Top / 腥倶荀

腥倶荀 ≪(No.3)

茯ャ紫咲ｃ †

↑

腱糸 †

↑

荀恰謙膤糸冴ャ＞散絎御帥若括 †

篋咲鐚医茵綽鐚蕭罨≦荀ュ鐚怨墾絎у熊帥鐚
茯睡榊憗с鐚鐚篋羝筝順紊絎医с鴻倶膓牙腟薑
筝純с鐚倶с＞散荀馹с鐚
腥吟с鐚絲乗院絎筝э医紊絲障鐚鐚鐚綣莨若帥у上
鐚鐚CPG＜帥紊眼у上緇ゆ糸膺肢吟篋羝≪罅鐚絖
九勝鐚3潟ャ若帥潟荵∫九勝綽鐚
  • Toshiyuki Kondo, Takanori Somei, Koji Ito: "A predictive constraints selection model for periodic motion pattern generation", Proceedings of 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'04), TP1-K2, pp.975-980, Sendai, Japan, (2004)

#ref(): File not found: "CPG-PM.gif" at page "腥倶荀"

#ref(): File not found: "crank.gif" at page "腥倶荀"

↑

若遵堺罕罧級綣桁絖膺 †

篋咲違帥若潟絖膺鐚с峨ヨ障鐚医荅茵э倶膓
臂｢膣≪鐚絖膺с鐚鐚ｻ腟薑絖膺号篏咲遵鐚篋
莖鐚 ョ医筝ц膓荀羆緇腱糸茵絖膺鴻腓
筝鐚
綽絖J.Piaget逸篋咲茯ャ脂絖膺罘罕鐚鐚鐚鐚域宴∝ャヨ罸莠鐚
鐚鐚鐚筝眼翫鐚ヨ罕篏紊眼鐚膵違菴咲鐚腥吟с鐚ョ医
緇腱糸茵絖膺箴蕁鐚鐚鐚鐚九勝鐚neural network鐚NN鐚綣桁絖膺鐚TD羈鐚у膺
鐚鐚鐚鐚絖膺緇NN茵荀(Schema)遵冴鐚ャョ医絖膺絖膺＞散
筝э絖膺蕭с鐚鐚
  • 菴ゆ鋈, 篌ょ綵, 篌ゅ: "若遵堺罕緇腱糸罧級茵絖膺", 荐羝九勝絖篌茫, Vol.40, No.3, (2004)

    #ref(): File not found: "roundtrip-results.gif" at page "腥倶荀"

    #ref(): File not found: "incremental.gif" at page "腥倶荀"

  • 絎薑
↑

篋咲-若吾с潟娯綽膤祉膓膓ゃ潟帥激с潟絎 †

篋咲篋阪轡筝睡綽ц蟹綽с鐚菴綛器綽腮
＜冴鐚若吾с潟眼緇篋咲絲障荀с茯茘ゃゃ鐚
鐚篋咲若吾с潟娯綽膓膓娯篏筝罨с鐚憟吟с篋咲眼吾莢紊с
鐚鐚腥吟с篋咲若吾с潟≫膓膓若吾с潟鴻罘
＞散茹ｆ腟鐚￥篋咲蕋純＜冴茹ｆ鐚蕋純娯篏荀
膀ゃ絲鐚
  • 菴ゆ鋈, ユ乗箙, 篌ゅ: "篋咲-若吾с潟娯綽膤祉膓膓娯篏絎憗罘醇＞散", 若吾с潟若激с鐚激潟吾2003茗羲茫, pp.432-437, 羞∴君紊∵伾初篌茘医, 球昆, (2003)
↑

