Towards scalable robotic intervention of children with Autism Spectrum Disorder using LLMs

In this paper, we propose a social robot capable of verbally interacting with children with Autism Spectrum Disorder (ASD). This communication is meant to teach perspective-taking using text generated using a Large Language Model (LLM) pipeline. The social robot NAO acts as a stimulator (verbally describes a social situation and asks a question), prompter (presents three options to choose from), and reinforcer (praises when the answer is correct). For the role of the stimulator, the social situation, questions, and options are generated using our LLM pipeline. We compare two approaches: GPT-2 + BART and GPT-2 + GPT-2, where the first GPT-2 common between the pipelines is used for unsupervised social situation generation. We use the SOCIALIQA dataset to fine-tune all of our LLM pipelines. We found that the GPT-2 + BART pipeline had a better BERTscore for generating the questions and the options by combining their individual loss functions. This observation was also consistent with the human evaluations. Lastly, the unsupervised generation of social situations was visualized using T-SNE plots, and the entire pipeline was evaluated for appropriateness for children with ASD by human experts.

Social Impressions of the NAO Robot and its Impact on Physiology

The social applications of robots possess intrinsic challenges with respect to social paradigms and heterogeneity of different groups. These challenges can be in the form of social acceptability, anthropomorphism, likeability, past experiences with robots etc. In this paper, we have considered a group of neurotypical adults to describe how different voices and motion types of the NAO robot can have effect on the perceived safety, anthropomorphism, likeability, animacy, and perceived intelligence of the robot. In addition, prior robot experience has also been taken into consideration to perform this analysis using a one-way Analysis of Variance (ANOVA). Further, we also demonstrate that these different modalities instigate different physiological responses in the person. This classification has been done using two different deep learning approaches, 1) Convolutional Neural Network (CNN), and 2) Gramian Angular Fields on the Blood Volume Pulse (BVP) data recorded. Both of these approaches achieve better than chance accuracy 25% for a 4 class classification.