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
via Google News
The Latest on: Drones
- Turkey’s armed drones bolster Erdogan’s hard-power tacticson October 7, 2020 at 9:00 pm
Azerbaijan’s military has published slick footage of Turkish-made armed drones blitzing scores of Armenian positions, striking air defence systems, artillery units and tanks. Nagorno-Karabakh is the ...
- Karabakh Capital Struck By Rockets, Droneson October 7, 2020 at 5:51 am
Karabakh region was targeted in heavy strikes by Azerbaijani forces overnight and Wednesday morning, an AFP correspondent said.
- FAA Waives Rules To Allow Drones To Inspect Bridges In North Carolinaon October 7, 2020 at 4:41 am
The FAA granted North Carolina a blanket waiver to fly Skydio drones beyond visual line of sight, for bridge inspections anywhere in the state for four years.
- How Azerbaijan's Drones Show what the Future War Looks Like | Opinionon October 7, 2020 at 3:00 am
The leading drone powers—Washington and Beijing—should be watching Azerbaijan and Armenia and learning about how drone swarms and loitering munitions work best.
- The FAA is opening the door a crack for self-flying drones like Skydio to reach their potentialon October 6, 2020 at 6:37 pm
But what happens when drones get smarter, and can dodge obstacles on their own? That’s the kind of drone that Skydio builds, and it appears to be successfully convincing the FAA to create exceptions ...
- New Navy shipbuilding plan calls for about 500 ships -- including 150 droneson October 6, 2020 at 5:15 pm
The Pentagon plans to build up a fleet of about 500 ships -- with 355 of those being manned and the rest being drones, according to documents released this week.
- New Functional Safety Test Bed For Autos, 5G And Droneson October 6, 2020 at 5:10 am
AERPAW has a $24M grant to build the U.S.’s first aerial, wireless experimentation platform including 5G cellular technology, vehicles and aerial systems. Researchers from various universities, ...
- Atlanta Falcons Using Drones To Cleanse Stadium Of Coronaviruson October 5, 2020 at 9:26 pm
When the Atlanta Falcons greet fans for the first time this season Sunday against the Carolina Panthers, Mercedes-Benz Stadium will be coronavirus clean — thanks to a pair of drones. Falcons ...
- Halloween Events, Drones Clean Stadium, Stores Close: News Nearbyon October 5, 2020 at 1:00 pm
Top news includes Falcons using drones to clean, stores closing in GA and Halloween events. How to share news, events on Patch.
- Skydio gains FAA approval to conduct bridge inspections with drones in North Carolinaon October 5, 2020 at 8:22 am
Skydio and the North Carolina Department of Transportation have gained FAA approval to conduct bridge inspections with drones in the state.
via Bing News