Developmental Scaffolding with Large Language Models

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.

To appear in IEEE Transactions on Robotics ©IEEE2023

References in corpus (12)

• Training language models to follow instructions with human feedback
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• LLaMA: Open and Efficient Foundation Language Models
• PaLM: Scaling Language Modeling with Pathways
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• PaLM-E: An Embodied Multimodal Language Model
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning
• A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?
• Semantic Exploration from Language Abstractions and Pretrained Representations
• AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot Manipulation
• LLM-BRAIn: AI-driven Fast Generation of Robot Behaviour Tree based on Large Language Model