eduzhai > Applied Sciences > Engineering >

D-ACC Dynamic Adaptive Cruise Control for Highways with Ramps Based on Deep Q-Learning

  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: An Adaptive Cruise Control (ACC) system allows vehicles to maintain a desiredheadway distance to a preceding vehicle automatically. It is increasinglyadopted by commercial vehicles. Recent research demonstrates that the effectiveuse of ACC can improve the traffic flow through the adaptation of the headwaydistance in response to the current traffic conditions. In this paper, wedemonstrate that a state-of-the-art intelligent ACC system performs poorly onhighways with ramps due to the limitation of the model-based approaches that donot take into account appropriately the traffic dynamics on ramps indetermining the optimal headway distance. We then propose a dynamic adaptivecruise control system (D-ACC) based on deep reinforcement learning that adaptsthe headway distance effectively according to dynamically changing trafficconditions for both the main road and ramp to optimize the traffic flow.Extensive simulations are performed with a combination of a traffic simulator(SUMO) and vehicle-to-everything communication (V2X) network simulator (Veins)under numerous traffic scenarios. We demonstrate that D-ACC improves thetraffic flow by up to 70 compared with a state-of-the-art intelligent ACCsystem in a highway segment with a ramp.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×