Hierarchical Trajectory Planning Based on Adaptive Motion Primitives and Bilevel Corridor

This paper presents an efficient and risk-aware search-optimization hierarchical trajectory planning method for automated vehicles in different road structures. The proposed approach incorporates a time-series motion risk field, capturing diverse road structures through a spatiotemporal map. Then, an adaptive motion primitive is developed, dynamically adjusting action time windows based on evolving risk and expected deviation during the search process. This enables efficient and accurate initial trajectory generation. Additionally, a bilevel corridor is introduced to extract the drivable area and re-represent the risk field, enabling trajectory smoothing to consider motion risk without resorting to non-convex optimization methods. Simulation results in structured and unstructured scenarios demonstrate that the proposed method improves efficiency, flexibility, and optimization quality compared to fixed-step search and single-level corridor-based optimization approaches. Real-world experiments on autonomous vehicles validated the dynamic characteristics and effectiveness of the proposed method in the actual environment.

I. Introduction

To Ensure safety and comfort, autonomous vehicles must navigate around obstacles and minimize the potential motion risk of future states [1], [2] in various driving scenarios, such as structured and unstructured (Fig. 1). In structured scenarios, motion risks primarily stem from other vehicles and lane boundaries, often represented as continuous constraints with high computational complexity [3], [4]. In unstructured scenarios, effectively incorporating the risk of dense, irregular obstacles and uneven road boundaries into planning poses significant challenges. Many algorithms rely on occupancy maps to facilitate simple obstacle avoidance instead [5], [6].