Simulation of Surgical Suturing Using Position-Based Dynamics and the Material Point Method for Robot Reinforcement Learning

2026-07-29

AI Summary

This work addresses the challenge that existing surgical suturing simulation environments struggle to simultaneously model sutures, soft tissues, and their complex interactions with high fidelity, thereby hindering the learning of autonomous robotic suturing skills. To overcome this limitation, the authors present a high-fidelity reinforcement learning–oriented suturing simulation platform that, for the first time, integrates Position-Based Dynamics (PBD) for suture modeling with the Material Point Method (MPM) for soft tissue representation. A novel bidirectional contact coupling mechanism is introduced to enable realistic interactions involving friction and dragging forces. Leveraging CUDA multi-stream GPU parallelization, the system achieves significant acceleration across multiple scenarios, substantially improving training efficiency. Experimental results demonstrate that agents trained in this environment achieve success rates of 80% and 68% on needle insertion and extraction subtasks, respectively, under stringent distance thresholds, validating the platform’s effectiveness and training stability.

Abstract

Recent advances in robotics research have created a strong demand for high-performance simulators. Surgical robotics simulation faces unique challenges due to the need to model diverse objects, such as rigid instruments, soft tissue, and fluids. While many studies simulate sutures or soft tissue independently, only a few have considered the complete soft-tissue suturing scenario, including the contact between sutures and deformable tissue during suture insertion. Building on previous work, this paper presents a novel suturing simulation environment using sutures modelled by position-based dynamics (PBD) and soft bodies modelled by the material point method (MPM) while considering two-way contact with frictional and drag forces. We introduce a contact coupling method between the PBD suture and the MPM soft tissue, enabling visually plausible suture-tissue interactions. The simulator is optimized for GPU execution with parallel scenes using multiple CUDA streams, and we present a Reinforcement Learning (RL) environment for autonomous suturing sub-tasks, including needle insertion, driving, and extraction. Using ML-Agents, RL agents trained in the simulator show stable learning and achieve 80% and 68% success rates in needle insertion and extraction, respectively, under the strictest distance threshold.

Problem

• surgical suturing simulation
• soft tissue interaction
• position-based dynamics
• material point method
• robot reinforcement learning

Innovation

• Position-Based Dynamics
• Material Point Method
• suture-tissue contact coupling
• GPU-accelerated simulation
• reinforcement learning for surgical robotics