KOBAYASHI Hiroaki 小林博明

Researcher Number	60130811
Other IDs
External Links
Affiliation (based on the past Project Information) *help	2009 – 2011: Meiji University, 理工学部, 教授 2003 – 2005: 明治大学, 理工学部, 教授 1997 – 2000: 明治大学, 理工学部, 教授
Review Section/Research Field	Principal Investigator Intelligent mechanics/Mechanical systems / Intelligent mechanics/Mechanical systems
Keywords	Principal Investigator FPGA / GA / NEURAL NETWORK CONTROL / JOINT STIFFNESS / ニューラルネットワーク制御 / 関節剛性 / 腱駆動 / STRUCTURAL ANALYSIS / BIPED ROBOT / POSITION HYBRID CONTROL … More / FORCE / TENDON / ZMP制御 / 厳密な入出力線形化法 / 関節空間直交化法 / 腱駆動ロボット機構 / 機構解析 / 適応制御 / 厳密な入出力線形化 / 位置。力ハイブリッド制御 / 強度計算 / 非線形弾性テンショナー / 腰軌道の生成 / 腱駆動2足歩行ロボット / 位置・力ハイブリット制御 / 構造解析 / 二足歩行ロボット / ニュートラルネットワーク制御 / 位置・力ハイブリッド制御 / ROBOT SYSTEM / MULTI AGENT / SET-POINT CONTROL / INPUT-OUTPUT LINEARIZATION / REDUNDANT TENDONS / TENDON-DRIVEN / 知的制御 / 関節剛性調節 / 冗長性 / 腱駆動ロボットアーム / 筋電位 / ゴニオメータ / ロボット / 非線形弾性 / リアプノフ安定性 / 強化学習 / 適応制御 / ロボットハンド / ロボットシステム / マルチエージェント / ニューラルネット制御 / 定値制御 / 入出力線形化 / 冗長腱 / 知能ロボティクス / 知能ロボティックス / ロボティックス / 機械学習 / 制御工学 / 知能ロボット / 機械知能 Less

Reinforcement Learning of Action Strategies and Joint Stiffness of Tendon-driven Biped RobotPrincipal Investigator
- Principal Investigator
  
  KOBAYASHI Hiroaki
- Project Period (FY)
  2009 – 2011
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Intelligent mechanics/Mechanical systems
- Research Institution
  Meiji University
INTELLIGENT CONTROL OF TENDON-DRIVEN ROBOTIC MECHANISMS.Principal Investigator
- Principal Investigator
  
  KOBAYASHI Hiroaki
- Project Period (FY)
  2003 – 2005
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Intelligent mechanics/Mechanical systems
- Research Institution
  SCHOOL OF SCIENCE AND TECHNOLOGY, MEIJI UNIVERSITY
DEVELOPMENT OF A ROBOTIC ARM DRIVEN WITH REDUNDANT TENDONS TO WORK COOPERATIVELY WITH HUMANS.Principal Investigator
- Principal Investigator
  
  KOBAYASHI Hiroaki
- Project Period (FY)
  1997 – 2000
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Intelligent mechanics/Mechanical systems
- Research Institution
  MEIJI UNIVERSITY

All 2012 2011 2010 2009 2006 2005 2004 2003

All Journal Article Presentation

[Journal Article] Evaluation of the Improved Penalty Avoiding Rational Policy Making Algorithm in Real World Environment2012
- Author(s)
  Kazuteru Miyazaki, Masaki Itou, Hiroaki Kobayashi
- Journal Title
  
  Lecture Notes in Computer Science
  
  Volume: 7196 Pages: 270-280
- DOI
  10.1007/978-3-642-28487-8_28
- ISBN
  9783642284861, 9783642284878
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot2012
- Author(s)
  Seiya Kuroda, Kazuteru Miyazaki and Hiroaki Kobayashi
- Journal Title
  
  Lecture Notes in Computer Science
  
  Volume: Vol.7188 Pages: 297-308
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] Evaluation of the Improved Penalty Avoiding Rational Policy Making Algorithm in Real World Environment2012
- Author(s)
  Kazuteru Miyazaki, Masaki Itou, and Hiroaki Kobayashi
- Journal Title
  
