FusionPlanner: A Multi-task Motion Planner for Mining Trucks via Multi-sensor Fusion

• DOI: 10.48550/arxiv.2308.06931
• Publication Date: 2023-01-01
• Authors: Siyu Teng; Luxi Li; Yuchen Li; Xuemin Hu; Lingxi Li; Yunfeng Ai; Long Chen
• Keywords: Planner; Robustness; Benchmark (surveying); Open Pit Mining

In recent years, significant achievements have been made in motion planning for intelligent vehicles. However, as a typical unstructured environment, open-pit mining attracts limited attention due to its complex operational conditions and adverse environmental factors. A comprehensive paradigm unmanned transportation mines is proposed this research. Firstly, we propose multi-task algorithm, called FusionPlanner, autonomous trucks by the multi-sensor fusion method adapt both lateral longitudinal control tasks transportation. Then, develop novel benchmark MiningNav, which offers three validation approaches evaluate trustworthiness robustness of well-trained algorithms roads mines. Finally, introduce Parallel Mining Simulator (PMS), new high-fidelity simulator specifically designed scenarios. PMS enables users manage mine from single-truck multi-truck scheduling perspectives. The performance FusionPlanner tested MiningNav PMS, empirical results demonstrate reduction number collisions takeovers our planner. We anticipate will bring one step closer continuous round-the-clock