Smooth Sampling-Based Model Predictive Control Using Deterministic Samples

TL;DR

This paper introduces dsMPPI, a deterministic sampling approach for model predictive control that produces smoother control inputs for nonlinear systems by combining MPPI with CEM techniques.

Contribution

The paper proposes a novel deterministic sampling method for MPPI, enhancing smoothness and efficiency in nonlinear control applications.

Findings

dsMPPI achieves smoother trajectories than existing methods.

Deterministic sampling improves control input smoothness.

Experimental results validate the effectiveness of dsMPPI.

Abstract

Sampling-based model predictive control (MPC) is effective for nonlinear systems but often produces non-smooth control inputs due to random sampling. To address this issue, we extend the model predictive path integral (MPPI) framework with deterministic sampling and improvements from cross-entropy method (CEM)--MPC, such as iterative optimization, proposing deterministic sampling MPPI (dsMPPI). This combination leverages the exponential weighting of MPPI alongside the efficiency of deterministic samples. Experiments demonstrate that dsMPPI achieves smoother trajectories compared to state-of-the-art methods.