Decision-making of connected and automated vehicles(CAV)includes a sequence of driving maneuvers that improve safety and efficiency,characterized by complex scenarios,strong uncertainty,and high real-time requirements...Decision-making of connected and automated vehicles(CAV)includes a sequence of driving maneuvers that improve safety and efficiency,characterized by complex scenarios,strong uncertainty,and high real-time requirements.Deep reinforcement learning(DRL)exhibits excellent capability of real-time decision-making and adaptability to complex scenarios,and generalization abilities.However,it is arduous to guarantee complete driving safety and efficiency under the constraints of training samples and costs.This paper proposes a Mixture of Expert method(MoE)based on Soft Actor-Critic(SAC),where the upper-level discriminator dynamically decides whether to activate the lower-level DRL expert or the heuristic expert based on the features of the input state.To further enhance the performance of the DRL expert,a buffer zone is introduced in the reward function,preemptively applying penalties before insecure situations occur.In order to minimize collision and off-road rates,the Intelligent Driver Model(IDM)and Minimizing Overall Braking Induced by Lane changes(MOBIL)strategy are designed by heuristic experts.Finally,tested in typical simulation scenarios,MOE shows a 13.75%improvement in driving efficiency compared with the traditional DRL method with continuous action space.It ensures high safety with zero collision and zero off-road rates while maintaining high adaptability.展开更多
随着可再生能源并网发电量的不断增加,由电力电子设备引发的电力系统次同步振荡问题逐渐凸显,给电力系统的安全稳定运行带来了新的挑战。除此之外,当目标电力系统规模较大时,常用的基于线性化模型的分析方法面临着维数灾难。为了解决上...随着可再生能源并网发电量的不断增加,由电力电子设备引发的电力系统次同步振荡问题逐渐凸显,给电力系统的安全稳定运行带来了新的挑战。除此之外,当目标电力系统规模较大时,常用的基于线性化模型的分析方法面临着维数灾难。为了解决上述问题,根据强化学习原理,通过动作-评价(Actor-Critic)学习框架提出一种对风机换流器控制参数的优化策略。通过搜集永磁直驱风机(permanent magnetic synchronous generator,PMSG)运行状态数据,训练强化学习代理(Agent),以此评估风机运行状态及其稳定性,并寻找优化风机换流器参数的最优策略。该训练方法得到的代理能够基于时域采样数据对风机换流器参数进行优化,从而有效抑制由于换流器诱发的振荡现象,在没有建立线性化分析模型的情况下,能够有效优化并增强电力系统的稳定性。经实验验证,该优化策略在采样数据有噪声干扰的情况下仍然具有良好的优化性能。展开更多
Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adja...Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.展开更多
Actor-Critic是一种强化学习方法,通过与环境在线试错交互收集样本来学习策略,是求解序贯感知决策问题的有效手段.但是,这种在线交互的主动学习范式在一些复杂真实环境中收集样本时会带来成本和安全问题离线强化学习作为一种基于数据驱...Actor-Critic是一种强化学习方法,通过与环境在线试错交互收集样本来学习策略,是求解序贯感知决策问题的有效手段.但是,这种在线交互的主动学习范式在一些复杂真实环境中收集样本时会带来成本和安全问题离线强化学习作为一种基于数据驱动的强化学习范式,强调从静态样本数据集中学习策略,与环境无探索交互,为机器人、自动驾驶、健康护理等真实世界部署应用提供了可行的解决方案,是近年来的研究热点.目前,离线强化学习方法存在学习策略和行为策略之间的分布偏移挑战,针对这个挑战,通常采用策略约束或值函数正则化来限制访问数据集分布之外(Out-Of-Distribution,OOD)的动作,从而导致学习性能过于保守,阻碍了值函数网络的泛化和学习策略的性能提升.为此,本文利用不确定性估计和OOD采样来平衡值函数学习的泛化性和保守性,提出一种基于不确定性估计的离线确定型Actor-Critic方法(Offline Deterministic Actor-Critic based on UncertaintyEstimation,ODACUE).首先,针对确定型策略,给出一种Q值函数的不确定性估计算子定义,理论证明了该算子学到的Q值函数是最优Q值函数的一种悲观估计.然后,将不确定性估计算子应用于确定型Actor-Critic框架中,通过对不确定性估计算子进行凸组合构造Critic学习的目标函数.最后,D4RL基准数据集任务上的实验结果表明:相较于对比算法,ODACUE在11个不同质量等级数据集任务中的总体性能提升最低达9.56%,最高达64.92%.此外,参数分析和消融实验进一步验证了ODACUE的稳定性和泛化能力.展开更多
基金Supported by National Key R&D Program of China(Grant No.2022YFB2503203)National Natural Science Foundation of China(Grant No.U1964206).
