A Unified Knowledge Representation System for Robot Learning and Dialogue |
Posted on:2017-10-04 | Degree:M.S | Type:Thesis |
University:University of California, Los Angeles | Candidate:Shukla, Nishant | Full Text:PDF |
GTID:2448390005460415 | Subject:Computer Science |
Abstract/Summary: | |
To allow wide-spread adoption of consumer robotics, robots must be able to adapt to their environment by learning new skills and communicating with humans. Each chapter explains a contribution to achieve this goal. Chapter One covers a stochastic And-Or knowledge representation framework for robotic manipulations. Chapter Two further expands this established system for robustly learning from perception. Chapter Three unifies perception with natural language for a joint real-time processing of information. We've successfully tested the generalizability and faithfulness of our robotic knowledge acquisition and inference pipeline. We present proof of concepts in each of the three chapters. |
Keywords/Search Tags: | Chapter |
|
Related items |