Collaborative Trajectory Planning for Autonomous Mining Trucks: A Grouping and Prioritized Optimization Based Approach
Han Li, Peng Chen, Guizhen Yu, Bin Zhou, Zhixuan Han, Yaping Liao
Abstract
The bottleneck of trajectory planning for autonomous driving at mining site has shifted from single truck to multi trucks, particularly in the loading area where collaborative trajectory planning (CTP) in the loading area is crucial for efficient operation. The existing optimization-based methods that integrate all vehicle states and fail to generate the trajectories according to real time requirements. Other station-time graph-based method have significant limitations as they rely on the prior reference path and only adjust the speed of trucks but often incur infeasible trajectory when the scale of the trucks increases, causing traffic deadlock even collision. To facilitate a more productive CTP, we propose an efficient method by combing heuristic search and group priority optimization-based approach that strives to realize the efficient generation of safe trajectories. The proposed method essentially integrates two radical trajectory planners: i) heuristic search trajectory planning and ii) advanced sequential optimization method, and introduces a novel adaptive group priority based on the characteristics of mining site for easing the computational time of sequential optimization. Extensive simulation results demonstrate that the proposed method can resolve the collision between trucks and reduce the waiting time of trucks while overcoming excessive time consumption of CTP.