Impact of Different Failures on a Robot�s Perceived Reliability
Andrew Violette, Zhanxin Wu, Haruki Nishimura, Masha Itkina, Leticia Priebe Rocha, Mark Zolotas, Guy Hoffman, Hadas Kress-Gazit
AI summary
Problem
How do different types of robot failures (slips, lapses, mistakes) differentially impact users' perceived reliability, and does this perception recover after a failure?
Approach
Participants watched videos of a robot performing a pick-and-place task under various failure or success conditions, then placed real-money bets on the robot's future success to objectively measure perceived reliability.
Key results
- Slips and lapses cause the largest drops in perceived reliability
- Mistakes have minimal to negligible impact on perceived reliability
- Subsequent successful executions fully recover perceived reliability
- Some mistakes are misperceived as successful task completions
Why it matters
These findings guide HRI designers in prioritizing failure recovery strategies and demonstrate that physical success alone can effectively rebuild user trust after robot errors.
Abstract
Robots fail, potentially leading to a loss in the robot’s perceived reliability (PR), a measure correlated with trustworthiness. In this study we examine how various kinds of failures affect the PR of the robot differently, and how this measure recovers without explicit social repair actions by the robot. In a preregistered and controlled online video study, participants were asked to predict a robot’s success in a pick-and-place task. We examined manipulation failures (slips), freezing (lapses), and three types of incorrect picked objects or place goals (mistakes). Participants were shown one of 11 videos—one of five types of failure, one of five types of failure followed by a successful execution in the same video, or a successful execution video. This was followed by two additional successful execution videos. Participants bet money either on the robot or on a coin toss after each video. People’s betting patterns along with a qualitative analysis of their survey responses highlight that mistakes are less damaging to PR than slips or lapses, and some mistakes are even perceived as successes. We also see that successes immediately following a failure have the same effect on PR as successes without a preceding failure. Finally, we show that successful executions recover PR after a failure. Our findings highlight which robot failures are in higher need of repair in a human-robot interaction, and how trust could be recovered by robot successes.