Use and usability of software verification methods to detect behaviour interference when teaching an assistive home companion robot: A proof-of-concept study
Bibliographic record
Abstract
Abstract When studying the use of assistive robots in home environments, and especially how such robots can be personalised to meet the needs of the resident, key concerns are issues related to behaviour verification, behaviour interference and safety. Here, personalisation refers to the teaching of new robot behaviours by both technical and non-technical end users. In this article, we consider the issue of behaviour interference caused by situations where newly taught robot behaviours may affect or be affected by existing behaviours and thus, those behaviours will not or might not ever be executed. We focus in particular on how such situations can be detected and presented to the user. We describe the human–robot behaviour teaching system that we developed as well as the formal behaviour checking methods used. The online use of behaviour checking is demonstrated, based on static analysis of behaviours during the operation of the robot, and evaluated in a user study. We conducted a proof-of-concept human–robot interaction study with an autonomous, multi-purpose robot operating within a smart home environment. Twenty participants individually taught the robot behaviours according to instructions they were given, some of which caused interference with other behaviours. A mechanism for detecting behaviour interference provided feedback to participants and suggestions on how to resolve those conflicts. We assessed the participants’ views on detected interference as reported by the behaviour teaching system. Results indicate that interference warnings given to participants during teaching provoked an understanding of the issue. We did not find a significant influence of participants’ technical background. These results highlight a promising path towards verification and validation of assistive home companion robots that allow end-user personalisation.
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 | 0.016 | 0.041 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 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".