Developmental Scaffolding with Large Language Models

TL;DR

This paper explores using large language models as scaffolding agents in robotic learning, demonstrating that GPT-3.5 can accelerate structure discovery but struggles with understanding different object affordances.

Contribution

It introduces a novel application of LLMs as scaffolding agents in robotics, showing their potential and limitations without fine-tuning.

Findings

GPT-3.5-guided learning accelerates structure discovery

LLMs struggle with understanding diverse object affordances

LLMs can serve as moderate scaffolding agents in robotics

Abstract

Exploratoration and self-observation are key mechanisms of infant sensorimotor development. These processes are further guided by parental scaffolding accelerating skill and knowledge acquisition. In developmental robotics, this approach has been adopted often by having a human acting as the source of scaffolding. In this study, we investigate whether Large Language Models (LLMs) can act as a scaffolding agent for a robotic system that aims to learn to predict the effects of its actions. To this end, an object manipulation setup is considered where one object can be picked and placed on top of or in the vicinity of another object. The adopted LLM is asked to guide the action selection process through algorithmically generated state descriptions and action selection alternatives in natural language. The simulation experiments that include cubes in this setup show that LLM-guided (GPT3.5-guided) learning yields significantly faster discovery of novel structures compared to random exploration. However, we observed that GPT3.5 fails to effectively guide the robot in generating structures with different affordances such as cubes and spheres. Overall, we conclude that even without fine-tuning, LLMs may serve as a moderate scaffolding agent for improving robot learning, however, they still lack affordance understanding which limits the applicability of the current LLMs in robotic scaffolding tasks.