Large Language Model Driven Context-Aware Robotic Manipulation via Human Demonstration

This thesis introduces a novel zero-shot adaptive imitation learning framework that facilitates the power of foundational models to enable robots to perform context-aware manipulation tasks only from passive video demonstrations. This architecture is inspired by the human cognitive adaptability meta...

Full description

Bibliographic Details
Main Author: Hossain, Iftekher
Other Authors: Informaatioteknologian tiedekunta, Faculty of Information Technology, Jyväskylän yliopisto, University of Jyväskylä
Format: Master's thesis
Language:eng
Published: 2025
Subjects:
Online Access: https://jyx.jyu.fi/handle/123456789/102764