mlsanityData to 14 Oct 2026

End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions

arXiv 2212.11365 ↗First posted 21 Dec 2022eess.SY cs.SYcited by 10

On the map: Offline RL and imitation learning from data → Safe offline RL

Abstract (arXiv)

Imitation learning (IL) is a learning paradigm which can be used to synthesize controllers for complex systems that mimic behavior demonstrated by an expert (user or control algorithm). Despite their popularity, IL methods generally lack guarantees of safety, which limits their utility for complex safety-critical systems. In this work we consider safety, formulated as set-invariance, and the associated formal guarantees endowed by Control Barrier Functions (CBFs). We develop conditions under which robustly-safe expert controllers, utilizing CBFs, can be used to learn end-to-end controllers (which we refer to as CBF-Compliant controllers) that have safety guarantees. These guarantees are presented from the perspective of input-to-state safety (ISSf) which considers safety in the context of disturbances, wherein it is shown that IL using robustly safe expert demonstrations results in ISSf with the disturbance directly related to properties of the learning problem. We demonstrate these safety guarantees in simulated vision-based end-to-end control of an inverted pendulum and a car driving on a track.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 20 of its 38 references that are in the map. First posted on arXiv 21 Dec 2022.

Builds on

20 of 38 references.

References · 20

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2017End-to-end Driving via Conditional Imitation Learningcited by 485
  3. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
  4. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
  5. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 118
  6. 2019Learning for Safety-Critical Control with Control Barrier Functionscited by 69
  7. 2018Learning an Approximate Model Predictive Controller with Guaranteescited by 57
  8. 2018Linear model predictive safety certification for learning-based controlcited by 37
  9. 2020Imitation Learning with Stability and Safety Guaranteescited by 34
  10. 2020Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functionscited by 33
  11. 2019Risk-Aware Active Inverse Reinforcement Learningcited by 26
  12. 2018Input-to-State Safety With Control Barrier Functionscited by 15
8 more
  1. 2021Pointwise Feasibility of Gaussian Process-based Safety-Critical Control under Model Uncertaintycited by 13
  2. 2020Training Neural Network Controllers Using Control Barrier Functions in the Presence of Disturbancescited by 9
  3. 2021Model-Free Safety-Critical Control for Robotic Systemscited by 8
  4. 2016Autonomous Racing using Learning Model Predictive Controlcited by 7
  5. 2021Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State Safetycited by 7
  6. 2021Safety-Aware Preference-Based Learning for Safety-Critical Controlcited by 7
  7. 2021Safe Controller Synthesis with Tunable Input-to-State Safe Control Barrier Functionscited by 5
  8. 2019Characterizing Safety: Minimal Barrier Functions from Scalar Comparison Systemscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 2.

10 papers.

  1. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 26
  2. 2024SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systemscited by 14
  3. 2025Constrained Diffusers for Safe Planning and Controlcited by 10
  4. 2023Imitation Learning from Nonlinear MPC via the Exact Q-Loss and its Gauss-Newton Approximationcited by 5
  5. 2025A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racingcited by 2
  6. 2024Online Efficient Safety-Critical Control for Mobile Robots in Unknown Dynamic Multi-Obstacle Environmentscited by 1
  7. 2025Approximate Model Predictive Control for Microgrid Energy Management via Imitation Learningcited by 1
  8. 2025RISE: Robust Imitation through Stochastic Encodingcited by 0
  9. 2026Safety-Guaranteed Imitation Learning from Nonlinear Model Predictive Control for Spacecraft Close Proximity Operationscited by 0
  10. 2026Infeasible optimization problems and the hierarchical augmented Lagrangian method in imitation learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Learning Control Barrier Functions from Expert Demonstrations
  2. 2024Semi-Supervised Safe Visuomotor Policy Synthesis using Barrier Certificates
  3. 2026Is Your Safe Controller Actually Safe? A Critical Review of CBF Tautologies and Hidden Assumptions
  4. 2024Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning
  5. 2026TAIL-Safe: Task-Agnostic Safety Monitoring for Imitation Learning Policies
  6. 2026Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation
  7. 2025V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
  8. 2025Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection