Dialogue systems must understand children’s utterance intentions by considering their unique linguistic characteristics, such as syntactic incompleteness, pronunciation inaccuracies, and creative expressions, to enable natural conversational engagement in child–robot interactions. Even state-of-the-art large language models (LLMs) for language understanding and contextual awareness cannot comprehend children’s intent as accurately as humans because of their distinctive features. An LLM-based dialogue system should acquire the manner by which humans understand children’s speech to enhance its intention reasoning performance in verbal interactions with children. To this end, we propose a fine-tuning methodology that utilizes the LLM–human judgment discrepancy and interactive response data. The former data represent cases in which the LLM and human judgments of the contextual appropriateness of a child’s answer to a robot’s question diverge. The latter data involve robot responses suitable for children’s utterance intentions, generated by the LLM. We developed a fine-tuned dialogue system using these datasets to achieve human-like interpretations of children’s utterances and to respond adaptively. Our system was evaluated through human assessment using the Robotic Social Attributes Scale (RoSAS) and Sensibleness and Specificity Average (SSA) metrics. Consequently, it supports the effective interpretation of children’s utterance intentions and enables natural verbal interactions, even in cases with syntactic incompleteness and mispronunciations.

Tactile sensors have been widely used and researched in various fields of medical and industrial applications. Gradually, they will be used as new input devices and contact sensors for interactive robots. If a tactile sensor is to be applied to various forms of human–machine interactions, it needs to be soft to ensure comfort and safety, and it should be easily customizable and inexpensive. The purpose of this study is to estimate 3D contact position of a novel image-based areal soft tactile sensor (IASTS) using printed array markers and multiple cameras. First, we introduce the hardware structure of the prototype IASTS, which consists of a soft material with printed array markers and multiple cameras with LEDs. Second, an estimation algorithm for the contact position is proposed based on the image processing of the array markers and their Gaussian fittings. A series of basic experiments was conducted and their results were analyzed to verify the effectiveness of the proposed IASTS hardware and its estimation software. To ensure the stability of the estimated contact positions a Kalman filter was developed. Finally, it was shown that the contact positions on the IASTS were estimated with a reasonable error value for soft haptic applications.