The longitudinal trajectory planning of connected and autonomous vehicle (CAV) has been widely studied in the literature to reduce travel time or fuel consumptions. The safety impact of CAV trajectory planning to the mixed traffic flow with both CAV and human-driven vehicle (HDV), however, is not well understood yet. This study presents a reinforcement learning modeling approach, named Monte Carlo tree search-based autonomous vehicle safety algorithm, or MCTS-AVS, to optimize the safety of mixed traffic flow, on a one-lane roadway with signalized intersection control. Crash potential index (CPI) is defined to quantitively measure the safety performance of the mixed traffic flow. The CAV trajectory planning problem is firstly formulated as an optimization model; then, the solution procedure based on reinforcement learning is proposed. The tree-expansion determination module and rollout termination module are developed to identify and reduce the unnecessary tree expansion, so as to train the model more efficiently towards the desired direction. The case study results showed that the proposed algorithm was able to reduce the CPI by 76.56%, when compared with a benchmark model without any intelligence, and 12.08%, when compared with another benchmark model that the team developed earlier. These results demonstrated the satisfactory performance of the proposed algorithm in enhancing the safety of the mixed traffic flow.

中文翻译：

---

通过使用强化学习方法的互联和自主车辆轨迹规划来增强混合交通流的安全性

联网和自动驾驶汽车 (CAV) 的纵向轨迹规划已在文献中得到广泛研究，以减少旅行时间或燃料消耗。然而，CAV 轨迹规划对 CAV 和人类驾驶车辆 (HDV) 混合交通流的安全影响尚不清楚。本研究提出了一种强化学习建模方法，名为基于蒙特卡罗树搜索的自主车辆安全算法，或 MCTS-AVS，以优化具有信号化交叉口控制的单车道道路上混合交通流的安全性。碰撞潜在指数（CPI）被定义为定量衡量混合交通流的安全性能。CAV 轨迹规划问题首先被制定为一个优化模型；然后，提出了基于强化学习的求解过程。开发了树扩展确定模块和 rollout 终止模块来识别和减少不必要的树扩展，从而更有效地朝着所需方向训练模型。案例研究结果表明，与没有任何智能的基准模型相比，所提出的算法能够将 CPI 降低 76.56%，与团队早期开发的另一个基准模型相比，CPI 降低了 12.08%。这些结果证明了所提出的算法在提高混合交通流的安全性方面的令人满意的性能。案例研究结果表明，与没有任何智能的基准模型相比，所提出的算法能够将 CPI 降低 76.56%，与团队早期开发的另一个基准模型相比，CPI 降低了 12.08%。这些结果证明了所提出的算法在提高混合交通流的安全性方面的令人满意的性能。案例研究结果表明，与没有任何智能的基准模型相比，所提出的算法能够将 CPI 降低 76.56%，与团队早期开发的另一个基准模型相比，CPI 降低了 12.08%。这些结果证明了所提出的算法在提高混合交通流的安全性方面的令人满意的性能。