Toward Autonomous Robotic Minimally Invasive Surgery: A Hybrid Framework Combining Task-Motion Planning and Dynamic Behavior Trees

Abstract

The growing need for high levels of autonomy in Autonomous Robotic Surgery Systems (ARSS) calls for innovative approaches to reduce surgeons’ cognitive load, optimize hospital workflows, and ensure efficient task-level reasoning and adaptation during execution. This paper presents a novel hybrid framework that synergistically combines Task-Motion Planning and Dynamic Behavior Trees for ARSS in Minimally Invasive Surgery. Our approach is designed to address the challenges of coordinating multiple surgical tools within a small workspace, thereby making complex surgical tasks like multi-throw suturing feasible and efficient. Through an extensive evaluation in simulation across diverse initial conditions and noise scenarios, the proposed method demonstrates improved success rates, reduced execution times, and fewer regrasps compared to standalone approaches. Furthermore, it showcases robustness under increased noise conditions. By applying our framework to a complex multi-throw suturing task, we illustrate its capability to seamlessly handle comprehensive suturing tasks, including needle picking, insertion, extraction, and the handover of the needle between Patient Side Manipulators. The results suggest that our hybrid approach not only enhances ARSS autonomy but also adapts effectively to unexpected environmental changes, laying the groundwork for its potential applicability in real-world surgical robotics.

Keywords

• Autonomous systems
• behavior trees
• hierarchical deliberation
• minimally invasive surgery
• multi-throw suturing
• nonlinear optimization