消减换道行为影响的换道轨迹规划

Lane-changing Trajectory Planning Considering Mitigation of Lane-changing Impact on Surroundings

摘要:

构建了一种能够消减换道行为影响的换道轨迹规划，将帕累托最优理念引入至自主换道行为中，通过IDM（intelligent driver model）模型构建周边车辆的优化目标。采用5次多项式模型构建换道车辆的优化目标，引入多目标优化算法求解该多目标问题，从而获得换道车辆与周边车辆的帕累托最优前沿。实验表明相比于现有算法所提算法能够显著降低换道区域内所有车辆的总损失，提高区域内交通流运行状态及安全。

Abstract:

This paper proposes a novel lane-changing trajectory planning algorithm that could mitigate lane-changing impact. We introduce the intelligent driver model（IDM ）to construct the optimization objective of the surrounding vehicles， and we employ the quintic polynomial model to formulate the optimization objective of the lane-changing vehicle. Thereafter， we introduce the multiobjective optimization algorithm to solve the multi-objective problem， as a result， we obtain the pareto-optimal front of the lane-changing vehicle and the surrounding vehicles. Our experiments demonstrate that in comparison with the existing algorithms， our algorithm can significantly reduce the total cost of all vehicles within the region and improve the traffic flow operation state.