Personalised Explanations in Long-term Human-Robot Interactions
This addresses the problem of enhancing usability and comprehension in long-term human-robot interactions for domains like healthcare and domestic assistance, but it is incremental as it builds on prior XHRI work.
The paper tackles the challenge of personalizing explanations in human-robot interactions by proposing a framework that updates user knowledge models to adapt explanation detail, showing that a two-stage architecture reduces detail effectively when related user knowledge exists.
In the field of Human-Robot Interaction (HRI), a fundamental challenge is to facilitate human understanding of robots. The emerging domain of eXplainable HRI (XHRI) investigates methods to generate explanations and evaluate their impact on human-robot interactions. Previous works have highlighted the need to personalise the level of detail of these explanations to enhance usability and comprehension. Our paper presents a framework designed to update and retrieve user knowledge-memory models, allowing for adapting the explanations' level of detail while referencing previously acquired concepts. Three architectures based on our proposed framework that use Large Language Models (LLMs) are evaluated in two distinct scenarios: a hospital patrolling robot and a kitchen assistant robot. Experimental results demonstrate that a two-stage architecture, which first generates an explanation and then personalises it, is the framework architecture that effectively reduces the level of detail only when there is related user knowledge.