mlsanityData to 7 Oct 2026

Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach

arXiv 2407.02231 ↗First posted 2 Jul 2024cs.RO cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

This study presents a novel methodology incorporating safety constraints into a robotic simulation during the training of deep reinforcement learning (DRL). The framework integrates specific parts of the safety requirements, such as velocity constraints, as specified by ISO 10218, directly within the DRL model that becomes a part of the robot's learning algorithm. The study then evaluated the efficiency of these safety constraints by subjecting the DRL model to various scenarios, including grasping tasks with and without obstacle avoidance. The validation process involved comprehensive simulation-based testing of the DRL model's responses to potential hazards and its compliance. Also, the performance of the system is carried out by the functional safety standards IEC 61508 to determine the safety integrity level. The study indicated a significant improvement in the safety performance of the robotic system. The proposed DRL model anticipates and mitigates hazards while maintaining operational efficiency. This study was validated in a testbed with a collaborative robotic arm with safety sensors and assessed with metrics such as the average number of safety violations, obstacle avoidance, and the number of successful grasps. The proposed approach outperforms the conventional method by a 16.5% average success rate on the tested scenarios in the simulations and 2.5% in the testbed without safety violations. The project repository is available at https://github.com/ammar-n-abbas/sim2real-ur-gym-gazebo.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 15 of its 44 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

15 of 44 references.

References · 15

  1. 2017Safe Reinforcement Learning via Shieldingcited by 427
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  3. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  4. 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 154
  5. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 135
  6. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 90
  7. 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
  8. 2020Verifiably Safe Exploration for End-to-End Reinforcement Learningcited by 32
  9. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 31
  10. 2020Reachability-based Trajectory Safeguard (RTS): A Safe and Fast Reinforcement Learning Safety Layer for Continuous Controlcited by 28
  11. 2022Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environmentscited by 16
  12. 2022Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interactioncited by 15
3 more
  1. 2022Automating Reinforcement Learning with Example-based Resetscited by 11
  2. 2021Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planningcited by 7
  3. 2022Accelerating Robot Learning of Contact-Rich Manipulations: A Curriculum Learning Studycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Adversarial Attacks on Robotic Vision Language Action Modelscited by 31
  2. 2026The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspectivecited by 1
  3. 2026Developing AI Agents with Simulated Data: Why, what, and how?cited by 0