Multi-Objective Autonomous Braking System using Naturalistic Dataset
This work addresses pedestrian safety and passenger comfort in autonomous vehicles, but it is incremental as it applies existing reinforcement learning methods to a new dataset.
The paper tackled the problem of autonomous braking by developing a multi-objective system using deep reinforcement learning to maximize pedestrian safety and passenger comfort, resulting in a 50% reduction in negative impact on comfort while maintaining safe braking.
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 walked across a road under various traffic conditions within an interactive virtual reality environment. The policy for brake control is learned through computer simulation using two reinforcement learning methods i.e. Proximal Policy Optimization and Deep Deterministic Policy Gradient and the efficiency of each are compared. Results show that the system is able to reduce the negative influence on passenger comfort by half while maintaining safe braking operation.