Mortaza Zolfpour-Arokhlo

Modeling of route planning system based on Q value-based dynamic programming with multi-agent reinforcement learning algorithms

In this paper, a new model for a route planning system based on multi-agent reinforcement learning (MARL) algorithms is proposed. The combined Q-value based dynamic programming (QVDP) with Boltzmann distribution was used to solve vehicle delays problems by studying the weights of various components in road network environments such as weather, traffic, road safety, and fuel capacity to create a priority route plan for vehicles. The important part of the study was to use a multi-agent system (MAS) with learning abilities which in order to make decisions about routing vehicles between Malaysias cities. The evaluation was done using a number of case studies that focused on road networks in Malaysia. The results of these experiments indicated that the travel durations for the case studies predicted by existing approaches were between 0.00 and 12.33% off from the actual travel times by the proposed method. From the experiments, the results illustrate that the proposed approach is a unique contribution to the field of computational intelligence in the route planning system.

Route planning model of multi-agent system for a supply chain management

Sometimes in travel planning, finding the best route to the road transportation network by considering the environmental conditions that are affecting the actual time travel of the travellers are vital especially in handling the logistic operations in supply chain management (SCM). Furthermore, the policy strategy is needed in order to influence the managers or drivers to find the optimum and the most effective route for a trip plan in supporting the logistic operations of SCM. In this paper we analyze the effectiveness of the coordination model of the environmental conditions that are affecting for the travelling time based on multi-agent system for a road transportation network for supply chain management. A number of experimental cases have been used to evaluate the proposed approach transportation network problems in some Malaysian cities. Finally, experimental results affirmed that the proposed approach is practical and efficient.

A fast path planning algorithm for route guidance system

Path planning is applied in a variety of ways, including transportation, telecommunications, etc. Path planning to direct vehicles to their destination in a dynamic traffic situation, with the aim of reducing the motoring time and to ensure and efficient use of available road resources is the main challenge in route guidance system. In this paper we propose a fast path algorithm for finding the best shortest paths in the road network. This is poised to minimize costs between the origin and destination nodes. The proposed algorithm was compared with the Dijkstra algorithm in order to find the best and shortest paths using a sample of Tehran city road network. Three cases were tested through simulation using the proposed algorithm. The results show that the efficiency of proposed algorithm and could reduce the cost of vehicle routing on the path planning problems.

A multi-agent system approach to control road transportation network

Several challenges in road transportation network control cause an increasing number of vehicles to transport goods and people in our society. The concept of autonomous agents fits most actors in road transportation network, i.e., the weather, the traffic, the driver. Moreover, the traffic signals and the weather condition can also be regarded as an autonomous agent. Though, there is increasing number of agents, typical agents respond to changes in their environment inspite of highly couple. Most challenges for standard techniques are created by this domain in road transportation network from multi-agent systems such as road traffic control, weather and transport planning. This paper, first, proposes a new approach, and then, addresses the challenges for future works using multi-agent systems.

Route Guidance System Based on Self-Adaptive Algorithm

Self-adaptive systems are applied in a variety of ways, including transportation, telecommunications, etc. The main challenge in route guidance system is to direct vehicles to their destination in a dynamic traffic situation, with the aim of reducing the motoring time and to ensure an efficient use of available road resources. In this paper, we propose a self-adaptive algorithm for managing the shortest paths in route guidance system. This is poised to minimize costs between the origin and destination nodes. The proposed algorithm was compared with the Dijkstra algorithm in order to find the best and shortest paths using a sample simplified real sample of Kuala-Lumpur (KL) road network map. Four cases were tested to verify the efficiency of our approach through simulation using the proposed algorithm. The results show that the proposed algorithm could reduce the cost of vehicle routing and associated problems.