NCCR Robotics is a consortium of robotics laboratories across Switzerland, working on robots for improving the quality of life and to strengthen robotics in Switzerland and worldwide. Newsletter
Drones learn to navigate autonomously by imitating cars and bicycles
Developed by UZH researchers, the algorithm DroNet allows drones to fly completely by themselves through the streets of a city and in indoor environments. Therefore, the algorithm had to learn traffic rules and adapt training examples from cyclists and car drivers. All today’s commercial drones use GPS, which works fine above building roofs and in …
Continue reading “Drones learn to navigate autonomously by imitating cars and bicycles”
Past Events
| Date/Time | Event | Description |
|---|---|---|
|
1 Jun 2018 3:15 pm – 4:45 pm |
Distinguished Seminar in Robotics, Systems & Control | The Institute of Robotics and Intelligent Systems presents: Telerobotic Touch June 1st 2018, 15h15-16h15 Place: ETHZ, Main Building (HG G3) For those at EPFL: a video streaming will take place... |
DroNet: Learning to Fly by Driving
Posted on: January 23, 2018
So kommen Drohnen sicher durch die Stadt
Publication date: March 15, 2018
Published in: Neue Zürcher Zeitung
AI-Powered Drone Mimics Cars and Bikes to Navigate Through City Streets
Publication date: January 28, 2018
Published in: IEEE Spectrum
Autonomous high flying drones learn to navigate by watching traffic below
Publication date: January 26, 2018
Published in: ZDnet
Zürcher Algorithmus lenkt Drohnen sicher durch die Stadt
Publication date: January 25, 2018
Published in: Blick
Diese Drohne lernt durch Imitation
Publication date: January 24, 2018
Published in: Tages Anzeiger
The DroNet algorithm teaches drones to navigate city streets like cars
Publication date: January 24, 2018
Published in: Digital Trends
Drones learn to navigate autonomously by imitating cars and bicycles
Publication date: January 23, 2018
Published in: Alpha Galileo
Drones learn to navigate autonomously by imitating cars and bicycles
Publication date: January 23, 2018
Published in: Science Daily
Drones learn to navigate autonomously by imitating cars and bicycles
Publication date: January 23, 2018
Published in: phys.org
Prof. Dario Floreano NCCR Director & Professor Laboratory of Intelligent Systems (LIS) and Management Team, EPFL dario.floreano@epfl.ch +41 21 693 52 30
Dr. Jeffrey Delmerico Senior Researcher and Postdoc Robotics and Perception Group (RPG), UZH jeffdelmerico@ifi.uzh.ch +41 44 635 45 89
Can't see who you were looking for? You might want to try browsing by lab or looking in the A-Z people list.
Looking for publications? You might want to consider searching on the EPFL Infoscience site which provides advanced publication search capabilities.
Contact-based navigation for an autonomous flying robot
Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 51
Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 51
Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 52
Autonomous navigation in obstacle-dense indoor environments is very challenging for flying robots due to the high risk of collisions, which may lead to mechanical damage of the platform and eventual failure of the mission. While conventional approaches in autonomous navigation favor obstacle avoidance strategies, recent work showed that collision-robust flying robots could hit obstacles without breaking and even self-recover after a crash to the ground. This approach is particularly interesting for autonomous navigation in complex environments where collisions are unavoidable, or for reducing the sensing and control complexity involved in obstacle avoidance. This paper aims at showing that collision-robust platforms can go a step further and exploit contacts with the environment to achieve useful navigation tasks based on the sense of touch. This approach is typically useful when weight restrictions prevent the use of heavier sensors, or as a low-level detection mechanism supplementing other sensing modalities. In this paper, a solution based on force and inertial sensors used to detect obstacles all around the robot is presented. Eight miniature force sensors, weighting 0.9g each, are integrated in the structure of a collision-robust flying platform without affecting its robustness. A proof-of-concept experiment demonstrates the use of contact sensing for exploring autonomously a room in 3D, showing significant advantages compared to a previous strategy. To our knowledge this is the first fully autonomous flying robot using touch sensors as only exteroceptive sensors.
Posted on: July 1, 2013
Keywords: aerial robotics, aerial vehicle, autonomous robots, contact, flying robots, force, mav, navigation, robotics, sensing
Distributed Particle Swarm Optimization for Limited Time Adaptation in Autonomous Robots
Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 51
Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 51
Warning: Use of undefined constant citation_author - assumed 'citation_author' (this will throw an Error in a future version of PHP) in /home/clients/89f5f0444c120951cfdb7adc5e3aa2bf/web/dev-nccr-robotics/wp-content/themes/nccr-twentyseventeen-child/template-parts/post/content-publication.php on line 52
Evaluative techniques offer a tremendous potential for on-line controller design. However, when the optimization space is large and the performance metric is noisy, the time needed to properly evaluate candidate solutions becomes prohibitively large and, as a consequence, the overall adaptation process becomes extremely time consuming. Distributing the adaptation process reduces the required time and increases robustness to failure of individual agents. In this paper, we analyze the role of the four algorithmic parameters that determine the total evaluation time in a distributed implementation of a Particle Swarm Optimization algorithm. For a multi-robot obstacle avoidance case study, we explore in simulation the lower boundaries of these parameters with the goal of reducing the total evaluation time so that it is feasible to implement the adaptation process within a limited amount of time determined by the robots’ energy autonomy. We show that each parameter has a different impact on the final fitness and propose some guidelines for choosing these parameters for real robot implementations.
Posted on: November 20, 2012