Back to search

NJIT

Data-driven learning for robot physical intelligence

Abstract

dc:description.abstract

The physical intelligence, which emphasizes physical capabilities such as dexterous manipulation and dynamic mobility, is essential for robots to physically coexist with humans. Much research on robot physical intelligence has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous manner, robot learning from human demonstration (LfD) has achieved great progress, but still has limitations handling dynamic skills and compound actions. In this dissertation, a composite learning scheme which goes beyond LfD and integrates robot learning from human definition, demonstration, and evaluation is proposed. This method tackles advanced motor skills that require dynamic time-critical maneuver, complex contact control, and handling partly soft partly rigid objects. Besides, the power of crowdsourcing is brought to tackle case-specific engineering problem in the robot physical intelligence. Crowdsourcing has demonstrated great potential in recent development of artificial intelligence. Constant learning from a large group of human mentors breaks the limit of learning from one or a few mentors in individual cases, and has achieved success in image recognition, translation, and many other cyber applications. A robot learning scheme that allows a robot to synthesize new physical skills using knowledge acquired from crowdsourced human mentors is proposed. The work is expected to provide a long-term and big-scale measure to produce advanced robot physical intelligence.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy in Computer Engineering - (Ph.D.)
Discipline thesis:degree_discipline
Electrical and Computer Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhao, Leidi
Contributors dc:contributor
  • Cong Wang
  • Edwin Hou
  • Lu Lu

Subjects

dc:subject × 9

Identifiers

dc:identifier.*
Repository record dc:identifier
https://digitalcommons.njit.edu/dissertations/1549

Chain of custody

source
Harvested from
NJIT
Base URL
digitalcommons.njit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Zhao, Leidi. Data-driven learning for robot physical intelligence. https://digitalcommons.njit.edu/dissertations/1549