Landing Smoothly

by | Oct 15, 2020

AI To Land Drones Smoothly

 

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.

Credits: wevolver.com 

Robot compare

Science Fiction or Science Fact?

Is there a difference between Science Fiction and Science Fact? Well in most cases there are, however as technology relentlessly moves forward the line between

Wireless In-Flight Drone Recharging Tech For Prime Air

Amazon Prime Air is a drone delivery service that Amazon has been touting for almost four years now. Amazon’s drone delivery service delivered its first package on December 7, 2016. Almost four years later, it’s still a “future delivery system.” What’s missing? Probably something like wireless in-flight drone recharging from the tiny Portland-based Global Energy […]

World’s biggest drone — a 28-ton autonomous behemoth

Alabama rocket startup Aevum just unveiled the world’s biggest drone — a 28-ton autonomous behemoth that may soon rocket US military satellites into orbit Jay Skylus, the CEO of autonomous launch startup Aevum, stands in front of a Ravn X rocket-launching drone. Aevum Aevum, a quiet, scrappy, and ambitious rocket-launch startup, unveiled the biggest drone […]

3d printed rocket Relativity

3D printed rockets – the future of space exploration

Full-duration test of Aeon 1 rocket engine. Relativity Space said Monday that the company has successfully completed a full-duration test-firing of its Aeon 1 rocket engine, running it at full power for 187 seconds. The test at NASA’s Stennis Space Center in Mississippi took place with all of the engine’s key components—including turbopumps, injector, and […]

Drone Privacy Laws Around the World

As the use of drones expands around the world — according to the Federal Aviation Administration, there are currently 1.7 million drones registered in the United States alone — lawmakers have been faced with new and complex regulatory challenges to protect the privacy of ordinary citizens. The increased prevalence of drones has raised the prospect […]

Switching to Skydio and Increase Per-Pilot Revenue 37%

This blog is a teaser and summary of a longer-form written case study, available here at Skydio.com. One of the best parts of my job is talking to customers and listening to their stories about the way that Skydio 2 is changing the way they fly and in some cases, the way they fundamentally do […]

Fotokite – Tethered 24hr First Responder Drone

Fotokite already offers a clever response to two challenges for deploying drones: limited battery life and the need for a certified pilot. And now it’s tackling a third challenge with its new product: How to deploy a drone as quickly as possible in a first responder situation. Drones can be a tremendous asset to first […]

Skydio Autonomy™. A new age of drone intelligence

In last week’s blog, I shared with you some of the ways Skydio X2 was built to meet the needs of some of the drone industry’s most forward-thinking fleets. This week, I’d like to share some ideas about autonomy — what true autonomy is and why it matters, and how it will impact drone operations […]

DRONAMICS Announces World’s First Cargo Droneport Network

DRONAMICS, the world’s leading middle-mile cargo drone developer and operator, today unveiled the first 5 airports in its European network of cargo droneports. The DRONAMICS European Droneport Network is the world’s first cargo droneport network and includes private airports and airport groups operating more than 35 airports in 11 European countries, connecting 300 million […]

Non-Stop Flight from California to Sicily Completes NATO UAV Squadron

An RQ-4D Phoenix UAV from Northrop Grumman Corporation completed a 20-hour non-stop trans-Atlantic flight from California to Sicily, where it joined the NATO Alliance Ground Surveillance (AGS) squadron on Nov. 12 at Sigonella Air Base. The air vehicle is the last of five NATO RQ-4D aircraft, completing deliveries to the Main Operating Base (MOB) of […]

Request a NO OBLIGATION quote

The cost of a survey or inspection is simple to calculate, but is dependant on the mission and its location. Please provide details in order to complete an accurate quotation.  Get in touch we’ll be happy to provide a no obligation quotation

“Opportunities for the commercial application of drones is set to continue to grow…”

Digital Marketing Solutions

Have you looked at creating a promo for your business and found it too costly and complicated?

It’s time to impress your client base with affordable marketing solutions from Helix UAV. We can create a fully edited promotional film or you can have the raw footage (it’s yours).

To take your businesses potential to the next level lets show them what you’ve got.

3D imaging of objects and structures that can be interactively manipulated on your web page for your marketing purposes is now possible. You no longer need NASA you need Helix UAV.

Aerial Inspection

Aerial Surveying

Aerial Media

Aerial Imaging

Icon Logo for Helix UAV Drone Services 2

CORONAVIRUS

 

Government organisations or subsidiaries wishing to request assistance from Helix UAV during this extremely difficult time can send their requests via our dedicated email address:

 

coronavirus@helixuav.com

 

07480 041928

 

Please use the form below if you wish to subscribe to our news service. Please follow government guidelines and stay safe

 

HELIX UAV

 

 
 
 

You have sent your message