# Passivity-Centric Safe Reinforcement Learning for Contact-Rich Robotic Tasks

arXiv: https://arxiv.org/abs/2503.00287 · HTML: https://mlsanity.com/paper/2503.00287/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 1 Mar 2025.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 13 of 13)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones](https://mlsanity.com/paper/2010.15920/) (2020)
- [Conservative Safety Critics for Exploration](https://mlsanity.com/paper/2010.14497/) (2020)
- [Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks](https://mlsanity.com/paper/1906.08880/) (2019)
- [SRL-VIC: A Variable Stiffness-Based Safe Reinforcement Learning for Contact-Rich Robotic Tasks](https://mlsanity.com/paper/2406.13744/) (2024)
- [Auditing Robot Learning for Safety and Compliance during Deployment](https://mlsanity.com/paper/2110.05702/) (2021)
- [Learning robotic milling strategies based on passive variable operational space interaction control](https://mlsanity.com/paper/2304.01000/) (2023)
- [A Contact-Safe Reinforcement Learning Framework for Contact-Rich Robot Manipulation](https://mlsanity.com/paper/2207.13438/) (2022)
- [Learning passive policies with virtual energy tanks in robotics](https://mlsanity.com/paper/2301.12759/) (2023)
- [A Passive Variable Impedance Control Strategy with Viscoelastic Parameters Estimation of Soft Tissues for Safe Ultrasonography](https://mlsanity.com/paper/2309.14893/) (2023)
- [Design of an Energy-Aware Cartesian Impedance Controller for Collaborative Disassembly](https://mlsanity.com/paper/2302.03587/) (2023)

## Built on by (most cited first, 2 of 2)

- [Scaling Laws in Scientific Discovery with AI and Robot Scientists](https://mlsanity.com/paper/2503.22444/) (2025)
- [Contact-Safe Reinforcement Learning with ProMP Reparameterization and Energy Awareness](https://mlsanity.com/paper/2511.13459/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) has achieved remarkable success in various robotic tasks; however, its deployment in real-world scenarios, particularly in contact-rich environments, often overlooks critical safety and stability aspects. Policies without passivity guarantees can result in system instability, posing risks to robots, their environments, and human operators. In this work, we investigate the limitations of traditional RL policies when deployed in contact-rich tasks and explore the combination of energy-based passive control with safe RL in both training and deployment to answer these challenges. Firstly, we reveal the discovery that standard RL policy does not satisfy stability in contact-rich scenarios. Secondly, we introduce a textitpassivity-aware RL policy training with energy-based constraints in our safe RL formulation. Lastly, a passivity filter is exerted on the policy output for textitpassivity-ensured control during deployment. We conduct comparative studies on a contact-rich robotic maze exploration task, evaluating the effects of learning passivity-aware policies and the importance of passivity-ensured control. The experiments demonstrate that a passivity-agnostic RL policy easily violates energy constraints in deployment, even though it achieves high task completion in training. The results show that our proposed approach guarantees control stability through passivity filtering and improves the energy efficiency through passivity-aware training. A video of real-world experiments is available as supplementary material. We also release the checkpoint model and offline data for pre-training at hrefhttps://huggingface.co/Anonymous998/passiveRL/tree/mainHugging Face.