The DOI matches its Crossref record; 75 of the 78 references it cites were found in a registry or an index; none of the 94 sources its claims cite is checked for support yet.
Taxonomy of Trust-Relevant Failures and Mitigation Strategies
Open accessAbstract
We develop a taxonomy that categorizes HRI failure types and their impact on trust to structure the broad range of knowledge contributions. We further identify research gaps in order to support fellow researchers in the development of trustworthy robots. Studying trust repair in HRI has only recently been given more interest and we propose a taxonomy of potential trust violations and suitable repair strategies to support researchers during the development of interaction scenarios. The taxonomy distinguishes four failure types: Design, System, Expectation, and User failures and outlines potential mitigation strategies. Based on these failures, strategies for autonomous failure detection and repair are presented, employing explanation, verification and validation techniques. Finally, a research agenda for HRI is outlined, discussing identified gaps related to the relation of failures and HR-trust.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 of 94 cited sources checked · 0 supported · 0 flagged
In the paper
“In the specific instance, a variety of problems were detected automatically, such as navigation issues [15], forceful pushes to the robot, and hardware failures.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
What the sources say
- Not checked yetcites [15]
Strength:plain· not yet calibratedSingle caseTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For instance, feedback from on-site interviews showed that commission failures have a very high impact on trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Impact.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIn the paper
“An analysis of software failures, in particular navigation failures (which account for more than 99% of all software-related issues in this particular use case) in [15] reveals that in 1605 instances the robot had to ask for help as it could not recover from a navigation problem, making its failure obvious to the interacting humans, and hence potentially having an impact on trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
What the sources say
- Not checked yetcites [15]
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIn the paper
“An analysis of software failures, in particular navigation failures (which account for more than 99% of all software-related issues in this particular use case) in [15] reveals that in 1605 instances the robot had to ask for help as it could not recover from a navigation problem, making its failure obvious to the interacting humans, and hence potentially having an impact on trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
What the sources say
- Not checked yetcites [15]
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIn the paper
“The system data in [36] indicated that there were about 3.5 interactions per operational hour (i.e.time the robot is not resting or charging) with users that are actively using the robot.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
What the sources say
- Not checked yetcites [36]
Load-bearingStrength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Similarly, the impact of failure repetition is understudied, above all with respect to how it affects trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Mitigation of User Failures.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIn the paper
“Our discussions identified the category of intentional and unintentional User Failures as up-to-now understudied with respect to mitigation strategies [41].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Mitigation of User Failures.
What the sources say
- Not checked yetcites [41]
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“and no systematic studies of the other strategies exist so far.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Mitigation of User Failures.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIn the paper
“However, effects of robots showing negative emotions are in general understudied [42]”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Mitigation of User Failures.
What the sources say
- Not checked yetcites [42]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesNone of the sources cited for this claim have been checked yet.
In the paper
“Studies on trust within robotics have mainly been motivated by the literature on trust in automation [40,46,47], which operates with a conceptualization of trust as mere reliance.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.1 Approaches to Trust
What the sources say
- Not checked yetcites [40]
- Not checked yetcites [46]
- Not checked yetcites [47]
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
- It may state two separate claims as one. 38
- Probably not a substantial claim. 56
None of the sources cited for this claim have been checked yet.
In the paper
“Thus, we observed such failure about every 2 hours of autonomous operation, leading to a ratio of 7 : 1 for Software failures to interactions, leading to a Probability score of “3” in Tab. 2.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the case of the latter, by counting the number of forceful 1 http://strands-project.eu/ robot pushes and deliberate tampering, “intentional User failure” was observed in about 1 out of 200 interactions, scoring “2”.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As an example, we quote a participant, who complained that the robot appears “stupid”, because it would “start talking to a wall”, a consequence of misclassification leading to a commission failure.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Impact.
