Introduction Robotic positioning tasks involving indirectly observable targets present significant spatial reasoning challenges in human–robot interaction (HRI). A clinically relevant example is beam stopper positioning during intraoperative electron radiotherapy (IOERT), which requires aligning a mobile shielding device with an unseen radiation beam axis. Methods We propose an audiovisual assistance system that estimates the real-time intersection between the radiation beam and the floor plane, providing multimodal spatial guidance during both manual and teleoperated control. A within-subject experimental study was conducted to evaluate positioning accuracy, execution time, user experience, and workload across assisted and unassisted conditions. Results Audiovisual guidance reduced the mean positioning error by approximately 80% (from ∼ 0.30 m to less than 0.07 m) across both control modes without increasing completion time. Furthermore, the system mitigated performance degradation caused by unfavorable workspace geometries, minimized skill-based differences between operators, and significantly lowered perceived mental workload. Discussion These findings demonstrate that real-time multimodal feedback is a robust, effective strategy for improving spatial accuracy, consistency, and usability in HRI tasks with obscured target geometries.
No takes yet. Share an insight, caveat, or question.
Garrido-Rey et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: