Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control

TL;DR

This paper introduces an extended path integral control method that incorporates uncertainty into robot planning, enhancing robustness and enabling real-time application in complex environments through simulation and real-world experiments.

Contribution

It presents a novel extension to path integral control that embeds uncertainty, improving robustness and real-time performance in model-based robot planning.

Findings

Effective in diverse robotic tasks

Validated in simulation and real-world experiments

Operates in real-time without performance loss

Abstract

This work addresses the problem of robot interaction in complex environments where online control and adaptation is necessary. By expanding the sample space in the free energy formulation of path integral control, we derive a natural extension to the path integral control that embeds uncertainty into action and provides robustness for model-based robot planning. Our algorithm is applied to a diverse set of tasks using different robots and validate our results in simulation and real-world experiments. We further show that our method is capable of running in real-time without loss of performance. Videos of the experiments as well as additional implementation details can be found at https://sites.google.com/view/emppi.