SSP: Safety-guaranteed Surgical Policy via Joint Optimization of Behavioral and Spatial Constraints

1Shanghai Jiao Tong University
2The Chinese University of Hong Kong
3Massachusetts Institute of Technology

Corresponding Author
SSP Framework Teaser

SSP proposes a safety-guaranteed surgical policy framework that learns robust and safe executions of surgical actions. By integrating Neural ODEs for uncertainty-aware dynamics learning with a Robust Control Barrier Function (CBF) safety controller, the framework enforces behavioral and spatial constraints to safely deploy "black-box" policies (RL, IL, or CLF-based) on complex surgical tasks.

Abstract

The paradigm of robot-assisted surgery is shifting toward data-driven autonomy, where policies learned via Reinforcement Learning (RL) or Imitation Learning (IL) enable the execution of complex tasks. However, these "black-box" policies often lack formal safety guarantees, a critical requirement for clinical deployment. In this paper, we propose the Safety-guaranteed Surgical Policy (SSP) framework to bridge the gap between data-driven generality and formal safety. We utilize Neural Ordinary Differential Equations (Neural ODEs) to learn an uncertainty-aware dynamics model from demonstration data. This learned model underpins a robust Control Barrier Function (CBF) safety controller, which minimally alters the actions of a surgical policy to ensure strict safety under uncertainty. Our controller enforces two constraint categories: behavioral constraints (restricting the task space of the agent) and spatial constraints (defining surgical no-go zones). We instantiate the SSP framework with surgical policies derived from RL, IL and Control Lyapunov Functions (CLF). Validation on both the SurRoL simulation and da Vinci Research Kit (dVRK) demonstrates that our method achieves a near-zero constraint violation rate while maintaining high task success rates compared to unconstrained baselines.

Real-World Experiment Videos

BibTeX

@article{hu2026ssp,
  title={SSP: Safety-guaranteed Surgical Policy via Joint Optimization of Behavioral and Spatial Constraints},
  author={Jianshu Hu and Zhiyuan Guan and Lei Song and Kantaphat Leelakunwet and Hesheng Wang and Wei Xiao and Qi Dou and Yutong Ban},
  journal={arXiv preprint arXiv:2603.07032},
  year={2026}
}