Uncertainty in Action: Confidence Elicitation in Embodied Agents
This addresses the challenge of uncertainty in embodied AI for navigation and decision-making, but it is incremental as it builds on existing reasoning methods.
The paper tackled the problem of embodied agents expressing confidence in dynamic multimodal environments by introducing Elicitation and Execution Policies to structure reasoning, showing that structured approaches like Chain-of-Thoughts improve confidence calibration in tasks within Minecraft, but persistent challenges remain in distinguishing uncertainty under abductive settings.
Expressing confidence is challenging for embodied agents navigating dynamic multimodal environments, where uncertainty arises from both perception and decision-making processes. We present the first work investigating embodied confidence elicitation in open-ended multimodal environments. We introduce Elicitation Policies, which structure confidence assessment across inductive, deductive, and abductive reasoning, along with Execution Policies, which enhance confidence calibration through scenario reinterpretation, action sampling, and hypothetical reasoning. Evaluating agents in calibration and failure prediction tasks within the Minecraft environment, we show that structured reasoning approaches, such as Chain-of-Thoughts, improve confidence calibration. However, our findings also reveal persistent challenges in distinguishing uncertainty, particularly under abductive settings, underscoring the need for more sophisticated embodied confidence elicitation methods.