ERR@HRI 2.0 Challenge: Multimodal Detection of Errors and Failures in Human-Robot Conversations
This addresses the issue of conversational breakdowns and user trust in human-robot interaction, but it is incremental as it builds on previous work by providing an updated dataset and challenge.
The paper tackles the problem of detecting errors and failures in LLM-powered conversational robots by introducing the ERR@HRI 2.0 Challenge, which provides a multimodal dataset of 16 hours of human-robot interactions with annotations for robot errors and user correction intentions, and encourages benchmarking of machine learning models for failure detection.
The integration of large language models (LLMs) into conversational robots has made human-robot conversations more dynamic. Yet, LLM-powered conversational robots remain prone to errors, e.g., misunderstanding user intent, prematurely interrupting users, or failing to respond altogether. Detecting and addressing these failures is critical for preventing conversational breakdowns, avoiding task disruptions, and sustaining user trust. To tackle this problem, the ERR@HRI 2.0 Challenge provides a multimodal dataset of LLM-powered conversational robot failures during human-robot conversations and encourages researchers to benchmark machine learning models designed to detect robot failures. The dataset includes 16 hours of dyadic human-robot interactions, incorporating facial, speech, and head movement features. Each interaction is annotated with the presence or absence of robot errors from the system perspective, and perceived user intention to correct for a mismatch between robot behavior and user expectation. Participants are invited to form teams and develop machine learning models that detect these failures using multimodal data. Submissions will be evaluated using various performance metrics, including detection accuracy and false positive rate. This challenge represents another key step toward improving failure detection in human-robot interaction through social signal analysis.