Extracting Motion Skills from Expert's Proficient Operation Records Using Recurrent Neural Network

Sawaragi, Tetsuo; Kudoh, Takahiro; Ozawa, Shogo

doi:10.1016/s1474-6670(17)57114-1

Cited by 6 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there have already been some studies of learning systems in man-machine cooperation [1] [2], most ofthem only focused on short period operations in which the coop-0-7803-7860-1/03/$17.00 0 2003 IEEE 162 2) Humanoid Robotics Institute (HRI), Waseda University 3-4-1, Okubo, Shinjuku-kq Tokyo, 169-8555, Japan E-mail: {ogata, sugano) @paradise.mech.wased.ac.jp eration relation between the person and the machine is organized. Therefore, they did not discuss important aspects such as the mutual interaction after the relation organization, the collapse and modification of the relation, and the long process of development from a beginner to an expert.…”

Section: Introductionmentioning

confidence: 99%

Interactive learning in human-robot collaboration

Ogata

Masago²,

Sugano³

et al.

Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)

View full text Add to dashboard Cite

In this papel: we investigated interactive learning between humon subjects and robot experimentally, and its essential characteristics ore examined using the dynamical systems approach. Our research concentrated on the navigation system of a specially developed humanoid robot called Robovie and seven human subjects wliose eyes were covered, making them dependent on the robot f o r directions. We compared the usual feed-forword neural network (FFNN) without recursive connections and the recurrent neural network (R"). Although theperformances obtained with both the RNN and the FFNN improved in the early stages of learning, as the subject changed the operation by learning on its own. all performances gradually become unstable and failed. Results of a questionnaire given to the subjects confirmed that the FFNN gives better mental impressions, especially from the aspect of operabili@. When the robot used a consolidation-learning algorithm using the rehearsal outputs of the RNN, the perfarmonce improved even when interactive learning continued for a long time.The questionnaire results then also confirmed that the subject's mental impressions of the R" improved significantly. The dynamical systems analysis of RNNs support these differences.

show abstract

Section: Introductionmentioning

confidence: 99%

Interactive learning in human-robot collaboration

Ogata

Masago²,

Sugano³

et al.

Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)

View full text Add to dashboard Cite

show abstract

Innovations in Applied Artificial Intelligence

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Modular neural networks have the possibility of overcoming common scalability and interference problems experienced by fully connected neural networks when applied to large databases. In this paper we trial an approach to constructing modular ANN's for a very large problem from CEDAR for the classification of handwritten characters. In our approach, we apply progressive task decomposition methods based upon clustering and regression techniques to find modules. We then test methods for combining the modules into ensembles and compare their structural characteristics and classification performance with that of an ANN having a fully connected topology. The results reveal improvements to classification rates as well as network topologies for this problem.

show abstract

Analysis of task morphologies for networking behavioral skills via virtual reality

Sawaragi

Horiguchi²

Proceedings. IEEE 8th International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises (WET ICE'9

View full text Add to dashboard Cite

This paper presents a method f o r detecting invariant task structures that are commonly shared by the two different actors (i.e., a human performer and a mobile robot), who have different perception-acting capabilities. W e call such a property of having common structures as morphology of task structures, and we discuss about how this property functions well f o r the design of a mobile robot teleoperation system via a VRbased (i.e., virtual reality based) interface.

show abstract

Extracting Motion Skills from Expert's Proficient Operation Records Using Recurrent Neural Network

Cited by 6 publications

References 6 publications

Interactive learning in human-robot collaboration

Interactive learning in human-robot collaboration

Innovations in Applied Artificial Intelligence

Analysis of task morphologies for networking behavioral skills via virtual reality

Contact Info

Product

Resources

About