A Risk-aware Spatial-temporal Trajectory Planning Framework for Autonomous Vehicles Using QP-MPC and Dynamic Hazard Fields

2025-08-30

AI Summary

To address high computational overhead, poor adaptability to dynamic environments, and insufficient generalization validation in autonomous driving trajectory planning, this paper proposes a risk-aware spatiotemporal joint planning framework. Methodologically, it integrates dynamic hazard-field-guided spatial safety planning with spatiotemporal graph-based temporal planning, employs a multi-objective enhanced cost function, and implements a QP-MPC architecture incorporating quintic polynomial sampling, online dynamic risk assessment, and dual sub-rewards for comfort and efficiency. The key contribution lies in explicitly embedding dynamic risk into the spatiotemporal joint optimization process, enabling balanced trade-offs among safety, comfort, and efficiency. Extensive simulations across diverse complex scenarios—including lane changing, overtaking, and intersection navigation—demonstrate significant improvements over state-of-the-art optimization methods: +18.3% in trajectory stability, +12.7% in driving efficiency, and +21.5% in ride comfort.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Trajectory planning is a critical component in ensuring the safety, stability, and efficiency of autonomous vehicles. While existing trajectory planning methods have achieved progress, they often suffer from high computational costs, unstable performance in dynamic environments, and limited validation across diverse scenarios. To overcome these challenges, we propose an enhanced QP-MPC-based framework that incorporates three key innovations: (i) a novel cost function designed with a dynamic hazard field, which explicitly balances safety, efficiency, and comfort; (ii) seamless integration of this cost function into the QP-MPC formulation, enabling direct optimization of desired driving behaviors; and (iii) extensive validation of the proposed framework across complex tasks. The spatial safe planning is guided by a dynamic hazard field (DHF) for risk assessment, while temporal safe planning is based on a space-time graph. Besides, the quintic polynomial sampling and sub-reward of comforts are used to ensure comforts during lane-changing. The sub-reward of efficiency is used to maintain driving efficiency. Finally, the proposed DHF-enhanced objective function integrates multiple objectives, providing a proper optimization tasks for QP-MPC. Extensive simulations demonstrate that the proposed framework outperforms benchmark optimization methods in terms of efficiency, stability, and comfort across a variety of scenarios likes lane-changing, overtaking, and crossing intersections.

Problem

• Overcoming high computational costs in autonomous vehicle trajectory planning
• Addressing unstable performance in dynamic environments for safety
• Enhancing validation across diverse driving scenarios for reliability

Innovation

• Dynamic hazard field for risk-aware spatial planning
• QP-MPC integration with multi-objective cost function
• Quintic polynomial sampling for comfort optimization