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“To show how such a risk table can be used in a HRI context, the scores in Table 2 are from a real world use case.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > User.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Tab. 2 presents the results of this case study analysis, in terms of Probability and Impact scores derived from the retrospective analysis of the data sets from the deployments.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.2 Trust loss as a risk: A Case-Study
Strength:plain· not yet calibratedSingle caseTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“For instance, [33] revealed some of the Design failures that lead to the iterative improvements between annual deployments.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
What the sources say
- Not checked yetcites [33] source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Our efforts revealed that empirical research in HRI tries to more and more identify suitable mitigation strategies, but hardly considers the type of failure that caused the trust violation.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 6 CONCLUSION
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“In an online survey, Brooks et al. [7] explored people's reactions to failures in autonomous robots, namely a vacuum cleaner and a self-driving taxi, by manipulating four variables: context risk, failure severity, task support and human support.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [7] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, psychologists Tversky and Kahneman [74] as well as other ethicists find in this to be an omission bias, since the consequences of (not) acting can be the same.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.1 Approaches to Trust
What the sources say
- Not checked yetcites [74]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Also due to their little employment in society, long-term studies have not been conducted so far.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Additionally, a promise to change behavior can significantly speed the trust recovery process, but prior deception harms the effectiveness of a promise.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [68]
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“The aspects of trust repair and trust violations have been understudied in the field of HRI [4].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 1 INTRODUCTION
What the sources say
- Not checked yetcites [4]
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“However, trust harmed by deception and the same untrustworthy actions never fully recovers, even with actions of trust repair [68].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [68]
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“This improves reliability, safety and trustworthiness of the systems (see for example [23,77]) and will help mitigate some of the failures leading to loss of trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 1 INTRODUCTION
What the sources say
- Not checked yetcites [23]
- Not checked yetcites [77]
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“Actions (commissions) that fail expectations and thus damage trust are, according to some [19], worse than failures to act (omissions).”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.1 Approaches to Trust
What the sources say
- Not checked yetcites [19]
Strength:hedged· not yet calibratedTests✗ Asserted: fails✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The authors may not put it forward as true. The paper’s conclusions may not depend on it.
In the paper
“Based on the three-factor model by Hancock et al. [29], Hoff and Bashir [39] have also suggested a three-layered model in which these factors contribute to dispositional, situational and learned trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.2 Modeling Trust
What the sources say
- Not checked yetcites [39]
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Interestingly, major identified reasons for limited trust were communication problems during collaboration resulting in participant's uncertainty of their own ability to collaborate with the robot.The communication problems were strongly linked to the interface design.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [59] source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“Wagner et al. [75] propose a trust model based on risk.They define trust as “a belief, held by the trustor, that the trustee will act in a manner that mitigates the trustor's risk in a situation in which the trustor has put its outcomes at risk” [75, p.26:4].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.2 Modeling Trust
What the sources say
- Not checked yetcites [75] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Promises lead to a better trust recovery than apologies, and in general, the message timing and exact content was shown to be crucial [63].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [63] source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“In ongoing studies, several actions of trust repair have been proposed, including apologies, promises, internal or external attribution, and the showing of consistent series of trustworthy actions [4,14].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [4]
- Not checked yetcites [14]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“The challenge becomes more complex as trust has both static and dynamic components in human-robot interaction.Static components such as gender do not change, but dynamic components related to the system can be influenced [39].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 1 INTRODUCTION
What the sources say
- Not checked yetcites [39]
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“Billings proposed a three-factor model of trust in robots, including human characteristics such as ability and personality, environmental characteristics such as task and team, and robot characteristics such as performance and attributes [5].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.2 Modeling Trust
What the sources say
- Not checked yetcites [5]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Further, the participants initially had confidence in the robot itself, but were insecure of their own ability to collaborate due to their inability to predict the robot's intentions and instructions.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [59] source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“In an emergency setting, where an apology right after violated trust has not recovered trust, an apology right before the next trust decision point has repaired trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [63] source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“These three factors have also been identified in a meta-analysis on trust [29], where the authors stressed that too few studies have yet been conducted on environmental and human-related factors, although robot-related factors have been shown to affect trust the most.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.2 Modeling Trust
What the sources say
- Not checked yetcites [29] source
Strength:boosted· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Humans who misplace trust, understood as both underand over-reliance, might be exposed to serious danger, which is the reason safety concerns are of high consideration.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.1 Approaches to Trust
