Botson: An Accessible and Low-Cost Platform for Social Robotics Research

TL;DR

Botson is a low-cost, accessible social robot platform powered by a large language model, designed to improve trust in AI-human interactions by conveying non-verbal social cues.

Contribution

The paper introduces Botson, a novel, affordable social robot platform utilizing LLMs to facilitate research in human-robot social interactions.

Findings

Botson effectively conveys non-verbal social cues.

The platform is low-cost and accessible for research.

Potential to improve trust in AI-human interactions.

Abstract

Trust remains a critical barrier to the effective integration of Artificial Intelligence (AI) into human-centric domains. Disembodied agents, such as voice assistants, often fail to establish trust due to their inability to convey non-verbal social cues. This paper introduces the architecture of Botson: an anthropomorphic social robot powered by a large language model (LLM). Botson was created as a low-cost and accessible platform for social robotics research.