Trust in an Autonomous Guidance System and Resulting Behavior for a Planetary Rover Task
Bibliographic record
Abstract
We examined how human operator trust in navigational assistance differed when the assistance was human vs autonomous. As autonomy becomes ever more ubiquitous, it is critical to understand how trust in autonomous systems differs from that in another human. Benign navigational assistance was provided by either another human or an autonomous system and presented in an identical manner. Half of the subjects were deceived and told the assistance was provided by the opposite source. We quantified trust by how closely subjects' rover driving actions aligned with recommendations given by the navigational assistant. This metric of trust is objective, continuous, and unobtrusive. In addition, subjects self-reported their trust in the system after the experiment using a standard trust questionnaire. The presence of the navigational assistance changed subject behavior (p = 0.002) but there was not a significant difference between trust in the human and autonomous navigational assistance systems. This suggests that our subject pool was not more or less trusting in an autonomous system, as compared to assistance from another human, particularly when controlling for the system's efficacy. Self-reported trust on the post-experiment questionnaire correlated with objectively measured trust on difficult rover operating scenarios (p = 0.01, r = 0.45). Our findings inform future human-autonomy teaming design choices and provide a unique approach to quantify operator trust. Potential applications include crewed deep space missions where communication delays may require ground controllers to be replaced with onboard autonomous systems while maintaining and quantifying trust throughout.
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 | 0.002 | 0.015 |
| 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 | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".