We tackle the problem of autonomous driving in complex & competitive mixed-autonomy environments where autonomous vehicles interact with vehicles driven by humans. Formally, we model this problem as a partially-observable stochastic game and train reinforcement learning agents that cooperate with each other and sympathize with human-driven vehicles. Our autonomous agents learn general latent representations that enables them to coordinate in novel environments. For more details about each paper, please refer to the paper’s individual website:
Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic
Behrad Toghi, Rodolfo Valiente, Dorsa Sadigh, Ramtin Pedarsani, Yaser P. Fallah
2021 ADP3 Workshop at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
Watch my talk on Altruistic Maneuver Planning at “CVPR 2021 Workshop Autonomous Driving: Perception, Prediction and Planning” June 2021
Presenting our paper “Cooperative Autonomous Vehicles that Sympathize with Human Drivers“ at “IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)“, Sept 2021