arXiv (Cornell University) · 2019 · 18 citations · 12 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceAutonomous VehiclesMachine LearningOptimal ControlPolicy LearningReinforcement LearningTraffic EngineeringVehicle ControlAutonomous Vehicle Path PlanningDeep Reinforcement LearningLane FollowingPath TrackingPolynomial Trajectory DesignPolynomial Trajectory GenerationPure Pursuit ControlQ-learning
We apply Deep Q-network (DQN) with the consideration of safety during the task for deciding whether to conduct the maneuver. Furthermore, we design two similar Deep Q learning frameworks with quadratic approximator for deciding how to select a comfortable gap and just follow the preceding vehicle. Finally, a polynomial lane change trajectory is generated and Pure Pursuit Control is implemented for path tracking. We demonstrate the effectiveness of this framework in simulation, from both the decision-making and control layers. The proposed architecture also has the potential to be extended to other autonomous driving scenarios.
12
SUMO - Simulation of Urban MObility An Overview
Michael Behrisch, Laura Bieker, Jakob Erdmann et al. · elib (German Aerospace Center) · 2011 · 1.2K citations · Full text