Clinician-AI Collaboration in Endovascular Neurointerventions: In-Vitro User Study of Copilot Assistance Modes for Robotic Navigation Across the Autonomy Spectrum
Clinician-AI Collaboration in Endovascular Neurointerventions: In-Vitro User Study of Copilot Assistance Modes for Robotic Navigation Across the Autonomy Spectrum
This research introduces a framework called Copilot Assistance Modes (CAMs) to evaluate clinician-AI collaboration in robotic endovascular navigation. An in-vitro study involving experts and students assessed six navigation modes using patient-specific vascular phantoms. Results showed that while fully autonomous navigation achieved 81% success in simulation, performance dropped to 23% in vitro. In contrast, shared-autonomy modes achieved 92-97% success rates, comparable to direct manual control (95%). The study concludes that effective clinician-AI collaboration and control allocation are more critical for reliable navigation than increasing autonomy alone, particularly given the sim-to-real domain shift.
The study presents an in-vitro evaluation of clinician-AI collaboration modes for robotic endovascular navigation, highlighting a significant performance gap between simulation (81% success) and physical testing (23% success) for fully autonomous systems, while shared-autonomy modes achieved 92-97% success rates comparable to direct manual control.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S3
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
tic environments. This work introduces Copilot Assistance Modes (CAMs), a framework for clinician-AI collaboration in robotic endovascular navigation spanning the autonomy spectrum from manual operation to full autonomy. In the first in-vitro user study comparing clinician-AI collaboration strategies, 11 experts and two students evaluated six navigation modes in a patient-specific vascular phantom. Objective performa
Open source S3
nce metrics were combined with subjective assessments, including workload and usability. Autonomous performance was additionally evaluated both in silico and in vitro to investigate sim-to-real transfer. Hands-on manual navigation achieved the strongest overall performance (100% success). While fully autonomous navigation achieved 81% success in simulation, performance dropped to 23% in vitro. In contrast, several cl
Open source S4
inician-AI shared-autonomy modes achieved success rates of 92-97%, approximately four times higher than full autonomy and comparable to direct robotic control (95%), demonstrating mitigation of sim-to-real domain shift through clinician-AI collaboration. Among the evaluated AI-driven approaches, user-directed task delegation and rotational shared control demonstrated the most favorable balance between performance and
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org