Long-Short Term Agents for Pure-Vision Bronchoscopy Robotic Autonomy

TL;DR

This paper introduces a vision-only autonomous bronchoscopic navigation system that uses hierarchical agents and a world-model critic to navigate complex airways without external tracking, demonstrating high success rates in preclinical models.

Contribution

The paper presents a novel hierarchy of long-short agents and a world-model critic for sensor-free, vision-based bronchoscopic navigation, eliminating the need for external localization hardware.

Findings

Successfully navigated to all targets in a phantom model.

Achieved 80% success rate in ex vivo porcine lungs.

Comparable performance to expert bronchoscopists in vivo.

Abstract

Accurate intraoperative navigation is essential for robot-assisted endoluminal intervention, but remains difficult because of limited endoscopic field of view and dynamic artifacts. Existing navigation platforms often rely on external localization technologies, such as electromagnetic tracking or shape sensing, which increase hardware complexity and remain vulnerable to intraoperative anatomical mismatch. We present a vision-only autonomy framework that performs long-horizon bronchoscopic navigation using preoperative CT-derived virtual targets and live endoscopic video, without external tracking during navigation. The framework uses hierarchical long-short agents: a short-term reactive agent for continuous low-latency motion control, and a long-term strategic agent for decision support at anatomically ambiguous points. When their recommendations conflict, a world-model critic predicts future visual states for candidate actions and selects the action whose predicted state best matches the target view. We evaluated the system in a high-fidelity airway phantom, three ex vivo porcine lungs, and a live porcine model. The system reached all planned segmental targets in the phantom, maintained 80\% success to the eighth generation ex vivo, and achieved in vivo navigation performance comparable to the expert bronchoscopist. These results support the preclinical feasibility of sensor-free autonomous bronchoscopic navigation.