Four fundamental insights into transition methods are provided from the perspective of traffic engineers. An improved empirical transition method (i.e., Shortest-way) is developed with the goal of reducing the time spent on offset correction and the offset deviations of the coordinated phases during the transition period. Shortest-way operates stepwise and can be activated to correct offset at the scheduled time to switch plans. The maximum amount of adjustment that can be made to a transition cycle length is calculated based on the timing parameters of active phases in the old and new plans. The problem of cycle length distribution is formulated as a nonlinear integer programming problem, aiming at minimizing the sum of the squares of the intersection offset deviations of all the transition cycles. The portion of the cycle length that can be allocated to each phase in a transition cycle is calculated based on its splits in the old and new plans and its potential contribution to the maximum amount of adjustment to the cycle length. The numerical experimental results proved the potential advantage of Shortest-way over CORSIM Shortway and justified the necessity for managing the time to switch plans at the intersection level.
With people's awareness of health and environmental protection improve, and now more and more people began to choose the way of low carbon, energy saving, and free travel mode-riding. In our country, Cycling clothes, as an important equipment of riding movement which is gradually entering people's field of vision. Firstly, the paper analyzes the characteristics of the structure design of cycling clothes, then the selection of the functional fabrics, the design requirements of the pattern and the color. Finally make a prospect of the future development of riding clothes in China. which can provide reference for the latter research and enterprise production.
Real-time isolated signal control (RISC) at an intersection is of interest in the field of traffic engineering. Energizing RISC with reinforcement learning (RL) is feasible and necessary. Previous studies paid less attention to traffic engineering considerations and under-utilized traffic expertise to construct RL tasks. This study profiles the single-ring RISC problem from the perspective of traffic engineers, and improves a prevailing RL method for solving it. By qualitative applicability analysis, we choose double deep Q-network (DDQN) as the basic method. A single agent is deployed for an intersection. Reward is defined with vehicle departures to properly encourage and punish the agent’s behavior. The action is to determine the remaining green time for the current vehicle phase. State is represented in a grid-based mode. To update action values in time-varying environments, we present a temporal-difference algorithm TD(Dyn) to perform dynamic bootstrapping with the variable interval between actions selected. To accelerate training, we propose a data augmentation based on intersection symmetry. Our improved DDQN, termed D3ynQN, is subject to the signal timing constraints in engineering. The experiments at a close-to-reality intersection indicate that, by means of D3ynQN and non-delay-based reward, the agent acquires useful knowledge to significantly outperform a fully-actuated control technique in reducing average vehicle delay.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.