Learned Uncertainty Tubes via Recurrent Neural Networks for Planning Robust Robot Motions - LAAS - Laboratoire d'Analyse et d'Architecture des Systèmes Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Learned Uncertainty Tubes via Recurrent Neural Networks for Planning Robust Robot Motions

Simon Wasiela
  • Fonction : Auteur
  • PersonId : 1173154
Smail Ait Bouhsain
Marco Cognetti
  • Fonction : Auteur
  • PersonId : 1286741
Juan Cortés
Thierry Simeon

Résumé

In the context of generating robust robot motions, it is crucial to consider the effects of parameter uncertainties on the robot model. One approach to address this challenge is to compute ’uncertainty tubes’ that envelop the robot state for any combination of parameters within a given range, and to use these tubes to robustly check for collisions within a motion planning algorithm. However, computing them directly can be computationally expensive due to the need to solve and integrate potentially numerous nonlinear ordinary differential equations (ODEs) associated with robot dynamics. To overcome this limitation, we propose a GRU-based architecture that provides fast and accurate estimation of the uncertainty tubes. We demonstrate that GRUs achieve the best compromise between prediction accuracy, prediction time, and network size compared to RNNs and LSTMs, justifying our choice. Finally, we showcase the efficiency of the learning process within a motion planning framework for an aerial vehicle.
Fichier non déposé

Dates et versions

hal-04636454 , version 1 (05-07-2024)

Identifiants

  • HAL Id : hal-04636454 , version 1

Citer

Simon Wasiela, Smail Ait Bouhsain, Marco Cognetti, Juan Cortés, Thierry Simeon. Learned Uncertainty Tubes via Recurrent Neural Networks for Planning Robust Robot Motions. 27th European Conference on Artificial Intelligence (ECAI), Oct 2024, Santiago de Compostela, Spain. ⟨hal-04636454⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More