> Machine learning for resilient & creative robots
We develop novel learning algorithms for creative adaptation in robotics.
Main projects
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 project 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 diagnosis 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 alternative approach that does not require diagnosis, 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.
Highlights
One of our papers was on the cover of Nature!
A. Cully, J. Clune, D. Tarapore, J.-B Mouret (2015).
Robots that can adapt like animals.
Nature. 521. (7553) 503-507. Nature Publishing Group.
10.1038/nature14422
→ [
pdf ] [
url ] [
source code ] [
video ] [
video ]
Main publications
Pre-prints / arxiv
2015
J.-B Mouret, J. Clune (2015). Illuminating search spaces by mapping elites.
arXiv preprint. [url]
Articles in peer-reviewed journals
2022
T. Anne, E. Dalin, I. Bergonzani, S. Ivaldi, J.-B Mouret (2022). First do not fall: learning to exploit a wall with a damaged humanoid robot.
IEEE Robotics and Automation Letters. IEEE.
→ [pdf] [url] [video]
K. Chatzilygeroudis, V. Vassiliades, F. Stulp, S. Calinon, J.-B Mouret (2020). A survey on policy search algorithms for learning robot controllers in a handful of trials.
IEEE Transactions on Robotics. 36. (2) 328--347.
→ [pdf] [url]
R. Kaushik, P. Desreumaux, J.-B Mouret (2020). Adaptive Prior Selection for Repertoire-based Online Learning in Robotics.
Frontiers in Robotics and AI.
→ [pdf] [url] [video]
J. Rieffel*, J.-B Mouret* (2018). Adaptive and Resilient Soft Tensegrity Robots.
Soft Robotics. (* J. Rieffel and J.-B. Mouret contributed equally to this work). https://doi.org/10.1089/soro.2017.0066[url] [video]
A. Cully, K. Chatzilygeroudis, F. Allocati, J.-B Mouret (2018). Limbo: A Flexible High-performance Library for Gaussian Processes modeling and Data-Efficient Optimization.
The Journal of Open Source Software. 3. (26) 545. The Open Journal. 10.21105/joss.00545
K. Chatzilygeroudis, V. Vassiliades, J.-B Mouret (2017). Reset-free Trial-and-Error Learning for Robot Damage Recovery.
Robotics and Autonomous Systems. 1-19. Elsevier. 10.1016/j.robot.2017.11.010
→ [pdf] [url] [source code] [video]
A. Cully, J.-B Mouret (2016). Evolving a Behavioral Repertoire for a Walking Robot.
Evolutionary Computation. 24. (1) 59-88. MIT Press. 10.1162/EVCO_a_00143
→ [pdf] [url] [video]
A. Cully, J. Clune, D. Tarapore, J.-B Mouret (2015). Robots that can adapt like animals.
Nature. 521. (7553) 503-507. Nature Publishing Group. 10.1038/nature14422
→ [pdf] [url] [source code] [video] [video]
S. Koos, A. Cully, J.-B Mouret (2013). Fast Damage Recovery in Robotics with the T-Resilience Algorithm.
International Journal of Robotics Research (IJRR). 32. (14) 1700-1723. SAGE Publications. 10.1177/0278364913499192
→ [pdf] [url]
Articles in peer-reviewed conferences
2020
D. Bossens, J.-B Mouret, D. Tarapore (2020). Learning behaviour-performance maps with meta-evolution.
Proc. of GECCO
→ [pdf] [url]
S. Paul, K. Chatzilygeroudis, K. Ciosek, J.-B Mouret, M. Osborne, S. Whiteson (2018). Alternating Optimisation and Quadrature for Robust Control.
AAAI 2018 - The Thirty-Second AAAI Conference on Artificial Intelligence
→ [pdf] [url]
R. Pautrat, K. Chatzilygeroudis, J.-B Mouret (2018). Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search.
IEEE International Conference on Robotics and Automation (ICRA)
→ [pdf] [url] [video]
K. Chatzilygeroudis, J.-B Mouret (2018). Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics.
IEEE International Conference on Robotics and Automation (ICRA)
→ [pdf] [url] [video]
R. Kaushik, K. Chatzilygeroudis, J.-B Mouret (2018). Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards.
Conference on Robot Learning (CoRL)
→ [pdf] [url]
K. Chatzilygeroudis, R. Rama, R. Kaushik, D. Goepp, V. Vassiliades, J.-B Mouret (2017). Black-Box Data-efficient Policy Search for Robotics.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
→ [pdf] [url] [source code] [video]
J. Spitz, K. Bouyarmane, S. Ivaldi, J.-B Mouret (2017). Trial-and-Error Learning of Repulsors for Humanoid QP-based Whole-Body Control.
Proc. of IEEE Humanoids
→ [pdf] [url] [video]
D. Tarapore, J. Clune, A. Cully, J.-B Mouret (2016). How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm?.
Proc. of GECCO ACM. 10.1145/2908812.2908875
→ [pdf] [url] [source code]
J.-M Jehanno, A. Cully, C. Grand, J.-B Mouret (2014). Design of a Wheel-Legged Hexapod Robot for Creative Adaptation.
17th International Conference on Climbing and Walking Robots (CLAWAR) 267-276. 10.1142/9789814623353_0032
→ [pdf] [video]
M. Oliveira, S. Doncieux, J.-B Mouret, C. Peixoto Santos (2013). Optimization of Humanoid Walking Controller: Crossing the Reality Gap.
Proc. of IEEE Humanoids 1-7. 10.1109/HUMANOIDS.2013.7029963
→ [pdf]
S. Koos, J.-B Mouret (2011). Online Discovery of Locomotion Modes for Wheel-Legged Hybrid Robots: a Transferability-based Approach.
14th International Conference on Climbing and Walking Robots (CLAWAR). Highly Recommended Paper, category ``control of CLAWAR'' 70-77. 10.1142/9789814374286_0008
→ [pdf] [url] [video] [video] [video]
Workshops, book chapters, and minimally reviewed conferences
2016
V. Papaspyros, K. Chatzilygeroudis, V. Vassiliades, J.-B Mouret (2016). Safety-Aware Robot Damage Recovery Using Constrained Bayesian Optimization and Simulated Priors.
Bayesian Optimization: Black-box Optimization and Beyond (workshop at NIPS)
→ [pdf] [url] [video]
General audience
2016
J.-B Mouret, A. Cully (2016). Des robots qui s’adaptent aux dommages en seulement quelques minutes.
Interstices. INRIA.[url]
