Descrizione del progetto
Progettare robot resistenti come gli animali
I robot rappresentano il futuro, ma nonostante decenni di ricerca, hanno ancora un grande difetto: sono macchine fragili che possono facilmente rompersi in condizioni difficili. Tuttavia, esiste un modo per creare robot a basso costo in grado di riprendersi autonomamente (e immediatamente) da danni imprevisti. Il progetto ResiBots, finanziato dal Consiglio europeo della ricerca, rivoluzionerà il nostro approccio alla tolleranza ai guasti e produrrà robot resistenti e adattivi come gli animali. In particolare, il progetto utilizzerà algoritmi di apprendimento per tentativi ed errori che consentiranno ai robot di scoprire rapidamente comportamenti compensativi senza richiedere sensori costosi o piani di emergenza predefiniti. L’obiettivo generale è quello di incrementare sostanzialmente la durata di vita dei robot senza aumentarne il costo. Il progetto aprirà la strada a nuovi percorsi di ricerca per macchine adattive.
Obiettivo
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.
Campo scientifico
- 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
Programma(i)
Argomento(i)
Meccanismo di finanziamento
ERC-STG - Starting GrantIstituzione ospitante
78153 Le Chesnay Cedex
Francia