The State of Robotics – 2022 news rewind

Welcome to our 2022 robotics news rewind! We’ll be highlighting some of the most impressive feats of robotics engineering that we covered throughout the year in our robotics news series. 

It’s incredible to see the progress that has been made in the robotics field this year. We’d like to take this time to thank all of the engineers, scientists, and technicians who have dedicated themselves to pushing the boundaries of robotics technology. Without their hard work and dedication, robotics would not have become the incredible field that it is today. Thank you all!

This was 2022!

Bringing assistive robots – Labrador Retriever Robot

Video Source: Labrador Systems 

As we age or face physical limitations, moving objects around the house become a major blocker for living independently. But robotics has the potential to support those in need of an extra hand. And Labrador is just that robot. This semi-autonomous mobile table fulfils its mission flawlessly, empowering those to move objects in their house. From groceries to books, it moves a variety of things around the house. Labrador can navigate autonomously in your house, carry a load of up to 11 kg, and adjust its height. Easy to use, practical, and smart. Labrador is a great example of home automation.

Playing again – University of Tsukuba, Digital Nature Group

Video Source: Digital Nature Group 

Robots will soon help us retake our favourite sports even if our physical abilities limit us. This is the basic idea behind the Drone badminton project developed at the University of Tsukuba. This innovative drone enables people with low vision to play badminton using a drone as a ball and a special racket capable of moving the drone by the movement of the player. This unique robot has the potential to diversify the physical activities available and improve the physical and mental health of people with low vision. 

Improving safety – Australian Droid+Robot

Video Source: Rajant Corporation 

When accidents hit, robots are also there for us. One of the United States’ largest underground limestone mining operations suffered a pillar and roof collapse. Luckily there were no injuries. And luckily, Australian Droid+Robot was around. Their mobile robots were able to go beyond the collapsed section and inspect all the required areas autonomously feeding video data at up to 80 Mbps, something unprecedented in mining. The inspection made it possible to re-enter the operation and begin remediation efforts. An important milestone for the industry.

Sky’s the limit – AirCar

Video Source: Klein Vision

Another milestone was achieved in the aviation or automotive industry. Well, this is up to you to decide. AirCar, a dual-mode car-aircraft vehicle, moved closer to production as airworthiness certification in Slovakia was granted. The challenging flight tests included the full range of flight and performance manoeuvres and demonstrated astonishing static and dynamic stability in the aircraft model. AirCar flew 70+ hours of test flights, including cross-country flights with 200 takeoffs and landings.

Robots for music – Georgia Tech Center for Music Technology

Video Source: Georgia Tech Center for Music Technology

Robotics is amazing, but what we can do together is groundbreaking. This project combines computational modelling approaches for perception, interaction, and improvisation, with precise locomotion to develop a real-time collaboration between human and robotic players. Combining human qualities with robotic traits, researchers are expanding the horizon of automation. 

Modular robotics – The Chinese University of Hong Kong

Video Source: Robotics & AI Lab – CUHK Shenzhen

This is a mesmerising research project! Presenting FreeSN, a modular self-reconfigurable robot made of strut and node modules. On one hand, the node modules are mainly a low-carbon steel spherical shells. On the other hand, the strut modules contain two freeform connectors that provide strong magnetic connections and flexible spherical motions. FreeSN shares the benefits of freeform connection and strut-node structures. This means good adaptability to the environment and improved structural stability, which allow swarm systems to tackle different scenarios and tasks. 

Reconfigurable robot –
HCI Engineering group, MIT CSAIL

Video Source: MIT CSAIL HCI Engineering Group

Meet Electro Voxel, a reconfigurable robot that utilises electromagnet-based actuation to reconfigure its structure in three dimensions. Every cube-based node can reposition via pivoting. The electromagnets embedded into the edges of each cube, interchangeably create identically and oppositely polarised electromagnet pairs, resulting in repulsive or attractive forces, respectively. The robot has also been tested in microgravity on a parabolic flight to explore future uses of this technology in zero gravity. 

Flying like a bird – GRIFFIN ERC

Video Source: GRVC Robotics Laboratory

Now, a research project that is certainly taking off! This is an autonomous flapping-wing robot. With onboard perception and manipulation capabilities, this bioinspired robot flies like a bat. Armed with 3 tails, this robot has good lateral manoeuvrability and is able to take off with short distances in vertical take-offs. The bioinspired design also allows the robot to reach velocity performance up to 10 m/s. Charged with a perception module, the robot is capable of taking manoeuvres based on the environment and the task assigned.    