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“Nordqvist and Lindblom [59] analyze trustworthiness of industrial robots with an operators' experience framework.The evaluation framework consists of the factors ability, benevolence, integrity, perceived safety, time on task and errors, where in total 12 user experience (UX) goals were characterized, 2 for each component.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [59] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“The need for research on trust in artificial agents in cases of inevitable failure has been highlighted as well [5].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [5]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, the authors reported an interesting but non-significant tendency showing a preference for both task and human support in high severity situations, and a preference for only task support in low severity situations.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 2.3 Trust, Failure, and Repair
What the sources say
- Not checked yetcites [7] source
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Intentional misbehavior is harder to address, since the user acted purposefully.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Explanations for the end user can be a suitable mean to repair trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Rich data sets, comprising task and error logs [32], user demographics [36], and navigation failures [15] have been obtained from these deployments, and analysed for the case study for this paper.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.2 Trust loss as a risk: A Case-Study
What the sources say
- Not checked yetcites [32]
- Not checked yetcites [36]
- Not checked yetcites [15]
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Consequently, many failure types can be detected from system logs and from dedicated anomaly or failure detection modules that allow to estimate the probability of them occurring.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“As Lewicki and Wiethoff [49] explain restoring trust after a violation is a three-step process: (1) exchanging information about the perceived trust violation, (2) willingness to forgive the violator, and (3) reaffirm their commitment.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.3 Mitigation Strategies
What the sources say
- Not checked yetcites [49]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“To assess the impact of individual failures, we base our assessment of a qualitative analysis in the context of the care deployment within the STRANDS project [24,33,34].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Impact.
What the sources say
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We differentiate four different failure types with respect to their impact on trust and the related mitigation strategies: (1) Design, (2) System, (3) Expectation, and (4) User (see Table 1 for condensed failure type descriptions).”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.1 The Taxonomy
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Of course, Expectation failures could lead to unintentional User failures.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > User.
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When a user misbehaves, the response the system gives will influence future behavior of the user towards the system.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“It shall be noted that this constitutes merely a case study, based on available data, allowing only some scores to be robustly computed from logs, while others have to be informed guesses, based on the authors' experience.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.2 Trust loss as a risk: A Case-Study
Strength:plain· not yet calibratedSingle caseTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“The other probability scores are much harder to obtain in a post-mortem analysis of long-term deployment, and require more focused studies, e.g.[33], involving the users directly.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Probability and Detection.
What the sources say
- Not checked yetcites [33] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“While De Visser et al. [14] stress the importance of trust repair and list possible mitigation strategies, these strategies have not been linked to different failure types before.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3 PROPOSAL
What the sources say
- Not checked yetcites [14]
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, improving trust through the interaction design for other prospective users will still be a viable way to go.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.3 Mitigation Strategies
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These scores are system-and scenario-specific.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > User.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Hancock et al. [29] provide a detailed overview on HRI studies on the impact of robot design features on trust in HRI.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.3 Mitigation Strategies
What the sources say
- Not checked yetcites [29] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Explanations to end users do not necessarily need to be in natural language, but can use cues such as closed eyes, blinking lights, nodding head etc.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In case of a system breakdown, the trust lost in the system can be minimized when alternatives are available.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“As mentioned by Baker et al. [4], models of human-automation and human-human trust are a helpful starting point, but do not account for the complexities of building and maintaining trust in HRI.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3 PROPOSAL
What the sources say
- Not checked yetcites [4]
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Our discussions on User Failures revealed that there is little to no research on how to mitigate this type of failure.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the correct level of detail of abstractions and human-comprehensible explanations are challenging.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Strength:plain· not yet calibratedTests✓ Asserted: passes✗ Checkable: fails✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Proper design allows for smooth interactions and substantial research is available in HRI on understanding robot-related factors affecting trust in the interaction design, such as social skills [35], robot role [27], and communication style [60].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.3 Mitigation Strategies
What the sources say
- Not checked yetcites [35] source
- Not checked yetcites [27]
- Not checked yetcites [60]
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While it is intuitive that Interaction Design is important to foster trust, it can also be a tool in reestablishing trust.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.3 Mitigation Strategies
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The assessment is not an exact science; within this case study we do not aim for a comprehensive analysis of this STRANDS system, but rather present the concepts of considering trust loss as a risk open to a systematic analysis.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Impact.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Depending on the type of failure that has taken place, there are different possible mitigation strategies that can help regain the trust of the user.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.3 Mitigation Strategies
