In the robot soccer competition platform, the cur- rent confrontation decision-making system suffers from dif- ficulties in optimization and adaptability. Therefore, we pro- pose a new self-adaptive decision-making （...In the robot soccer competition platform, the cur- rent confrontation decision-making system suffers from dif- ficulties in optimization and adaptability. Therefore, we pro- pose a new self-adaptive decision-making （SADM） strategy. SADM compensates for the restrictions of robot physical movement control by updating the task assignment and role assignment module using situation assessment techniques. It designs a self-adaptive role assignment model that assists the soccer robot in adapting to competition situations similar to how humans adapt in real time. Moreover, it also builds an accurate motion model for the robot in order to improve the competition ability of individual robot soccer. Experimental results show that SADM can adapt quickly and positively to new competition situations and has excellent performance in actual competition.展开更多
Reinforcement learning-based traffic signal control systems (RLTSC) can enhance dynamic adaptability, save vehicle travelling timeand promote intersection capacity. However, the existing RLTSC methods do not consider ...Reinforcement learning-based traffic signal control systems (RLTSC) can enhance dynamic adaptability, save vehicle travelling timeand promote intersection capacity. However, the existing RLTSC methods do not consider the driver’s response time requirement, sothe systems often face efficiency limitations and implementation difficulties.We propose the advance decision-making reinforcementlearning traffic signal control (AD-RLTSC) algorithm to improve traffic efficiency while ensuring safety in mixed traffic environment.First, the relationship between the intersection perception range and the signal control period is established and the trust region state(TRS) is proposed. Then, the scalable state matrix is dynamically adjusted to decide the future signal light status. The decision will bedisplayed to the human-driven vehicles (HDVs) through the bi-countdown timer mechanism and sent to the nearby connected automatedvehicles (CAVs) using the wireless network rather than be executed immediately. HDVs and CAVs optimize the driving speedbased on the remaining green (or red) time. Besides, the Double Dueling Deep Q-learning Network algorithm is used for reinforcementlearning training;a standardized reward is proposed to enhance the performance of intersection control and prioritized experiencereplay is adopted to improve sample utilization. The experimental results on vehicle micro-behaviour and traffic macro-efficiencyshowed that the proposed AD-RLTSC algorithm can simultaneously improve both traffic efficiency and traffic flow stability.展开更多
文摘In the robot soccer competition platform, the cur- rent confrontation decision-making system suffers from dif- ficulties in optimization and adaptability. Therefore, we pro- pose a new self-adaptive decision-making （SADM） strategy. SADM compensates for the restrictions of robot physical movement control by updating the task assignment and role assignment module using situation assessment techniques. It designs a self-adaptive role assignment model that assists the soccer robot in adapting to competition situations similar to how humans adapt in real time. Moreover, it also builds an accurate motion model for the robot in order to improve the competition ability of individual robot soccer. Experimental results show that SADM can adapt quickly and positively to new competition situations and has excellent performance in actual competition.
基金Science&Technology Research and Development Program of China Railway(Grant No.N2021G045)the Beijing Municipal Natural Science Foundation(Grant No.L191013)the Joint Funds of the Natural Science Foundation of China(Grant No.U1934222).
文摘Reinforcement learning-based traffic signal control systems (RLTSC) can enhance dynamic adaptability, save vehicle travelling timeand promote intersection capacity. However, the existing RLTSC methods do not consider the driver’s response time requirement, sothe systems often face efficiency limitations and implementation difficulties.We propose the advance decision-making reinforcementlearning traffic signal control (AD-RLTSC) algorithm to improve traffic efficiency while ensuring safety in mixed traffic environment.First, the relationship between the intersection perception range and the signal control period is established and the trust region state(TRS) is proposed. Then, the scalable state matrix is dynamically adjusted to decide the future signal light status. The decision will bedisplayed to the human-driven vehicles (HDVs) through the bi-countdown timer mechanism and sent to the nearby connected automatedvehicles (CAVs) using the wireless network rather than be executed immediately. HDVs and CAVs optimize the driving speedbased on the remaining green (or red) time. Besides, the Double Dueling Deep Q-learning Network algorithm is used for reinforcementlearning training;a standardized reward is proposed to enhance the performance of intersection control and prioritized experiencereplay is adopted to improve sample utilization. The experimental results on vehicle micro-behaviour and traffic macro-efficiencyshowed that the proposed AD-RLTSC algorithm can simultaneously improve both traffic efficiency and traffic flow stability.
