Trial-and-error learning for damage recovery with a quadruped robot

Auteur : Jean-Baptiste Mouret

Informations générales

Encadrants Jean-Baptiste Mouret
Téléphone 03 54 95 85 08
Bureau C 104

Context and motivation

Our team works on new machine learning algorithms to allow robots to adapt to unexpected situations. For instance, we seek to make a hexapod robot that broke a leg re-learn to walk in a few minutes. We recently obtained promising results (see and [1]).

We now wish to extend the adaptation possibilities by making our approach work on highly dynamic quadruped robot ( To do so, a new gait controller has to be designed and our learning algorithms have to be adapted.

The objectives of this internship are:

  1. develop a fast simulator;

  2. adapt the walking and learning algorithms for quadruped locomotion.

We aim at experimenting on the robots as much as possible but we have the support of 2 engineers. In case of blocking hardware issues, most of the work can be done in simulation.


  • C++ programming,

  • Python programming,

  • use of ROS,

  • English

  • machine learning.


Cully, Antoine, Jeff Clune, Danesh Tarapore, and Jean-Baptiste Mouret. (2015) “Robots That Can Adapt like Animals”. Nature 521, no. 7553 (May 27, 2015): 503–7

Chatzilygeroudis K, Mouret JB. (2018) “Using parameterized black-box priors to scale up model-based policy search for robotics”. IEEE International Conference on Robotics and Automation (ICRA)


Comments are closed.