Safe Deep Q-Network for Autonomous Vehicles at Unsignalized Intersection
This addresses safety challenges for autonomous vehicles in complex urban environments, but it is incremental as it builds on existing DRL and LSTM methods.
The paper tackles autonomous vehicle navigation through pedestrian crowds at unsignalized intersections by proposing a safe deep reinforcement learning approach that uses LSTM models for state perception and trajectory prediction, combined with a collision prediction algorithm to mask unsafe actions. The result shows no collisions with pedestrians in CARLA simulations across similar and different intersection topologies while maintaining reasonable speeds.
We propose a safe DRL approach for autonomous vehicle (AV) navigation through crowds of pedestrians while making a left turn at an unsignalized intersection. Our method uses two long-short term memory (LSTM) models that are trained to generate the perceived state of the environment and the future trajectories of pedestrians given noisy observations of their movement. A future collision prediction algorithm based on the future trajectories of the ego vehicle and pedestrians is used to mask unsafe actions if the system predicts a collision. The performance of our approach is evaluated in two experiments using the high-fidelity CARLA simulation environment. The first experiment tests the performance of our method at intersections that are similar to the training intersection and the second experiment tests our method at intersections with a different topology. For both experiments, our methods do not result in a collision with a pedestrian while still navigating the intersection at a reasonable speed.