start-ver=1.4 cd-journal=joma no-vol=3 cd-vols= no-issue= article-no= start-page=1499 end-page=1504 dt-received= dt-revised= dt-accepted= dt-pub-year=2002 dt-pub=20028 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Control of hyper-redundant robot using QDSEGA en-subtitle= kn-subtitle= en-abstract= kn-abstract=

We consider a flexible autonomous system. To realize the system, we employ a hyper-redundant system (a flexible hardware system) and reinforcement learning controller "QDSEGA" (Q-learning with structuring exploration space based on genetic algorithm) which is a flexible software system. In this paper we apply QDSEGA for controlling of the hyper-redundant robot. To demonstrate the effectiveness, a task of acquisition of locomotion patterns is applied to a multi-legged formation and a snake-like formation, from which an effective locomotion is obtained.

en-copyright= kn-copyright= en-aut-name=ItoKazuyuki en-aut-sei=Ito en-aut-mei=Kazuyuki kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=MatsunoFumitoshi en-aut-sei=Matsuno en-aut-mei=Fumitoshi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= affil-num=1 en-affil= kn-affil=Okayama University affil-num=2 en-affil= kn-affil=Tokyo Institute of Technology en-keyword=Hyper-redundant systems kn-keyword=Hyper-redundant systems en-keyword=Q-learning kn-keyword=Q-learning en-keyword=Reinforcement learning kn-keyword=Reinforcement learning en-keyword=Genetic Algorithm kn-keyword=Genetic Algorithm en-keyword=QDSEGA kn-keyword=QDSEGA END start-ver=1.4 cd-journal=joma no-vol=3 cd-vols= no-issue= article-no= start-page=1724 end-page=1727 dt-received= dt-revised= dt-accepted= dt-pub-year=2002 dt-pub=20028 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Recognition of elastic characteristic of object using pneumatic parallel manipulator en-subtitle= kn-subtitle= en-abstract= kn-abstract=

The goal of this study is to develop a mechanical system that can display elastic characteristic of an object aiming at the application in the field of virtual reality. A pneumatic parallel manipulator is introduced as a driving mechanism, which consequently brings the capability of minute force displaying property owing to the air compressibility. A compliance control system without using force/moment sensor is constructed by introducing a disturbance observer, and a compliance display scheme is proposed. The validity of the proposed scheme is verified experimentally.

en-copyright= kn-copyright= en-aut-name=TakaiwaMasahiro en-aut-sei=Takaiwa en-aut-mei=Masahiro kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=NoritsuguToshiro en-aut-sei=Noritsugu en-aut-mei=Toshiro kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= en-aut-name=FujieKenichi en-aut-sei=Fujie en-aut-mei=Kenichi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=3 ORCID= affil-num=1 en-affil= kn-affil=Okayama University affil-num=2 en-affil= kn-affil=Okayama University affil-num=3 en-affil= kn-affil=Okayama Univeristy en-keyword=compliance control kn-keyword=compliance control en-keyword=force feedback kn-keyword=force feedback en-keyword=manipulators kn-keyword=manipulators en-keyword=observers kn-keyword=observers en-keyword=position control kn-keyword=position control en-keyword=virtual reality kn-keyword=virtual reality END start-ver=1.4 cd-journal=joma no-vol=3 cd-vols= no-issue= article-no= start-page=1409 end-page=1410 dt-received= dt-revised= dt-accepted= dt-pub-year=2002 dt-pub=20028 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=A new method for 3-D shape measurement and surface reflectance of an object with rangefinder en-subtitle= kn-subtitle= en-abstract= kn-abstract=

An object for computer graphics application requires the following two information: the three dimensional (3D) shape and surface reflectance property of the object. We proposed a 3D shape and surface reflectance measurement system using the new sensor, which can detect the incidence position and the angle of the light simultaneously. Experimental results successfully demonstrate the efficacy of the method.

en-copyright= kn-copyright= en-aut-name=NaritaDaisuke en-aut-sei=Narita en-aut-mei=Daisuke kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=OhtaniKozo en-aut-sei=Ohtani en-aut-mei=Kozo kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= en-aut-name=BabaMitsuru en-aut-sei=Baba en-aut-mei=Mitsuru kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=3 ORCID= affil-num=1 en-affil= kn-affil=Okayama University affil-num=2 en-affil= kn-affil=Okayama University affil-num=3 en-affil= kn-affil=Okayama University en-keyword=laser rangefinder kn-keyword=laser rangefinder en-keyword=3-D shape and surface reflectance of an object kn-keyword=3-D shape and surface reflectance of an object END start-ver=1.4 cd-journal=joma no-vol=3 cd-vols= no-issue= article-no= start-page=1588 end-page=1591 dt-received= dt-revised= dt-accepted= dt-pub-year=2002 dt-pub=20028 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Modeling uncertainty of flexible structures with unknown high-order modal parameters - a geometric characterization of frequency responses en-subtitle= kn-subtitle= en-abstract= kn-abstract=

A control-oriented uncertainty modeling on frequency domain is presented for a class of spectral systems with unknown high-order modal parameters. At any user-specified frequency, the set of all the frequency responses of the feasible systems is characterized on a complex plane in terms of the convex bull of several circle segments, where the system is said to be feasible if partial modal parameters are given and some other conditions are satisfied by the unknown parameters. We emphasize that such a characterization enables us to quantify the least upper bounds of errors for any nominal models, and to develop further efficient results using some additional information. It is shown that, the DC gain information of the system reduces the size of the feasible set to the half or smaller for all frequencies. The efficiency of the presented scheme is demonstrated by a simple example of ideal flexible beam.

en-copyright= kn-copyright= en-aut-name=ImaiJun en-aut-sei=Imai en-aut-mei=Jun kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= affil-num=1 en-affil= kn-affil=Okayama University en-keyword=feasible sets kn-keyword=feasible sets en-keyword=Kelvin-Voigt damping kn-keyword=Kelvin-Voigt damping en-keyword=dc gain kn-keyword=dc gain END start-ver=1.4 cd-journal=joma no-vol=3 cd-vols= no-issue= article-no= start-page=1609 end-page=1612 dt-received= dt-revised= dt-accepted= dt-pub-year=2002 dt-pub=20028 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Evolutionary constitution of game player agents en-subtitle= kn-subtitle= en-abstract= kn-abstract=

In this paper, we propose a constitution method of game player agent that adopts a neural network as a state evaluation function for the game player, and evolves its weights and structure by evolutionary strategy. In this method, we attempt to acquire a better state evaluation function by evolving weights and structure simultaneously.

en-copyright= kn-copyright= en-aut-name=HandaHisashi en-aut-sei=Handa en-aut-mei=Hisashi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=HoriuchiTadashi en-aut-sei=Horiuchi en-aut-mei=Tadashi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= affil-num=1 en-affil= kn-affil=Okayama University affil-num=2 en-affil= kn-affil=Matsue National College of Technology en-keyword=Evolutionary Computations kn-keyword=Evolutionary Computations en-keyword=State Evaluation Function kn-keyword=State Evaluation Function en-keyword=Neural Networks kn-keyword=Neural Networks END