Don't Get Yourself into Trouble! Risk-aware Decision-Making for Autonomous Vehicles
This work addresses safety for autonomous vehicles by enabling them to avoid and react to risky situations, but it is incremental as an extension of previous research.
The paper tackles the problem of risk-aware decision-making for autonomous vehicles by developing a framework that integrates high-level risk-based path planning with reinforcement learning-based low-level control, evaluated in CARLA simulation to improve safety.
Risk is traditionally described as the expected likelihood of an undesirable outcome, such as collisions for autonomous vehicles. Accurately predicting risk or potentially risky situations is critical for the safe operation of autonomous vehicles. In our previous work, we showed that risk could be characterized by two components: 1) the probability of an undesirable outcome and 2) an estimate of how undesirable the outcome is (loss). This paper is an extension to our previous work. In this paper, using our trained deep reinforcement learning model for navigating around crowds, we developed a risk-based decision-making framework for the autonomous vehicle that integrates the high-level risk-based path planning with the reinforcement learning-based low-level control. We evaluated our method in a high-fidelity simulation such as CARLA. This work can improve safety by allowing an autonomous vehicle to one day avoid and react to risky situations.