A robotic ibex – Kawasaki

Video Source: Kazumichi Moriyama

Bex is a quadruped walking robot that takes advantage of the walking technology developed in humanoid robots. Bex can carry light cargo, such as transporting materials at farms. The robot is capable of carrying up to 100 kilograms. Other applications involve inspection in vast industrial plants. And, of course, it can also take you for a ride.  

Going faster – Toyota Research Institute 

Video Source: Toyota Research Institute

But we can go faster. Way faster with the Toyota Research Institute which has been teaching cars to autonomously drift. They have successfully programmed a vehicle to autonomously drift around obstacles on a closed track, providing a glimpse into the future of safer mobility for all. The idea behind this research is to utilise controlled, autonomous drifting to avoid accidents by navigating sudden obstacles or hazardous road conditions like black ice.

Going smaller – SquRo, Beijing Institute of Technology  

Video Source: IEEE Spectrum

This is SquRo, a robot developed by the Beijing Institute of Technology. The robot can walk, crawl, climb over objects, and turn sharply with great agility. Researchers first used X-Rays of real rats to better understand the animal’s anatomy. They then designed SQuRO to have a similar structure, movement patterns, and degrees of freedom. As a result, the robot can overcome obstacles 30 millimetres high – or 33 per cent of its own height.

Crawling like no other – Suzumori Endo Lab, Tokyo Institute of Technology  

Video Source: Suzumori Endo Robotics Laboratory

This next robot developed by Suzumori Endo Lab can also move through tight spaces. The robot can move forward in an unknown space as it recognises and adapts to the spatial shape of the environment. The key feature of this robot is the tensegrity structure that allows it to actively generate propulsive force as it presses its body against a wall in its surrounding environment. It includes a novel artificial muscle arrangement that induces large deformation in the tensegrity structure. The muscle arrangement allows the displacements in the axial and radial directions. 

A path for saving lives – MIT

Video Source: Kim Yoonho

Robots can also help us move objects where no one can. For example, inside our body. Check how this robotic arm is guiding a soft and thin magnetic wire through arteries and vessels by using magnetic actuators. This system developed by MIT’s researchers aims to help surgeons quickly and remotely treat patients experiencing a stroke or aneurysm, clearing clots. With a modified joystick, surgeons in one hospital may control a robotic arm at another location to safely operate on a patient during a critical window of time that could save the patient’s life and preserve their brain function.

A new DARPA challenge – University of Washington

Video Source: University of Washington Robot Learning Lab

DARPA is now sending high-speed autonomous vehicles off-road! This year, we start a 3-year journey, pushing the limits of all-terrain racing. This video shows a test of autonomous off-road driving conducted by University of Washington researchers. Compared to on-road driving, off-road terrain lacks man-made structure and contains challenging features including vegetation, uneven and low-friction surfaces, reduced visibility and rapidly changing terrain surface properties. Researchers aim to improve existing approaches to perception, planning, and control. 

Going open source – Skybrush 

Video Source: COLLMOT

We stand behind open-source projects since they make way for innovation. Just take a look at Skybrush, a drone-show management platform! In early May, Skybrush announced the release of their ultimate multi-UAV mission and drone show management platform as an open-source project. Skybrush has also advanced on the drone swarm research front, with 30, 50, and up to 100 autonomous drones flying together in different cooperative scenarios. Besides putting on an impressive show, the drone orchestration platform can be used in other industries. It has practical applications for agriculture, surveillance and delivery – among other use cases.

Delivery robots – Wing

Video Source: Wing

Look at Wing and its drone delivery system, which is growing in Australia. The company allows small businesses to access a delivery infrastructure. Companies can ship their products through a system of different bases in the city, called wing nests. Once on the wing nest, drones can travel up to 6 miles in 6 minutes. This covers a wide range of houses. The delivery zones can expand as more wing nests get added to the network. 

Drones and wind – California Institute of Technology

Video Source: Autonomous Robotics and Control Lab at Caltech

But for drones to autonomously perform delivering tasks, they need to be able to adapt to wind conditions in real-time. This is a field that is not well understood yet. A team of engineers from Caltech is expanding our knowledge in this area. They developed Neural-Fly, a deep-learning method that can help drones cope with new and unknown wind conditions in real-time by incorporating pre-trained representations through deep learning. Neural-Fly uses an algorithm to learn the shared representation, using only 12 minutes of flight data. With the learned representation, Neural-Fly achieves precise flight control with substantially smaller tracking errors. It’s been used to improve drone performance at wind speeds ranging up to 43.6 kilometres per hour.