  Lecture Notes in Computer Science
  
  Volume: Vol.7196 Pages: 270-280
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot2012
- Author(s)
  Seiya Kuroda, Kazuteru Miyazaki, Hiroaki Kobayashi
- Journal Title
  
  Lecture Notes in Computer Science
  
  Volume: 7188 Pages: 293-308
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] Threshold Learning in the Improved Penalty Avoiding Rational Policy Marking Algorithm2010
- Author(s)
  Kazuteru Miyazaki, Ryouhei Kobayashi, and Hiroaki Kobayashi
- Journal Title
  
  Proc. of SICE Annual Conference 2010
  
  Pages: 3240-3245
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] Threshold Learning in the Improved Penalty Avoiding Rational Policy Marking Algorithm2010
- Author(s)
  Kazuteru Miyazaki, Ryouhei Kobayashi, Hiroaki Kobayashi
- Journal Title
  
  Proc.of SICE Annual Conference 2010
  
  Pages: 3240-3245
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] A New Improved PenaltyAvoiding Rational Policy Making Algorithm for Keepaway with Conti-nuous State Spaces2009
- Author(s)
  Takuji Watanabe, Kazuteru Miyazaki, and Hiroaki Kobayashi
- Journal Title
  
  Journal of Advanced Computational Intelligence and Intelligent Informatics
  
  Volume: Vol.13, No.6 Pages: 675-683
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] A New Improved Penalty Avoiding Rational Policy Making Algorithm for Keepaway with Continuous State Spaces2009
- Author(s)
  Takuji Watanabe, Kazuteru Miyazaki, HIroaki Kobayashi
- Journal Title
  
  Journal of Advanced Computational Intelligence and Intelligent Informatics Vol.13, No.6
  
  Pages: 675-683
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21560275
[Journal Article] 腱駆動ロボットの作業に適した関節剛性のGAによる学習2006
- Author(s)
  朴贊逸, 小林博明
- Journal Title
  
  日本ロボット学会誌 24-2(未定)
- NAID
  10017484615
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Joint Stiffness Optimization of Robotic Arms with Adjustable Joint Elasticity for Force/Position Hybrid Control2006
- Author(s)
  Chan Il Park, Hiroaki Kobayashi
- Journal Title
  
  Proc.of Movic 2006, Daejon (to appear)
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Joint Stiffness optimization of Robotic Arms with Adjustable Joint Elasticity for Force/Position Hybrid Control2006
- Author(s)
  Chan H Park, Hiroaki Kobayashi
- Journal Title
  
  Proc. of Movic 206 (未定)
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Optimization of Tendon-Driven Robot Joint Stiffness using GA-based Learning2006
- Author(s)
  Chan Il Park, Hiroaki Kobayashi
- Journal Title
  
  Journal of the Robotics Society of Japan 24-2(to appear)
- NAID
  10017484615
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] 腱駆動ロボットの作業に適した関節剛性のGAによる学習2006
- Author(s)
  朴贄逸, 小林博明
- Journal Title
  
  日本ロボット学会誌 24・4(未定)
- NAID
  10017484615
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] 腱駆動式ロボットの知的制御-位置・力ハイブリッドANN制御2005
- Author(s)
  小林博明, 朴贊逸
- Journal Title
  
  明治大学理工学研究所紀要 43(4)
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Intelligent Control of Tendon-Driven Robots - Force/Position Hybrid Control-2005
- Author(s)
  Hiroaki Kobayashi, Chan Il Park
- Journal Title
  
  Meiji University 43-4
  
  Pages: 27-41
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] 腱駆動ロボットの知的制御一位置・力ハイブリッドANN制御2005
- Author(s)
  小林博明, 朴贄逸
- Journal Title
  
  明治大学科学技術研究所紀要 43・4
  
  Pages: 27-41
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Force /Position Hybrid Control for Geometrically Constrained Tendon-Driven Flexible Joint Robot2004
- Author(s)
  Chan H Park, Hiroaki Kobayashi
- Journal Title
  
