Sampling-based Model Predictive Control Leveraging Parallelizable Physics Simulations

• Published in: arXiv.org
• Main Authors: Pezzato, Corrado, Salmi, Chadi, Spahn, Max, Trevisan, Elia, Alonso-Mora, Javier, Carlos Hernandez Corbato
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 04.12.2023
• Subjects: Collision avoidance; Dynamic models; Motion planning; Navigation; Predictive control; Robot dynamics; Sampling; Simulation; Task complexity

We present a method for sampling-based model predictive control that makes use of a generic physics simulator as the dynamical model. In particular, we propose a Model Predictive Path Integral controller (MPPI), that uses the GPU-parallelizable IsaacGym simulator to compute the forward dynamics of a...