HPTune: Hierarchical Proactive Tuning for Collision-Free Model Predictive Control
Wei Zuo, Chengyang Li, Yikun Wang, Bingyang Cheng, Zeyi Ren, Shuai Wang, Derrick Wing Kwan Ng, Yik-Chung Wu
TL;DR
This work tackles the inefficiency of myopic, failure-triggered MPC tuning in dynamic obstacle environments. It introduces HPTune, a hierarchical proactive tuning framework that extends evaluation to non-executed actions via fast-level risk indicators $d^{h+1,n}_\text{prox}$ and $v^{h+1,n}_\text{closing}$ and a slow-level backpropagation-based loss $L(t)$ with components $L_1$, $L_2$, and $L_3$. It further integrates Doppler LiDAR-derived obstacle velocities through a Kalman filter to enhance motion prediction. Empirical results in the CARLA simulator show substantial improvements in navigation pass rates and motion smoothness compared to baselines, demonstrating safer and more efficient collision-free MPC motion planning driven by proactive, situation-tailored tuning.
Abstract
Parameter tuning is a powerful approach to enhance adaptability in model predictive control (MPC) motion planners. However, existing methods typically operate in a myopic fashion that only evaluates executed actions, leading to inefficient parameter updates due to the sparsity of failure events (e.g., obstacle nearness or collision). To cope with this issue, we propose to extend evaluation from executed to non-executed actions, yielding a hierarchical proactive tuning (HPTune) framework that combines both a fast-level tuning and a slow-level tuning. The fast one adopts risk indicators of predictive closing speed and predictive proximity distance, and the slow one leverages an extended evaluation loss for closed-loop backpropagation. Additionally, we integrate HPTune with the Doppler LiDAR that provides obstacle velocities apart from position-only measurements for enhanced motion predictions, thus facilitating the implementation of HPTune. Extensive experiments on high-fidelity simulator demonstrate that HPTune achieves efficient MPC tuning and outperforms various baseline schemes in complex environments. It is found that HPTune enables situation-tailored motion planning by formulating a safe, agile collision avoidance strategy.