基于预测轨迹的无人驾驶矿用卡车主动防撞方法研究

Research on Active Anti-collision Method of Unmanned Mine Truck Based on Predicted Trajectory

现有的矿用卡车(简称“矿卡”)无人驾驶系统在环境复杂的矿区中运行存在很多安全隐患,例如调度系统规划轨迹问题、未及时更新矿区运行地图以及地面与车载数据出现轨迹部分丢包问题,这些都可能导致无人矿卡因参考轨迹错误而发生重大安全事故。为此,文章针对这些安全问题提出了一种基于预测轨迹的主动防撞方法。首先,其基于车载传感器采用基于模型的方法预测出无人矿卡的运行轨迹;然后,在预测的轨迹上做碰撞预测,使用方向包围盒(oriented boundingbox,OBB)碰撞检测方法,依据车辆当前位置寻找最近的碰撞检测栅格点,并根据距离计算相对速度;最后,无人矿卡根据自动紧急制动系统(advanced emergencybrakingsystem,AEBS)控制算法进行级联制动(即多级部分制动和全制动)。仿真验证结果表明,在没有期望轨迹时,矿卡可以及时地实现主动制动,保障了车辆的安全运行。

Existing mine truck unmanned driving systems operating in complex mining areas have many potential safety hazards, such as problems with the planning trajectory of the dispatching system, failure to update the mining area operation map in time, and the loss of trajectories data between the ground and on-board system. All of these may lead to major security incidents for unmanned mine trucks due to incorrect reference trajectories. To this end, this paper proposes an active collision avoidance method based on predicted trajectories to solve the above safety issues. First, a model-based method is used to predict running trajectory of unmanned mine truck based on on-board sensors. Then, collision prediction is made on the predicted trajectory, and the OBB (oriented bounding box) collision detection method is used to find the nearest vehicle according to the current position of the vehicle. Finally, the unmanned mine truck performs cascade braking (ie multi-stage partial braking and full braking) according to the AEBS (advanced emergency braking system) control algorithm. Simulation results show that when there is no expected trajectory, mine truck can realize active braking in time, which ensures the safe operation of the vehicle.