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If the user was not aware of any misbehavior, asking the user for justification of their actions can create awareness of their mistakes.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Explanations.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is a very practical mitigation strategy to ensure the issue does not occur again and only applies to System failures.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3.3 Mitigation Strategies
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“However, they base their framework on the error taxonomy of Reason [61] which does not account for the interactive nature of HRI.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 3 PROPOSAL
What the sources say
- Not checked yetcites [61] source
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This type of failure can be caused either by a Design failure or an Expectation failure which influences its impact on trust and potential mitigation strategies.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > User.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We argue that a framing of failure situations will have an impact on trust repair and needs to be considered in future studies, but above all in future interaction designs.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 6 CONCLUSION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“The belief aspects from [11,18] and modelled in the logics mentioned above seem to match the expectation failure type discussed above.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.5 Logics for Trust Loss Detection
What the sources say
- Not checked yetcites [11]
- Not checked yetcites [18]
Strength:hedged· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“However, they do not match the more complex models of trust as introduced in Section 2.2.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.5 Logics for Trust Loss Detection
What the sources say
- Not checked yetcites [11]
- Not checked yetcites [18]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“A complete axiomatisation is provided but complexity and decidability are not considered.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.5 Logics for Trust Loss Detection
What the sources say
- Not checked yetcites [37]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Failure classifications often come with severity rankings, such as the failure classification by Carlson and Murphy [10].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Severity Rankings.
What the sources say
- Not checked yetcites [10] source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“So far, little research has been done on how users can be trained in HRI (since research mostly focuses on how users can train robots [1]), but existing work shows that “training is essential” [9].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Involve Authority Figure.
What the sources say
- Not checked yetcites [1]
- Not checked yetcites [9]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other words, the failure detection problem is considered a classification problem, where a model of the failure itself can either be defined or learned.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.1 Failure Detection
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“STRIPS and its derivatives are widely used to describe a robot's deliberate actions and external events.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.3 Formalism for representing plans
What the sources say
- Not checked yetcites [20]
Strength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“These approaches only partially fulfill Miller's criteria of selectivity, though: although minimality criteria are considered, there are generally many possible explanations and it is not necessarily clear how to pick the most appropriate ones.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.2 Offering Explanations
What the sources say
- Not checked yetcites [25]
- Not checked yetcites [22]
- Not checked yetcites [51]
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“The identification of a potentially known problem can then be deferred to approaches to generation explanations, utilising domain knowledge as formally defined in the following section and also explored in [30].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.1 Failure Detection
What the sources say
- Not checked yetcites [30]
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Some studies on people's willingness to help robots after repeated failure indicate that repeatedly helping robots in need when the suggested repair strategy is successful does not reduce likability [3].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Mitigation of User Failures.
What the sources say
- Not checked yetcites [3]
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While automated detection of a failure is the first necessary step in failure mitigation, the next goal should be automated trust loss detection to be able to respond appropriately.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Automated recognition of Trust Loss.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
In the paper
“According to Miller [57], explanations should be contrastive, selective, and social.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.2 Offering Explanations
What the sources say
- Not checked yetcites [57]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Formal verification, simulation based testing and end user experiments can help improve the safety, reliability and trust in robotic systems [23,77], as well as help mitigate as system failure (all), design failure and expectation failure (end user experiments).”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.1 Failure Detection
What the sources say
- Not checked yetcites [23]
- Not checked yetcites [77]
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“The downside of this approach is its being less generic and its requiring hand-crafted template modeling.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.2 Offering Explanations
What the sources say
- Not checked yetcites [76]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Furthermore, different cues in user behavior need to be distinguishable to detect trust loss of the user in the system.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Automated recognition of Trust Loss.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Counterfactual explanations have recently been applied to generating explanations for plan failures [25], for explaining why an action plan contains a specific action [22], and to explain why an action plan does (not) adhere to moral principles [51].”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.2 Offering Explanations
What the sources say
- Not checked yetcites [25]
- Not checked yetcites [22]
- Not checked yetcites [51]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“A complementary approach relates to anomaly detection (e.g. recently surveyed in [28]).It aims to detect any deviation from a normal behaviour of a system, without necessarily classifying a problem.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.1 Failure Detection
What the sources say
- Not checked yetcites [28]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, this does not give insights into how much overall trust is harmed.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Mitigation of User Failures.
