Cross-modal Task Understanding and Execution of Voice-fingertip Reading Instruction by Using Small Family Service Robotic
Bibliographic record
Abstract
The correct understanding of human task instructions is an important basic condition for family service robots to carry out their work. In daily family scenarios, single-modal voice commands often have the problem of missing pronoun references, which makes robots unable to identify the target object to be operated. In this paper, a novel cross-modal instruction task understanding and execution framework based on the fusion of speech and visual information is proposed, which is based on the computing architecture of robot terminal and cloud server. By inputting the speech recognition results of the sound into the pre-trained Bert model, the first-level task classification label is obtained. Then, the robotic turns the camera to the location of the sound source. By using the lightweight visual object detection model to obtain the target area pointed by the finger, the robotic completes the confirmation of the visual instruction and entity of the object, and obtains the semantic label of the visual entity. The information of visual entity semantic label and the first level task classification label is fused to obtain the second level subtask classification label. Finally, the experimental results confirm that the framework can be used for robot task understanding and execution of cross-modal instructions, and will be helpful for promoting the application of family service robots.
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 | 0.000 | 0.001 |
| 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 | 0.001 |
| 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".