Reconciling RaiSim with the Maximum Dissipation Principle - AGIMUS - Next generation of AI-powered robotics for agile production
Article Dans Une Revue IEEE Transactions on Robotics Année : 2024

Reconciling RaiSim with the Maximum Dissipation Principle

Résumé

Recent progress in reinforcement learning (RL) in robotics has been obtained by training control policy directly in simulation. Particularly in the context of quadrupedal locomotion, astonishing locomotion policies depicting high robustness against environmental perturbations have been trained by leveraging RaiSim simulator. While it avoids introducing forces at distance, it has been shown recently that RaiSim does not obey the maximum dissipation principle, a fundamental principle when simulating rigid contact interactions. In this note, we detail these relaxations and propose an algorithmic correction of the RaiSim contact algorithm to handle the maximum dissipation principle adequately. Our experiments empirically demonstrate our approach leads to simulation following this fundamental principle.
Fichier principal
Vignette du fichier
raisim-revisited.pdf (511.3 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04438175 , version 1 (05-02-2024)
hal-04438175 , version 2 (25-09-2024)

Identifiants

  • HAL Id : hal-04438175 , version 2

Citer

Quentin Le Lidec, Justin Carpentier. Reconciling RaiSim with the Maximum Dissipation Principle. IEEE Transactions on Robotics, In press. ⟨hal-04438175v2⟩
161 Consultations
168 Téléchargements

Partager

More