What the sources say
- Not checked yetcites [3]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“The resulting logic is, in general, undecidable but decidable fragments are identified.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > 4.5 Logics for Trust Loss Detection
What the sources say
- Not checked yetcites [43] source
- Not checked yetcites [44]
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As mentioned before, the current logics that allow trust (loss) modeling are fairly simplistic.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Automated recognition of Trust Loss.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As the STRANDS use case has shown, proper recognition and standardized scoring of trust loss could greatly benefit trust research in HRI.”
§ Taxonomy of Trust-Relevant Failures and Mitigation Strategies > Automated recognition of Trust Loss.
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper relies on this without support.
Human responses to robotic systems are complex and depend on factors such as the system's morphology, behaviour, and deployment context.
“Human responses towards robotic systems are very complex in their nature and depend on many factors, such as the morphology and behavior of the system and the context in which they are deployed.”
The paper relies on this without support.
Information about limitations following automation errors aids trust recovery.
“Following errors of automation, information related to limitations further aid in trust recovery.”
The paper relies on this without support.
No taxonomy for trust repair in HRI exists.
“A taxonomy for trust repair in HRI does not exist, but a framework for rebuilding trust in automation has been proposed by Marinaccio et al. [55].”
The authors state this as an assumption.
Once trust is broken because of a Design failure, redesigning the system becomes even more challenging.
“However, we can assume that once trust is broken due to a Design failure, the redesign of the system becomes even more challenging.”
The paper relies on this without support.
In human-human interaction, apologies are more effective than shifting blame elsewhere.
“In human-human interaction, they are more effective than shifting the blame elsewhere.”
The authors state this as an assumption.
Unintentional negative behaviour will not be repeated once the user becomes aware of it.
“We assume that unintentional negative behavior will not be repeated once the user becomes aware of it.”
The paper relies on this without support.
Robots that interact with humans in the wild will at some point face failure situations inflicted by the robot, the human, or unexpected environmental events.
“Robots that interact with humans in the wild will at some point face failure situations, which can either be inflicted by the robot, the human, or by unexpected environmental events.”
The paper relies on this without support.
It is in human nature to anthropomorphize robots, for example by projecting a personality onto them or reading emotions into their output.
“It is in our nature to anthropomorphize robots, for example by projecting a personality onto the robot or reading emotions into its output.”
The authors state this as an assumption.
There exists an empty action in the operator set with no preconditions, no delete list, and no add list.
“We assume the existence of the empty action ϵ ∈ O, which has an empty precondition, an empty delete list, and an empty add list.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Also, creating AI with the ability to explain and justify its decision-making process [5,38,44] could increase the end-users willingness to accept the AI's recommendations [53,55].”
From Being Trustworthy is Not Enough: How Untrustworthy Artificial Intelligence (AI) Can Deceive the End-Users and Gain Their Trust (2023) · cites this paper as [53]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Software-failure ratio is reversed
MinorAt 3.5 interactions per operational hour and one software failure about every two hours, there are about seven interactions per failure-not seven software failures per interaction.
“Thus, we observed such failure about every 2 hours of autonomous operation, leading to a ratio of 7 : 1 for Software failures to interactions, leading to a Probability score of "3" in Tab. 2.”
“there were about 3.5 interactions per operational hour (i.e.time the robot is not resting or charging) with users that are actively using the robot.”
Marinaccio citation points to a different reference
MinorThe text attributes the trust-rebuilding framework to Marinaccio et al. at reference [55], but entry 55 is a paper by Malle et al. The Marinaccio paper is listed as entry 56.
“a framework for rebuilding trust in automation has been proposed by Marinaccio et al. [55].”
“55. Bertram F Malle, Matthias Scheutz, Jodi Forlizzi, and John Voiklis. 2016. Which robot am i thinking about?: The impact of action and appearance on people's evaluations of a moral robot.”
