2023 · 13 citations · 21 references
ComputingAutomotive EngineeringAutonomous SystemsAutonomous VehiclesMachine LearningMotion PlanningPolicy LearningReinforcement LearningTrajectory PredictionVehicle ControlAutonomous Vehicle SafetyDeep Reinforcement LearningLane Change PlanningRisk Constraint SatisfactionSafe LearningSafe Policy LearningSafe Reinforcement LearningUnsafe Driving
Deep reinforcement learning (DRL) has become a powerful method for autonomous driving while often lacking safety guarantees. In this paper, we propose a Risk-fused Constraint Deep Reinforcement Learning (RCDRL) with D3QN network for safe decision making in lane change maneuver. The problem is formulated as a state-wise MDP (SCMDP), which embeds a rule-based risk-fused Constraint module. We map the decision action to the trajectory layer via a polynomial curve-based trajectory planner, which is combined with the predicted trajectories of surrounding vehicles to assess future risk and correct the unsafe action. Therefore, the proposed method can deal with unsafe decision actions when training the policy network. To investigate the decision performance, the trained RCDRL policy is tested and validated under different traffic densities. In particular, we implement real vehicle tests to validate the effectiveness of the proposed method. Simulation and real vehicle tests demonstrated that the proposed RCDRL method achieves better performance, especially in safe decision. In addition, the framework can be extended with other advanced DRL networks.
21
Christopher J. Watkins, Peter Dayan · Machine Learning · 1992 · 9K citations · Full text
Review - Mastering the game of Go with deep neural networks and tree search
2017 · 838 citations · Full text
Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
Noam Brown, Tüomas Sandholm · Science · 2017 · 559 citations
Nan Li, Dave W. Oyler, Mengxuan Zhang et al. · IEEE Transactions on Control Systems Technology · 2017 · 287 citations