mlsanityData to 7 Oct 2026

Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

arXiv 2108.06266 ↗First posted 13 Aug 2021cs.RO cs.LG cs.SYcited by 337

Not on the map. Why?

Cited by 23 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The last half-decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. This article provides a concise but holistic review of the recent advances made in using machine learning to achieve safe decision making under uncertainties, with a focus on unifying the language and frameworks used in control theory and reinforcement learning research. Our review includes: learning-based control approaches that safely improve performance by learning the uncertain dynamics, reinforcement learning approaches that encourage safety or robustness, and methods that can formally certify the safety of a learned control policy. As data- and learning-based robot control methods continue to gain traction, researchers must understand when and how to best leverage them in real-world scenarios where safety is imperative, such as when operating in close proximity to humans. We highlight some of the open challenges that will drive the field of robot learning in the coming years, and emphasize the need for realistic physics-based benchmarks to facilitate fair comparisons between control and reinforcement learning approaches.

Key facts. Cited by 337 papers in the map (data through 7 Oct 2026). Builds on 89 of its 158 references that are in the map. First posted on arXiv 13 Aug 2021.

Builds on

89 of 158 references.

References · 89

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015Trust Region Policy Optimizationcited by 2,503
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  4. 2017Constrained Policy Optimizationcited by 928
  5. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  6. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  7. 2017Deep Reinforcement Learning that Matterscited by 727
  8. 2017A Brief Survey of Deep Reinforcement Learningcited by 466
  9. 2017Robust Adversarial Reinforcement Learningcited by 439
  10. 2017Safe Reinforcement Learning via Shieldingcited by 427
  11. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
  12. 2019Control Barrier Functions: Theory and Applicationscited by 332
38 more
  1. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  2. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 290
  3. 2019Challenges of Real-World Reinforcement Learningcited by 282
  4. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  5. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  6. 2018Safe Exploration in Continuous Action Spacescited by 237
  7. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  8. 2019Active Domain Randomizationcited by 161
  9. 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 156
  10. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 150
  11. 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 140
  12. 2016EPOpt: Learning Robust Neural Network Policies Using Model Ensemblescited by 136
  13. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  14. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 129
  15. 2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
  16. 2017AI Safety Gridworldscited by 108
  17. 2020Conservative Safety Critics for Explorationcited by 107
  18. 2017Cautious Model Predictive Control using Gaussian Process Regressioncited by 91
  19. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 91
  20. 2018The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systemscited by 87
  21. 2017Uncertainty-Aware Reinforcement Learning for Collision Avoidancecited by 86
  22. 2018Neural Lander: Stable Drone Landing Control using Learned Dynamicscited by 82
  23. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  24. 2020An empirical investigation of the challenges of real-world reinforcement learningcited by 75
  25. 2016Safe Exploration in Finite Markov Decision Processes with Gaussian Processescited by 72
  26. 2018Safe Reinforcement Learning with Model Uncertainty Estimatescited by 70
  27. 2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 68
  28. 2019Learning for Safety-Critical Control with Control Barrier Functionscited by 66
  29. 2021Risk-Averse Offline Reinforcement Learningcited by 65
  30. 2017OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real Worldcited by 64
  31. 2020Robust Reinforcement Learning using Adversarial Populationscited by 64
  32. 2019Deep Drone Racing: From Simulation to Reality with Domain Randomizationcited by 63
  33. 2018Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learningcited by 61
  34. 2020Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functionscited by 61
  35. 2019Risk Averse Robust Adversarial Reinforcement Learningcited by 54
  36. 2017Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Controlcited by 50
  37. 2019Certified Adversarial Robustness for Deep Reinforcement Learningcited by 47
  38. 2021Robust Control Barrier-Value Functions for Safety-Critical Controlcited by 47

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 35; 2023: 76; 2024: 76; 2025: 68; 2026: 69.

337 papers.

Sort:

By area:

  1. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 403
  2. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  3. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 77
  4. 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learningcited by 69
  5. 2023Constrained Decision Transformer for Offline Safe Reinforcement Learningcited by 65
  6. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learningcited by 58
  7. 2024A Survey on Robotics with Foundation Models: toward Embodied AIcited by 53
  8. 2022Reachability Constrained Reinforcement Learningcited by 52
  9. 2023Direct Parameterization of Lipschitz-Bounded Deep Networkscited by 49
  10. 2023State-wise Safe Reinforcement Learning: A Surveycited by 48
  11. 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 44
  12. 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 42
38 more
  1. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 42
  2. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  3. 2023Model-Based Runtime Monitoring with Interactive Imitation Learningcited by 37
  4. 2025Failure Prediction at Runtime for Generative Robot Policiescited by 36
  5. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  6. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  7. 2023Iterative Reachability Estimation for Safe Reinforcement Learningcited by 33
  8. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  9. 2025VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layercited by 32
  10. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 31
  11. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 30
  12. 2024Efficient Reinforcement Learning with Large Language Model Priorscited by 30
  13. 2023Introspective Tips: Large Language Model for In-Context Decision Makingcited by 28
  14. 2023Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPscited by 27
  15. 2023MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulationcited by 27
  16. 2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithmscited by 27
  17. 2026World-Gymnast: Training Robots with Reinforcement Learning in a World Modelcited by 25
  18. 2023ICICLE: Interpretable Class Incremental Continual Learningcited by 24
  19. 2023Formally Explaining Neural Networks within Reactive Systemscited by 24
  20. 2024Truly No-Regret Learning in Constrained MDPscited by 23
  21. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 22
  22. 2023Provably Efficient Model-Free Algorithms for Non-stationary CMDPscited by 21
  23. 2022Back to the Manifold: Recovering from Out-of-Distribution Statescited by 19
  24. 2023ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPscited by 19
  25. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 19
  26. 2022GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systemscited by 17
  27. 2023Optimal Exploration for Model-Based RL in Nonlinear Systemscited by 17
  28. 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learningcited by 17
  29. 2023Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractionscited by 16
  30. 2022Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interactioncited by 15
  31. 2024On Safety in Safe Bayesian Optimizationcited by 15
  32. 2024Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificatescited by 15
  33. 2024Distributionally Robust Constrained Reinforcement Learning under Strong Dualitycited by 15
  34. 2021Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processescited by 14
  35. 2025General agents contain world modelscited by 14
  36. 2021Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noisecited by 13
  37. 2021Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learningcited by 13
  38. 2022On Controller Tuning with Time-Varying Bayesian Optimizationcited by 13

50 most cited of 337 All 337 (JSON)