SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience

Résumé

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 achieve agile and safe quadruped locomotion. We formulate robot parkour as a constrained reinforcement learning (RL) problem designed to maximize the emergence of agile skills within the robot's physical limits while ensuring safety. We first train a policy without vision using privileged information about the robot's surroundings. We then generate experience from this privileged policy to warm-start a sample efficient off-policy RL algorithm from depth images. This allows the robot to adapt behaviors from this privileged experience to visual locomotion while circumventing the high computational costs of RL directly from pixels. We demonstrate the effectiveness of our method on a real Solo-12 robot, showcasing its capability to perform a variety of parkour skills such as walking, climbing, leaping, and crawling.
Fichier principal
Vignette du fichier
2409.13678v1.pdf (3.55 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04730062 , version 1 (10-10-2024)

Identifiants

Citer

Elliot Chane-Sane, Joseph Amigo, Thomas Flayols, Ludovic Righetti, Nicolas Mansard. SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience. Conference on Robot Learning, Nov 2024, Munich (Allemagne), Germany. ⟨10.48550/arXiv.2409.13678⟩. ⟨hal-04730062⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More