Author
Çelik, B., Ahmetoglu, A., Ugur, E., Öztop, Erhan
Publication Date
2023
Publication Place
-
IEEE
Type
Document
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
978-166547075-9
Record ID
fbb8f176-4dec-499b-bb73-fadeaf4ac0c4
Library Location
Computer Science
Date
2023
Notes
TÜBİTAK ; Osaka University ; New Energy and Industrial Technology Development Organization ; Japan Society for the Promotion of Science
Sample Text
Exploration and self-observation are key mechanisms of infant sensorimotor development. These processes are further guided by parental scaffolding to accelerate 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.
DOI
10.1109/ICDL55364.2023.10364374