Citations
Cites
Judgment under Uncertainty: Heuristics and Biases
Tversky, A., & Kahneman, D. (1975) · Utility, Probability, and Human Decision Making · doi:10.1007/978-94-010-1834-0_8 · Cited by 22,650
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605 · cited 2×
“Drawing on the model from organizational contexts by Mayer et al. [56] and the model on trust in automation by Lee and See [47], Wagner et al. [75] propose a trust model based on risk.”
BackgroundMethodExplanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Reason, J. (1990) · doi:10.1017/cbo9781139062367 · Cited by 5,108
STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving
Fikes, R. E., & Nilsson, N. J. (1971) · Artificial Intelligence · doi:10.1016/0004-3702(71)90010-5 · Cited by 4,882
(1987) · Medical Entomology and Zoology · Cited by 4,269
Clarke, E. M., & Schlingloff, B. (1999) · Cited by 4,237
A survey of robot learning from demonstration
Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.10.024 · Cited by 3,227
Rempel, J. K., Holmes, J. G., & Zanna, M. P. (1985) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.49.1.95 · Cited by 3,146 · cited 2×
“Hence, perceived benevolence may promote acceptance of a robot’s changing behaviour [52], as with human interpersonal relationships [62].”
Background
Flagged first, then by citations
3 of the 78 references couldn’t be matched to a known paper.
Research works printed but not linked: 8
- Paul Gainer , Clare Dixon , Kerstin Dautenhahn , Michael Fisher , Ullrich Hustadt , Joe Saunders , and Matt Webster . 2017. CRutoN: Automatic Verification of aRobotic Assistant's Behaviours. InCritical Systems: Formal Methods and Auto-mated Verification - Joint 22nd International Workshop on Formal Methods forIndustrial Critical Systems - and - 17th International Workshop on AutomatedVerification of Critical Systems , FMICS-AVoCS 2017 , Turin, Italy, September 18--20,2017, Proceedings (Lecture Notes in Computer Science), Laure Petrucci, CristinaSeceleanu, and Ana Cavalcanti (Eds.), Vol. 10471 . Springer , Turin, Italy, 119--133.https://doi.org/10.1007/978--3--319--67113-0_8 10.1007/978--3--319--67113-0_8 Paul Gainer, Clare Dixon, Kerstin Dautenhahn, Michael Fisher, Ullrich Hustadt,Joe Saunders, and Matt Webster. 2017. CRutoN: Automatic Verification of aRobotic Assistant's Behaviours. InCritical Systems: Formal Methods and Auto-mated Verification - Joint 22nd International Workshop on Formal Methods forIndustrial Critical Systems - and - 17th International Workshop on AutomatedVerification of Critical Systems, FMICS-AVoCS 2017, Turin, Italy, September 18--20,2017, Proceedings (Lecture Notes in Computer Science), Laure Petrucci, CristinaSeceleanu, and Ana Cavalcanti (Eds.), Vol. 10471. Springer, Turin, Italy, 119--133.https://doi.org/10.1007/978--3--319--67113-0_8 · DOI
- Xiaowei Huang and Marta Zofia Kwiatkowska . 2017. Reasoning about CognitiveTrust in Stochastic Multiagent Systems. InProceedings of the Thirty-First AAAIConference on Artificial Intelligence , February 4--9 , 2017 , San Francisco, California ,USA., Satinder P. Singh and Shaul Markovitch (Eds.). AAAI Press , 3768--3774.http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14566 Xiaowei Huang and Marta Zofia Kwiatkowska. 2017. Reasoning about CognitiveTrust in Stochastic Multiagent Systems. InProceedings of the Thirty-First AAAIConference on Artificial Intelligence, February 4--9, 2017, San Francisco, California,USA., Satinder P. Singh and Shaul Markovitch (Eds.). AAAI Press, 3768--3774.http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14566
- John D. Lee and Katrina A . See . 2004 . Trust in Automation : Designing forAppropriate Reliance.Human Factors 46, 1 (2004), 50--80. John D. Lee and Katrina A. See. 2004. Trust in Automation: Designing forAppropriate Reliance.Human Factors46, 1 (2004), 50--80.
