Leveraging Cognitive States for Adaptive Scaffolding of Understanding in Explanatory Tasks in HRI

Understanding how scaffolding strategies influence human understanding in human-robot interaction is important for developing effective assistive systems. This empirical study examines linguistic scaffolding strategies that rely on negation as a key mechanism for steering users away from potential errors, while also considering the role of hesitations as a means to mitigate the increased processing costs associated with negation. In an adaptive strategy, the user state regarding the current state of understanding and processing capacity was estimated via a scoring scheme based on task performance, prior scaffolding strategy, and current eye gaze behavior. In the study, the adaptive strategy of providing negations and hesitations was compared with a non-adaptive strategy of providing only affirmations. This paper presents a new architecture for social human–robot interaction that integrates continuous monitoring with adaptive scaffolding, illustrating the full loop from perception to tailored instructional support. The adaptive scaffolding strategy was produced by the computational model SHIFT , which is embedded within the robot control architecture RISE . Our findings indicate that using adaptive scaffolding strategies with SHIFT tends to (1) increase processing costs, as reflected in longer reaction times, but (2) improve task understanding, evidenced by a lower error rate of almost 23%. We assessed the efficiency of SHIFT’ s selected scaffolding strategies across different cognitive states, finding that in three out of five states, the error rate was lower compared to the baseline condition. We discuss how these results align with the assumptions of the SHIFT model and highlight areas for refinement. Moreover, we demonstrate how scaffolding strategies, such as negation and hesitation, contribute to more effective human-robot explanatory dialogues.