethernet bandwidth, it can simplify design and integration efforts, claimed the company.

NVIDIA updates Isaac simulation platform

The Isaac tools that GR00T uses are capable of creating new foundation models for any robot embodiment in any environment, according to NVIDIA. Among these tools are Isaac Lab for reinforcement learning, and OSMO, a compute orchestration service.

NVIDIA DRIVE Thor for robot axis

The company also announced NVIDIA DRIVE Thor, which now supersedes NVIDIA DRIVE Orin as a SoC for autonomous driving applications.

Other notable sessions (worth watching the replays):

• Geordie Rose, CEO of Sanctuary: “Using Omniverse to generate first-person experiential data for humanoid robots”
• Aaron Saunders, chief technology officer of Boston Dynamics: “Deploying AI in real-world robots”
• Vincent Vanhouke, senior director of robotics at Google Deepmind: “Robotics in the age of GenAI”

Interesting robots seen at GTC24:

• Agility DIGIT (static)
• Apptronik Apollo (static)
• Unitree H1
• 1X Eve
• Fourier Analysis – GR1
• Disney BD-X droids
• ANYbotics ANYmal
• Enchanted Tools Mirokai
• Richtech Robotics ADAM

The post GTC 2024 and R-24 recap appeared first on The Robot Report.

The Robotics Factory is dedicated to creating, accelerating, and scaling Pittsburgh-area startups. | Source: Robotics Factory

The Robotics Factory has accepted five companies to its Scale Residency program. The Innovation Works and Pittsburgh Robotics Network initiative is dedicated to creating, accelerating, and scaling robotics companies in the Pittsburgh region.

ESTAT Actuation, KEF Robotics, Thiopoly, Thorne Baby, and Piximo make up the organization‘s first residency cohort. The Robotics Factory will provide these five companies with one year of access to its facilities in the Tech Forge building in Lawrenceville, Pa., part of “Robotics Row.”

“The Scale program helps these companies grow from concept to commercialization,” stated Kevin Dowling, managing director of the Robotics Factory. “Our staff of engineers and entrepreneurs offers guidance to these budding startups, all of which have found a fit in their respective markets and further solidify this region as a global robotics hub.”

In addition to the Robotics Factory’s facilities, the organization will provide hands-on support, access to cutting-edge tools, grant funding, connections to local manufacturers, and educational resources to support rapid prototyping and production. Pittsburgh is home to more than 100 robotics companies, so the participants will have access to a wide range of local resources, noted the organization.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Meet the Start program’s pilot projects

The Robotics Factory’s pilot cohort of the Scale program covers a wide range of capabilities. ESTAT Actuation creates electro-adhesive clutches and brakes that it said are 10 times lighter, 10 times more compact, and 1,000 times more efficient than conventional hardware. The company spun out from Carnegie Mellon University in 2019.

KEF Robotics, the second startup in the program, provides state-of-the-art autonomy software to fly pilotless aircraft. Founded in 2018, the computer vision company said its algorithms use cameras to ensure autonomous flights across various platforms.

Next, Thorne Baby produces a play yard that opens automatically with no assembly required. The company created its product for easy in-home mobility and on-the-go portability.

Thiopoly develops an accurate physical library of medications to ensure highly accurate dispensing systems. Finally, Piximo constructs mobile minimarts operated by remote drivers and provides production scalability.

While in the residency program, company employees can get training in designing products for manufacturability by creating functional prototypes. The Robotics Factory will connect them with suitable manufacturers in the Pittsburgh region, enabling them to expand their supply chains and enhance production scalability.

The Scale residency program is funded through a $63 million Build Back Better Regional Challenge grant awarded to the Southwestern Pennsylvania New Economy Collaborative. The Robotics Factory also runs the Accelerate program, which aims to foster the next generation of robotics startups in Pittsburgh. 

The post Robotics Factory adds five startups to its residency pilot cohort appeared first on The Robot Report.

Locus Lock is designing RF systems to provide navigational security. Source: Locus Lock

Flying back from Miami last week, I put my life in the hands of two strangers, just because they wore gold epaulets. These commercial pilots, in turn, trusted their onboard computers to safely navigate the passengers home. The computers accessed satellite data from the Global Positioning System to set the course.

This chain of command is very fragile. The International Air Transport Association (IATA) reported last month an increased level of GPS spoofing and signal jamming since the outbreak of the wars in Ukraine and Israel. This poses the threat of catastrophe to aviators everywhere.

For example, last September, OPS Group reported that a European flight en route to Dubai almost entered into Iranian airspace without clearance. In 2020, Iran shot down an uncleared passenger aircraft that entered its territory. This has made the major airlines, avionics manufacturers, and NATO militaries and governments scramble to find solutions.

Navigational errors can be very dangerous for commercial aircraft. Source: OPS Group

Locus Lock founder came out of drone R&D

At ff Venture Capital, we recognize that GPS spoofing and jamming are fundamental problems for aerial, terrestrial, and marine autonomous systems in moving the industry forward. This investment thesis is grounded on a simple belief that the deployment of cost-effective uncrewed systems requires the trust of human operators who can’t afford to question the data.

When machines go awry, so does the industry. Just ask Cruise! This conviction led us to invest in Locus Lock. The company said it is taking an innovative software approach to GNSS signal processing using radio frequency, at a fraction of the cost of comparable hardware sold by military contractors.

Last week, I sat down with Locus Lock founder Hailey Nichols, a former University of Texas researcher in the school’s Radionavigation Laboratory. UT’s Lab is best known for its work with SpaceX and Starlink.

At Aurora, Nichols focused on integrating suites of sensors such as lidar, GPS, radar, and computer vision for uncrewed aerial vehicles (UAVs). However, she quickly became frustrated with the costs and quality of the sensors.

“They were physically heavy [and] power-intensive, and it made it quite hard for engineers to integrate,” she recalled. “This problem frustrated me so much that I went back to grad school to study it further, and I joined a lab down at the University of Texas.”

In Austin, the roboticist saw a different approach to sensor data, using software for signal processing.

“The radio navigation lab was very highly specialized in signal processing, specifically bringing in advanced software algorithms and robust estimation techniques forward to sensor technology,” explained Nichols. “This enabled more precise, secure, and reliable data, like positioning, navigation, and timing.”

Her epiphany came when she saw the market demand for the lab’s GNSS receiver from the U.S. Department of Defense and commercial partners after Locus Lock published research on autonomous vehicles accurately navigating urban canyons.

Navigating urban canyons is a challenge for conventional satellite-based systems. Source: Quora

Reliable navigation needed for dual-use applications

Today, Locus Lock is ready to market its product more widely for dual-use applications across the spectrum of autonomy for commercial and defense use cases.

“Current GPS receivers often fail in what’s called ‘urban multipath,'” said Nichols. “This is where there’s building interference and shrouding of the sky can cause positioning errors. This can be problematic for autonomous cars, drones, and outdoor robotics that need access to centimeter-level positioning to make safe and informed decisions about where they are on the road or in the sky.”

The RF engineer continued: “Our other applicable industry is defense tech. With the rise of the Ukraine conflict and the Israel conflict in the Middle East, we’ve seen a massive amount of deliberate interference. So bad actors that are either spoofing or jamming, causing major outages or disruptions in GPS positioning.”

Locus Lock addresses this problem by enabling its GPS processing suite as a software solution, and unlike hardware, it’s affordable and extremely flexible.

“The ability to be backward-compatible and future-proof where we can constantly update and evolve our GPS processing suite to evolving attack vectors ensures that our customers are given the most cutting-edge and up-to-date processing techniques to enable centimeter-level positioning globally,” added Nichols.

“So our GNSS receivers are software-defined radio [SDR] with a specialized variant of inertially aided RTK [real-time kinematics],” she said, claiming that it provides a differentiator from competing products. “What that means is we’re doing some advanced sensor-fusion techniques with GNSS signals in addition to inertial navigation to ensure that, even in these pockets of urban canyons where you may not have access to GNSS signals … the GPS receiver [will] still provide centimeter-level positioning.”

As Nichols boasted, Locus Lock is an enabler of “next generation autonomous mobility.”

Locus Lock looks to affordable centimeter-level accuracy

While traditional GPS components cost around $40,000, Locus Lock said its its proprietary software and a 2-in. board cost around $2,000. Today, centimeter accuracy is inaccessible to most robot companies because most suppliers of robust hardware are military contractors, including L3Harris Technologies, BAE Systems, Northrop Grumman, and Elbit Systems.

“We’ve specifically made sure to cater our solution towards more low-cost environments that can proliferate mass-market autonomy and robotics into the ecosystem,” stated Nichols.

