Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging
This addresses safety-critical issues in autonomous driving for ramp merging scenarios, but it is incremental as it builds on existing control barrier function methods by adding probabilistic estimates.
The paper tackles the problem of ensuring safety and efficiency in autonomous driving, specifically for ramp merging, by integrating probabilistic control barrier functions into reinforcement learning to handle model uncertainty, achieving safe policies validated in CARLA simulator and on NGSIM data.
Prior work has looked at applying reinforcement learning and imitation learning approaches to autonomous driving scenarios, but either the safety or the efficiency of the algorithm is compromised. With the use of control barrier functions embedded into the reinforcement learning policy, we arrive at safe policies to optimize the performance of the autonomous driving vehicle. However, control barrier functions need a good approximation of the model of the car. We use probabilistic control barrier functions as an estimate of the model uncertainty. The algorithm is implemented as an online version in the CARLA (Dosovitskiy et al., 2017) Simulator and as an offline version on a dataset extracted from the NGSIM Database. The proposed algorithm is not just a safe ramp merging algorithm but a safe autonomous driving algorithm applied to address ramp merging on highways.