Ludovic De Matteis

Ludovic De Matteis

PhD Student in robotics - Science enthousiast and keen learner

Publications

You can also find my articles on my Google Scholar profile.

Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot

Published in IEEE-ICHR, 2025

In this paper, we present a methodology that leverages Constraints-as-Terminations (CaT) and domain randomization techniques to enable sim-to-real transfer. Through a series of qualitative and quantitative experiments, we evaluate our approach in terms of balance maintenance, velocity control, and responses to slip and push disturbances.

Recommended citation: Constant Roux, Elliot Chane-Sane, Ludovic De Matteïs, Thomas Flayols, Jérôme Manhes, Olivier Stasse, Philippe Souères. Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot, IEEE-ICHR 2025. https://arxiv.org/pdf/2503.22459

Optimal Control of Closed Loop Walkers

Published in IEEE-IROS - Submitted, in review, 2025

In this paper, we present a method for controlling robots with closed kinematic loops (such as parallel actuation). We propose to use a serial model - for instance based on an underlying main chain - and to use additionnal constraints to account for closures. We demonstrate the advatages of this method by comparing it to a classical simplified model of the robot on several motions (walk, jump, sidewalk, and climbing stairs).

Recommended citation: Ludovic de Matteis, Virgile Batto, Justin Carpentier, Nicolas Mansard. Optimal Control of Walkers with Parallel Actuation. 2024. https://gepettoweb.laas.fr/articles/ldematte_icra2025.html

Collision Avoidance in Model Predictive Control using Velocity Damper

Published in IEEE-ICRA - Submitted, in review, 2025

In this paper, we propose a method to include collision avoidance in the control of a manipulator robot based on a velocity damper model. This allows to account for approach velocity and permits collision avoidance for a wider spectrum of applications than classical avoidance methods. We implemented our method on a Panda robot to perform several comparisons. In this paper, I mainly contributed to writing the derivatives of the collision avoidance constraint with respect to the robot state and controls in order to use it in a DDP setting.

Recommended citation: Arthur Haffemayer, Armand Jordana, Ludovic de Matteis, Krzysztof Wojciechowski, Florent Lamiraux, et al.. Collision Avoidance in Model Predictive Control using Velocity Damper. 2024. https://gepettoweb.laas.fr/articles/haffemayer2025.html

Extended URDF: Accounting for parallel mechanism in robot description

Published in RAAD 2025, 2025

In this paper, we introduce an extension to the widely used Unified Robot Description Format (URDF) to support closed-loop kinematic structures. Our approach relies on augmenting URDF with minimal additional information to allow more efficient modeling of complex robotic systems while maintaining compatibility with existing design and simulation frameworks.

Recommended citation: Virgile Batto, Ludovic De Matteïs, Nicolas Mansard. Extended URDF: Accounting for parallel mechanism in robot description. 2025. https://arxiv.org/pdf/2504.04767

Control of humanoid robots with parallel mechanisms using kinematic actuation models

Published in IEEE-IROS - Submitted, in review, 2025

In this paper, we present a method for controlling robots with closed kinematic loops (such as parallel actuation). We propose demonstrate a method to take efficiently into account the closed kinematics by using analytical formulations of different mechanisms.

Recommended citation: Victor Lutz, Ludovic de Matteïs, Virgile Batto, Nicolas Mansard. Control of humanoid robots with parallel mechanisms using kinematic actuation models. 2025. https://arxiv.org/pdf/2503.22459

CLEO: Closed-Loop kinematics Evolutionary Optimization of bipedal structures

Published in , 2024

In this paper, we propose a general approach to assist the design of serial-parallel humanoid legs using an evolutionary optimization strategy. The optimization problem incorporates design constraints and locomotion-task requirements as objective functions. It uses parallelized trajectory evaluation for efficient exploration of the design space.

Recommended citation: Virgile Batto, Ludovic de Matteis, Thomas Flayols, Margot Vulliez, Nicolas Mansard. CLEO: Closed-Loop kinematics Evolutionary Optimization of bipedal structures. 2024. https://insa-toulouse.hal.science/hal-04717159/