no code implementations • 10 Mar 2024 • Johann Huber, François Hélénon, Mathilde Kappel, Elie Chelly, Mahdi Khoramshahi, Faïz Ben Amar, Stéphane Doncieux
We believe these results to be a significant step toward the generation of large datasets that can lead to robust and generalizing robotic grasping policies.
1 code implementation • 6 Oct 2023 • François Hélénon, Johann Huber, Faïz Ben Amar, Stéphane Doncieux
This framework addresses two main issues: the lack of an off-the-shelf vision module for detecting object pose and the generalization of QD trajectories to the whole robot operational space.
1 code implementation • 6 Oct 2023 • Johann Huber, François Hélénon, Hippolyte Watrelot, Faiz Ben Amar, Stéphane Doncieux
More than 7000 reach-and-grasp trajectories have been generated with Quality-Diversity (QD) methods on 3 different arms and grippers, including parallel fingers and a dexterous hand, and tested in the real world.
no code implementations • 21 Oct 2022 • Elias Hanna, Alex Coninx, Stéphane Doncieux
This paper studies the impact of the initial data gathering method on the subsequent learning of a dynamics model.
no code implementations • 17 May 2022 • Aurélien Morel, Yakumo Kunimoto, Alex Coninx, Stéphane Doncieux
Grasping a particular object may require a dedicated grasping movement that may also be specific to the robot end-effector.
1 code implementation • 28 Sep 2021 • Astrid Merckling, Nicolas Perrin-Gilbert, Alex Coninx, Stéphane Doncieux
Our experimental results show that the approach leads to efficient exploration in challenging environments with image observations, and to state representations that significantly accelerate learning in RL tasks.
no code implementations • 10 Apr 2021 • Alexandre Chenu, Nicolas Perrin-Gilbert, Stéphane Doncieux, Olivier Sigaud
In particular, we show empirically that, if the mapping is smooth enough, i. e. if two close policies in the parameter space lead to similar outcomes, then diversity algorithms tend to inherit exploration properties of MP algorithms.
no code implementations • 15 Sep 2019 • Astrid Merckling, Alexandre Coninx, Loic Cressot, Stéphane Doncieux, Nicolas Perrin-Gilbert
Indeed, a compact representation of such a state is beneficial to help robots grasp onto their environment for interacting.
1 code implementation • 30 Jan 2019 • Léni K. Le Goff, Ghanim Mukhtar, Alexandre Coninx, Stéphane Doncieux
A robot with the ability to build and adapt this interpretation process according to its own tasks and capabilities would push away the limits of what robots can achieve in a non controlled environment.
no code implementations • 7 Nov 2018 • Marija Jegorova, Stéphane Doncieux, Timothy Hospedales
Leveraging our generative policy network, a robot can sample novel behaviors until it finds one that works for a new environment.
no code implementations • 24 Jul 2015 • Stéphane Doncieux, Jean Liénard, Benoît Girard, Mohamed Hamdaoui, Joël Chaskalovic
A neurocomputational model of the Basal Ganglia brain nuclei is then considered and its most salient features according to this methodology are presented and discussed.