Summary
In conversations involving many people and a robot, it can be hard for the robot to know exactly who to talk to and what to say next. The researchers created a new system called HiBRIDGE that helps the robot make smarter and clearer decisions by breaking down the choices into steps and using math that handles uncertainty well. They tested this system on older conversations and found it performed better than other methods. They also showed that people understood the robot’s behavior explanations better when using this system, and it worked well in real-time group talks. Overall, HiBRIDGE helps robots join group conversations more naturally and clearly.
human-robot interactiondialogue managementBayesian neural networkuncertainty modelinghierarchical decision processgroup communicationexplainabilitymachine learningprobabilistic modelingreal-time systems
Authors
Massimiliano Nigro, Hatice Gunes, Micol Spitale, Fethiye Irmak Dogan
Abstract
In multi-party human-robot interaction, a robot must continuously decide whom to address and what to say to participate effectively in the conversation. In real-world interactions, this is challenging because several behaviours may be plausible at the same time: a robot might continue a topic with one participant, involve another through a question, or address the whole group, with the appropriate choice depending on both whom it addresses and the interaction context. Current approaches remain limited in representing uncertainty when several behaviours are plausible and in structuring decisions into semantically meaningful intermediate steps that make robot decisions easier to interpret. Addressing these, we present HiBRIDGE, a hierarchical Bayesian neural network framework for group-robot dialogue management. Its Bayesian formulation enables uncertainty-aware prediction and robust learning from limited interaction data, while the hierarchical approach formulates behaviour selection as a structured, multi-stage decision process. We further use decision-tree surrogates to investigate whether this structure can support more interpretable explanations. Across three offline group-HRI datasets, our findings show that Bayesian formulations outperform their deterministic counterparts and several state-of-the-art baselines. Next, through an online study (N=20), we show that explanations derived from the hierarchical model are rated as more helpful for understanding robot behaviour and are preferred over those derived from the flat model. Finally, through our in-person study (N=12), we demonstrate the feasibility of HiBRIDGE for autonomous real-time group interaction, with both hierarchical and flat Bayesian variants positively perceived. Overall, HiBRIDGE combines strong predictive performance with a structured decision process that supports more interpretable explanations of robot behaviour.