PERFORMANCE-DERIVED BEHAVIOR VOCABULARIES: DATA-DRIVEN ACQUISITION OF SKILLS FROM MOTION

Author:

JENKINS ODEST CHADWICKE1,MATARIĆ MAJA J.1

Affiliation:

1. Robotics Research Laboratory, Center for Robotics and Embedded Systems, Computer Science Department, University of Southern California, 941 West 37th Place, SAL 228, Los Angeles, CA, 90089, USA

Abstract

Control for and interaction with humanoid robots is often restrictive due to limitations of the robot platform and the high dimensionality of controlling systems with many degrees of freedom. We focus on the problem of providing a "skill-level interface" for a humanoid robot. Such an interface serves as (i) a modular foundation for structuring task-oriented control, (ii) a parsimonious abstraction of motor-level control (e.g. PD-servo control), and (iii) a means for grounding interactions between humans and robots through common skill vocabularies. Our approach to constructing skill-level interfaces is two-fold. First, we propose a representation for a skill-level interface as a "behavior vocabulary," a repertoire of modular exemplar-based memory models expressing kinematic motion. A module in such a vocabulary encodes a flow field (or gradient field) in joint angle space that describes the "flow" of kinematic motion for a particular skill-level behavior, enabling prediction from a given kinematic configuration. Second, we propose a data-driven method for deriving behavior vocabularies from time-series data of human motion using spatio-temporal dimension reduction and clustering. Results from evaluating an implementation of our methodology are presented along with the application of derived behavior vocabularies as predictors towards on-line humanoid trajectory formation and off-line motion synthesis.

Publisher

World Scientific Pub Co Pte Lt

Subject

Artificial Intelligence,Mechanical Engineering

Reference27 articles.

1. Intelligence without representation

2. Behaviour-based control: examples from navigation, learning, and group behaviour

3. Verbs and adverbs: multidimensional motion interpolation

4. M. J. Matarić, Imitation in Animals and Artifacts, eds. C. Nehaniv and K. Dautenhahn (MIT Press, 2002) pp. 392–422.

Cited by 39 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A primitive-based representation of dance: modulations by experience and perceptual validity;Journal of Neurophysiology;2023-11-01

2. Annotating Motion Primitives for Simplifying Action Search in Reinforcement Learning;IEEE Transactions on Emerging Topics in Computational Intelligence;2022-10

3. Representing, learning, and controlling complex object interactions;Autonomous Robots;2018-04-30

4. From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning;Journal of Artificial Intelligence Research;2018-01-31

5. Goal-directed robot manipulation through axiomatic scene estimation;The International Journal of Robotics Research;2017-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3