Graph-based Path Planning with Dynamic Obstacle Avoidance for Autonomous Parking
🤖 AI Summary
To address safety and real-time performance challenges in complex parking scenarios involving coexisting static and dynamic obstacles, this paper proposes a time-indexed online path planning method. The approach introduces three key contributions: (1) a novel time-indexed Hybrid A* algorithm that explicitly incorporates dynamic obstacle motion prediction into the node expansion process; (2) an adaptive intermediate-goal-driven framework for online local replanning; and (3) support for diverse parking geometries—including perpendicular, angled, and parallel parking—via unified geometric modeling. Evaluated across multiple simulated scenarios, the method achieves a 23% higher path success rate and reduces average planning time by 37% compared to mainstream spline-based approaches, while maintaining zero collisions throughout all trials. These results demonstrate substantial improvements in both planning robustness and computational efficiency under complex, dynamic urban parking conditions.
Application Category
📝 Abstract
Safe and efficient path planning in parking scenarios presents a significant challenge due to the presence of cluttered environments filled with static and dynamic obstacles. To address this, we propose a novel and computationally efficient planning strategy that seamlessly integrates the predictions of dynamic obstacles into the planning process, ensuring the generation of collision-free paths. Our approach builds upon the conventional Hybrid A star algorithm by introducing a time-indexed variant that explicitly accounts for the predictions of dynamic obstacles during node exploration in the graph, thus enabling dynamic obstacle avoidance. We integrate the time-indexed Hybrid A star algorithm within an online planning framework to compute local paths at each planning step, guided by an adaptively chosen intermediate goal. The proposed method is validated in diverse parking scenarios, including perpendicular, angled, and parallel parking. Through simulations, we showcase our approach's potential in greatly improving the efficiency and safety when compared to the state of the art spline-based planning method for parking situations.
Problem
Research questions and friction points this paper is trying to address.
Dynamic obstacle avoidance in autonomous parking path planning
Efficient collision-free path generation in cluttered environments
Integration of time-indexed Hybrid A star for online planning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Time-indexed Hybrid A star algorithm
Dynamic obstacle prediction integration
Online planning framework adaptation
🔎 Similar Papers
No similar papers found.
