Decoupled Real-Time Trajectory Planning for Multiple Autonomous Mining Trucks in Unloading Areas
Qingyuan Yang, Yunfeng Ai, Siyu Teng, Yu Gao, Chenglin Cui, Bin Tian, Long Chen
Abstract
Cooperative trajectory planning for autonomous vehicles has garnered significant attention in structured environments, but corresponding methodologies for unstructured environments remains relatively underexplored. The unloading area, an integral component of open-pit mines, exemplifies a quintessential unstructured environment. Implementing cooperative planning for autonomous mining trucks (AMTs) within these unloading areas is crucial as the optimization of processes in these areas substantially enhances the overarching safety, productivity, and cost-effectiveness of mining operations. Hence, enhancing the operational efficiency of AMTs in the unloading area can considerably elevate productivity levels of open-pit mines. This article focuses on the real-time cooperative trajectory planning problem for AMTs in such areas, which is challenging due to i) small and irregular space ii) complex operations iii) need for path stability and speed flexibility. We propose a decoupled multi-vehicle trajectory planning (MVTP) method that decomposes trajectory planning into path planning and speed planning. Specifically, we present driving behavior enhanced path planning and sequential real-time cooperative speed planning methods. Our method is compared with several state-of-the-art MVTP methods and proves to be both secure and efficient.