Locus Lock puts its software on a 2-in. board. Source: Oliver Mitchell

Nichols added that Locus Lock’s GNSS receiver is able to pull in data from global and regional satellite constellations.

“[This gives] us more access to any signals in the sky at any given time,” said the startup founder. “Diversity is also increasingly important in next-generation GPS receivers because it allows the device to evade jammed or afflicted channels.”

Grand View Research estimated that the SDR market will climb to nearly $50 billion by 2030. As uncrewed systems proliferate, Locus Lock’s price point should also come down, asserted Nichols.

“And while there are some companies that have progressed their autonomy stacks to be quite high, they haven’t gotten their prices down to make sense in a mass-market scenario,” she said. “And so it’s crucial to enable this next generation of autonomous mobility at large to not compromise on performance but to be able to provide this at an affordable price. Locus Lock is providing high-end performance at a much lower price point.”

Nichols even predicted that the company could eventually get product to under $1,000, if not less, with more adoption.

Source: Grand View Research

Tesla Optimus takes steps toward more mobile systems

Yesterday, Tesla published on X the latest video of its Optimus humanoid moving fluidly at an incredible gait for a robot. Pitchbook recently predicted that this could be a breakout period for humanoids, with 84 leading companies now having raised over $4.6 billion.

Tesla’s Optimus Robot Achieves New Milestones in Mobility and Task Efficiency

Advanced Mobility Showcased:
Tesla’s latest clip of the Optimus humanoid robot demonstrates significant advancements in fluid mobility, as the robot is seen taking smooth strides within a testing… pic.twitter.com/hMlq2w3tQ7

— Tesla Pablo (@pablo9948967714) February 25, 2024

At the same time, the prospect of such advanced machines being hijacked via GPS spoofing into the service of terrorists, cybercriminals, or hostile governments is very real and horrifying. Thankfully, Nichols and her team are working with the Army Futures Command.

“A lot of this work has been done in spoofing and jamming — not only detection, but also mitigation,” she said. “We detect the type of RF environment that we are operating in to mitigate it and inform that end user with the situational awareness that is needed to assess ongoing attacks.”

“In addition, we can iterate much faster and bring in world-class experts on security and encryption to ensure that we protect secure military signals as much as possible,” said Nichols. “Our software can find assured reception that is demanded by these increasingly expensive and important assets that the military needs to protect.”

In ffVC’s view, our newest portfolio company is mission-critical to operating drones, robots, and other autonomous vessels safely, affordably, and securely in an increasingly dangerous world.

The post Locus Lock promises to protect autonomous systems from GPS spoofing appeared first on The Robot Report.

In late 2019, after years of studying aviation and aerospace engineering, Hector (Haofeng) Xu decided to learn to fly helicopters. At the time, he was pursuing his PhD in MIT’s Department of Aeronautics and Astronautics, so he was familiar with the risks associated with flying small aircraft. But something about being in the cockpit gave Xu a greater appreciation of those risks. After a couple of nerve-wracking experiences, he was inspired to make helicopter flight safer.

In 2021, he founded the autonomous helicopter company Rotor Technologies, Inc.

It turns out Xu’s near-misses weren’t all that unique. Although large, commercial passenger planes are extremely safe, people die every year in small, private aircraft in the U.S. Many of those fatalities occur during helicopter flights for activities like crop dusting, fighting fires, and medical evacuations.

Rotor is retrofitting existing helicopters with a suite of sensors and software to remove the pilot from some of the most dangerous flights and expand use cases for aviation more broadly.

“People don’t realize pilots are risking their lives every day in the U.S.,” Xu explained. “Pilots fly into wires, get disoriented in inclement weather, or otherwise lose control, and almost all of these accidents can be prevented with automation. We’re starting by targeting the most dangerous missions.”

Rotor’s autonomous machines are able to fly faster and longer and carry heavier payloads than battery powered drones, and by working with a reliable helicopter model that has been around for decades, the company has been able to commercialize quickly. Rotor’s autonomous aircraft are already taking to the skies around its Nashua, New Hampshire, headquarters for demo flights, and customers will be able to purchase them later this year.

“A lot of other companies are trying to build new vehicles with lots of new technologies around things like materials and power trains,” said Ben Frank ’14, Rotor’s chief commercial officer. “They’re trying to do everything. We’re really focused on autonomy. That’s what we specialize in and what we think will bring the biggest step-change to make vertical flight much safer and more accessible.”

Building a team at MIT

As an undergraduate at Cambridge University, Xu participated in the Cambridge-MIT Exchange Program (CME). His year at MIT apparently went well — after graduating Cambridge, he spent the next eight years at the Institute, first as a PhD student, then a postdoc, and finally as a research affiliate in MIT’s Department of Aeronautics and Astronautics (AeroAstro), a position he still holds today. During the CME program and his postdoc, Xu was advised by Professor Steven Barrett, who is now the head of AeroAstro. Xu said Barrett has played an important role in guiding him throughout his career.

“Rotor’s technology didn’t spin out of MIT’s labs, but MIT really shaped my vision for technology and the future of aviation,” Xu said.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Xu’s first hire was Rotor Chief Technology Officer Yiou He SM ’14, PhD ’20, whom Xu worked with during his PhD. The decision was a sign of things to come: The number of MIT affiliates at the 50-person company is now in the double digits.

“The core tech team early on was a bunch of MIT PhDs, and they’re some of the best engineers I’ve ever worked with,” Xu said. “They’re just really smart and during grad school they had built some really fantastic things at MIT. That’s probably the most critical factor to our success.”

To help get Rotor off the ground, Xu worked with the MIT Venture Mentoring Service (VMS), MIT’s Industrial Liaison Program (ILP), and the National Science Foundation’s New England Innovation Corps (I-Corps) program on campus.

A key early decision was to work with a well-known aircraft from the Robinson Helicopter Company rather than building an aircraft from scratch. Robinson already requires its helicopters to be overhauled after about 2,000 hours of flight time, and that’s when Rotor jumps in.

The core of Rotor’s solution is what’s known as a “fly by wire” system — a set of computers and motors that interact with the helicopter’s flight control features. Rotor also equips the helicopters with a suite of advanced communication tools and sensors, many of which were adapted from the autonomous vehicle industry.

Rotor Technologies retrofits its autonomy stack onto existing helicopters. | Credit: Rotor Technologies

“We believe in a long-term future where there are no longer pilots in the cockpit, so we’re building for this remote pilot paradigm,” Xu said. “It means we have to build robust autonomous systems on board, but it also means that we need to build communication systems between the aircraft and the ground.”

Rotor is able to leverage Robinson’s existing supply chain, and potential customers are comfortable with an aircraft they’ve worked with before — even if no one is sitting in the pilot seat. Once Rotor’s helicopters are in the air, the startup offers 24/7 monitoring of flights with a cloud-based human supervision system the company calls Cloudpilot. The company is starting with flights in remote areas to avoid risk of human injury.

“We have a very careful approach to automation, but we also retain a highly skilled human expert in the loop,” Xu said. “We get the best of the autonomous systems, which are very reliable, and the best of humans, who are really great at decision-making and dealing with unexpected scenarios.”

Autonomous helicopters take off

Using small aircraft to do things like fight fires and deliver cargo to offshore sites is not only dangerous, it’s also inefficient. There are restrictions on how long pilots can fly, and they can’t fly during adverse weather or at night.

Most autonomous options today are limited by small batteries and limited payload capacities. Rotor’s aircraft, named the R550X, can carry loads up to 1,212 pounds, travel more than 120 miles per hour, and be equipped with auxiliary fuel tanks to stay in the air for hours at a time.

Some potential customers are interested in using the aircraft to extend flying times and increase safety, but others want to use the machines for entirely new kinds of applications.

“It is a new aircraft that can do things that other aircraft couldn’t — or maybe even if technically they could, they wouldn’t do with a pilot,” Xu said. “You could also think of new scientific missions enabled by this. I hope to leave it to people’s imagination to figure out what they can do with this new tool.”

Rotor plans to sell a small handful of aircraft this year and scale production to produce 50 to 100 aircraft a year from there.

Meanwhile, in the much longer term, Xu hopes Rotor will play a role in getting him back into helicopters and, eventually, transporting humans.

“Today, our impact has a lot to do with safety, and we’re fixing some of the challenges that have stumped helicopter operators for decades,” Xu said. “But I think our biggest future impact will be changing our daily lives. I’m excited to be flying in safer, more autonomous, and more affordable vertical take-off and-landing aircraft, and I hope Rotor will be an important part of enabling that.”

Editor’s Note: This article was republished with permission from MIT News.

The post Rotor Technologies propels advances in autonomous helicopters appeared first on The Robot Report.

