本研究提出了一种适用于自动驾驶车辆的多风格自适应跟驰决策框架,结合深度强化学习(DRL)与改进的粒子群优化算法,实现了对不同驾驶风格的精确控制。该框架通过DRL算法设计自适应的跟驰速度控制策略,并基于驾驶安全性、效率、舒适性和...本研究提出了一种适用于自动驾驶车辆的多风格自适应跟驰决策框架,结合深度强化学习(DRL)与改进的粒子群优化算法,实现了对不同驾驶风格的精确控制。该框架通过DRL算法设计自适应的跟驰速度控制策略,并基于驾驶安全性、效率、舒适性和紧急制动等因素构建了复杂的奖励机制。为进一步优化跟驰性能,本文在传统粒子群优化算法中引入了莱维扰动,以精确计算奖励函数中的最优权重组合,确保算法在不同驾驶场景下均能灵活应对。实验结果显示,该算法在多种复杂交通场景中具有鲁棒性,提供了更安全、高效且舒适的驾驶体验。In this study, a multi-style adaptive following decision framework for self-driving vehicles is proposed, which combines deep reinforcement learning (DRL) with an improved particle swarm optimization algorithm to achieve accurate control of different driving styles. The framework designs an adaptive following speed control strategy through the DRL algorithm. In order to further optimize the following speed performance, this paper introduces the Lévy perturbation into the tradi-tional particle swarm optimization algorithm to accurately calculate the optimal weight combinations in the reward function, ensuring that the algorithm can flexibly cope with different driving scenarios. Experimental results show that the algorithm is robust in multiple complex traffic scenarios, providing a safer, more efficient and comfortable driving experience.展开更多
A new emergency evacuation car-following model （EECM） is proposed. The model aims to capture the main characteristics of traffic flow and driver behavior under an emergency evacuation, and it is developed on the bas...A new emergency evacuation car-following model （EECM） is proposed. The model aims to capture the main characteristics of traffic flow and driver behavior under an emergency evacuation, and it is developed on the basis of minimum safety distances with parts of the drivers＇ abnormal behavior in a panic emergency situation. A thorough questionnaire survey is undertaken among drivers of different ages. Based on the results from the survey, a safety-distance car-following model is formulated by taking into account two new parameters： a differential distributing coefficient and a driver＇ s experiential decision coefficient, which are used to reflect variations of driving behaviors under an emergency evacuation situation when compared with regular conditions. The formulation and derivation of the new model, as well as its properties and applicability are discussed. A case study is presented to compare the car-following trajectories using observed data under regular peak-hour traffic conditions and theoretical EECM results. The results indicate the consistency of the analysis of assumptions on the EECM and observations.展开更多
文摘本研究提出了一种适用于自动驾驶车辆的多风格自适应跟驰决策框架,结合深度强化学习(DRL)与改进的粒子群优化算法,实现了对不同驾驶风格的精确控制。该框架通过DRL算法设计自适应的跟驰速度控制策略,并基于驾驶安全性、效率、舒适性和紧急制动等因素构建了复杂的奖励机制。为进一步优化跟驰性能,本文在传统粒子群优化算法中引入了莱维扰动,以精确计算奖励函数中的最优权重组合,确保算法在不同驾驶场景下均能灵活应对。实验结果显示,该算法在多种复杂交通场景中具有鲁棒性,提供了更安全、高效且舒适的驾驶体验。In this study, a multi-style adaptive following decision framework for self-driving vehicles is proposed, which combines deep reinforcement learning (DRL) with an improved particle swarm optimization algorithm to achieve accurate control of different driving styles. The framework designs an adaptive following speed control strategy through the DRL algorithm. In order to further optimize the following speed performance, this paper introduces the Lévy perturbation into the tradi-tional particle swarm optimization algorithm to accurately calculate the optimal weight combinations in the reward function, ensuring that the algorithm can flexibly cope with different driving scenarios. Experimental results show that the algorithm is robust in multiple complex traffic scenarios, providing a safer, more efficient and comfortable driving experience.
基金The National Key Technology R&D Program of China during the 10th Five-Year Plan Period(No.2005BA41B11)the National Natural Science Foundation of China(No.50578003)
文摘A new emergency evacuation car-following model （EECM） is proposed. The model aims to capture the main characteristics of traffic flow and driver behavior under an emergency evacuation, and it is developed on the basis of minimum safety distances with parts of the drivers＇ abnormal behavior in a panic emergency situation. A thorough questionnaire survey is undertaken among drivers of different ages. Based on the results from the survey, a safety-distance car-following model is formulated by taking into account two new parameters： a differential distributing coefficient and a driver＇ s experiential decision coefficient, which are used to reflect variations of driving behaviors under an emergency evacuation situation when compared with regular conditions. The formulation and derivation of the new model, as well as its properties and applicability are discussed. A case study is presented to compare the car-following trajectories using observed data under regular peak-hour traffic conditions and theoretical EECM results. The results indicate the consistency of the analysis of assumptions on the EECM and observations.
