eduzhai > Applied Sciences > Engineering >

V2I Connectivity-Based Dynamic Queue-Jump Lane for Emergency Vehicles A Deep Reinforcement Learning Approach

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 20 pages

Abstract: Emergency vehicle (EMV) service is a key function of cities and isexceedingly challenging due to urban traffic congestion. A main reason behindEMV service delay is the lack of communication and cooperation between vehiclesblocking EMVs. In this paper, we study the improvement of EMV service under V2Iconnectivity. We consider the establishment of dynamic queue jump lanes (DQJLs)based on real-time coordination of connected vehicles. We develop a novelMarkov decision process formulation for the DQJL problem, which explicitlyaccounts for the uncertainty of drivers reaction to approaching EMVs. Wepropose a deep neural network-based reinforcement learning algorithm thatefficiently computes the optimal coordination instructions. We also validateour approach on a micro-simulation testbed using Simulation of Urban Mobility(SUMO). Validation results show that with our proposed methodology, thecentralized control system saves approximately 15 EMV passing time than thebenchmark system.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×