New system employs a deep neural network to overcome the challenge of ground-effect turbulence
Landing multi-rotor drones smoothly is difficult. Complex turbulence is created by the airflow from each rotor bouncing off the ground as the ground grows ever closer during a descent. This turbulence is not well understood nor is it easy to compensate for, particularly for autonomous drones. That is why takeoff and landing are often the two trickiest parts of a drone flight. Drones typically wobble and inch slowly toward a landing until power is finally cut, and they drop the remaining distance to the ground.
At Caltech’s Center for Autonomous Systems and Technologies (CAST), artificial intelligence experts have teamed up with control experts to develop a system that uses a deep neural network to help autonomous drones “learn” how to land more safely and quickly, while gobbling up less power. The system they have created, dubbed the “Neural Lander,” is a learning-based controller that tracks the position and speed of the drone, and modifies its landing trajectory and rotor speed accordingly to achieve the smoothest possible landing.
“This project has the potential to help drones fly more smoothly and safely, especially in the presence of unpredictable wind gusts, and eat up less battery power as drones can land more quickly,” says Soon-Jo Chung, Bren Professor of Aerospace in the Division of Engineering and Applied Science (EAS) and research scientist at JPL, which Caltech manages for NASA. The project is a collaboration between Chung and Caltech artificial intelligence (AI) experts Anima Anandkumar, Bren Professor of Computing and Mathematical Sciences, and Yisong Yue, assistant professor of computing and mathematical sciences.
A paper describing the Neural Lander was presented at the Institute of Electrical and Electronics Engineers (IEEE) International Conference on Robotics and Automation on May 22. Co-lead authors of the paper are Caltech graduate students Guanya Shi, whose PhD research is jointly supervised by Chung and Yue, as well as Xichen Shi and Michael O’Connell, who are the PhD students in Chung’s Aerospace Robotics and Control Group.
Deep neural networks (DNNs) are AI systems that are inspired by biological systems like the brain. The “deep” part of the name refers to the fact that data inputs are churned through multiple layers, each of which processes incoming information in a different way to tease out increasingly complex details. DNNs are capable of automatic learning, which makes them ideally suited for repetitive tasks.
To make sure that the drone flies smoothly under the guidance of the DNN, the team employed a technique known as spectral normalization, which smooths out the neural net’s outputs so that it doesn’t make wildly varying predictions as inputs or conditions shift. Improvements in landing were measured by examining deviation from an idealized trajectory in 3D space. Three types of tests were conducted: a straight vertical landing; a descending arc landing; and flight in which the drone skims across a broken surface—such as over the edge of a table—where the effect of turbulence from the ground would vary sharply.
The new system decreases vertical error by 100 percent, allowing for controlled landings, and reduces lateral drift by up to 90 percent. In their experiments, the new system achieves actual landing rather than getting stuck about 10 to 15 centimeters above the ground, as unmodified conventional flight controllers often do. Further, during the skimming test, the Neural Lander produced a much a smoother transition as the drone transitioned from skimming across the table to flying in the free space beyond the edge.
“With less error, the Neural Lander is capable of a speedier, smoother landing and of gliding smoothly over the ground surface,” Yue says. The new system was tested at CAST’s three-story-tall aerodrome, which can simulate a nearly limitless variety of outdoor wind conditions. Opened in 2018, CAST is a 10,000-square-foot facility where researchers from EAS, JPL, and Caltech’s Division of Geological and Planetary Sciences are uniting to create the next generation of autonomous systems, while advancing the fields of drone research, autonomous exploration, and bioinspired systems.
“This interdisciplinary effort brings experts from machine learning and control systems. We have barely started to explore the rich connections between the two areas,” Anandkumar says.
Besides its obvious commercial applications—Chung and his colleagues have filed a patent on the new system—the new system could prove crucial to projects currently under development at CAST, including an autonomous medical transport that could land in difficult-to-reach locations (such as a gridlocked traffic). “The importance of being able to land swiftly and smoothly when transporting an injured individual cannot be overstated,” says Morteza Gharib, Hans W. Liepmann Professor of Aeronautics and Bioinspired Engineering; director of CAST; and one of the lead researchers of the air ambulance project.
Learn more: “Neural Lander” Uses AI to Land Drones Smoothly
The Latest on: Drones
[google_news title=”” keyword=”drones ” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Drones
- The US moves toward banning DJI droneson April 26, 2024 at 10:00 am
The "Countering CCP Drones Act" ban bill could force DJI drones out of US due to security risks. Rep. Stefanik claims DJI threatens national security as it passes data to China. DJI's ties to ...
- Drones, GPS Trackers Used in Multi-State Burglary Ring With Victims in RI — Fugitive Arrestedon April 26, 2024 at 9:52 am
A fugitive has been arrested and arraigned in a multi-state burglary ring, United States Attorney Zachary A. Cunha announced on Friday.
- ‘Loyal wingman’ fighter drones tested for first time in Britainon April 26, 2024 at 8:57 am
Loyal wingman” fighter drones that will fly alongside British aircraft are a step closer to reality after the technology was successfully tested for the first time.
- Ukraine Sidelines Expensive US Tanks After Russian Drones Keep Attacking Themon April 26, 2024 at 8:50 am
Ukraine has withdrawn expensive U.S.-donated M1A1 Abrams main battle tanks from the front lines after Russian drones destroyed five of the heavy Western tanks it fought for months to obtain, The ...
- The British Navy Will Use Lasers To Zap Drones Out Of The Sky: Here's Howon April 26, 2024 at 7:45 am
Instead of using expensive ordinance to shoot down missiles, what if we used a futuristic laser instead? That's what the British Navy is working on.
- Cheap Russian drones overwhelm US-made Abrams tanks, taken out of actionon April 26, 2024 at 6:27 am
By bne IntelliNews Ukrainian forces are withdrawing US-provided Abrams M1A1 main battle tanks from the front lines after at least five have been destroyed by cheap Russian drones, according to the AP.
- Duel In The Dark: Russian Snipers Battle Baba Yaga Droneson April 26, 2024 at 5:38 am
Russia's is deploying snipers with thermal imaging sights to tackle Baba Yaga night bombing drones — but the drones have a new trick up their sleeve.
- Bipartisan bill seeks to grow NASA program using drones to fight wildfireson April 26, 2024 at 2:00 am
New legislation attempts to improve NASA’s Advanced Capabilities for Emergency Response to Operations program so firefighters can more effectively use drones.
- Ukraine withdraws Abrams tanks from front line because of Russian drones – APon April 25, 2024 at 10:50 pm
The Associated Press has learned that the Ukrainian Defence Forces have withdrawn US-supplied Abrams tanks from the front line because of the threat of attacks by Russian drones, while the Americans ...
- DJI Unveils Agras T50 and T25 Drones for Enhanced Agricultural Productivityon April 25, 2024 at 8:35 am
New Models Offer Advanced Features for Efficient Crop Management with Upgraded SmartFarm App DJI, a global leader in civilian drones and creative camera technology, today launched the Agras T50 and T2 ...
via Bing News