The Ingenuity helicopter achieved much in its nearly three years on Mars. | Source: NASA/JPL-Caltech

The Ingenuity helicopter, the first ever aircraft to fly on another planet, ended its nearly three-year journey on Mars, said NASA yesterday. The helicopter, originally intended as a technology demonstration, has surpassed all of NASA’s expectations and completed dozens more flights than originally planned. 

While the Ingenuity remains upright and in communication with ground controllers, it will not be able to fly again. NASA received images of its Jan. 18 flight this week showing that one or more of its rotor blades had sustained damage during landing, making the helicopter no longer capable of flight. 

“The historic journey of Ingenuity, the first aircraft on another planet, has come to end,” said NASA Administrator Bill Nelson in a release. “That remarkable helicopter flew higher and farther than we ever imagined and helped NASA do what we do best – make the impossible, possible. Through missions like Ingenuity, NASA is paving the way for future flight in our solar system and smarter, safer human exploration to Mars and beyond.”

On Jan. 18, Ingenuity’s team planned for the helicopter to make a short vertical flight to determine its location. The helicopter had executed an emergency landing on its previous flight, leaving NASA’s engineers unsure of exactly where it touched ground. 

NASA’s data shows that, as it had planned, the helicopter rose to a maximum height of 40 ft. (12 m) and hovered for 4.5 seconds before starting its descent at a velocity of 3.3 feet per second (1 meter per second). At about 3 ft. (1 m) above the Martian surface, Ingenuity lost communication with the Perseverance rover, which serves as a communications relay for the helicopter. 

Ingenuity’s team reestablished communications with the helicopter the following day, and NASA Jet Propulsion Laboratory (JPL) was able to gather more information about the flight. Several days later, new images showed that a rotor blade had been damaged.

The team is still investigating the cause of the communications dropout and the helicopter’s orientation when it touched down.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Ingenuity survived the journey to Mars

When Ingenuity started its journey on Mars, strapped to the belly of the Perseverance rover, NASA hoped it would perform at least five experimental test flights over 30 days. It first lifted off the Martian surface on April 19, 2021, proving that powered, controlled flight on another planet was possible. It was not designed to carry payloads or execute other missions.

After completing its initial mission, Ingenuity became an operations demonstration. During this phase, it served as an aerial scout for Perseverance scientists and rover drivers. In 2023, the helicopter expanded NASA‘s knowledge of its aerodynamic limits when it completed two successful flight tests. 

“At NASA JPL, innovation is at the heart of what we do,” stated Laurie Leshin, director of NASA JPL. “Ingenuity is an exemplar of the way we push the boundaries of what’s possible every day. I’m incredibly proud of our team behind this historic technological achievement and eager to see what they’ll invent next.”

Helicopter pushed the boundaries of flight on Mars

In the end, Ingenuity’s mission lasted almost 1,000 sols (Martian days or 24 hours, 39 minutes, 35 seconds), more than 33 times longer than NASA originally planned. Because of this, Ingenuity’s team had to constantly innovate to keep the helicopter running as long as possible. 

While on Mars, Ingenuity was upgraded with the ability to autonomously choose landing sites in treacherous terrain. It also dealt with dead sensors, cleaned itself after dust storms, operated from 48 different airfields, performed three emergency landings, and survived a Marian winter. 

The helicopter was only designed to survive during spring. To keep it running through the coldest parts of winter, Ingentity powered its heaters throughout the night. This, however, caused the flight computer to periodically freeze and reset. These power “brownouts,” as NASA called them, pushed the team to redesign Ingenuity’s winter operations to keep it up and running. 

In its nearly three years on Mars, the Ingenuity helicopter performed 72 flights, flew more than 14 times farther than planned, and logged more than two hours of total flight time. 

Now that flight operations have concluded, the Ingenuity team will perform final tests on the helicopter’s systems and download the remaining imagery and data in Ingenuity’s onboard memory. Right now, the Perseverance rover is too far away for it to capture images of the helicopter at its final airfield. 

The post After 72 flights, NASA says goodbye to Ingenuity helicopter appeared first on The Robot Report.

Wing Aviation LLC, the commercial drone delivery segment of Google parent Alphabet Inc., recently obtained Federal Aviation Administration, or FAA, exemptions to support its “fast-mile deliveries.” The company claimed that the updated exemptions for its detect-and-avoid approach open the door for it to safely scale in the U.S. 

The company first earned its Air Carrier Certification from the FAA in 2019. With that certification, Wing has begun a commercial drone service delivering goods from local businesses to homes in the U.S.

“Wing has had its regulatory approval since 2019,” Shannon Nash, the chief financial officer of Wing, told The Robot Report. “This is not new for us, this is expanding.” 

This latest expansion allows the company to continue beyond visual line-of-sight (BVLOS) operations without visual observers, something Wing has already been doing in Australia and Ireland. 

“What this [grant] provides is the framework to not only still allow us to fly beyond visual line of sight, but also remove what are called visual observers,” said Justin Shore, chief of staff for public policy and government affairs at Wing. “So we have a couple of visual observers throughout the Dallas-Fort Worth area and city that are really just looking at the airspace above them and making sure there’s no crewed traffic that is there right at that time.” 

Wing’s drones will use its Automatic Dependent Surveillance-Broadcast-based (ADS-B) detection and avoidance (DAA) system inside a portion of Dallas airspace where traditional aircraft must continually broadcast their positions. The company said the expansion also enables it to deploy in similar airspace surrounding other major U.S. cities. 

“At the end of the day, this new summary grant that we’re getting from the FAA just allows us to be more efficient and be able to pass that on to the consumer down the line, as we can expand,” Shore said. 

Wing takes holistic approach to BVLOS flights

Wing said designed its drone delivery system to integrate into existing last-mile logistics services in urban and suburban areas. The company added that its drones fly in underutilized airspace over populated areas.

Wing asserted that its holistic approach to the BVLOS flights has led to successful commercial deliveries on three continents for several years now. 

In the U.S., Wing works with FedEx Express and Walgreens in Virginia, and with Walmart in Texas. When a customer orders an item to be delivered by drone, employees at the relevant store package the order.

Next, a Wing drone picks up the order in designated spots, so stores don’t need to add infrastructure, other than Wing’s Autoloaders.

“When you think about a partner like Walmart, they already have processes in terms of how they get the goods outside of the store and deliver it,” Nash said. “You think of curbside pickup, and we saw the advent of that during COVID-19. So we aimed to not disrupt those processes of our customers.” 

Drone deliveries leave the ‘nest’

Wing’s drones live in what the company calls “nests,” and they travel from the nearest nest to the store to pick up orders. Once the drone gets to the store, it picks up the items from Wing’s Autoloader.

“What the Autoloader does is it basically allows the person that we call the ‘pick packer’ who comes out of the store to load [the order] into the Autoloader and leave,” Nash said. “So then the drone can come and pick it up from the Autoloader and take off.” 

The drones fly completely autonomously, according to Nash. No operators fly them remotely, but they are monitored to ensure they get to their destinations safely. 

“It’s fast delivery. In general, it’s under 30 minutes,” Nash said. “You see a lot of our deliveries in that 10-minute time frame. In fact, our fastest delivery was just under 3 minutes.” 

Customers can track their orders in real time on their phones using the Wing app. When the drone gets to the customer’s residence, it lowers the order using a tether and unclips the package. Once the order is fully unloaded, the customer can start unpacking. 

Wing said it has completed more than 350,000 commercial deliveries to date. Nash noted that its most delivered item is coffee. 

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

Designing with safety at the core

Wing drones don’t land when they pick up or drop off goods, increasing the safety of the system and making it less likely the drone might crash or hit someone as it lands. Wing said it conducts comprehensive aviation community outreach to work with other users in the surrounding airspace. 

The company added that it has built a robust approach that separates its on-demand flights in time and space from one another and other aircraft using layered mitigations both before and during flights. This is similar to the systems that airplanes use to ensure safe flights. 

This detect-and-avoid technology is used both in drones and in crewed aircraft.

“They call it ‘see and avoid’ in a crewed aircraft,” Shore explained. “If you’re a pilot, you’re looking out your window. If you see an aircraft, your job is to then move and avoid that other aircraft.”

“Well, in a drone, you can’t do that,” he said. “There’s no one on the drone looking out the window, so they call it ‘detect and avoid,’ and it’s a way to actually understand what other aircraft are around you.” 

“It’s all about a bunch of different layers of safety that we put on to make sure there’s always another layer of safety that we’re taking into consideration while we’re flying,” Shore said. 

Wing works to avoid disruptions

As it scales up its operations, Wing also works with the communities in which it delivers to ensure that its drones don’t disturb the people living there.

