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

TL;DR

This paper introduces SSP, a framework that combines neural ODE-based uncertainty modeling with control barrier functions to ensure safety in data-driven surgical policies, achieving near-zero violations in simulation and real robot tests.

Contribution

The paper presents a novel safety-guaranteed surgical policy framework that integrates behavioral and spatial constraints using Neural ODEs and CBFs, ensuring safety without sacrificing task success.

Findings

Near-zero constraint violation rate in validation tests

High task success rate maintained with safety constraints

Effective safety enforcement across RL, IL, and CLF-based policies

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 in 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.