Watch these autonomous drones zip through the woods – ZDNet

Drones trained using “privileged expert” achieve amazing abilities.
By for Robotics | October 26, 2021 | Topic: Robotics

Expert human drone pilots have proven incredibly adept at piloting UAV through complex courses at high speeds which are still unmatched by autonomous systems. But researchers at the University of Zurich and Intel Labs are collaborating to change that, and their work, recently presented in the journal Science Robotics, could have far-reaching implications for the future of commercial drones.
“Autonomous navigation in environments where conditions are constantly changing is restricted to very low speeds,” explains Matthias Müller, Lead of Embodied AI Lab at Intel Labs. “This makes drones unable to operate efficiently in real-world situations where something unexpected may block their path and time matters.”
That’s obviously a big impediment to safely rolling out drones for commercial use. The solution seems to be harnessing the decision-making abilities of expert pilots to train drones to function autonomously.
“In partnership with the University of Zurich, we were able to show how a drone trained exclusively in simulation by imitating an expert pilot is able to perform in challenging real-world scenarios and environments that weren’t used during the training of the convolutional network,” says Müller. “The trained autonomous drone was able to fly through previously unseen environments, such as forests, buildings and trains, keeping speeds up to 40 km/h, without crashing into trees, walls or any other obstacles – all while relying only on its onboard cameras and computation.”
The results were achieved by having the drone’s neural network learn from a simulated expert pilot that flew a virtual drone through a simulated environment full of complex obstacles. The expert had access to the full 3D environment while the drone’s neural network only had access to the camera observations with realistic sensor noise and imperfect state estimation. 
That input imbalance (what researchers call a “privileged expert”) forced the drone to learn to act with exceptional dexterity in less than ideal conditions. The quadrotor demonstrated a decrease in the latency between perception and action while simultaneously demonstrating resiliency in the face of perception artifacts, such as motion blur, missing data, and sensor noise.
“Existing systems use sensor data to create a map of the environment and then plan trajectories within the map – these steps require time and errors compound, making it impossible for the drones to fly at high speeds,” says Müller. “Unlike current systems, future drones could learn navigation end-to-end in a simulated environment before going out into the real-world. This research shows significant promise in deploying these new systems in a wide array of scenarios including disaster relief, construction sites, search and rescue, agriculture and logistics, and more.”
One of the benefits of this system is its applicability to a wide variety of real-world environments. The approach demonstrated in the research involved experiments that tested in a set of human-made environments (e.g. simulated disaster zone and urban city streets) and also diverse natural environments (forests of different types and densities and steep snowy mountain terrains). Future application areas for the technology could be disaster relief scenarios, construction sites, search and rescue, agriculture and logistics, and delivery.
By for Robotics | October 26, 2021 | Topic: Robotics
Robotics
Meet Japan’s drone traffic management system
Robotics
New Age of Sail combines robots and sailboats
Virtual Reality
VR for mental health and memory
Robotics
Autonomous race cars to battle at Indy Speedway
Please review our terms of service to complete your newsletter subscription.
You agree to receive updates, promotions, and alerts from ZDNet.com. You may unsubscribe at any time. By joining ZDNet, you agree to our Terms of Use and Privacy Policy.
You agree to receive updates, promotions, and alerts from ZDNet.com. You may unsubscribe at any time. By signing up, you agree to receive the selected newsletter(s) which you may unsubscribe from at any time. You also agree to the Terms of Use and acknowledge the data collection and usage practices outlined in our Privacy Policy.
Meet Japan’s drone traffic management system
Air traffic control for drones is paving the way for commercial UAV delivery.
Transport for NSW to investigate the use of driverless rideshare services
Using autonomous vehicles on state and local roads is one of the priorities set out in the NSW government’s future transport technology roadmap.
New Age of Sail combines robots and sailboats
One man’s quest to use sailboats for science.
Best robot vacuum 2021: Roomba isn’t your only option
The year’s best robot vacuums so far — single and multi-function — at a range of prices.
Autonomous race cars to battle at Indy Speedway
The first-ever event showcases open source development in driverless race cars.
Robots for kids: Best STEM kits and other tech gifts for hackers of all ages
If you want to spark the imagination of your kids and help them hone tech skills they’ll need as adults, check out this list of our favorite tech toys. …
Back pain reducing exoskeleton for e-commerce workers
The exoskeleton market might just hit its stride in e-commerce fulfillment.
Navy to organize maritime robot competition
The future of sea supremacy will very likely be autonomous.
Australia signs deal with NASA to send a rover to the moon
An Australian-built semi-autonomous rover will be developed to examine oxygen found in lunar soil.
© 2021 ZDNET, A RED VENTURES COMPANY. ALL RIGHTS RESERVED. Privacy Policy | Cookie Settings | Advertise | Terms of Use

source