Project

Back to overview

Bio-inspired control of microflyers in highly complex environments

Applicant Floreano Dario
Number 155907
Funding scheme Project funding (Div. I-III)
Research institution Laboratoire de systèmes intelligents EPFL - STI - IMT - LIS
Institution of higher education EPF Lausanne - EPFL
Main discipline Other disciplines of Engineering Sciences
Start/End 01.01.2015 - 31.12.2019
Approved amount 354'507.00
Show all

All Disciplines (2)

Discipline
Other disciplines of Engineering Sciences
Information Technology

Keywords (3)

Artificial Vision; Flying robots; Bio-inspired systems

Lay Summary (French)

Lead
Malgré le nombre croissant d'applications utilisant des robots volants autonomes, ces derniers sont encore restreints à des vols à haute altitude, où le danger de collision est le plus faible. En observant les insectes volants on remarque que, à l'inverse des robots volants, ils sont capables de naviguer et de subvenir à leurs besoins dans des environnements complexes malgré leur vision à basse résolution et la petite taille de leur cerveau. Par exemple, ils sont capables de voler efficacement au travers d'une forêt épaisse et d'intercepter des proies en plein vol pour se nourrir. Ceci est possible en grande partie grâce à leur navigation basée sur la vision à œil composé. Des microrobots volants dotés de ces capacités pourraient être utilisés, par exemple, à basse altitude dans des zones urbaines, ou à l’intérieur des bâtiments
Lay summary

Objectifs du travail de recherche

Le but de ce projet est de développer des systèmes innovants de contrôle de vol basés sur la vision. L'objectif étant de permettre à des microrobots d’appréhender des petits événements visuels dans des environnements statiques et dynamiques. Le projet comportera deux parties principales. D’un coté, nous allons développer des systèmes de navigation et d'évitement de collisions dans des environnements contenant des petits objets statiques à des emplacements aléatoires. De l’autre coté, nous allons développer des systèmes capables de détecter et d'interagir avec des petits objets se déplaçant dynamiquement dans le champ visuel des microrobots. Cela permettra aux robots de suivre, éviter, ou former des essaims avec d'autres agents. Pour atteindre ces objectifs, nous allons nous inspirer de résultats obtenus lors d’un projet parallèle : des études comportementales effectuées sur des insectes volants dans des environnements et situations similaires.

Contexte scientifique et social du projet de recherche

Les résultats obtenus lors de ce projet vont permettre de mieux comprendre les mécanismes qui permettent aux insectes volants de naviguer de façon sûre dans des environnements très complexes.

Ce projet va indubitablement impacter l’utilisation des drones civils non seulement dans leurs applications actuelles, comme la cartographie rapide, mais également dans leurs futures utilisations pour la livraison des paquets dans l’espace urbain ou encore dans le cadre de missions d’exploration et de secourisme dans des bâtiments endommagés par des catastrophes telles que tremblements de terre ou accidents nucléaire.

Direct link to Lay Summary Last update: 13.11.2014

Responsible applicant and co-applicants

Employees

Publications

Publication
The role of optic flow pooling in insect flight control in cluttered environments
Lecoeur Julien, Dacke Marie, Floreano Dario, Baird Emily (2019), The role of optic flow pooling in insect flight control in cluttered environments, in Scientific Reports, 9(1), 7707-7707.
Learning Vision-Based Flight in Drone Swarms by Imitation
Schilling Fabian, Lecoeur Julien, Schiano Fabrizio, Floreano Dario (2019), Learning Vision-Based Flight in Drone Swarms by Imitation, in IEEE Robotics and Automation Letters, 4(4), 4523-4530.
Spatial Encoding of Translational Optic Flow in Planar Scenes by Elementary Motion Detector Arrays
Lecoeur Julien, Baird Emily, Floreano Dario (2018), Spatial Encoding of Translational Optic Flow in Planar Scenes by Elementary Motion Detector Arrays, in Scientific Reports, Springer US, 8(1), 5821.

Collaboration

Group / person Country
Types of collaboration
Prof. Emily Baird, Vision Group, Department of Biology, University of Lund Sweden (Europe)
- in-depth/constructive exchanges on approaches, methods or results
- Publication
- Research Infrastructure
- Exchange of personnel

