mlsanityData to 14 Oct 2026

Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments

arXiv 2205.06311 ↗First posted 12 May 2022cs.RO cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning (RL) has shown promising results in the motion planning of manipulators. However, no method guarantees the safety of highly dynamic obstacles, such as humans, in RL-based manipulator control. This lack of formal safety assurances prevents the application of RL for manipulators in real-world human environments. Therefore, we propose a shielding mechanism that ensures ISO-verified human safety while training and deploying RL algorithms on manipulators. We utilize a fast reachability analysis of humans and manipulators to guarantee that the manipulator comes to a complete stop before a human is within its range. Our proposed method guarantees safety and significantly improves the RL performance by preventing episode-ending collisions. We demonstrate the performance of our proposed method in simulation using human motion capture data.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 12 May 2022.

Builds on

15 of 31 references.

References · 15

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017Hindsight Experience Replaycited by 1,136
  3. 2017Constrained Policy Optimizationcited by 983
  4. 2017Safe Reinforcement Learning via Shieldingcited by 449
  5. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 353
  6. 2018Safe Exploration in Continuous Action Spacescited by 247
  7. 2018Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specificationscited by 72
  8. 2017OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real Worldcited by 70
  9. 2019Towards Practical Multi-Object Manipulation using Relational Reinforcement Learningcited by 55
  10. 2019Exploration via Hindsight Goal Generationcited by 54
  11. 2020Verifiably Safe Exploration for End-to-End Reinforcement Learningcited by 34
  12. 2020Reachability-based Trajectory Safeguard (RTS): A Safe and Fast Reinforcement Learning Safety Layer for Continuous Controlcited by 28
3 more
  1. 2020Robotic Table Tennis with Model-Free Reinforcement Learningcited by 15
  2. 2020Online Shielding for Stochastic Systemscited by 11
  3. 2020Complex Robotic Manipulation via Graph-Based Hindsight Goal Generationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 0; 2024: 6; 2025: 5; 2026: 4.

18 papers.

Sort:

By area:

  1. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 34
  2. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 26
  3. 2022Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interactioncited by 17
  4. 2024Safe Reinforcement Learning on the Constraint Manifold: Theory and Applicationscited by 15
  5. 2024Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulationcited by 14
  6. 2024Learning Control Barrier Functions and their application in Reinforcement Learning: A Surveycited by 8
  7. 2024RAIL: Reachability-Aided Imitation Learning for Safe Policy Executioncited by 5
  8. 2025From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policiescited by 5
  9. 2024Safe Reinforcement Learning for Power System Control: A Reviewcited by 3
  10. 2024Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approachcited by 3
  11. 2025A Design Co-Pilot for Task-Tailored Manipulatorscited by 2
  12. 2026X-Safe: Embodiment-Agnostic Safeguarding for Robot Arm Manipulation Policies via Action Maskingcited by 2
6 more
  1. 2025Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspectivecited by 1
  2. 2025Leveraging Analytic Gradients in Provably Safe Reinforcement Learningcited by 1
  3. 2025A Parametric Model for Near-Optimal Online Synthesis with Robust Reach-Avoid Guaranteescited by 0
  4. 2026Vision-Based Safe Human-Robot Collaboration with Uncertainty Guaranteescited by 0
  5. 2026No Free Checker: A Survey of Verifiers for Robot Policiescited by 0
  6. 2026Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Modelscited by 0