Robot-supported interventions for joint attention (JA) in autistic children have shown encouraging outcomes, yet most remain confined to stationary robots in indoor settings, limiting opportunities for skill generalization and broader developmental benefits. We introduce an intervention that employs a quadruped robot dog as a peer-like partner for JA training across both indoor and outdoor environments. In this intervention, the robot dog directs children’s attention to distributed targets in the environment and initiates JA trials. A four-week pre-post exploratory study with six autistic children demonstrated improvements in JA performance and indications of transfer to daily social communication. Spontaneous behaviors such as motor imitation (crawling) and novel social interactions with the robot also emerged, suggesting potential for broader developmental gains. These findings provide initial evidence for the efficacy of mobile robot-supported JA interventions in naturalistic contexts and offer implications for future design.

Children with high-functioning autism (HFA) often face challenges in emotional recognition and expression, leading to emotional distress and social difficulties. Conversational agents developed for HFA children in previous studies show limitations in children's learning effectiveness due to the conversational agents’ inability to dynamically generate personalized and contextual content. Recent advanced generative Artificial Intelligence techniques, with the capability to generate substantial diverse and high-quality texts and visual content, offer an opportunity for personalized assistance in emotional learning for HFA children. Based on the findings of our formative study, we integrated large language models and text-to-image models to develop a tool named EmoEden supporting children with HFA. Over a 22-day study involving six HFA children, it is observed that EmoEden effectively engaged children and improved their emotional recognition and expression abilities. Additionally, we identified the advantages and potential risks of applying generative AI to assist HFA children in emotional learning.

Text entry in virtual reality (VR) often faces challenges in terms of efficiency and task loads. Prior research has explored various solutions, including specialized keyboard layouts, tracked physical devices, and hands-free interaction. Yet, these efforts often fall short of replicating the efficiency of real-world text entry, or introduce additional spatial and device constraints. This study leverages the extensive capabilities of large language models (LLMs) in context perception and text prediction to enhance text entry efficiency by reducing users’ manual keystrokes. Three LLM-assisted text entry methods - Simplified Spelling, Content Prediction, and Keyword-to-Sentence Generation - are introduced, aligning with user cognition and the contextual predictability of English text at word, grammatical structure, and sentence levels. Through user experiments encompassing various text entry tasks on an Oculus-based VR prototype, these methods demonstrate a 16.4%, 49.9%, 43.7% reduction in manual keystrokes, translating to efficiency gains of 21.4%,74.0%, 76.3%, respectively. Importantly, these methods do not increase manual corrections compared to manual typing, while significantly reducing physical, mental, and temporal loads and enhancing overall usability. Long-term observations further reveal users’ strategies for using these LLM-assisted methods, showing that users’ proficiency with the methods can reinforce their positive effects on text entry efficiency.