Scientific events

Active participation

Title Type of contribution Title of article or contribution Date Place Persons involved
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Aerial Swarms Workshop Talk given at a conference Learning Vision-based Flight in Drone Swarms by Imitation 04.11.2019 The Venetian hotel, Macau, China Schilling Fabian; Floreano Dario;
Intel NIS workshop 2019 Poster Learning Vision-based Flight in Drone Swarms by Imitation 09.09.2019 Munich, Germany Schilling Fabian; Floreano Dario;
The 9th International Symposium on Adaptive Motion of Animals and Machines Poster Learning Vision-based Flight in Drone Swarms by Imitation 20.08.2019 EPFL, Lausanne, Switzerland Schilling Fabian;
IEEE RAS Summer School on Multi-Robot Systems Individual talk Learning Vision-based Flight in Drone Swarms by Imitation 29.07.2019 CTU Prague, Czech Republic Schilling Fabian;
EPFL EDRS Research Day 2019 Poster Learning Vision-based Flight in Drone Swarms by Imitation 19.06.2019 EPFL, Lausanne, Switzerland Schilling Fabian;
BMI Symposium: Controlling Behavior in Animals and Robots 2018 Poster Learning vision-based cohesive flight in drone swarms 03.12.2018 EPFL, Lausanne, Switzerland Schilling Fabian;
Intel NIS workshop 2018 Poster Learning vision-based cohesive flight in drone swarms 03.09.2018 Munich, Germany Floreano Dario; Schilling Fabian;
Robot 2017 Talk given at a conference Human-friendly drones 22.11.2017 Seville, Spain Floreano Dario;
ICIRA Talk given at a conference Biologically inspired drones 15.08.2017 Wuhang, China Floreano Dario;
Aerial Robotics Workshop Talk given at a conference From vision-based to morphofunctional drones 20.06.2017 Toronto, Canada Floreano Dario;
ETH Robotics distinguished lecture Individual talk Biologically inspired drones 18.11.2016 Zurich, Switzerland Floreano Dario;
Robotics 2025 Individual talk Drones: from biology to engineering 27.10.2016 Foshan, Guandong, China Floreano Dario;
Max-Planck Symposium on Intelligent Systems Individual talk Biologically inspired drones 28.04.2016 Tübingen, Germany Floreano Dario;
European Robotics Forum Talk given at a conference Visually guided drones 21.03.2016 Ljubliana, Slovenia Floreano Dario;
Robotics Center Inauguration, Imperial College London Individual talk Biologically inspired drones 24.09.2015 London, Great Britain and Northern Ireland Floreano Dario;
Gordon Conference on Neuroethology Talk given at a conference Vision-based flight in insects and drones 29.06.2015 Firenze, Italy Floreano Dario; Lecoeur Julien;
APAC Innovation Summit Talk given at a conference Invited Keynote: Biologically Inspired Drones 22.06.2015 Hong Kong, Hongkong Floreano Dario;


Self-organised

Title Date Place
Conference on Collective Behavior 07.05.2018 Trieste, Italy

Communication with the public

Communication Title Media Place Year
Talks/events/exhibitions EPFL Drone Days Western Switzerland 2017
Other activities Guide at journée des gymnasiens Western Switzerland 2017

Use-inspired outputs

Associated projects

Number Title Start Funding scheme
188457 Vision-based Aerial Swarms 01.01.2020 Project funding (Div. I-III)
180861 A Submillimeter Minimally Invasive System for Cardiac Arrhythmia Ablations 01.09.2019 Bridge - Discovery
125773 NCCR Robotics: Intelligent Robots for Improving the Quality of Life (phase I) 01.12.2010 National Centres of Competence in Research (NCCRs)

Abstract

We will develop novel vision-based controllers for mini-drones handle small events in static and dynamic environments. The project is divided in two parts. In the first part, we will address flight control in complex static environments made of a random layout of several objects at different distances from the agent, which capture typical situations while flying through a forest of trees. This part will involve the modeling of vision-based strategies used by flying insects to maneuver safely among obstacles. These strategies will be implemented on autonomous microflyers and characterized in environments where the navigation goal cannot be reached by state-of-the-art algorithms, such as flying through narrow openings against a richly textured environment. In the second part, we will address strategies to deal with small dynamic events, such as other agents (insects or robots) flying in the same environment, in order to avoid, follow, and fly in formation with them. We will take inspiration from the biological evidence that specifically tuned and strategically located receptive fields could be responsible for the detection and tracking of other moving objects in the visual field.We will benefit from an ongoing cooperation with Prof. Emily Baird in the Biology Department of the University of Lund in Sweden, who will carry out experimental work with real insects exposed to the situations described above (see also accompanying statement from Prof. Baird; the work at Lund will not be funded by this grant, but we will put in place frequent exchange of students between EPFL and Lund University). The models will be initially developed and assessed in physics-based simulations of flying vehicles and of compound eye vision. The most promising models will be validated on small drones with insect-like dynamics, which will be an adaptation of customizable and programmable drones developed in our lab. The visual sensors of these drones will consist of the curved artificial compound eyes developed in a previous project. We expect that this project will result in the next generation of drones capable of visually guided flight through forests, in urban streets, and in formation with other flying robots, which so far has been achieved only by sharing GPS coordinates among drones. We also expect that the ongoing collaboration with insect biologists will shed new light on the behavior and potential mechanisms employed by living insects faced with similar situations.
-