![]() Experimental results show that the proposed collective learning method leads to better results compared to the independent mode in which each agent controls the intersection individually. The total average energy of the sets of correlated agents as fuzzy sub-graphs is computed and the relationship between these values and the effectiveness of the collective learning is studied. In each set, collective learning composed of Q-learning and function approximation method is used to learn the optimal control policy. The network is divided into correlated agents' sets. The interaction between the agents can be represented by a fuzzy graph in which each vertex shows an agent in the network. A network composed of several intersections is considered as a multi-agent system composed of multiple interacting agents. In this paper, a fuzzy graph is used for urban traffic network modeling. The interaction between the agents can be represented by the graph theory. Multi-agent systems provide proper modeling in real-world applications such as intelligent transportation systems. In addition, the result achieved from a coordinated situation slightly superior that obtained from isolated situation, which means the proposed method provides good performance both in an isolated and coordinated situations. Based on the obtained results, the adaptive fuzzy logic and Webster based coordinated method outperforms the other methods in terms of the average of waiting time, travel time, travel speed, and queue lengths. The cyclic backpressure strategy was selected due to its similarity with our proposed method. It is compared with non-optimized fixed time control and the cyclic backpressure strategy suggested in the literature. ![]() The proposed method is investigated in both coordinated and isolated circumstances. This method eliminates the starvation that occurs at minor roads due to the non-cyclic strategy. ![]() These minimum green times can be used for pedestrian crossing purposes. It is a cyclic method, which means that all-feasible phases at the intersection are get at least a minimum green signal during each cycle. The proposed method is based on fuzzy logic and Webster optimum cycle formula. In this paper, the coordinated control method for an arterial road network is proposed. Traffic control systems for an urban traffic management play an important role in reducing congestion and the negative effects of social and economic aspects. The results clearly shows that proposed method decreases the delay time. The output of this paper indicate that the short action times increase the traffic control system performances despite more yellow signal duration. The performances of these methods are evaluated in real-time through the Simulation of Urban Mobility traffic simulator. Thus the proposed strategy uses not just information of intersection also uses the data of adjacent intersection as an input. ![]() Our approach does not just aim to minimize delay time by waiting time during the red-light signal also aims to decrease delay time caused by vehicles slowing down when approaching the intersection and caused by the required time to accelerate after the green light signal. Also, this study proposes a novel approach to the Deep Q-Learning based adaptive traffic control system for determine the best action. This study evaluates five different action durations. Deep Q-Learning has been applied to a traffic environment for adaptive learning. This paper seeks to understand the performance differences in different action durations for adaptive traffic management. Despite many successful studies about Reinforcement Learning based traffic control, there remains uncertainty about what the best actions to actualize adaptive traffic signal control. Reinforcement learning is one of the best algorithms used for adaptive traffic signal controllers. Adaptive traffic signal control is the control technique that adjusts the signal times according to traffic conditions and manages the traffic flow.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |