mlsanityData to 7 Oct 2026

safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics

arXiv 2109.06325 ↗First posted 13 Sep 2021cs.RO cs.LG cs.SYcited by 42

Not on the map. Why?

Abstract (arXiv)

In recent years, both reinforcement learning and learning-based control -- as well as the study of their safety, which is crucial for deployment in real-world robots -- have gained significant traction. However, to adequately gauge the progress and applicability of new results, we need the tools to equitably compare the approaches proposed by the controls and reinforcement learning communities. Here, we propose a new open-source benchmark suite, called safe-control-gym, supporting both model-based and data-based control techniques. We provide implementations for three dynamic systems -- the cart-pole, the 1D, and 2D quadrotor -- and two control tasks -- stabilization and trajectory tracking. We propose to extend OpenAI's Gym API -- the de facto standard in reinforcement learning research -- with (i) the ability to specify (and query) symbolic dynamics and (ii) constraints, and (iii) (repeatably) inject simulated disturbances in the control inputs, state measurements, and inertial properties. To demonstrate our proposal and in an attempt to bring research communities closer together, we show how to use safe-control-gym to quantitatively compare the control performance, data efficiency, and safety of multiple approaches from the fields of traditional control, learning-based control, and reinforcement learning.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

24 of 37 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2016OpenAI Gymcited by 1,684
  4. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  5. 2017Deep Reinforcement Learning that Matterscited by 727
  6. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
  7. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
  8. 2017Robust Adversarial Reinforcement Learningcited by 439
  9. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
  10. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  11. 2019Control Barrier Functions: Theory and Applicationscited by 332
  12. 2018Safe Exploration in Continuous Action Spacescited by 237
12 more
  1. 2019Benchmarking Model-Based Reinforcement Learningcited by 158
  2. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 129
  3. 2017AI Safety Gridworldscited by 108
  4. 2017Cautious Model Predictive Control using Gaussian Process Regressioncited by 91
  5. 2020An empirical investigation of the challenges of real-world reinforcement learningcited by 75
  6. 2020Flightmare: A Flexible Quadrotor Simulatorcited by 69
  7. 2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 68
  8. 2019Learning for Safety-Critical Control with Control Barrier Functionscited by 66
  9. 2020Robust Reinforcement Learning using Adversarial Populationscited by 64
  10. 2018Linear model predictive safety certification for learning-based controlcited by 34
  11. 2017Safe Learning of Quadrotor Dynamics Using Barrier Certificatescited by 32
  12. 2017Optimal and Learning Control for Autonomous Robotscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 7; 2024: 6; 2025: 10; 2026: 11.

42 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 135
  3. 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learningcited by 69
  4. 2022Reachability Constrained Reinforcement Learningcited by 52
  5. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  6. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 23
  7. 2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 22
  8. 2022Evaluating Model-free Reinforcement Learning toward Safety-critical Taskscited by 18
  9. 2022Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificatecited by 16
  10. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  11. 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learningcited by 12
  12. 2025A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safetycited by 12
30 more
  1. 2024Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agentscited by 11
  2. 2024Can we hop in general? A discussion of benchmark selection and design using the Hopper environmentcited by 7
  3. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Drivingcited by 6
  4. 2023Feasible Policy Iteration for Safe Reinforcement Learningcited by 4
  5. 2023Robust Safe Reinforcement Learning under Adversarial Disturbancescited by 4
  6. 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agentscited by 4
  7. 2023Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizoncited by 3
  8. 2024Towards Fast Safe Online Reinforcement Learning via Policy Finetuningcited by 3
  9. 2025Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learningcited by 2
  10. 2025A Primer on SO(3) Action Representations in Deep Reinforcement Learningcited by 2
  11. 2025An Energy-Based Mechanism for Compositional Behaviorcited by 2
  12. 2026ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Modelscited by 2
  13. 2025ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attackscited by 1
  14. 2025Bi-Level Reinforcement Learning Pathway for Sim-to-Real Optimalitycited by 1
  15. 2026LC-SAC: Lyapunov-Constrained Soft Actor-Critic via Koopman Operator Theory for Trajectory Tracking and Stabilizationcited by 1
  16. 2026CRAX: Fast Safe Reinforcement Learning Benchmarkingcited by 1
  17. 2022FORESEE: Prediction with Expansion-Compression Unscented Transform for Online Policy Optimizationcited by 0
  18. 2023Harmonic Control Lyapunov Barrier Functions for Constrained Optimal Control with Reach-Avoid Specificationscited by 0
  19. 2024Training Verifiably Robust Agents Using Set-Based Reinforcement Learningcited by 0
  20. 2024Safe Bayesian Optimization for Complex Control Systems via Additive Gaussian Processescited by 0
  21. 2024Physics-model-guided Worst-case Sampling for Safe Reinforcement Learningcited by 0
  22. 2025MagBotSim: Physics-Based Simulation and Reinforcement Learning Environments for Magnetic Roboticscited by 0
  23. 2026SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotioncited by 0
  24. 2026Exploiting Differential Flatness for Efficient Learning-based Model Predictive Control of Constrained Multi-Input Control Affine Systemscited by 0
  25. 2026parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learningcited by 0
  26. 2026T2S-MPC: Time-Embedded Online Adaptive Model Predictive Control for Time-Varying Dynamicscited by 0
  27. 2026Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learningcited by 0
  28. 2026Safe Online Learning via Smooth Safety-Structured Policy Compositioncited by 0
  29. 2026Safe and Robust Neural Policy Learning with Statistical Verification for Sim-to-Real Deployment in Roboticscited by 0
  30. 2026ASGARD: Action-Space Guard for UAV Resilience via Reinforcement Learningcited by 0