Uncertainty Guided Exploratory Trajectory Optimization for Sampling-Based Model Predictive Control

TL;DR

The paper introduces UGE-TO, a novel trajectory optimization method that enhances exploration and robustness in sampling-based model predictive control by generating diverse trajectories using uncertainty-based distributions.

Contribution

It presents a new uncertainty-guided sampling approach that improves exploration and convergence in trajectory optimization, integrating it into MPC for better performance.

Findings

UGE-MPC achieves 72.1% faster convergence in obstacle-free environments.

66% faster convergence with higher success rate in cluttered environments.

The approach improves exploration and robustness in complex environments.

Abstract

Trajectory optimization depends heavily on initialization. In particular, sampling-based approaches are highly sensitive to initial solutions, and limited exploration frequently leads them to converge to local minima in complex environments. We present Uncertainty Guided Exploratory Trajectory Optimization (UGE-TO), a trajectory optimization algorithm that generates well-separated samples to achieve a better coverage of the configuration space. UGE-TO represents trajectories as probability distributions induced by uncertainty ellipsoids. Unlike sampling-based approaches that explore only in the action space, this representation captures the effects of both system dynamics and action selection. By incorporating the impact of dynamics, in addition to the action space, into our distributions, our method enhances trajectory diversity by enforcing distributional separation via the Hellinger distance between them. It enables a systematic exploration of the configuration space and improves robustness against local minima. Further, we present UGE-MPC, which integrates UGE-TO into sampling-based model predictive controller methods. Experiments demonstrate that UGE-MPC achieves higher exploration and faster convergence in trajectory optimization compared to baselines under the same sampling budget, achieving 72.1% faster convergence in obstacle-free environments and 66% faster convergence with a 6.7% higher success rate in the cluttered environment compared to the best-performing baseline. Additionally, we validate the approach through a range of simulation scenarios and real-world experiments. Our results indicate that UGE-MPC has higher success rates and faster convergence, especially in environments that demand significant deviations from nominal trajectories to avoid failures. The project and code are available at https://ogpoyrazoglu.github.io/cuniform_sampling/.