Thomas Flayols — accepted AI-conference papers

2024

CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning

Elliot Chane-Sane, Pierre-Alexandre Leziart, Thomas Flayols, Olivier Stasse, Philippe Souères, Nicolas Mansard

IROS 2024

Deep Reinforcement Learning (RL) has demonstrated impressive results in solving complex robotic tasks such as quadruped locomotion. Yet, current solvers fail to produce efficient policies respecting hard constraints. In this work, we advocate for integrating constraints into robot learning and prese

Cited by 35 Source ↗code ↗Scholar ↗

2024

SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience

Elliot Chane-Sane, Joseph Amigo, Thomas Flayols, Ludovic Righetti, Nicolas Mansard

CoRL 2024poster

Parkour poses a significant challenge for legged robots, requiring navigation through complex environments with agility and precision based on limited sensory inputs. In this work, we introduce a novel method for training end-to-end visual policies, from depth pixels to robot control commands, to a…

Cited by 7 Source ↗Scholar ↗

2022

Improved Control Scheme for the Solo Quadruped and Experimental Comparison of Model Predictive Controllers

Pierre-Alexandre Léziart, Thomas Corbères, Thomas Flayols, Steve Tonneau, Nicolas Mansard, Philippe Souères

RA-L 2022

This letter presents significant improvements to the nominal control architecture of the open-access Solo-12 quadruped that were done to implement and compare different centroidal Model Predictive Controllers (MPC). This work was motivated by our previous study in which various MPC schemes of increa

Cited by 6 Source ↗Scholar ↗

2022

Real-time Footstep Planning and Control of the Solo Quadruped Robot in 3D Environments

Fanny Risbourg, Thomas Corbères, Pierre-Alexandre Léziart, Thomas Flayols, Nicolas Mansard, Steve Tonneau

IROS 2022poster

Quadruped robots have proved their robustness to cross complex terrain despite little environment knowledge. Yet advanced locomotion controllers are expected to take advantage of exteroceptive information. This paper presents a complete method to plan and control the locomotion of quadruped robots w…

Cited by 20 Source ↗Scholar ↗

2022

Simulation Aided Co-Design for Robust Robot Optimization

Gabriele Fadini, Thomas Flayols, Andrea Del Prete, Philippe Souères

RA-L 2022

This letter outlines a bi-level algorithm to concurrently optimize robot hardware and control parameters in order to minimize energy consumption during the execution of tasks and to ensure robust performance. The outer loop consists in a genetic algorithm that optimizes the co-design variables accor

Cited by 23 Source ↗Scholar ↗

2021

Comparison of predictive controllers for locomotion and balance recovery of quadruped robots

Thomas Corbères, Thomas Flayols, Pierre-Alexandre Léziart, Rohan Budhiraja, Philippe Souères, Guilhem Saurel +1

ICRA 2021poster

As locomotion decisions must be taken by considering the future, most existing quadruped controllers are based on a model predictive controller (MPC) with a reduced model of the dynamics to generate the motion and a whole- body controller to execute it. Yet the simplifying assumptions of the MPC are…

Cited by 19 Source ↗Scholar ↗

2021

Contact Forces Preintegration for Estimation in Legged Robotics using Factor Graphs

Médéric Fourmy, Thomas Flayols, Pierre-Alexandre Léziart, Nicolas Mansard, Joan Solà

ICRA 2021poster

State estimation, in particular estimation of the base position, orientation and velocity, plays a big role in the efficiency of legged robot stabilization. The estimation of the base state is particularly important because of its strong correlation with the underactuated dynamics, i.e. the evolutio…

Cited by 33 Source ↗Scholar ↗

2021

Implementation of a Reactive Walking Controller for the New Open-Hardware Quadruped Solo-12

Pierre-Alexandre Léziart, Thomas Flayols, Felix Grimminger, Nicolas Mansard, Philippe Souères

ICRA 2021poster

This paper aims at showing the dynamic performance and reliability of the low-cost, open-access quadruped robot Solo-12, which is developed within the framework of Open Dynamic Robot Initiative. It presents the implementation of a state-of-the-art control pipeline, close to the one that was previous…

Cited by 49 Source ↗Scholar ↗

2021

Solving Footstep Planning as a Feasibility Problem Using L1-Norm Minimization

Daeun Song, Pierre Fernbach, Thomas Flayols, Andrea Del Prete, Nicolas Mansard, Steve Tonneau +1

RA-L 2021

Extended version of the paper to be published in IEEE Robotics and Automation Letters

Cited by 23 Source ↗Scholar ↗

2020

An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research

Felix Grimminger, Avadesh Meduri, Majid Khadiv, Julian Viereck, Manuel Wüthrich, Maximilien Naveau +7

RA-L 2020

We present a new open-source torque-controlled legged robot system, with a low-cost and low-complexity actuator module at its core. It consists of a high-torque brushless DC motor and a low-gear-ratio transmission suitable for impedance and force control. We also present a novel foot contact sensor

Cited by 238 Source ↗code ↗Scholar ↗