Speech-Based Path Refinement in Robot- Assisted Surgery through Virtual Obstacles
Bibliographic record
Abstract
Abstract Mobile surgical robots must operate within the spatial constraints of the operating room (OR) while adhering to strict safety and integration requirements. While robots progress towards autonomy, it remains important that humans always maintain control over the robots’ actions. For example, when planning paths to navigate through the OR, it is possible that the robot overlooks an obstacle or lacks contextual information, such as predicting humans’ intent to move or sudden environmental changes, including accidents. Therefore, the path planning must be both precise and modifiable by the medical staff. Existing systems for modifying robot paths often disrupt the surgical workflow, require extensive training, or, in the case of speech-controlled systems, offer only limited interaction vocabularies. This paper proposes a speech-based system to refine the mobile robot path using natural language as input. Our core contribution is a natural language interface that enables users to modify robot paths by converting verbal instructions into virtual obstacles, thereby reshaping the planned path.We demonstrate the feasibility of this system in a simulated ophthalmic surgery scenario. We evaluated the system on 10 different surgical environment occupancy maps and three different voice commands per map, resulting in a success rate of 96.67%. Path comparisons between human-drawn and automatically generated paths confirm the intended behavior of the system.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".