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...
Main Author: | |
---|---|
Other Authors: | , , , |
Format: | Master's thesis |
Language: | eng |
Published: |
2025
|
Subjects: | |
Online Access: | https://jyx.jyu.fi/handle/123456789/102764 |