基于PER-APF算法的无人驾驶汽车换道轨迹规划

针对传统人工势场算法在解决无人驾驶汽车换道轨迹规划过程中存在的不足,提出一种基于势能重构人工势场 (Potential Energy Reconstruction- Artificial Potential Field, PER-APF) 的无人驾驶汽车换道轨迹规划算法。首先,建立了具有斥力区分的道路边界约束条件和多约束换道轨迹规划模型,通过判断障碍车辆与道路边沿的距离来保证换道过程的安全性与有效性；其次,提出了基于势能重构的改进APF算法,通过构建虚拟区域以及重构物理势能力场,有效的解决了目标不可达以及局部最优问题。仿真结果表明,所设计的PER-APF算法能够快速有效地为无人驾驶汽车规划一条安全合理的换道轨迹。

Lane Changing Trajectory Planning of Driverless Vehicle Based on PER-APF Algorithm

In order to solve the limitation problems of traditional artificial potential field algorithm in lane changing trajectory planning of driverless vehicle, a lane changing trajectory planning algorithm is proposed based on potential energy reconstruction and artificial potential field (PER-APF) algorithm. Firstly, the road boundary constraints with repulsive force differentiation and lane changing trajectory planning model with multiple constraints are established. By judging the distance between obstacle vehicles and road edges, to ensure the safety and effectiveness of vehicle lane changing process. In addition, with constructed virtual circular area and reconstructed physical potential energy field, the PER-APF algorithm can solve the problem of unreachable target and local optimization effectively. The simulation results show that the PER-APF algorithm can plan a reasonable lane change trajectory for driverless vehicle quickly and effectively.