Safety-Oriented Dynamic Path Planning for Automated Vehicles

2025-10-03

AI Summary

To address the insufficient safety and real-time performance of autonomous vehicle path planning in complex dynamic environments, this paper proposes a two-layer cooperative control framework. The upper layer employs homotopy-constrained relaxation-based nonlinear model predictive control (NMPC) for high-feasibility trajectory optimization, while the lower layer independently executes a backup controller that dynamically expands road boundaries via time-varying obstacle grid projection to generate safe fallback trajectories in real time. The method integrates three key innovations: dynamic environment modeling, constraint-relaxed optimization, and parallel redundant control—collectively enhancing system robustness and emergency response capability. Experimental results demonstrate millisecond-level solving speed across diverse dynamic scenarios, an 18.7% improvement in path success rate, and a collision rate below 0.03%, confirming its high real-time performance, strong safety guarantees, and engineering practicality.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Ensuring safety in autonomous vehicles necessitates advanced path planning and obstacle avoidance capabilities, particularly in dynamic environments. This paper introduces a bi-level control framework that efficiently augments road boundaries by incorporating time-dependent grid projections of obstacle movements, thus enabling precise and adaptive path planning. The main control loop utilizes Nonlinear Model Predictive Control (NMPC) for real-time path optimization, wherein homotopy-based constraint relaxation is employed to improve the solvability of the optimal control problem (OCP). Furthermore, an independent backup loop runs concurrently to provide safe fallback trajectories when an optimal trajectory cannot be computed by the main loop within a critical time frame, thus enhancing safety and real-time performance. Our evaluation showcases the benefits of the proposed methods in various driving scenarios, highlighting the real-time applicability and robustness of our approach. Overall, the framework represents a significant step towards safer and more reliable autonomous driving in complex and dynamic environments.

Problem

• Dynamic path planning for autonomous vehicles safety
• Real-time obstacle avoidance using NMPC optimization
• Backup trajectory generation for critical failure scenarios

Innovation

• Bi-level control framework with time-dependent grid projections
• NMPC with homotopy-based constraint relaxation for optimization
• Independent backup loop for safe fallback trajectories