“We spend a lot of time in the communities in which we serve and really connect with them,” Nash said. “Even before we go into the communities, we do a lot of pre-work.”

For example, the company worked closely with representatives from the autistic community in Ireland to ensure its drones weren’t too loud when they flew overhead. 

“A personal story for me, and one of my favorite stores of some of the pre-work we’ve done, is from when we were going into Ireland,” Nash said. “We spent a bunch of time meeting with autism groups there. I’m the mother of a 25-year-old autistic adult male, and we spent a lot of time understanding that community and how sound impacts somebody with autism in particular.” 

Wing plans to continue to grow this year. In particular, the company said it hopes to establish more nests for its drones, expanding service area and potentially opening up new partnerships. 

The post Wing gears up for drone delivery growth with updated FAA exemption appeared first on The Robot Report.

Top row, from left to right: the Ella smart stroller, Soft Robotics’ food packer, and the TM25S. Bottom row: Salidrone, M4, and Zipline’s delivery drone. | Source: NVIDIA

Outside the glare of the klieg lights that ChatGPT commanded this past year, a troupe of autonomous machines nudged forward the frontiers of robotics, according to NVIDIA.

Ella smart stroller makes a splash at CES

Ella — a smart stroller from Glüxkind Technologies, a startup in Vancouver, Canada — kicked off the year when it was named an honoree in the CES 2023 Innovation Awards.

The canny carriage uses computer vision running on the NVIDIA Jetson edge AI platform to follow parents. Its AI-powered abilities, like smart braking and a rock-my-baby mode, captured the attention of media outlets like Good Morning America and The Times of London as well as an NVIDIA AI Podcast interview with its husband-and-wife cofounders.

A member of NVIDIA Inception, a free program for cutting-edge startups, Glüxkind was one of seven companies with NVIDIA-powered products recognized at the Las Vegas event in January. They included:

• John Deere for its fully autonomous tractor
• AGRIST for its robot that automatically harvests bell peppers
• Inception member Skydio for its drone that can fly at a set distance and height without manual intervention
• Neubility, another Inception member, for its self-driving delivery robot
• Seoul Robotics, a partner in the NVIDIA Metropolis vision AI software, for its Level 5 Control Tower that can turn standard vehicles into self-driving care
• WHILL for its one-person vehicle that automatically guides a user inside places like airports or hospitals

mGripAI dexterously packs food

Bedford, Mass.-based Inception member Soft Robotics introduced its mGripAI system to an $8 trillion food industry hungry for automation. It combines 3D vision and AI to grasp delicate items such as chicken wings, attracting investors that include Tyson Foods and Johnsonville.

Soft Robotics uses the NVIDIA Omniverse platform and NVIDIA Isaac Sim robotics simulator to create 3D renderings of chicken parts on conveyor belts or in bins. With help from AI and the ray-tracing capabilities of NVIDIA RTX technology, the robot gripper can handle as many as 100 picks per minute, even under glare or changing light conditions.

“We’re all in on Omniverse and Isaac Sim, and that’s been working great for us,” David Weatherwax, senior director of software engineering at Soft Robotics, said in a January interview.

TM25S provides a keen eye in the factory

In a very different example of industrial digitalization, electronics manufacturer Quanta is inspecting the quality of its products using the TM25S, an AI-enabled robot from its subsidiary, Techman Robot.

Using Omniverse, Techman built a digital twin of the inspection robot — as well as the product to be inspected — in Isaac Sim. Programming the robot in simulation reduced time spent on the task by over 70%, compared with programming manually on the real robot.

Then, with optimization tools in Isaac Sim, Techman explored a massive number of program options in parallel on NVIDIA GPUs. The end result, shown in the video below, was an efficient solution that reduced the cycle time of each inspection by 20%.

Saildrone takes to the seas for data science

Saildrone, another Inception startup in Alameda, Calif., created uncrewed watercraft that can cost-effectively gather data for science, fisheries, weather forecasting and more.

NVIDIA Jetson modules process data streams from their sensors, some with help from NVIDIA Metropolis vision AI software such as NVIDIA DeepStream, a development kit for intelligent video analytics.

The video below shows how three of Saildrone’s smart sailboats are helping evaluate ocean health around the Hawaiian Islands.

Caltech M4 sets its sights on Mars

The next stop for one autonomous vehicle may be the red planet.

Caltech’s Multi-Modal Mobility Morphobot, or M4, can configure itself to walk, fly, or drive at speeds up to 40 mph (see video below). An M42 version is now in development at NASA as a Mars rover candidate and has attracted interest for other uses such as reconnaissance in fire zones.

Since releasing a paper on it in Nature Communications, the team has been inundated with proposals for the shape-shifting drone built on the NVIDIA Jetson platform.

Zipline delivery drones fly high

The year ended on a high note with Zipline announcing that its delivery drones flew more than 55 million miles and made more than 800,000 deliveries since the company’s start in 2011. The San Francisco-based company said it now completes one delivery every 70 seconds, globally.

That’s a major milestone for the Inception startup, the field it’s helping pioneer, and the customers who can receive everything from pizza to vitamins up to seven faster than by truck.

Zipline’s latest drone uses two Jetson Orin NX modules. It can carry 8 lb. of cargo for 10 miles at up to 70 mph to deliver packages in single-digit minutes while reducing carbon emissions 97% in comparison with gasoline-based delivery vehicles.

NVIDIA notes maker machines that inspire and amuse

Individual makers designed two autonomous vehicles this year worth special mentions.

Goran Vuksic with his AI-powered droid. | Source: NVIDIA

Kabilan KB, a robotics developer and student in Coimbatore, India, built an autonomous wheelchair using Jetson to run computer vision models that find and navigate a path to a user’s desired destination. The undergrad at the Karunya Institute of Technology and Sciences aspires to one day launch a robotics startup.

Finally, an engineering manager in Copenhagen who’s a self-described Star Wars fanatic designed an AI-powered droid based on an NVIDIA Jetson Orin Nano Developer Kit. Goran Vuksic shared his step-by-step technical guide, so others can build their own sci-fi companions.

More than 6,500 companies and 1.2 million developers — as well as a community of makers and enthusiasts — use the NVIDIA Jetson and Isaac platforms for edge AI and robotics.

To get a look at where autonomous machines will go next, see what’s coming at CES in 2024.

Editor’s note: This blog reposted with permission from NVIDIA.

The post NVIDIA picks 6 noteworthy autonomous systems of 2023 appeared first on The Robot Report.

NVIDIA Jetson Xavier NX processes sensor inputs for the P1 delivery drone. Source: Zipline

Robotics, simulation, and artificial intelligence are providing new capabilities for supply chain automation. For example, Zipline International Inc. drone deliveries and Amazon Robotics digital twins for package handling demonstrate how NVIDIA Corp. technologies can enable industrial applications.

“You can pick the right place for your algorithms to run to make sure you’re getting the most out of the hardware and the power that you are putting into the system,” said A.J. Frantz, navigation lead at Zipline, in a case study.

NVIDIA claimed that its Jetson Orin modules can perform up to 275 trillion operations per second (TOPS) to provide mission-critical computing for autonomous systems in everything from delivery services and agriculture to mining and undersea exploration. The Santa Clara, Calif.-based company added that Jetson’s energy efficiency can help businesses electrify their vehicles and reduce carbon emissions to meet sustainability goals.

Zipline drones rely on Jetson Xavier NX to avoid obstacles

Founded in 2011, Zipline said it has completed more than 800,000 deliveries of food, medication, and more in seven countries. The San Francisco-based company said its drones have flown over 55 million miles using NVIDIA Jetson edge AI platform for autonomous navigation and landings.

Zipline, which raised $330 million in April at a valuation of $4.2 billion, is a member of the NVIDIA Inception program, in which startups can get technology support. The company’s Platform One, or P1, drone uses Jetson Xavier NX system-on-module (SOM) to process sensor inputs.

“The NVIDIA Jetson module in the wing is part of what delivers our acoustic detection and avoidance system, so it allows us to listen for other aircraft in the airspace around us and plot trajectories that avoid any conflict,” Frantz explained.

Zipline’s fixed-wing drones can fly out more than 55 miles (88.5 km), at 70 mph (112.6 kph) from several distribution centers and then return. Capable of hauling up to 4 lb. (1.8 kg) of cargo, they autonomously fly and release packages at their destinations by parachute.

Learn from Agility Robotics, Amazon, Disney, Teradyne and many more.

P2 hybrid drone includes Jetson Orin NX for sensor fusion, safety

Zipline’s Platform Two, or P2, hybrid drone can fly fast on fixed-wing flights, as well as hover. It can carry 8 lb. (3.6 kg) of cargo for 10 miles (16 km), as well as a droid that can be lowered on a tether to precisely place deliveries. It’s intended for use in dense, urban environments.

