Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging
On the map: Offline RL and imitation learning from data → Safe offline RL
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 17 of its 32 references that are in the map. First posted on arXiv 1 Dec 2022.
Builds on
17 of 32 references.
References · 17
- 2021Convex optimizationcited by 2,479
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2017Constrained Policy Optimizationcited by 928
- 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
- 2019Control Barrier Functions: Theory and Applicationscited by 332
- 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 261
- 2020Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functionscited by 61
- 2020Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Functioncited by 42
- 2021Model-based Constrained Reinforcement Learning using Generalized Control Barrier Functioncited by 30
- 2019Adaptive Safety with Control Barrier Functionscited by 25
- 2021Learning Robust Output Control Barrier Functions from Safe Expert Demonstrationscited by 19
- 2020Numerically Stable Dynamic Bicycle Model for Discrete-time Controlcited by 15
5 more
- 2019Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraintscited by 12
- 2019Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificatescited by 12
- 2021Probabilistic Safety-Assured Adaptive Merging Control for Autonomous Vehiclescited by 10
- 2019Probabilistic Safety Constraints for Learned High Relative Degree System Dynamicscited by 9
- 2021Feasibility Enhancement of Constrained Receding Horizon Control Using Generalized Control Barrier Functioncited by 3
Built on by
Citing papers per year: 2023: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Barrier Function Overrides For Non-Convex Fixed Wing Flight Control and Self-Driving Cars
- 2025Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersection
- 2025Uncertainty-Aware Safety-Critical Decision and Control for Autonomous Vehicles at Unsignalized Intersections
- 2020Learning Control Barrier Functions from Expert Demonstrations
- 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
- 2021Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning
- 2026A Risk-Sensitive and Uncertainty-Aware Decision-Making and Control Framework for Safe and Robust Autonomous Driving
- 2021Safe Imitation Learning on Real-Life Highway Data for Human-like Autonomous Driving