- Michael Lewis , Katia Sycara , and Phillip Walker . 2018. The Role of Trust inHuman-Robot Interaction. InFoundations of Trusted Autonomy , Hussein A.Abbass , Jason Scholz, and Darryn J. Reid (Eds.). Springer International Publishing ,Cham, 135--159. https://doi.org/10.1007/978--3--319--64816--3_8 10.1007/978--3--319--64816--3_8 Michael Lewis, Katia Sycara, and Phillip Walker. 2018. The Role of Trust inHuman-Robot Interaction. InFoundations of Trusted Autonomy, Hussein A.Abbass, Jason Scholz, and Darryn J. Reid (Eds.). Springer International Publishing,Cham, 135--159. https://doi.org/10.1007/978--3--319--64816--3_8 · DOI
- John K Rempel , John G Holmes , and Mark P Zanna . 1985. Trust in close relation-ships.Journal of personality and social psychology49, 1 ( 1985 ), 95. John K Rempel, John G Holmes, and Mark P Zanna. 1985. Trust in close relation-ships.Journal of personality and social psychology49, 1 (1985), 95.
- Laurence Thomas . 1987. Friendship. Synthese72, 2 ( 1987 ), 217--236 . Laurence Thomas. 1987. Friendship. Synthese72, 2 (1987), 217--236.
- Ning Wang , David V. Pynadath , and Susan G. Hill . 2016. Trust Calibration within a Human-Robot Team: Comparing Automatically Generated Explanations . In11th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE , New York, NY,USA, 109--116. Ning Wang, David V. Pynadath, and Susan G. Hill. 2016. Trust Calibration within a Human-Robot Team: Comparing Automatically Generated Explanations. In11th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE,New York, NY,USA, 109--116.
- M. Webster , D. Western , D. AraizaIllan , C. Dixon , K. Eder , M. Fisher , and A. Pipe . 2020. A Corroborative Approach to Verification and Validation of Human--RobotTeams.International Journal of Robotics Research39 ( 2020 ), 73--99. M. Webster, D. Western, D. AraizaIllan, C. Dixon, K. Eder, M. Fisher, and A. Pipe.2020. A Corroborative Approach to Verification and Validation of Human--RobotTeams.International Journal of Robotics Research39 (2020), 73--99.
Cited by
Sorted by citations
Items 101–103 of 103
Goo, H. G., & Evers, V. (2026) · Conferência Latino-Americana de Interação Humano-Computador (CLIHC) · doi:10.5753/clihc.2026.21754
Guerra, E., Söhngen, Y. N., & Prilla, M. (2026) · Mensch und Computer (MuC) · doi:10.1145/3820253.3820273
Guided Temporal Modeling for Perceived Failure Detection in Human–Robot Interaction
Ravandi, B. S., Akalın, N., & Riveiro, M. (2026) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3776574.3832483
Metadata
- Authors
- Tolmeijer, S., Weiss, A., Hanheide, M., Lindner, F., Powers, T. M., Dixon, C., & Tielman, M. L.
- Affiliations
- University of Zurich (CH)
- TU Wien (AT)
- University of Lincoln (GB)
- Universität Ulm (DE)
- University of Delaware (US)
- University of Liverpool (GB)
- Delft University of Technology (NL)
- ORCID
- Venue
- Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction
- Publisher
- ACM
- Published
- 2020-03-09
- Pages
- 3-12
- OpenAlex
- W3010109960
- Semantic Scholar
- 0daae809a2018e7b2124570a8c031e310891ee98
- Cited by
- 103
- References
- 78
- Citations by year
- 2026: 6 · 2025: 22 · 2024: 18 · 2023: 17 · 2022: 14 · 2021: 20 · 2020: 6
- FWCI
- 20.10
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM/IEEE International Conference on Human-Robot Interaction (HRI) (publishedVersion, other-oa)
- Research Explorer (The University of Manchester) (publishedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich) (acceptedVersion, other-oa)
- Research Repository (Delft University of Technology) (submittedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, other-oa)
- Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich)
- Funders
- UKRIHubs for Robotics and AI in Hazardous Environments (EP/R026092(FAIR-SPACE), EP/R026084 (RAIN))
- Topics
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Keywords
- human-robot interaction, trust in robots, breach of trust, failure taxonomy, trust repair, design failure, system failure, explanation, verification and validation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