The P2 uses two Jetson Orin NX modules. One is for sensor fusion system to understand environments. The other is in the droid for redundancy and safety.

Zipline claimed that its drones, nicknamed “Zips,” can deliver items 7x faster than ground vehicles. It boasted that it completes one delivery every 70 seconds globally.

“Our aircraft fly at 70 miles per hour, as the crow flies, so no traffic, no waiting at lights — we’re talking minutes here in terms of delivery times,” said Joseph Mardall, head of engineering at Zipline. “Single-digit minutes are common for deliveries, so it’s faster than any alternative.”

In addition to transporting pizza, vitamins, and medications, Zipline works with Walmart, restaurant chain Sweetgreen, Michigan Medicine, MultiCare Health Systems, Intermountain Health, and the government of Rwanda, among others. It delivers to more than 4,000 hospitals and health centers.

Amazon uses Omniverse, Adobe Substance 3D for realistic packages

For warehouse robots to be able to handle a wide range of packages, they need to be trained on massive but realistic data sets, according to Amazon Robotics.

“The increasing importance of AI and synthetic data to run simulation models comes with new challenges,” noted Adobe Inc. in a blog post. “One of these challenges is the creation of massive amounts of 3D assets to train AI perception programs in large-scale, real-time simulations.”

Amazon Robotics turned to Adobe Substance 3D, Universal Scene Description (USD), and NVIDIA Omniverse to develop random but realistic 3D environments and thousands of digital twins of packages for training AI models.

NVIDIA Omniverse integrates with Adobe Substance 3D to generate realistic package models for training robots. Source: Adobe

NVIDIA Omniverse allows simulations to be modified, shared

“The Virtual Systems Team collaborates on a wide range of projects, encompassing both extensive solution-level simulations and individual workstation emulators as part of larger solutions,” explained Hunter Liu, technical artist at Amazon Robotics.

“To describe the 3D worlds required for these simulations, the team utilizes USD,” he said. “One of the team’s primary focuses lies in generating synthetic data for training machine learning models used in intelligent robotic perception programs.”

The team uses Houdini for procedural mesh generation and Substance 3D Designer for texture generation and loading virtual boxes into Omniverse, added Haining Cao, a texturing artist at Amazon Robotics.

The team has developed multiple workflows to represent the vast variety of packages that Amazon handles. It has gone from generating two to 300 assets per hour, said Liu.

“To introduce further variations, we utilize PDG (Procedural Dependency Graph) within Houdini,” he noted. “PDG enables us to efficiently batch process multiple variations, transforming the Illustrator files into distinct meshes and textures.”

After generating the synthetic data and publishing the results to Omniverse, the Adobe-NVIDIA integration enables Amazon’s team to change parameters to, for example, simulate work cardboard. The team can also use Python to trigger randomized values and collaborate on the data within Omniverse, said Liu.

In addition, Substance 3D includes features for creating “intricate and detailed textures while maintaining flexibility, efficiency, and compatibility with other software tools,” he said. Simulation-specific extensions bundled with NVIDIA Isaac Sim allow for further generation of synthetic data and live simulations using robotic manipulators, lidar, and other sensors, Liu added.

The post NVIDIA Jetson supports Zipline drone deliveries, as Omniverse enables Amazon digital twins appeared first on The Robot Report.

ffVC hosted the Drones & Robotics AI Summit in New York. Source: Robert Wright Photographs

The Big Apple is the center of the East Coast innovation corridor, which stretches north to Boston and Canada and south to Washington, D.C., and North Carolina’s Research Triangle. On Nov. 8, more than 200 leaders within the drone, robotics, and artificial intelligence ecosystem gathered at the Drones & Robotics AI Summit 2023 in New York to network, ideate, and demonstrate innovative technologies.

The plenum of speakers also included numerous government officials promoting innovation and technology investments. The summit, put on by ff Venture Capital and Genius New York, proved once and for all that mechatronics has a home in the Empire State, rivaling even California’s Silicon Valley.

Inaugurating the summit, my partner and ffVC founder John Frankel reminded the audience that there is really nothing new under the sun, as the ancient Greeks created an automate therapaenis, a robotic servant in the 3rd century BCE.

NYPD demonstrates public safety drones

The NYPD demonstrates a drone. Credit: Robert Wright Photographs

The Drones & Robotics AI Summit program quickly accelerated into the 21st century with Capt. Michael Gulinello of the New York City Police Department’s Drones & Robotics unit. He showcased more than 20 use cases of uncrewed aerial systems (UASes) recently deployed against active shooters, shark attacks, and crowd control. 

Gulinello’s team also parked a UAS command vehicle outside the event, enabling attendees to witness live demonstrations in the heart of Times Square. The captain said he looks forward to the day when robots will be ubiquitous in policing, with the public having confidence in its ability to protect their privacy and safety.

The NYPD’s strategic command center that operates drone fleets falls under the oversight of New York City’s chief technology officer, Matthew Fraser. At the summit, I had an opportunity to sit down and speak with Fraser about his new initiatives to partner with startups and private capital.

New York seeks innovative solutions to urban problems

The CTO and civil servant has spent more than 17 years leading information technologies across city agencies, including the Department of Buildings, the Department of Environmental Protection, and the NYPD. Fraser said his experiences informed him as he launched the SmartCities Testbed for startups looking to apply their inventions to urban problems, such as using drones for building exterior inspections or computer vision for traffic monitoring.

Fraser encouraged the more than 100 startups gathered to apply. His approach to inviting entrepreneurs to shake up established agencies is also present in the new AI Action Plan, which that lays out a clear path to integrating machine learning technologies into the fabric of the nation’s largest metropolitan area.

In Fraser’s words, AI could augment social services by providing a safety net to the most vulnerable citizens, ensuring that no one falls through the cracks and that they can access the full benefits that they are entitled to receive. This thinking follows the recent statements by his boss, Mayor Eric Adams.

“Artificial intelligence is one of the most impactful technological advances of our time,” stated the mayor. “While AI has the potential to improve services and processes across our government, we must also be mindful of its associated risks. With the release of our AI Action Plan, the first-of-its-kind for a major U.S. city, we are cementing our commitment to this emerging technology’s responsible use and ensuring that we are deploying the right tools in the right ways.”

According to the report, the findings used information gathered by 18 city agencies with the goal of harnessing “the power of AI for good.”

Matt Fraser, CTO of New York City (left), and Oliver Mitchell of ffVC have a fireside chat. Credit: Robert Wright Photographs

Public sector looks for private partners

Attendees of the Drones & Robotics AI Summit also heard from the federal government — specifically, the U.S. Department of Defense through its partner, the National Security Innovation Network (NSIN). The panel included:

• Alice Globus, chief financial officer of Nanotronics
• Shane Skopak, vice president of business development at DZYNE Technologies
• Bhargav Patel, senior technologist at the Department of Homeland Security
• Grant Fox, director for the Mid-Atlantic Region at NSIN and moderator

Their session deconstructed the types of opportunities for startups from federal law enforcement and military agencies, especially in light of the new CHIPS Act and the Build America Buy America initiative. The panel also examined the grants available for public/private partnerships and defense missions.

These opportunities were especially evident in NSIN’s newsletter after the summit. It promoted the 2024 X-Force Fellowship program, 2023 NSIN Foundry and Forge cohorts, and the NSIN Emerge accelerator. It also spotlighted the Defense Acceleration Ecosystem (INDUS-X) challenges and the xTech Good Vibrations Challenge.

In addition, the Department of Homeland Security has its own Urban Security Technology Laboratory (NUSTL) to test drone and other hardware innovations. Dual use was probably best exemplified on the panel by Nanotronics, which offers numerous AI products for the aerospace industry, as well as the career path of Shane Skopak, former Navy test pilot and current business development lead for DZYNE Industries.

NSIN panel discusses public-private collaboration. Credit: Robert Wright Photographs

Now is the time to invest in robotics, say VCs

To many founders, investors look like a homogenous group of executives with checkbooks capitalizing on their ideas. However, this view could cause them to miss finding the right partner for launching their businesses.

The deployment of capital in the private markets is driven by various factors, ranging from governments seeking to bolster jobs to venture capitalists driving returns and corporate partners looking for a strategic business fit. The Drones & Robotics AI Summit enabled founders to “speed date” and meet a wide variety of investors.

They included fellow panelists Peter Finn at investment bank BGL, Sasha Jostrom-Reiser of early-stage VC firm Cybernetix, Besty Mulé of later-stage VC F-Prime, and Jason Hong of corporate VC Micron Ventures. We discussed the implications of large language models (LLMs) on robotics and why now is a good time to invest.

