The Robot Report

  • Home
  • News
  • Technologies
    • Batteries / Power Supplies
    • Cameras / Imaging / Vision
    • Controllers
    • End Effectors
    • Microprocessors / SoCs
    • Motion Control
    • Sensors
    • Soft Robotics
    • Software / Simulation
  • Development
    • Artificial Intelligence
    • Human Robot Interaction / Haptics
    • Mobility / Navigation
    • Research
  • Robots
    • AGVs
    • AMRs
    • Consumer
    • Collaborative Robots
    • Drones
    • Exoskeletons
    • Industrial
    • Self-Driving Vehicles
    • Unmanned Maritime Systems
  • Markets
    • Agriculture
    • Healthcare
    • Logistics
    • Manufacturing
    • Mining
    • Security
  • Financial
    • Investments
    • Mergers & Acquisitions
    • Earnings
  • Resources
    • Careers
    • COVID-19
    • Digital Issues
    • Publications
      • Collaborative Robotics Trends
      • Robotics Business Review
    • RBR50 Winners 2022
    • Search Robotics Database
    • Videos
    • Webinars / Digital Events
  • Events
    • RoboBusiness
    • Robotics Summit & Expo
    • Healthcare Robotics Engineering Forum
    • DeviceTalks
    • R&D 100
    • Robotics Weeks
  • Podcast
    • Episodes
    • Leave a voicemail

DroNet Teaches Drones to Autonomously Navigate Cities

By Steve Crowe | January 26, 2018

Whether it be for package delivery, surveillance, data collection or entertainment, drones are expected to one day be a common sight in the skies. But to do so, drones will need to autonomously navigate unstructured environments.

Most of today’s drones use GPS, which works great when the drones are flying at high altitudes. But according to researchers, there could be problems if drones have to navigate autonomously at low altitudes through unstructured city streets with cars, cyclists or pedestrians.

This led researchers at the University of Zurich and the National Centre of Competence in Research NCCR Robotics to develop Drone Network (DroNet), a convolutional neural network (CNN) that can safely fly drones through a city at low altitudes by imitating how cars and bicycles navigate.

How DroNet was trained

To train DroNet on how to steer a drone, the researchers used a dataset collected by cars. And to train the system to avoid collisions, the team simply strapped a GoPro camera to a bicycle and rode around Zurich. Then by imitating cars and bicycles, the drone automatically learned the rules of the road.

This DroNet dataset was captured with a GoPro camera and a bicycle riding around Zurich. (Credit: University of Zurich)

DroNet produces two outputs from the data captured by the drone’s on-board camera:

  • A steering angle to help the drone navigate while avoiding obstacles
  • A collision probability that enables the drone to recognize dangerous situations – pedestrians or bicyclists – and react accordingly.

A paper detailing DroNet was recently published in the journal IEEE Robotics and Automation Letters. Check out DroNet in action in the video below:

“DroNet recognizes static and dynamic obstacles and can slow down to avoid crashing into them,” said Davide Scaramuzza, professor for robotics and perception at the University of Zurich. “With this algorithm we have taken a step forward towards integrating autonomously navigating drones into our everyday life.”

One thing the researchers find surprising is DroNet’s ability to generalize. Despite no indoor data being used to train it, DroNet learned to autonomously navigate indoor environments such as parking lots and offices.

DroNet was also designed to require little computational power compared to other CNNs. This allows real-time performance, even on a CPU, according to the team.

DroNet

The researchers didn’t train DroNet with data from indoor environments, but the system can generalize and navigate parking lots, offices and more. (Credit: University of Zurich)

Deep Neural Networks for drones

DroNet isn’t the first time Scaramuzza used CNNs on drones. Two years ago, he used pictures taken with a camera on a hiker’s head to train a network. That network enabled a drone with minimal on-board sensing to autonomously navigate through a forest.

The idea was to study the problem of perceiving forest or mountain trails from a single monocular image captured by a robot traveling on the trail itself. Here’s video of that system in action:

As for DroNet, the researchers have shared their datasets and trained networks. And they admit that if DroNet is to play a significant role in the future of commercial drones, the algorithm needs to improve to enable faster, more agile flying.

About The Author

Steve Crowe

Steve Crowe is Editorial Director, Robotics, WTWH Media, and co-chair of the Robotics Summit & Expo. He joined WTWH Media in January 2018 after spending four-plus years as Managing Editor of Robotics Trends Media. He can be reached at [email protected]

Tell Us What You Think! Cancel reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Articles Read More >

myoshirt
ETH Zurich develops wearable muscles
International Federation of Robotics appoints new president, VP
impossible mining auv
Impossible Mining raises $10.1M for underwater mining robot
UR20 cobot Universal Robots
Anders Beck introduces the UR20; California bans autonomous tractors

2021 Robotics Handbook

The Robot Report Listing Database

Latest Robotics News

Robot Report Podcast

Anders Beck introduces the UR20; California bans autonomous tractors
See More >

Sponsored Content

  • Magnetic encoders support the stabilization control of a self-balancing two-wheeled robotic vehicle
  • How to best choose your AGV’s Wheel Drive provider
  • Meet Trey, the autonomous trailer (un)loading forklift
  • Kinova Robotics launches Link 6, the first Canadian industrial collaborative robot
  • Torque sensors help make human/robot collaborations safer for workers

RBR50 Innovation Awards

Leave us a voicemail

The Robot Report
  • Mobile Robot Guide
  • Collaborative Robotics Trends
  • Field Robotics Forum
  • Healthcare Robotics Engineering Forum
  • RoboBusiness Event
  • Robotics Business Review
  • Robotics Summit & Expo
  • About The Robot Report
  • Subscribe
  • Advertising
  • Contact Us

Copyright © 2022 WTWH Media LLC. All Rights Reserved. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of WTWH Media
Privacy Policy | Advertising | About Us

Search The Robot Report

  • Home
  • News
  • Technologies
    • Batteries / Power Supplies
    • Cameras / Imaging / Vision
    • Controllers
    • End Effectors
    • Microprocessors / SoCs
    • Motion Control
    • Sensors
    • Soft Robotics
    • Software / Simulation
  • Development
    • Artificial Intelligence
    • Human Robot Interaction / Haptics
    • Mobility / Navigation
    • Research
  • Robots
    • AGVs
    • AMRs
    • Consumer
    • Collaborative Robots
    • Drones
    • Exoskeletons
    • Industrial
    • Self-Driving Vehicles
    • Unmanned Maritime Systems
  • Markets
    • Agriculture
    • Healthcare
    • Logistics
    • Manufacturing
    • Mining
    • Security
  • Financial
    • Investments
    • Mergers & Acquisitions
    • Earnings
  • Resources
    • Careers
    • COVID-19
    • Digital Issues
    • Publications
      • Collaborative Robotics Trends
      • Robotics Business Review
    • RBR50 Winners 2022
    • Search Robotics Database
    • Videos
    • Webinars / Digital Events
  • Events
    • RoboBusiness
    • Robotics Summit & Expo
    • Healthcare Robotics Engineering Forum
    • DeviceTalks
    • R&D 100
    • Robotics Weeks
  • Podcast
    • Episodes
    • Leave a voicemail