Socially-Aware Automated Vehicles in Dense Urban Environments
Automated vehicles will have to operate in dense urban environments where pedestrians, cyclists, and people with accessibility needs are regularly crossing the road. In this context, a deep reinforcement learning based multi-objective autonomous braking system is presented. The design of the system is formulated in a continuous action space and seeks to maximize both pedestrian safety and perception as well as passenger comfort. The vehicle agent is trained against a large naturalistic dataset containing pedestrian road-crossing trials in which respondents walk across an urban road under various traffic conditions in an interactive virtual reality environment. Results show that the system is able to reduce the negative influence on passenger comfort by half while maintaining safe braking operations.
- Socially-aware automation is needed for its acceptance
- It requires multi-objective optimization
- We need innovative tools to collect naturalistic datasets for training
Bilal Farooq is Canada Research Chair in Disruptive Transportation Technologies and Services. He is currently an Assistant Professor at Ryerson University and Founding Director of Laboratory of Innovations in Transportation (LiTrans). He has received the Early Researcher Award both in the province of Québec (2014) and Ontario (2018). He has published more than 80 research articles in top-tier peer-reviewed international journals and conferences. Bilal is interested in understanding the network and behavioural effects of connected and automated vehicles and in developing the associated algorithms and models.