As Hong noted, increased memory and computing power enable the development of AI at a scale that could make robots even more impactful than previously thought. Jostrom-Reiser added that this trend has lowered costs and increased adoption, “driving interest from businesses to invest in AI applications.

Mulé commented further that the convergence of AI and declining sensor costs have improved mechatronic performance so much that it has opened the door for new upstarts to capitalize on unforeseen opportunities. Finn suggested this will lead to more M&A exits and even IPOs.

All of us agreed that the macro trends of labor shortages, aging populations, and declining startup costs set up investment returns to dramatically climb in the next five years. In summary, it’s a great time to invest.

Investment panel at Drones & Robotics AI Summit. Source: Robert Wright Photographs

Drones & Robotics AI Summit looks at deliveries

Before breaking for lunch, we discussed fast-food drone delivery with Bobby Healy of Manna, an ffVC portfolio company. He shared on-screen examples of his current pilots throughout the Irish coast, especially the Dublin suburb of Balbriggan.

Healy started the keynote with a cellphone video of a child excitedly watching a drone dropping off a shopping bag. Today, the town is used to the buzzing quadcopters. Services continue without fanfare; it’s now just part of life.

“In Balbriggan, 40% of the population uses our service 1.6 times a month, and we are confident that this number will continue to grow as word of mouth contributes to popularizing the service,” said Healy.

Today, the repeat usage percentage has grown considerably. Ironically, one of the most-requested items is a hot cup of coffee, Healy noted.

The Irish entrepreneur illustrated how his fleet is moving at remarkable speed against terrestrial (driving) options and at a fraction of the cost. He even calculated that Manna is improving sustainability in terms of saving trees. This past Halloween, Manna made news in the U.S. with candy deliveries.

“After over four years of operations and over 150,000 flights logged in Europe, we are excited to be touching down in the United States to offer the residents of Dallas/Fort Worth a lightning-quick and sustainable home delivery service,” said Andrew Patton, head of U.S. for Manna Drone Delivery. “We are taking Halloween to new heights, with a fun new way for kids to trick or treat – especially when the weather isn’t very Halloween-compatible!”

This is only the beginning of their global expansion with more flights, more restaurants, and more trees that all of us need. Another speaker at the Drones & Robotics AI Summit was Rishap Malhotra of Drone Up, a Virginia Beach, Va.-based last-mile delivery operation.

Update on ‘Roadmap for U.S. Robotics’

Henrik Christensen then led a discussion on the state of the robotics industry in 2023. The University of California San Diego (UCSD) professor is the author of “A Roadmap for U.S. Robotics,” which is now researching its fifth edition.

The roadmap sets the congressional funding priorities for the U.S. in science and technology. Christensen has been traveling across the country setting up workshops with academics, industry leaders, and inventors discussing the most pressing issues in moving robotics forward.

I participated in one workshop at the University of Pennsylvania in September debating the opportunities for automation in infrastructure and technical hurdles in perception and manipulation. This endeavor is on top of Christensen’s teaching and lab responsibilities at UCSD, executive obligations at Robust.ai, and his own investment activities, formerly at RoboGlobal.

One of the most startling statistics that Christensen presented is that 81% of people between the ages of 18 to 29 play video games for over 10 hours a week. While many would bemoan this figure, he sees it as an opportunity for leveraging their active thumbs in controlling machines across factories, warehouses, farms, and construction sites.

As our population continues to age, these skills will become more vital in creating robotic devices to aid seniors with the most basic living skills in their homes and healthcare facilities. Christensen pointed to the lessons learned during the COVID-19 pandemic as a guide to enabling the U.S. to lead the world toward an automated future.

Henrik Christensen discusses pandemic lessons for U.S. robotics. Credit: Robert Wright Photographs

New York State to expand startup opportunities

While Christensen provided a national view, we were privileged to host Commissioner Hope Knight of New York’s Empire State Development Corporation (ESD) to share the state’s perspective. ffVC has partnered with the ESD to fund innovations born in the Excelsior State since 2014.

Most recently, ffVC opened an office in Syracuse’s TechGarden, the incubator space shared with Genius NY. It will mentor and finance startups in the drones and robotics space.

At the Drones & Robotics AI Summit, Knight outlined the opportunities for founders within the automation space in New York, such as accelerators throughout the state and startup tax incentives. They are intended to expand opportunities for small businesses throughout the region, especially in growing technology fields that can provide jobs to populations ignored by traditional corporations, she said.

As a venture investor, I left Knight’s keynote enthusiastic about New York State leading the nation in recruiting a fresh crop of diverse founders within the UAS space, bringing with them unique experiences and solutions to previously unaddressed problems.

Commissioner Hope Knight discusses drone advances and New York State initiatives. Credit: Robert Wright Photographs

Startups show the way to industry change

The Drones & Robotics AI Summit then flowed right into a lightning round of demonstrations by Genius NY’s current and previous cohorts. The audience had the chance to see the full spectrum of uncrewed systems, including mission-planning software, quadcopter blades, and complete mechanical systems.

The presenting startups included Aloft, Vermeer, Geopipe, Vermeer, Votix, TruWeather Solutions, Greenjets, Voltela, Dronehub, ArchAngel, and Blueflite, the 2023 Grand Prize Winner. Blueflite co-founder Frank Noppel shared his appreciation for the Genius NY program and the Upstate region.

“In Syracuse, we’ve discovered a unique ecosystem perfectly suited for Blueflite’s ambitions,” he said. “Firstly, we’ve found the opportunity to collaborate with top-tier manufacturing facilities for batch production using advanced 3D-printing technology while adhering to the most stringent aerospace standards.”

“Secondly, Syracuse provides access to the world’s most advanced drone test facility, which is required for our ongoing drone production and R&D efforts,” said Noppel. “Lastly, the city’s thriving community of drone tech companies that we can integrate into our drone platform makes it one of the most competitive drone solutions out there. Together, these elements make Syracuse the ideal fit for Blueflite.”

Kara Jones, executive director of Genius NY, echoed his sentiments. “From autonomous flights for travel to improving how we transport goods, to improving processes around data collection and inspections, to health care, defense, and more – UAS is transforming how we live and work,” she said.

“These GENIUS NY teams are at the leading edge of their technologies and have demonstrated their strong potential for growth and success,” said Jones. “As market demands evolve and technology advances, these and other UAS companies have access to the most robust concentration of firms, infrastructure, and investments anywhere in the country, here in New York.”

Genius NY startups conducted demonstrations. Credit: Robert Wright Photographs

ffVC provides portfolio insights

The Drones & Robotics AI Summit concluded with a deep dive into ffVC’s portfolio led by our head of platform, Charlotte Japp. The companies gathered represented the full spectrum of automation sector, with Christian Sanz of SkyCatch (drones), Miika Satori of Cambrian Vision (collaborative robots), and Jesse Canella of TensorFlight (artificial intelligence).

Sanz shared tips on how to close deals with investors and key customer accounts by showing up at their headquarters uninvited ready to work. While some would say this is borderline stalking, SkyCatch’s revenues prove otherwise.

Japp pressed the group for more founder tips, with Satori voicing the importance of strategic partners to forge multi-faceted relationships to encompass reselling, R&D, as well as capital investments. Cambrian is on the heels of announcing the closing of its next round with a corporate venture supporting its global sales effort in Europe, Japan, and the U.S.

Canella added his own thoughts on working with market leaders to create feedback loops to proactively grow its customer lifetime value.

Portfolio panel at Drones & Robotics AI Summit. Credit: Robert Wright Photographs

As my colleague, Charlotte Japp, reflected on the session, “Portfolio companies shared best practices on fundraising and corporate relationships. The early stage founders in the audience got a kick out of the unconventional practices suggested, from watching the same TV show as a prospective customer to boarding a plane for an IRL meeting that an investor hasn’t asked for.”

The summit already helped to keep New York innovation local. “I came to this event as someone who has a novice interest in the drone tech industry, looking to enter and acquire experience by potentially joining a drone company,” said one young entrepreneur. “I found that there are a lot more New York-based companies in this industry than I previously thought. This was very helpful, as I assumed that I would need to relocate elsewhere in order to join a drone tech company.”

Frank Sinatra would be proud — “Start spreading the news….”

The post New York Drones & Robotics AI Summit heralds growing automation industry appeared first on The Robot Report.

Doodle Labs’ Sense technology helps robotic systems like drones remain connected when they encounter signal interference in the field. | Source: Doodle Labs

Doodle Labs has released Sense, a new feature set for the company’s multi-band Mesh Rider Radios that addresses the challenges of interference for long-range, mission-critical robotics, and connected teams applications for a more resilient datalink. 

