A Reinforcement Learning Framework for Safety-Aware Haptic Shared Control in Surgical Robotics
A Reinforcement Learning Framework for Safety-Aware Haptic Shared Control in Surgical Robotics
This research introduces a reinforcement learning framework for safety-aware haptic shared control in surgical robotics, modeling the interaction as a two-agent cooperative Markov game. The study compares MADDPG, rMAPPO, and an epigraph-constrained approach, showing that rMAPPO achieves the highest return and tracking performance in simulation, while the epigraph approach produces more conservative motions. Real-world trials demonstrate the effectiveness of fixed-impedance policies and the impact of learned partner policies on command alignment.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S3
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
n, comparing learned human control with a task-tuned fixed-impedance baseline. This model-free multi-agent reinforcement learning framework supports joint policy adaptation without requiring a complete analytical interaction model. It compares MADDPG and rMAPPO with an epigraph-constrained approach under common geometric task definitions. In simulation, rMAPPO generally achieved the highest return and tracking perfor
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org