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
- China develops multi-functional swarm drones capable of mid-air separationon March 19, 2024 at 12:52 am
Chinese researchers unveil a groundbreaking combat drone that can split into smaller drones, revolutionizing military tactics. Inspired by nature, these segmented drones mimic maple seeds' aerodynamic ...
- US Destroys Houthi Missiles, Drones in New Yemen Strikeon March 19, 2024 at 12:19 am
The U.S. military said it destroyed seven missiles and three drones Monday in areas of Yemen controlled by Houthi rebels that presented threats to merchant ships and U.S. Navy vessels. Iran-backed ...
- Drones are key to gain advantage over Russia, Ukraine army chief sayson March 18, 2024 at 8:32 pm
The development of unmanned systems, or drones, is key to give Kyiv an advantage over "a numerically superior" Russian forces, Ukraine's Commander-in-Chief Oleksandr Syrskyi said late on Monday.
- Chinese scientists create swarming drones that can rapidly multiply mid-air to create a tactical shockon March 18, 2024 at 8:00 pm
Once this new device reaches the target airspace it can split in the blink of an eye into two, three or even six smaller drones, depending on battle needs Like many researchers in the history of drone ...
- US strikes drones and missiles in Houthi controlled areas of Yemenon March 18, 2024 at 7:44 pm
The US armed forces said that they carried out self-defence strikes against drones, missiles and weapons storage containers in areas of Yemen controlled by the Iran-backed Houthi militia on Monday.
- U.S. military sea drones warn of potential threatson March 18, 2024 at 4:29 pm
Sea drones that work on and below the surface are helping the military patrol the dangerous seas in the Middle East. NBC News' Courtney Kube got an exclusive look at how they work.
- Gunvor Says Drones Shut 600,000 Barrels of Russian Refiningon March 18, 2024 at 10:52 am
Gunvor Group Ltd. Chief Executive Officer Torbjörn Törnqvist estimates about 600,000 barrels of Russia’s daily oil-refining capacity has been knocked out by Ukrainian drone strikes.
- Russian refineries targeted by Ukraine's droneson March 18, 2024 at 6:23 am
Ukraine has been striking Russian oil refineries in heavy drone attacks, causing a fire at Rosneft's biggest refinery in what President Vladimir Putin said was an attempt to disrupt the presidential ...
- Ukrainian government allocating $128 million for procurement of attack droneson March 18, 2024 at 4:41 am
The Ukrainian government is allocating an additional Hr 5 billion (around $128 million) to purchase attack drones for the military, Economy Minister Yuliia Svyrydenko announced on March 18.
- EVs With Built-In Camera Drones Have Already Landed in Chinaon March 17, 2024 at 11:00 pm
Still the stuff of concepts and flights of fancy in the West, automakers on the other side of the world are putting copters in their cars.
via Bing News