Sense aims to help dismounted connected teams and advanced robotic systems like drones and uncrewed ground vehicles stay connected when they encounter signal interference in the field. This interference can threaten connectivity and hinder performance and can include anything from interference from WiFi devices in urban areas or active jamming attempts in the field of battle.

These lapses in connectivity can interrupt the transmission of critical payloads, like video or scan data, or even command-and-control of a robotic system. Sense is engineered to actively monitor in-band interference and automatically switch channels or frequency bands to find the best-performing frequency. 

When combined with Doodle Labs’ Mesh Rider’s Low Probability of Intercept/Low Probability of Detection (LPI/LPD) waveform, this new feature set ensures uninterrupted communication and enhances the operational efficiency of advanced systems in fields like defense, public safety, and commercial industries. 

When Sense is activated, the Mesh Rider Radio scans for interference and background noise across all frequency bands, utilizing the full potential of packing multiple frequency bands into a single radio. Once the node on the network is deployed into the field, Sense continually monitors the health of its LPI/LPD datalink signal. 

If the datalink starts to experience significant interference, Sense automatically shifts to a better-performing channel with the current band, or to a different band altogether. This maintains connectivity while also optimizing performance during the mission. 

Using multiple frequency bands not only facilitates global deployment in areas with differing legal frequency allocation but also significantly expands the radio’s ability to avoid interference or jamming by utilizing all available spectrums with multiple frequency bands. 

The system is aimed at commercial customers like drones and UGV OEMs, offering them the enhanced ability to operate in densely populated and RF noisy urban environments. The system is also battle-tested in Ukraine, where it’s helping avoid interference caused by active jamming. 

Sense is an advanced paid feature that will be available as a firmware upgrade to all Doodle Labs Mesh Rider Radio customers. 

The post Doodle Labs launches Sense interference avoidance features appeared first on The Robot Report.

The Federal Aviation Administration (FAA) granted Airobotics, a manufacturer of uncrewed aircraft systems (UAS) and a subsidiary of Ondas Holdings, an Airworthiness Type Certification for its Optimus 1-EX. The system is only the second-ever Uncrewed Aircraft to receive this certification and the first “drone-in-a-box” system.

The FAA’s Type Certificate is the highest level of Airworthiness Certification granted by the agency. Airobotics’ Optimus system is designated by the FAA for fully automated drone operations for emergency response and digital data capturing. 

“We are thrilled to be the only US company currently to have the capability to deploy fully automated drones with Type Certificate in the US as permanent aerial infrastructures in populated and complex environments,” Meir Kliner, Airobotics’ CEO, said. “Drones without an airworthiness certificate face great obstacles in obtaining waivers to operate over people and active roads, and we believe that our Type certified Optimus-1EX drone will soon be deployed in a broader range of scenarios. The last type certificate given by the FAA was for a package delivery drone and now we have opened the opportunity for more lifesaving applications such as Drone First Responding (DFR), rapid infrastructure survey for disaster relief applications and more.”

This certification was a result of a four-year intensive engineering and operational review process conducted by the FAA.

The Optimus System is already at work regularly in urban environments in the United Arab Emirates (UAE). Airobotics plans to leverage this experience in the UAE, and their newly type-certified vehicle, to conduct similar operations in urban environments across the US.

Airobotics’ Optimus System is an autonomous unmanned aircraft system that focuses on high-value applications within the industrial, homeland security and smart city services market. The system includes an industrial-grade drone-in-a-box and the Optimus Airbase, which allows for robotic battery and payload swapping.

Earlier this year, Airobotics announced that it had completed the acquisition of the assets of Iron Drone Ltd, an Israeli-based company that creates autonomous counter-drone systems. The acquisition became effective on March 6, 2023.

Ondas announced it was acquiring Airobotics in July 2022, with the goal of accelerating American Robotics‘, another Ondas subsidiary, technical development and regulatory roadmap and expanding the breadth of applications, use cases and vertical AR targets.

The post Airobotics’ Optimus drone receives FAA Airworthiness appeared first on The Robot Report.

XTEND, the developer of XOS, an operating system that serves as a human extension to help users that have no flight experience operate drones, has acquired Performance Rotors, a Singapore-based drone inspection company. The financial terms of the agreement were not disclosed. 

This acquisition will help to boost XTEND’s ability to offer human-guided, remote interactive operations in a range of inspection scenarios and grow its global business.

XTEND’s system uses virtual reality, sensor fusion and its patented Mark & Fly technology to empower users with little or no flight experience to make better decisions while flying drones. The system is designed to be wearable, mobile and lightweight, and can be controlled with single-hand, natural hand gestures. 

“Our acquisition of Performance Rotors marks the latest step in furthering XTEND’s vision of making remote interactive operations accessible to everyone, in a range of scenarios, including inspection, public safety and security,” Aviv Shapira, co-founder, and CEO at XTEND, said. “Every day, people risk their lives to make our world safer. Inspection is just one area, among many, where machines, robots and drones can be used to accomplish what people can’t, in a more economical, efficient, and safer manner. We are delighted that Keith Ng, Performance Rotors’ co-founder and CEO, and his team are joining XTEND on our journey towards making XOS the operating system of choice for controlling drones, robots, vehicles, smart devices, and smart machines remotely, safely, and intuitively.”

Performance Rotors offers drone asset inspection services for a variety of industries, including oil & gas, maritime, and infrastructure inspections. The company also offers aerial services, like aerial photography and videography, and digitalization services. 

“Performance Rotors’s mission has always been to develop drones and robotics solutions for data acquisition in GPS-denied and confined space environments, without the risk to human lives,” Keith Ng, co-founder, and CEO of Performance Rotors, said. “Our extensive client base spans many of the world’s major oil and gas, maritime and infrastructure projects, and our hardware is being used across the World, particularly in APAC. We are confident that combining XTEND’s innovative XOS software with our world-class technology brings the best of the industry together in one powerful and easy-to-use solution that comprehensively addresses the critical challenges facing our customers today.”

Chartered Group, a global private equity firm, led the acquisition. The group provides investment funds and opportunities for a greener and more digitized world. 

“The acquisition of Performance Rotors not only enriches XTEND’s offering in industrial inspection, but it will also enable Aviv and his team to further diversify their expertise in oil and gas, maritime and infrastructure projects, and develop XTEND’s software business globally, particularly here in APAC and Japan,” Eyal Agmoni, Chairman of Chartered Group, said. 

The post XTEND acquires drone inspection company Performance Rotors appeared first on The Robot Report.

WiBotic’s new PowerPad Pro with a drone. | Source: WiBotic

“PowerPad Pro enhances drone functionality for our partners working in environments where autonomous or semi-autonomous operations are a priority,” Ben Waters, co-founder and CEO of WiBotic, said. “We designed it as a flexible solution for those who either already own and operate drones – and have their own infrastructure in place – or those who are looking for a more cost-effective option for fully autonomous operations. PowerPad Pro can be used as a stand-alone landing platform, or it can be integrated into any number of enclosures and form factors such as trailers, sheds, or even truck beds.”

One of WiBotic’s first partners for PowerPad Pro is Valmont Industries Inc., a global leader that provides vital infrastructure and advances agricultural productivity while driving innovation through technology.

“Valmont has been working closely with WiBotic and other partners to enhance our drone inspection capabilities,” Angi Chamberlain, VP of UAS Technology Solutions at Valmont, said. “For the first time, PowerPad Pro provides a charging platform that works with any of the different UAVs we use. Remote flight plan uploads and automated sensor data downloads also allow us to perform inspections on a moment’s notice at any location where the platform is deployed.”

Wireless Data Transfer

During battery charging, PowerPad Pro’s wireless data transfer enables UAVs to quickly and easily download flight and sensor data to an industrial computer inside the pad. The data can then be processed locally and/or automatically transmitted to a central location using LTE or long-range data backhaul radios.

Using the same wireless data link, remote operators can upload flight plans or monitor flights in real time, ensuring safe and controlled flights. Without this capability, high-resolution images, video and other data can quickly fill the UAV’s onboard storage. By removing this restriction, PowerPad Pro provides more flexibility and versatility in the missions that UAVs can perform.

Autonomous Charging

In addition to wireless data transfer, PowerPad Pro also automatically begins wireless battery charging upon landing. This eliminates the need for cables and connectors and allows different sizes and types of UAVs to share a common landing pad platform (or series of platforms) deployed across large areas.

Unlike contact-based charging stations, WiBotic’s patented technology provides power through the air. The pad is fully sealed to the elements, protecting both electronics and mechanical components from dust, debris, rain, insects and other environmental factors that may eventually impact reliability. Programmable voltage and current also help extend battery lifespan, reducing the need for costly battery replacements and maintenance.

