HPTune: Hierarchical Proactive Tuning for Collision-Free Model Predictive Control

2026-01-29

AI Summary

This work addresses the inefficiency of traditional model predictive control (MPC) parameter tuning, which relies solely on executed actions and suffers from sparse failure events. To overcome this limitation, the authors propose HPTune, a hierarchical active tuning framework that, for the first time, incorporates unexecuted actions into the evaluation process. The upper layer constructs a fast risk metric based on predicted approach velocity and distance, while the lower layer performs fine-grained optimization by integrating closed-loop backpropagation loss. Furthermore, the framework leverages multimodal perception from Doppler LiDAR to enhance motion prediction accuracy. Evaluated in high-fidelity simulation, HPTune significantly outperforms baseline methods, achieving safe, agile, and scenario-adaptive collision-free motion planning.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Model Predictive Control
• Parameter Tuning
• Collision Avoidance
• Motion Planning
• Failure Sparsity

Innovation

• Hierarchical Proactive Tuning
• Model Predictive Control
• Doppler LiDAR
• Collision-Free Motion Planning
• Closed-Loop Backpropagation