Effect of Domestic Trainee Robots’ Errors on Human Teachers’ Trust
Bibliographic record
Abstract
It is anticipated that intelligent robots will gain the ability to learn from humans how to perform tasks, and will assist them in many contexts such as with household chores in the near future; therefore, people should have the confidence to trust these robots after teaching them how to do a task. Like most machines, robots may sometimes behave in an erroneous manner and such errors can easily undermine trust in the robots, depending on their severity. Nevertheless, when a robot has been taught a task by humans, we hypothesize that the teachers may ignore small mistakes made by the robot, if it shows significant improvements while practising the task. We first conducted a study with 173 participants in which the perceived severity of different robot errors in a household chore (preparing food) was investigated. We then used the results to create scenarios of different levels of severity and conducted a second study with 138 participants to investigate the impact of error severity on trust. Participants remotely taught their preferences in food preparation tasks to robots. Over several practice rounds, robots’ behaviour improved, but the robots made either (a) no errors, (b) a small, or (c) a big error at the end, depending on the experimental condition. Small errors significantly affected trust and big errors had an even more adverse impact. Trust in the robot was found to be correlated with personality traits of the participants as well as with their disposition to trust other people.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.032 | 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 teacher head, 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".