荐膊≪ †

↑

峨recruitャ綣桁絖膺羈 †

茲逸蕭罨≦鐚祉潟球ュ腱糸鐚怨篏鐚逸若違帥鴻
緇峨荅帥鐚鐚祉潟泣若≪若翠≫鐚＜潟潟若鐚NGnetц篌
鐚NGNetс倶腥咲莇罐篏у蚊違鐚鐚倶蚊膣違逸阪∽逸RBF鐚
違紊с荐膊莢激紜鐚筝刻膕蚊鐚綽荀倶蚊с絖膺蚊障鐚
腥吟с鐚NGnetActor-Critic綣桁絖膺冴ャ茵絖膺茵鐚筝倶駕RBF
紊с鐚荅箴＜峨recruitmentワevolutionary recruitment strategy鐚罅鐚
  • Toshiyuki Kondo, Koji Ito: "A Study on Designing Robot Controllers by Using Reinforcement Learning with Evolutionary State Recruitment Strategy", Lecture Notes in Computer Science 3141 -Biologically Inspired Approaches to Advanced Information Technology: First International Workshop BioADIT 2004 Lausanne Switzerland January 29-30 2004 Revised Selected Papers, Springer -Verlag Berlin Heideberg, pp.244-257, (2004)
  • Toshiyuki Kondo, Koji Ito: "A Reinforcement Learning with Evolutionary State Recruitment Strategy for Autonomous Mobile Robots Control", Journal of Robotics and Autonomous Systems, vol.46, no.2, pp.111-124 Elsevier, (2004)
  • 菴ゆ鋈, 篌ゅ: "峨recruitmentャ綣桁絖膺緇腱糸九勝荐荐", 荐羝九勝絖篌茫, Vol.39, No.9, pp.857-864, (2003)

    #ref(): File not found: "pegpush.gif" at page "腥倶荀"

    #ref(): File not found: "push-lo-fr-loop.gif" at page "腥倶荀"

↑

綛合完榊≪ャ若≪吾ャ若帥≪緇腱糸綵∽紫腟膤祉演峨綵∽ †

LEGO(TM) Robot Project targets evolving a suitable body shape and its nervous system (i.e. artificail 
neural network-based controller) for a light seeking robot. Using a grammar-based gene encoding method,
we can save computational resources (length of genotype), in other words, it enables to evolve much 
faster than ordinary coding methods. In the current situation, I revised "dynamically-rearranging 
neural networks" method much more useful. For example, instead of each synapse, each neuron has its 
own NM interpretation table, and then each synapse originated from same neuron uses the interpretation 
table. In addition, effective area of each NM is restricted within some small range (this is genetic 
parameter). It is expected this enables the emerged network to have more complicated structure and 
flexibility, redundancy. In this study, we are concerned with the interaction between three specific 
adaptive systems: evolutionary change by species, ontogenic change by an individual as it matures; and
learning by the individual as it acquires experience. We present experiments in which a population of
individuals, each grown from a single cell according to its particular genome, into an adult form 
corresponding to a simple robot body and NNet which allows it to function in and learn about its 
environment.
  • Submitted to 7th Joint Symposium on Neural Computation 7 Apr 00
↑

膩罘純腑腟莊≪ †

Recently, Evolutionary Robotics approach has been attracting a lot of concerns in the field of robotics
and artificial life. In this approach, neural networks are widely used to construct controllers for 
autonomous mobile agents, since they intrinsically have generalization, noise-tolerant abilities and so 
on. However, the followings are still open questions; 1) gap between simulated and real environments, 
2) evolutionary and learning phase are completely separated, and 3) conflict between stability and 
evolvability/adaptability. In this article, we try to overcome these problems by incorporating the 
concept of dynamic rearrangement function of biological neural networks with the use of neuromodulators.
  • 菴ゆ鋈, 渇腴紊, 綏罔, Peter Eggenberger: "峨ｃ鴻九勝ユс絎" - 膩罘純腑腟莊≪罅 -, 荐羝九勝絖篌茫, Vol.35, No.11, pp.1407-1414, (1999)
↑

篏膤祉冴ャ窮阪綽≪ †

Conventional arti.cial intelligent (AI) system have been criticized for its brittleness under 
hostile/dynamic changing environments. Therefore, recently much attention has been focused on the 
reactive planning systems such as behavior-based AI. However, in the behavior-based AI approaches, how 
to construct a mechanism that realizes adequate arbitration among competence modules is still an open 
question. In this paper, we propose a new decentralized consensus-making system inspired from the 
biological immune system. And we apply our proposed method to behavior arbitration of an autonomous 
mobile robot as a practical example. To verify the feasibility of our method, we carry out some 
experiments.In addition, we propose an adaptation mechanism, and try to construct a suitable immune 
network for adequate action selection.
  • 菴ゆ鋈, 渇腴紊, 綏罔: "篏膤祉緇腱糸茵茯水罘罕窮榊≪筝羈", 荐羝九勝絖篌茫, Vol.35, No.2, pp.262-270, (1999)