Human strategies for correcting `human-robot' errors during a laundry sorting task
🤖 AI Summary
This study investigates natural human error-correction behaviors and communication strategies when interacting with domestic robots (Laundrobot) in home settings. Using a concealed Wizard-of-Oz experiment (N=42), participants instructed a humanoid-appearing but remotely operated robot to perform laundry sorting, while multimodal behavioral cues—including vocal fillers, pointing gestures, facial touching, and microexpressions—were coded and qualitatively categorized. The work identifies, for the first time, three adaptive response strategies: pedagogical correction, responsibility attribution, and incremental acceptance. Crucially, it reveals morphological–functional mismatch as the cognitive root of trust breakdown and expectation misalignment. Results show significant attenuation of corrective behaviors with repeated error exposure, and 63% of users adopted interaction patterns akin to those used with intelligent assistants. Findings provide empirically grounded guidelines for designing fault-tolerant interfaces and principled anthropomorphism in domestic robotics.
Application Category
📝 Abstract
Mental models and expectations underlying human-human interaction (HHI) inform human-robot interaction (HRI) with domestic robots. To ease collaborative home tasks by improving domestic robot speech and behaviours for human-robot communication, we designed a study to understand how people communicated when failure occurs. To identify patterns of natural communication, particularly in response to robotic failures, participants instructed Laundrobot to move laundry into baskets using natural language and gestures. Laundrobot either worked error-free, or in one of two error modes. Participants were not advised Laundrobot would be a human actor, nor given information about error modes. Video analysis from 42 participants found speech patterns, included laughter, verbal expressions, and filler words, such as ``oh'' and ``ok'', also, sequences of body movements, including touching one's own face, increased pointing with a static finger, and expressions of surprise. Common strategies deployed when errors occurred, included correcting and teaching, taking responsibility, and displays of frustration. The strength of reaction to errors diminished with exposure, possibly indicating acceptance or resignation. Some used strategies similar to those used to communicate with other technologies, such as smart assistants. An anthropomorphic robot may not be ideally suited to this kind of task. Laundrobot's appearance, morphology, voice, capabilities, and recovery strategies may have impacted how it was perceived. Some participants indicated Laundrobot's actual skills were not aligned with expectations; this made it difficult to know what to expect and how much Laundrobot understood. Expertise, personality, and cultural differences may affect responses, however these were not assessed.
Problem
Research questions and friction points this paper is trying to address.
Understanding human communication patterns during robotic failures in laundry tasks
Improving domestic robot speech and behaviors for better human-robot interaction
Assessing how robot appearance and capabilities affect human expectations
Innovation
Methods, ideas, or system contributions that make the work stand out.
Studied human communication patterns during robotic failures
Analyzed speech and gestures for error correction strategies
Assessed impact of robot appearance and capabilities
🔎 Similar Papers
No similar papers found.