Industry Benefits

By offering these dual benefits – wireless data transfer coupled with autonomous charging – PowerPad Pro dramatically enhances drone operations across a number of industries:

• Energy & Utilities: Utility operators need data from infrastructure inspection every day – not once or twice a year. Permanently deployed UAVs with the ability to fly multiple repetitive missions, using one PowerPad Pro or a series of them over long distances, are critical for reducing inspection costs while increasing inspection frequency.
• Construction: Remotely monitoring construction sites provides innumerable benefits in terms of safety, build quality and owner/builder/subcontractor relations. However, most construction data is extremely high bandwidth and getting it to engineers and project managers at remote locations is extremely difficult without a solution like PowerPad Pro.
• Defense: Drones are frequently equipped with high-resolution cameras, infrared sensors and other advanced imaging equipment that gather terabytes of data. In a combat zone, however, it’s extremely dangerous to leave a protected vehicle to swap batteries or retrieve the SD cards that contain that data. A fully autonomous platform like PowerPad Pro ensures the warfighter remains protected while he or she gathers intelligence on enemy movements.
• Agriculture: UAVs have made monitoring thousands of acres of farmland easier than ever before – but that’s not to say it’s easy. Drones still have limited flight time and limited onboard data storage. A network of strategically placed PowerPad Pros solves this problem by providing charging stations across the entire farm and an automatic backhaul of data to the farm HQ where it can be put to immediate use.

While these onboard chargers can be integrated into nearly any UAV, Wibotic is pleased to announce BlueHalo as the first partner for PowerPad Pro. The BlueHalo Intense Eye V2 (IE-V2) and E900 models can now be purchased with WiBotic’s PowerPad Pro to support both charging and data offload.

“BlueHalo provides UAVs to both the commercial and defense sectors, with extensive experience in applications ranging from inspection and monitoring to intelligence, surveillance and reconnaissance (ISR) missions,” Mary Clum, Sector President and Corporate Executive Vice President of BlueHalo, said. “There is a growing demand for permanently deployed and remotely controlled UAVs. PowerPad Pro has given us a single, reliable tool to integrate autonomous charging and data offload capabilities into our UAV platforms, allowing us to offer new solutions and better support critical customer missions.”

The post WiBotic releases automatic drone charging pad appeared first on The Robot Report.

A team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has introduced a method for drones to master vision-based fly-to-target tasks in intricate and unfamiliar environments. The team used liquid neural networks that continuously adapt to new data inputs. 

MIT CSAIL’s team found that the liquid neural networks performed strongly in making reliable decisions in unknown domains like forests, urban landscapes and environments with added noise, rotation and occlusion. The networks even outperformed many state-of-the-art counterparts in navigation tasks and the team hopes it could enable potential real-world drone applications like search and rescue, delivery and wildlife monitoring. 

“We are thrilled by the immense potential of our learning-based control approach for robots, as it lays the groundwork for solving problems that arise when training in one environment and deploying in a completely distinct environment without additional training,” Daniela Rus, CSAIL director and the Andrew (1956) and Erna Viterbi Professor of Electrical Engineering and Computer Science at MIT, said. “Our experiments demonstrate that we can effectively teach a drone to locate an object in a forest during summer, and then deploy the model in winter, with vastly different surroundings, or even in urban settings, with varied tasks such as seeking and following. This adaptability is made possible by the causal underpinnings of our solutions. These flexible algorithms could one day aid in decision-making based on data streams that change over time, such as medical diagnosis and autonomous driving applications.”

The team’s new class of machine-learning algorithms captures the casual structure of tasks from high-dimensional, unstructured data, like pixel inputs from a drone-mounted camera. The liquid neural networks then extract the crucial aspects of the task and ignore irrelevant features, allowing acquired navigation skills to transfer targets seamlessly to new environments. 

In their research, the team found that liquid networks offered promising preliminary indications of their ability to address a crucial weakness in deep machine-learning systems. Many machine learning systems struggle with capturing causality, frequently over-fit their training data and fail to adapt to new environments or changing conditions. These problems are especially prevalent for resource-limited embedded systems, like aerial drones, that need to traverse varied environments and respond to obstacles instantaneously. 

The system was first trained on data collected by a human pilot to see how it transferred learned navigation skills to new environments under drastic changes in scenery and conditions. Traditional neural networks only learn during the training phase, while liquid neural networks have parameters that can change over time. This makes them interpretable and resilient to unexpected or noisy data. 

In a series of quadrotor closed-loop control experiments, MIT CSAIL’s drones underwent range tests, stress tests, target rotation and occlusion, hiking with adversaries, triangular loops between objects and dynamic target tracking. The drones were able to track moving targets and executed multi-step loops between objects in entirely new environments. 

MIT CSAIL’s team hopes that the drones’ ability to learn from limited expert data and understand a given task while generalizing to new environments could make autonomous drone deployment more efficient, cost-effective and reliable. Liquid neural networks could also enable autonomous air mobility drones to be as environmental monitors, package deliverers, autonomous vehicles and robotic assistants. 

The research was published in Science Robotics. MIT CSAIL Research Affiliate Ramin Hasani and Ph.D. student Makram Chahine; Patrick Kao ’22, MEng ’22; and Ph.D. student Aaron Ray SM ’21 wrote the paper with Ryan Shubert ’20, MEng ’22; MIT postdocs Mathias Lechner and Alexander Amini; and Rus. The research was partially funded by Schmidt Futures, the U.S. Air Force Research Laboratory, the U.S. Air Force Artificial Intelligence Accelerator, and the Boeing Co. 

The post MIT uses liquid neural networks to teach drones navigation skills appeared first on The Robot Report.

The MIT team tested its collision avoidance system in a flight environment with six drones and in simulation. | Source: MIT

A research team from MIT created a trajectory-planning system called Robust MADER that can allow drones working together in the same airspace to pick safe paths forward without crashing into each other. The algorithm is an updated version of MADER, a 2020 project that worked well in simulation but didn’t hold up in real-world testing. 

The original MADER system involved each agent broadcasting its trajectory so fellow drones know where it’s planning to go. In simulation, this worked without problems, with all drones considering each other’s trajectories when planning their own. When put to the test, the team found that it didn’t take into account delays in communication between drones, resulting in unexpected collisions. 

“MADER worked great in simulations, but it hadn’t been tested in hardware. So, we built a bunch of drones and started flying them. The drones need to talk to each other to share trajectories, but once you start flying, you realize pretty quickly that there are always communication delays that introduce some failures,” Kota Kondo, an aeronautics and astronautics graduate student, said.

Robust MADER is able to generate collision-free trajectories for drones even when there is a delay in communications between agents. The system is an asynchronous, decentralized, multiagent trajectory planner, meaning each drone formulates its own trajectory and then checks with drones nearby to ensure it won’t run into any of them. 

The drones optimize their new trajectories using an algorithm that incorporates the trajectories they received from nearby drones, and agents constantly optimize and broadcast new trajectories to avoid collisions. 

To get around any delays in sharing trajectories, every drone has a delay-check period, where it spends a fixed amount of time repeatedly checking for communications from other agents to see if its new trajectory is safe. If it finds a possible collision, it abandons the new trajectory and keeps going on its current one. The length of this delay-check period depends on the distance between agents and other environmental factors that could hamper communications. 

While the system does require all drones to agree on each new trajectory, they don’t all have to agree at the same time, making it a scalable system. It could be used in any situation where multiple drones are working together in the same airspace like spraying pesticides over crops. 

The MIT team ran hundreds of simulations in which they artificially introduced communication delays, and found that MADER was 100% successful at avoiding collisions. When tested with six drones and two aerial obstacles in a flight environment, Robust MADER was able to avoid all collisions, while the old algorithm would have caused seven collisions. 

Moving forward, the research team hopes to put Robust MADER to the test outdoors, where obstacles can affect communications. They also hope to outfit drones with visual sensors so they can detect other agents or obstacles, predict their movements and include that information in trajectory optimizations. 

Kota Konda wrote the paper with Jesus Tordesillas, a postdoc; Parker C. Lusk, a graduate student; Reinaldo Figueroa, Juan Rached, and Joseph Merkel, MIT undergraduates; and senior author Jonathan P. How, the Richard C. Maclaurin Professor of Aeronautics and Astronautics, a principal investigator in the Laboratory for Information and Decision Systems (LIDS), and a member of the MIT-IBM Watson AI Lab. This work was supported by Boeing Research and Technology.

The post MIT researchers create algorithm to stop drones from colliding midair appeared first on The Robot Report.