Human-centric Autonomous Driving in an AV-Pedestrian Interactive Environment Using SVO

Crosato, Luca; Wei, Chongfeng; Ho, Edmond S.L.; Shum, Hubert P.H.

Abstract

As Autonomous Vehicles (AV) are becoming a reality, the design of efficient motion control algorithms will have to deal with the unpredictable and interactive nature of other road users. Current AV motion planning algorithms suffer from the freezing robot problem, as they often tend to overestimate collision risks. To tackle this problem and design AV that behave human-like, we integrate a concept from Psychology called Social Value Orientation into the Reinforcement Learning (RL) framework. The addition of a social term in the reward function design allows us to tune the AV behaviour towards the pedestrian from a more reckless to an extremely prudent one. We train the vehicle agent with a state of the art RL algorithm and show that Social Value Orientation is an effective tool to obtain pro-social AV behaviour.

Citation

Crosato, L., Wei, C., Ho, E. S., & Shum, H. P. (2021, September). Human-centric Autonomous Driving in an AV-Pedestrian Interactive Environment Using SVO. Presented at IEEE ICHMS 2021 - 2nd IEEE International Conference on Human-Machine Systems, Magdeburg, Germany

• Presentation Conference Type: Conference Paper (published)
• Conference Name: IEEE ICHMS 2021 - 2nd IEEE International Conference on Human-Machine Systems
• Start Date: Sep 8, 2021
• End Date: Sep 10, 2021
• Acceptance Date: Jul 6, 2021
• Online Publication Date: Oct 27, 2021
• Publication Date: 2021
• Deposit Date: Jul 13, 2021
• Publicly Available Date: Sep 11, 2021
• Publisher: Institute of Electrical and Electronics Engineers
• ISBN: 9781665401708
• DOI: https://doi.org/10.1109/ichms53169.2021.9582640
• Public URL: https://durham-repository.worktribe.com/output/1138740