Food-tasting robots – University of Cambridge

Video Source: Cambridge University

Researchers from the University of Cambridge trained Beko to assess the saltiness of a dish at different stages of the chewing process, imitating a process that is similar in humans. Beko, which has already been trained to make omelettes, tasted nine different variations of scrambled eggs and tomatoes at three different stages of the chewing process. The researchers attached a conductance probe to the robot arm, which acts as a salinity sensor. Their results showed a significant improvement in the ability of robots to assess saltiness over other electronic tasting methods. And in case you were wondering, the food was blended to imitate the change in texture caused by chewing. Yum!

Robotics world cup – B-Human

Video Source: Team B-Human

But enough talk about food. What about a workout? We’ll wrap up this series with a great play from the RoboCup German Open 2022. During the final match, we saw a B-Human robot deliver an awesome assist. Watch right after kickoff as the robot in the black jersey, the one closest to the ball, dashes off-screen to the left, to a free space. As it turns out, it’s a perfect position to receive a brilliant pass. As its team player dribbles, pushing the ball further to the opponent’s half, the first robot is patiently waiting. With the opening, the robot takes its chances and passes the ball to the initial robot. Beautiful pass, excellent control and outstanding definition. Remember, these robots are operating fully autonomously! Pretty impressive. 

A robot learns to imagine itself – Columbia University

Video Source: Columbia Engineering

Researchers from Columbia University developed a visual self-model using deep neural networks that allowed a robot to learn the relationship between its motor actions and the volume it occupied in its environment. The researchers placed a robotic arm inside a circle of five streaming video cameras. The video footage was fed to the network as the robot wiggled and contorted. This allowed it to learn exactly how its body moved in response to various motor commands. After about three hours, the robot learned the relationship between its motor actions and the volume it occupied in its environment. Much like an infant exploring itself for the first time in a hall of mirrors. 

Textile robot – Columbia University

Video Source: UNSW Community

Researchers at the University of New South Wales are also working on an impressive project. They developed a new class of smart textiles that can shape-shift and turn two-dimensional material into 3D structures. The material is constructed from tiny soft artificial muscles. These muscles are long silicone tubes that can change shape thanks to hydraulics. The artificial muscles can be programmed to contract or expand into a variety of shapes depending on their initial structure. The smart textile can either be attached to existing passive material or yarn to create an active fabric.

Spider grip – Columbia University

Video Source: Rice University

What’s next is not fabric, but something from a scifi movie. Rice University researchers found a way to use dead spiders as robotic grippers. What started with a dead spider in a lab became a gripper; Necrobotics. If you haven’t noticed yet, spiders’ legs curl up when they die. This is because spiders extend their legs with hydraulic pressure and when spiders die they lose this ability. Researchers tapped into the hydraulic infrastructure of dead spiders using a needle, and by pumping air, they extended the spider’s legs. Releasing the pressure retracted the legs, allowing them to grab objects.

Engagement with our open-source community 

This year, our work and engagement with the robotics community kept growing. We run several events and workshops. This included a webinar series for robotics entrepreneurs that explored spinning out, investment and go to market. We also run a device track inside the Ubuntu Summit with several speakers and amazing hands-on sessions. 

Working with the maintainers, we deploy new tools like Gazebo and Foxglove as snaps for easier installation and management. Finally, our great engineers develop new tutorials and amazing blogs. 

Our responsibility and commitment to the Ubuntu robotics community will keep growing. We will continue creating training and learning programs. We will also improve the hosting and access to these materials for the wider community. Remember, Canonical’s robotics team is your team. 

A year to remember 

This video collects a compilation of 2022 robotics news. Amazing projects developed by amazing people. It ends with a shot from an interview with our friends at Roboat. During the interview, we mentioned that robotics is a journey, and like any other journey, the key is to surround yourself with experienced people. 

Thank you to all the researchers and entrepreneurs that made us dream to keep pushing the limits of robotics. 

As we start 2023, it is your work that will take us to a new chapter of innovation. And we cannot wait to see what you build next. On behalf of Canonical’s robotics team, thank you for an amazing 2022!