• Home
  • About Us
    • Member Directory
    • Contact Us
  • Blogs
    • Scientific Blogs
      • Technology
      • Environment
      • Health
    • Infinity Explorer
    • Traveler Book
    • Life Around
  • Publication
  • Scientific Advisory
  • Project
    • Future Projects
    • Ongoing Projects
    • Previous Projects
  • Services
    • Language Programs
    • Latest Software
    • Environmental Consultancy
    • Internship
    • Exercise
  • Career
    • Masters
    • PHDs
    • Postdoctorals
    • Travel Grants
    • Others

Rapid adaptation of deep learning teaches drones to survive any weather

Rapid adaptation of deep learning teaches drones to survive any weather

Share:

Twitter
Tweet
LinkedIn
Share
Facebook
fb-share-icon
WeChat
Follow by Email
Hardin Bitsky

Hardin Bitsky

Mr. Hardin, a future doctor of pharmacy, provides services as a content writer for scientific and technical niches.

To be truly useful, drones—that is, autonomous flying vehicles—will need to learn to navigate real-world weather and wind conditions.

Right now, drones are either flown under controlled conditions, with no wind, or are operated by humans using remote controls. Drones have been taught to fly in formation in the open skies, but those flights are usually conducted under ideal conditions and circumstances.

However, for drones to autonomously perform necessary but quotidian tasks, such as delivering packages or airlifting injured drivers from a traffic accident, drones must be able to adapt to wind conditions in real time—rolling with the punches, meteorologically speaking.

To face this challenge, a team of engineers from Caltech has developed Neural-Fly, a deep-learning method that can help drones cope with new and unknown wind conditions in real time just by updating a few key parameters.

 

Neural-Fly is described in a study published on May 4 in Science Robotics. The corresponding author is Soon-Jo Chung, Bren Professor of Aerospace and Control and Dynamical Systems and Jet Propulsion Laboratory Research Scientist. Caltech graduate students Michael O’Connell and Guanya Shi are the co-first authors.

Neural-Fly was tested at Caltech’s Center for Autonomous Systems and Technologies (CAST) using its Real Weather Wind Tunnel, a custom 10-foot-by-10-foot array of more than 1,200 tiny computer-controlled fans that allows engineers to simulate everything from a light gust to a gale.

“The issue is that the direct and specific effect of various wind conditions on aircraft dynamics, performance, and stability cannot be accurately characterized as a simple mathematical model,” Chung says. “Rather than try to qualify and quantify each and every effect of turbulent and unpredictable wind conditions we often experience in air travel, we instead employ a combined approach of deep learning and adaptive control that allows the aircraft to learn from previous experiences and adapt to new conditions on the fly with stability and robustness guarantees.”

O’Connell adds, “We have many different models derived from fluid mechanics, but achieving the right model fidelity and tuning that model for each vehicle, wind condition, and operating mode is challenging. On the other hand, existing machine learning methods require huge amounts of data to train yet do not match state-of-the-art flight performance achieved using classical physics-based methods. Moreover, adapting an entire deep neural network in real time is a huge—if not currently impossible—task.”

Neural-Fly, the researchers say, gets around these challenges by using a so-called separation strategy, through which only a few parameters of the neural network must be updated in real time.

“This is achieved with our new meta-learning algorithm, which pre-trains the neural network so that only these key parameters need to be updated to effectively capture the changing environment,” Shi says.

Time-lapse photo shows a drone equipped with Neural-Fly maintaining a figure-eight course amid stiff winds at Caltech’s Real Weather Wind Tunnel. Credit: California Institute of Technology

After obtaining as little as 12 minutes of flying data, autonomous quadrotor drones equipped with Neural-Fly learned how to respond to strong winds so well that their performance significantly improved (as measured by their ability to precisely follow a flight path). The error rate following that flight path is around 2.5 times to 4 times smaller compared to the current state-of-the-art drones equipped with similar adaptive control algorithms that identify and respond to aerodynamic effects but without deep neural networks.

