Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control
It addresses robot planning under uncertainty, offering incremental improvements for robotics applications.
This work tackles the problem of robot interaction in complex environments requiring online control and adaptation by extending path integral control to embed uncertainty into action, providing robustness for model-based planning; it validates the method in simulation and real-world experiments with real-time performance.
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.