@misc{oai:ir.soken.ac.jp:00003588,
 author = {奥野, 敬丞 and オクノ, ケイスケ and OKUNO, Keisuke},
 month = {2016-02-17, 2016-02-17},
 note = {This paper describes a stochastic framework for intelligent humanoid
robots, which can cooperate and interact with humans through integra-
tion of symbolic expressions and sensorimotor patterns. The research is
divided into 4 steps. Contributions of the each research step are: 1) an
estimation method of sensorimotor patterns of others without having pre-
defined user speciffic model in advance through interaction between self
and other, 2) a method to dynamically modify displaying motion pat-
terns and to bind the motions with symbol expressions according to per-
formance of human-learners, in order for conveying slight differences in
motions, where robotic system coaches humans motions, 3) analysis and
modeling of human-coaches' use of motions and symbolic expressions how
they change them dynamically according to learners performances, and
4) demonstration of the feasibility of the robotic motion coaching system,
which integrated the methods proposed in step 1) and 2), and the models
gained in step 3), through experiments of actual sport coaching tasks for
beginners resulted in improvements in motion learning.
In the Chapter 1, The main stream of robotics researches are introduced
as improvement in individual physical ability. Then, importance of in-
telligence of binding symbol expressions and unobservable sensorimotor
patterns, and intelligence to estimate the sensorimotor patterns from ob-
servable motions are discussed from interaction point of view.
In the Chapter 2, related works are introduced in various fields such
as Robotics, Conversation Analysis, Human-Agent Interaction, Skill and
Sports Science, and Anticipation of Intention of Others from neuroscience
and cognitive psychology point of view. Then, the chapter addresses chal-
lenges from the perspective of required functions for the research. After
the discussion of the approach for the resolution method, the Proto-symbol
Space method is introduced as a basic tool for the proposed methods.
The Chapter 3 describes an estimation method of sensorimotor patterns
of others from motion observation.
An approach is to bridge sensorimotor experience, or the Proto-symbol
Spaces, between the self and the other. The sensorimotor experience for
each are represented by the Proto-symbol Spaces for each in the research.
This approach would result in estimation error due to physical condition
diffierence between the self and the other. To clear this problem, a method
is proposed in order for adaptive acquisition of Proto-symbol Space of
other by sharing motion patterns and using open questions asking the
others' sensing status described by symbols. Simulation demonstrates
that it is possible to estimate sensorimotor patterns of others with 10-
20% errors, even when estimation target motions are not in database.
In the second half of the chapter, I discusses about a method to estimate
others' symbol conversion strategy from sensor patterns. The method uses
closed questions asking comparative evaluation of sets of shared motions.
The simulation demonstrates that the method can estimate the symbol
conversion strategy properly by sharing prepared sets of motions and using
the closed questions.
The Chapter 4 describes a proposing method for dynamic modification
of motion demonstration and for binding the motions with symbol ex-
pressions according to performance of human-learners. This method can
convey slight diffierences between learning target motions demonstrated by
a coach and motions performed by learners. Feasibility of the method is
demonstrated through experiments of actual sport coaching tasks for be-
ginners by using a robotic coaching system. The robotic system coaches
human-learners tennis forehand swing, by using emphatic motions and
adverbial expressions generated from the proposing method. The experi-
ments resulted in improvements in motion learning. However, it was not
possible to confirm whether either emphatic motions and/or adverbial
expressions is a contribution factor or not.
In the Chapter 5, I discuss about experiments for modeling how human-
coaches use emphatic motions and adverbial expressions. In the experi-
ments, human-coaches were asked to coach a robot-learner tennis forehand
swing, by using the emphatic motions and adverbial expressions. Analysis
of the results leads to models; two Adverbial Expression Use Models and
two Emphatic Motion Use Models.
In the Chapter 6, I attempt to integrate the methods proposed in Chapter
3 and 4, and the models obtained in Chapter 5. At first, I discuss about
integration of the robotic motion coaching system from Chapter 4 and
the models gained from Chapter 5. I then discuss a possible integration
of the method to estimate sensorimotor patterns from the Chapter 3, the
robotic motion coaching system from Chapter 4, and the models gained
from Chapter 5.
I demonstrated the feasibility of the robotic motion coaching system inte-
grated with one of the EMU-Model and one of the AEU-Model, by experi-
ments of a tennis forehand swing coaching task for beginners. I confirmed
that the EMU-Model and the AEU-Model contribute to improvement in
motion learning. It is demonstrated that value output by the EMU-Model
is a contribution factor by a statistic analysis. I also found there is an
improvement in motion learning when using the AEU-Models. However,
even though I found positive contribution of the adverbial expressions for
the improvement in motion learning, it is not able to decide whether the
adverbial expressions chosen by using the AEU-Model is a contribution
factor or not.
The thesis is then concluded in the Chapter 7., 総研大甲第1555号},
 title = {Cooperation and Interaction between Human and Humanoid Robots through Integration of Symbolic Expressions and Sensorimotor Patterns},
 year = {}
}