Project description
Designing robots as resilient as animals
Robots are the future, but despite decades of research, they still have a major flaw: they are fragile machines that can easily break down in difficult conditions. But there is a way to create low-cost robots that could autonomously (and immediately) recover from unforeseen damages. The European Research Council-funded project ResiBots will revolutionise our approach to fault tolerance and produce robots as resilient and adaptive as animals. Specifically, the project will use trial-and-error learning algorithms that allow robots to quickly discover compensatory behaviours without requiring expensive sensors or predefined contingency plans. The overall aim is to substantially increase the robots’ lifespan without increasing their cost. The project will pave the way for new research avenues for adaptive machines.
Objective
Despite over 50 years of research in robotics, most existing robots are far from being as resilient as the simplest animals: they are fragile machines that easily stop functioning in difficult conditions. The goal of this proposal is to radically change this situation by providing the algorithmic foundations for low-cost robots that can autonomously recover from unforeseen damages in a few minutes. The current approach to fault tolerance is inherited from safety-critical systems (e.g. spaceships or nuclear plants). It is inappropriate for low-cost autonomous robots because it relies on diagnostic procedures, which require expensive proprioceptive sensors, and contingency plans, which cannot cover all the possible situations that an autonomous robot can encounter. It is here contended that trial-and-error learning algorithms provide an alternate approach that does not require diagnostic, nor pre-defined contingency plans. In this project, we will develop and study a novel family of such learning algorithms that make it possible for autonomous robots to quickly discover compensatory behaviors. We will thus shed a new light on one of the most fundamental questions of robotics: how can a robot be as adaptive as an animal? The techniques developed in this project will substantially increase the lifespan of robots without increasing their cost and open new research avenues for adaptive machines.
Fields of science
Not validated
Not validated
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensorsoptical sensors
- natural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learning
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsautonomous robots
- natural sciencesearth and related environmental sciencesphysical geographynatural disasters
Programme(s)
Topic(s)
Funding Scheme
ERC-STG - Starting GrantHost institution
78153 Le Chesnay Cedex
France