Barrier Function Overrides For Non-Convex Fixed Wing Flight Control and Self-Driving Cars
On the map: End-to-end autonomous driving → Reinforcement learning for driving
also in 1 more
Abstract (arXiv)
Reinforcement Learning (RL) has enabled vast performance improvements for robotics systems. To achieve these results though, the agent often must randomly explore the environment, which for safety critical systems presents a significant challenge. Barrier functions can solve this challenge by enabling an override that approximates the RL control input as closely as possible without violating a safety constraint. Unfortunately, this override can be computationally intractable in cases where the dynamics are not convex in the control input or when time is discrete, as is often the case when training RL systems. We therefore consider these cases, developing novel barrier functions for two non-convex systems (fixed wing aircraft and self-driving cars performing lane merging with adaptive cruise control) in discrete time. Although solving for an online and optimal override is in general intractable when the dynamics are nonconvex in the control input, we investigate approximate solutions, finding that these approximations enable performance commensurate with baseline RL methods with zero safety violations. In particular, even without attempting to solve for the optimal override at all, performance is still competitive with baseline RL performance. We discuss the tradeoffs of the approximate override solutions including performance and computational tractability.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 27 of its 42 references that are in the map. First posted on arXiv 8 May 2025.
Builds on
27 of 42 references.
Closest ancestors · 1
Same direction, newest first
- 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving17 Jun
Other references · 26
- 2015Trust Region Policy Optimizationcited by 2,580
- 2021Convex optimizationcited by 2,515
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
- 2017Constrained Policy Optimizationcited by 983
- 2019Control Barrier Functions: Theory and Applicationscited by 372
- 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
- 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
- 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 175
- 2017Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learningcited by 117
- 2020Learning to be Safe: Deep RL with a Safety Criticcited by 116
- 2020Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Functioncited by 49
- 2021Safe Reinforcement Learning Using Advantage-Based Interventioncited by 47
14 more
- 2021Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violationscited by 39
- 2021Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safetycited by 30
- 2023A Systematic Review on Fostering Appropriate Trust in Human-AI Interactioncited by 21
- 2020Safe Multi-Agent Interaction through Robust Control Barrier Functions with Learned Uncertaintiescited by 20
- 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
- 2024Collision Avoidance and Geofencing for Fixed-wing Aircraft with Control Barrier Functionscited by 6
- 2016Multi-objective Compositions for Collision-Free Connectivity Maintenance in Teams of Mobile Robotscited by 5
- 2017Safe Certificate-Based Maneuvers for Teams of Quadrotors Using Differential Flatnesscited by 5
- 2021Model Free Barrier Functions via Implicit Evading Maneuverscited by 3
- 2021Control Barrier Function Meets Interval Analysis: Safety-Critical Control with Measurement and Actuation Uncertaintiescited by 3
- 2023Safe Exploration in Reinforcement Learning: Training Backup Control Barrier Functions with Zero Training Time Safety Violationscited by 3
- 2019Composition of Safety Constraints For Fixed-Wing Collision Avoidance Amidst Limited Communicationscited by 2
- 2020Safety With Limited Range Sensing Constraints For Fixed Wing Aircraftcited by 2
- 2023Discrete-time Control Barrier Functions for Guaranteed Recursive Feasibility in Nonlinear MPC: An Application to Lane Mergingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles
- 2020Learning Control Barrier Functions from Expert Demonstrations
- 2024Optimal control barrier functions for RL based safe powertrain control
- 2022Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging
- 2025A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
- 2024Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning
- 2024Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
- 2026Learning Safety-Guaranteed, Non-Greedy Control Barrier Functions Using Reinforcement Learning