Traffic signal control has long been considered as a critical topic in intelligent transportation systems. Most existing related methods either suffer from inefficient training or mainly focus on isolated intersections. This article aims at the cooperative for multi-intersection traffic signal, which novel end-to-end learning model is established and an efficient method proposed analogously, capable of adapting to large-scale scenarios. In method, input status are expressed by tensor without...

Automated lane change decision making ability is significant for vehicles to adjust lanes avoid collisions or overtake other vehicles. However, traditional methods predicting all the possible situations using hand-crafted features inefficient. In this paper, we propose a new agent based on deep reinforcement learning (DRL). order compare performance differences of diverse DRL and state representations, our agents are trained via different (DQN, A3C) representations. To demonstrate...

Intersections are the key to improve traffic efficiency. For intersections with complex conditions, if we want efficiency effectively, should make signals adjust adaptively according different status. Obviously, traditional fixed timing strategy is hard achieve this. In addition, cooperative control of multiple will maximize their overall interests and reduce contradictions between intersections. Therefore, in this paper, propose an adaptive signal method for based on deep reinforcement...

Longitudinal following control is the fundamental component of vehicle platoon control. Although cooperation vehicles helps to improve traffic efficiency, it exacerbates non-linearity system as well. The promising development reinforcement learning and neural networks brings inspiring ideas designs controller for non-linear system. This paper proposes a novel algorithm longitudinal based on deep deterministic policy gradient (DDPG) algorithms. Focusing control, this builds single-lane...

Traffic signal control has long been considered as a critical topic in intelligent transportation systems. Most existing learning methods mainly focus on isolated intersections and suffer from inefficient training. This paper aims at the cooperative for large scale multi-intersection traffic signal, which novel end-to-end based model is established efficient training method proposed correspondingly. In model, input status multi-intersections represented by tensor, not only significantly...

Intersections are the hubs of urban transport networks and bottlenecks transportation efficiency. Traditional fixed timing policies cannot be adjusted flexibly as traffic status changes. Adjusting lights adaptively according to different conditions would improve In recent years, with development machine learning, especially reinforcement learning technologies, these problems can solved help advanced AI methods. Traffic signal control just one kind these. Therefore, in this paper, an adaptive...