Autonomous learning of action-word semantics in a humanoid robot

Niehaus, Logan

Permalink

https://hdl.handle.net/2142/24151 Copy

Description

Title

Autonomous learning of action-word semantics in a humanoid robot

Author(s)

Niehaus, Logan

Issue Date

2011-05-25T14:57:30Z

Director of Research (if dissertation) or Advisor (if thesis)

Levinson, Stephen E.

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• language acquisition
• autonomous mental development
• cognitive robotics
• embodied cognition

Abstract

For creation of an artificial agent that is capable of using language naturally, models that only manipulate symbols or classify speech are ineffective. The semantic information which language conveys must be grounded in the agent’s complete sensorimotor experience. Typically, patterns from visual, auditory, and proprioceptive data streams which share the same conceptual cause are fused together in an associative memory at the core of the language model. Coupling of motor and auditory modalities, which is crucial for a large part of semantic understanding, presents a particularly difficult challenge. Words and actions both need models capable of capturing spatial and temporal structure, and training algorithms that can learn in a self-organizing, incremental fashion. Presented is a method for online learning of word and action lexicons based on the hidden Markov model. The model is then evaluated through action-word learning experiments implemented on a humanoid robot.

Graduation Semester

2011-05

Permalink

http://hdl.handle.net/2142/24151

Copyright and License Information

Copyright 2011 Logan Niehaus

Owning Collections