文摘Decision-making of connected and automated vehicles(CAV)includes a sequence of driving maneuvers that improve safety and efficiency,characterized by complex scenarios,strong uncertainty,and high real-time requirements.Deep reinforcement learning(DRL)exhibits excellent capability of real-time decision-making and adaptability to complex scenarios,and generalization abilities.However,it is arduous to guarantee complete driving safety and efficiency under the constraints of training samples and costs.This paper proposes a Mixture of Expert method(MoE)based on Soft Actor-Critic(SAC),where the upper-level discriminator dynamically decides whether to activate the lower-level DRL expert or the heuristic expert based on the features of the input state.To further enhance the performance of the DRL expert,a buffer zone is introduced in the reward function,preemptively applying penalties before insecure situations occur.In order to minimize collision and off-road rates,the Intelligent Driver Model(IDM)and Minimizing Overall Braking Induced by Lane changes(MOBIL)strategy are designed by heuristic experts.Finally,tested in typical simulation scenarios,MOE shows a 13.75%improvement in driving efficiency compared with the traditional DRL method with continuous action space.It ensures high safety with zero collision and zero off-road rates while maintaining high adaptability.
文摘随着可再生能源并网发电量的不断增加,由电力电子设备引发的电力系统次同步振荡问题逐渐凸显,给电力系统的安全稳定运行带来了新的挑战。除此之外,当目标电力系统规模较大时,常用的基于线性化模型的分析方法面临着维数灾难。为了解决上述问题,根据强化学习原理,通过动作-评价(Actor-Critic)学习框架提出一种对风机换流器控制参数的优化策略。通过搜集永磁直驱风机(permanent magnetic synchronous generator,PMSG)运行状态数据,训练强化学习代理(Agent),以此评估风机运行状态及其稳定性,并寻找优化风机换流器参数的最优策略。该训练方法得到的代理能够基于时域采样数据对风机换流器参数进行优化,从而有效抑制由于换流器诱发的振荡现象,在没有建立线性化分析模型的情况下,能够有效优化并增强电力系统的稳定性。经实验验证,该优化策略在采样数据有噪声干扰的情况下仍然具有良好的优化性能。
文摘提出一种基于模糊RBF网络的自适应模糊A ctor-C ritic学习.采用一个模糊RBF神经网络同时逼近A ctor的动作函数和C ritic的值函数,解决状态空间泛化中易出现的“维数灾”问题.模糊RBF网络能够根据环境状态和被控对象特性的变化进行网络结构和参数的自适应学习,使得网络结构更加紧凑,整个模糊A ctor-C ritic学习具有泛化性能好、控制结构简单和学习效率高的特点.M oun ta in C ar的仿真结果验证了所提方法的有效性.
基金supported by National Natural Science Foundation of China(52222215, 52272420, 52072051)。
文摘Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.
文摘Actor-Critic是一种强化学习方法,通过与环境在线试错交互收集样本来学习策略,是求解序贯感知决策问题的有效手段.但是,这种在线交互的主动学习范式在一些复杂真实环境中收集样本时会带来成本和安全问题离线强化学习作为一种基于数据驱动的强化学习范式,强调从静态样本数据集中学习策略,与环境无探索交互,为机器人、自动驾驶、健康护理等真实世界部署应用提供了可行的解决方案,是近年来的研究热点.目前,离线强化学习方法存在学习策略和行为策略之间的分布偏移挑战,针对这个挑战,通常采用策略约束或值函数正则化来限制访问数据集分布之外(Out-Of-Distribution,OOD)的动作,从而导致学习性能过于保守,阻碍了值函数网络的泛化和学习策略的性能提升.为此,本文利用不确定性估计和OOD采样来平衡值函数学习的泛化性和保守性,提出一种基于不确定性估计的离线确定型Actor-Critic方法(Offline Deterministic Actor-Critic based on UncertaintyEstimation,ODACUE).首先,针对确定型策略,给出一种Q值函数的不确定性估计算子定义,理论证明了该算子学到的Q值函数是最优Q值函数的一种悲观估计.然后,将不确定性估计算子应用于确定型Actor-Critic框架中,通过对不确定性估计算子进行凸组合构造Critic学习的目标函数.最后,D4RL基准数据集任务上的实验结果表明:相较于对比算法,ODACUE在11个不同质量等级数据集任务中的总体性能提升最低达9.56%,最高达64.92%.此外,参数分析和消融实验进一步验证了ODACUE的稳定性和泛化能力.
