Multimodal Sensing and Machine Learning to Compare Printed and Verbal Assembly Instructions Delivered by a Social Robot

In this paper, we compare a manual assembly task communicated to workers using both printed and robot-delivered instructions. The comparison was made using physiological signals (blood volume pulse (BVP) and electrodermal activity (EDA)) collected from individuals during an experimental study. In addition, we also collected responses of individuals using the NASA Task Load Index (TLX) survey. Furthermore, we mapped the collected physiological signals to the responses of participants for NASA TLX to predict their workload. For both the classification problems, we compare the performance of Convolutional Neural Networks (CNNs) and Long-Short-Term Memory (LSTM) models. Results show that for our CNN-based approach using multimodal data (both BVP and EDA) gave better results than using just BVP (approx. 8.38% more) and EDA (approx 20.49% more). Our LSTM-based model too had better results when we used multimodal data (approx 8.38% more than just BVP and 6.70% more than just EDA). Overall, CNNs performed better than LSTMs for classifying physiologies for paper vs robot-based instruction by 7.72%. The CNN-based model was able to give better classification results (approximately 17.83% more on an average across all responses of the NASA TLX) within a few minutes of training compared to the LSTM-based models.

Personalized Speech Emotion Recognition in Human-Robot Interaction using Vision Transformers

Emotions are an essential element in verbal communication, so understanding individuals' affect during a human-robot interaction (HRI) becomes imperative. This paper investigates the application of vision transformer models, namely ViT (Vision Transformers) and BEiT (BERT Pre-Training of Image Transformers) pipelines, for Speech Emotion Recognition (SER) in HRI. The focus is to generalize the SER models for individual speech characteristics by fine-tuning these models on benchmark datasets and exploiting ensemble methods. For this purpose, we collected audio data from different human subjects having pseudo-naturalistic conversations with the NAO robot. We then fine-tuned our ViT and BEiT-based models and tested these models on unseen speech samples from the participants. In the results, we show that fine-tuning vision transformers on benchmark datasets and and then using either these already fine-tuned models or ensembling ViT/BEiT models gets us the highest classification accuracies per individual when it comes to identifying four primary emotions from their speech: neutral, happy, sad, and angry, as compared to fine-tuning vanilla-ViTs or BEiTs.

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.