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
- North America Defense & Security Drones Markets, 2014-2018 & 2019-2025on July 23, 2019 at 4:30 am
DUBLIN, July 23, 2019 /PRNewswire/ -- The "North America Defense & Security Drones Market by Subsystem, UAV Type, Technology, End-user, Application, Frame, Range, Propulsion, Endurance, MTOW ... […]
- Yemeni Drones Launch Fresh Attack on Saudi Airbaseon July 23, 2019 at 3:08 am
The spokesman for Yemeni Armed Forces, Brigadier General Yahya Saree, said several Qasef-K2 (Striker-K2) combat drones had targeted the airbase near the city of Khamis Mushait on Tuesday morning, ... […]
- Drones Create Fascination at a University Gala Event With a Dancing Drone Show by TLC Creativeon July 23, 2019 at 1:32 am
Drone entertainment takes off for TLC Creative, as they bring creative, indoor team drone challenges and indoor dancing drone shows to corporate and private events. Special event guests are surprised ... […]
- Drones watch every U.S. ship in the Gulf, Iran’s navy chief claimson July 23, 2019 at 12:33 am
DUBAI — A fleet of drones has allowed Iran to watch every U.S. ship in the Persian Gulf region and develop an archive of their daily movements, Iran’s top naval commander said in an interview ... […]
- 3 Ways Drones can Help the Firefighterson July 23, 2019 at 12:31 am
With the inclusion of drone technology, firefighters can work more efficiently and effectively. FREMONT, CA: Presently, the technologically developed nations are employing drone technology to solve ... […]
- Drones Have Become A Lifesaving Tool For Fighting AZ Wildfireson July 22, 2019 at 4:59 pm
The whir of aerial drones provided a distinct soundtrack to the month it took to contain the Woodbury Fire, which ranks as the fifth-largest wildfire in Arizona history. The fire burned nearly ... […]
- VC Funding For Drones Surges In 2019, With More Focused Betson July 22, 2019 at 1:44 pm
3D Robotics, a Berkeley, Calif.-based company that's the second-largest venture capital bet in the sector, tried to compete against Chinese consumer drones, lost big and exited the market. It scaled ... […]
- Top Gun pilots' split-second timing outmatches drones, former Navy strike fighter tactics instructor sayson July 22, 2019 at 11:54 am
“Top Gun: Maverick,” the highly anticipated sequel to the 1980s classic, features the return of Tom Cruise as Lt. Pete “Maverick” Mitchell as he and other pilots wrestle with the new age of drone ... […]
- Drones Market 2019 Global Production Technology, Demand and Development Trend Research Report to 2028on July 22, 2019 at 8:28 am
A drone is either functioned by an onboard computer, controlled autonomously, or remotely by a human pilot. The size of a drone varies from small sized ones driven by electric motors to the large ... […]
- Agriculture Robots & Drones Market NextGen Technological Advancements, Professional Survey and Future Industry Trends 2024on July 22, 2019 at 8:03 am
Jul 22, 2019 (HTF Market Intelligence via COMTEX) -- AMA recently published a detailed study of over 180+ pages in its repository on 'Agriculture Robots & Drones' market covering interesting aspects ... […]
via Bing News