Neural-Fly, which was developed in collaboration with Caltech’s Yisong Yue, Professor of Computing and Mathematical Sciences, and Anima Anandkumar, Bren Professor of Computing and Mathematical Sciences, is based on earlier systems known as Neural-Lander and Neural-Swarm. Neural-Lander also used a deep-learning method to track the position and speed of the drone as it landed and modify its landing trajectory and rotor speed to compensate for the rotors’ backwash from the ground and achieve the smoothest possible landing; Neural-Swarm taught drones to fly autonomously in close proximity to each other.

Though landing might seem more complex than flying, Neural-Fly, unlike the earlier systems, can learn in real time. As such, it can respond to changes in wind on the fly, and it does not require tweaking after the fact. Neural-Fly performed as well in flight tests conducted outside the CAST facility as it did in the wind tunnel. Further, the team has shown that flight data gathered by an individual drone can be transferred to another drone, building a pool of knowledge for autonomous vehicles.

At the CAST Real Weather Wind Tunnel, test drones were tasked with flying in a pre-described figure-eight pattern while they were blasted with winds up to 12.1 meters per second—roughly 27 miles per hour, or a six on the Beaufort scale of wind speeds. This is classified as a “strong breeze,” in which it would be difficult to use an umbrella. It ranks just below a “moderate gale,” in which it would be difficult to move and whole trees would be swaying. This wind speed is twice as fast as the speeds encountered by the drone during neural network training, which suggests Neural-Fly could extrapolate and generalize well to unseen and harsher weather.

The drones were equipped with a standard, off-the-shelf flight control computer that is commonly used by the drone research and hobbyist community. Neural-Fly was implemented in an onboard Raspberry Pi 4 computer that is the size of a credit card and retails for around $20.

Paper co-authors include Anandkumar and Yue, as well as Xichen Shi, and former Caltech postdoc Kamyar Azizzadenesheli, now an assistant professor of computer science at Purdue University.

Related article:

Discovery about coral-algal symbiosis could help coral reefs recover after bleaching events

Hepatitis Outbreak In Children: Explainer On Adenovirus Type 41, The Possible Culprit

Read more

PrevPreviousPeople Are Having Surgery To Make Themselves Taller
NextResearchers use silicon nanoparticles to visualize coalescence of quantized vortices that occur in superfluid heliumNext

LATEST Blogs

Breakfast and health problems

Skipping Breakfast May Increase a Child’s Risk of Psychosocial Health Problems

September 7, 2022
James webb telescope

NASA’s Webb Space Telescope Captures a Cosmic Tarantula

September 7, 2022

Worse Than Smoking – Bad Sleep Can Worsen Lung Disease

August 31, 2022
Nanotechnology

Dr. Muhammad Adeel Addressed the International Con-ference as keynote speaker

August 23, 2022
Benefits of Mushrooms

Top 10 Health Benefits of Mushrooms, the Ultimate Superfood

August 18, 2022

New Way Invented To Produce Oxygen on Mars for Future Explorers

August 18, 2022

Evidence of Unprecedented Modern Sea-Level Rise Found in Ancient Caves

August 18, 2022

Research Shows Salt Substitutes Lower Risk of Heart Attack/Stroke and Death

August 13, 2022
covid symptoms

Hair Loss and Sexual Dysfunction Join Fatigue and Brain Fog in List of Long COVID Symptoms

August 13, 2022
protein

Most People Are Eating Too Much Protein – And It Has Serious Consequences

August 13, 2022

Categories

  • Scientific Blogs
  • Infinity Explorer
  • Traveler Book
  • Life Around

If you have tried to make a difference and you believe you deserve to be acknowledge, then please submit your story to us

Subscribe

Virtual Green Innovation Hub (VGI-H) is an emerging platform for young researchers which works as a bridge between You and the society.

Useful Links

Home
About us
Blogs

Subscribe Now

Don’t miss our future updates! Get Subscribed Today!

Copyright ©2022 Virtual Green Innovation Hub. All Rights Reserved.

Don’t miss our future updates. Get Subscribed Today!