School of Computer Science and Information Engineering,Hefei University of Technology
Repairing the damaged road network is an important part of the disaster emergency response. It mainly studies how to effectively dispatch the repair crew to quickly restore the traffic capacity of the damaged road network and provide an effective guarantee for the smooth implementation of the subsequent emergency rescue.However, the eixsting work cannot find a feasiblesolution under a large amount of continuously damaged road sections. To this end, this paper firstly constructs a road network model and a repair crew scheduling model based on Markov decision process, and then designs the corresponding actions, states and reward functions. Then, an algorithm for repair crew scheduling under continuously damaged road sections based on Q-learning is presented. The simulation results show that the proposed algorithm has good reliability and can obtain a better scheduling scheme at a lower cost in the environment of continuously damaged road sections.