  Proc. of 6th IFAC-Symp. on Nonlinear Control System
  
  Pages: 1547-1552
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Force/Position Hybrid Control for Geometrically Constrained Tendon-Driven Flexible Joint Robot2004
- Author(s)
  Chan Il Park, Hiroaki Kobayashi
- Journal Title
  
  Proc.of 2003 Int.Symp.on Advanced Intelligent Systems, Stuttgart
  
  Pages: 1547-1552
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] A New Impedance Control Concept for Elastic Joint Robots - A case of a 1 DOF Robot with Programmable Linear Passive Impedance -2003
- Author(s)
  Ryuta Ozawa, Hiroaki Kobayashi
- Journal Title
  
  Proc.of 2003 Int.Conf.of Robotics and Automation, Taipei
  
  Pages: 3126-3131
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] A New Impedance Control Concept for Elastic Joint Robots -A case of a 1 DOF robot with Programmable Linear Passive Impedance-2003
- Author(s)
  Ryota Ozawa, Hiroaki Kobayashi
- Journal Title
  
  Proc. of 2003 Int. Conf. of Robotics and Automation
  
  Pages: 3126-3131
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Adaptive Neural Network Control of Tendon-Driven Mechanism with Elastic Tendon2003
- Author(s)
  Hiroaki Kobayashi, Ryuta Ozawa
- Journal Title
  
  AUTOMATICA 39・9
  
  Pages: 1509-1666
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Journal Article] Adaptive Neural Network Control of Tendon-Driven Mechanism with Elastic Tendons2003
- Author(s)
  Hiroaki Kobayashi, Ryuta Ozawa
- Journal Title
  
  Automatica 39-9
  
  Pages: 1509-1666
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15560225
[Presentation] 罰と報酬を用いる強化学習の失敗確率伝播に関する研究2011
- Author(s)
  村岡宏紀、宮崎和光、小林博明
- Organizer
  第54回自動制御連合講演会
- Place of Presentation
  豊橋技術科学大学
- Year and Date
  2011-11-20
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] 腱駆動2足歩行ロボットにおける腰軌道の強化学習への固定状態導入による効率化の研究2011
- Author(s)
  伊藤大貴、岡島勇也、田中純夫、小林博明、宮崎和光
- Organizer
  第54回自動制御連合講演会
- Place of Presentation
  豊橋技術科学大学
- Year and Date
  2011-11-20
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot2011
- Author(s)
  Seiya Kuroda, Kazuteru Miyazaki, Hiroaki Kobayashi
- Organizer
  The 9th European Workshop on Reinforcement Learning (EWRL-9)
- Place of Presentation
  Athens Royal Olympic Hotel
- Year and Date
  2011-09-11
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot2011
- Author(s)
  Seiya Kuroda, Kazuteru Miyazaki and Hiroaki Kobayashi
- Organizer
  The 9th European Workshop on Reinforcement Learning(EWRL-9)
- Place of Presentation
  Athens Royal Olympic Hotel
- Year and Date
  2011-09-11
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] Threshold Learning in the Improved Penalty Avoiding Rational Policy Marking Algorithm2010
- Author(s)
  Kazuteru Miyazaki, Ryouhei Kobayashi, and Hiroaki Kobayashi
- Organizer
  SICE Annual Conference 2010
- Place of Presentation
  Grand Hotel, Taipei, Taiwan
- Year and Date
  2010-08-21
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] Threshold Learning in the Improved Penalty Avoiding Rational Policy Mazking Algorithm2010
- Author(s)
  Kazuteru Miyazaki, Ryouhei Kobayashi, Hiroaki Kobayashi
- Organizer
  SICE Annual Conference 2010
- Place of Presentation
  Grand Hotel, Taipei, Taiwan
- Year and Date
  2010-08-21
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] マルチエージェント連続タスクへの改良型罰回避政策形成アルゴリズムの適用とサッカーロボットを用いた実験による評価2010
- Author(s)
  伊藤昌樹、宮崎和光、小林博明
- Organizer
  第53回自動制御連合講演会
- Place of Presentation
  高知市高知城ホール
- Year and Date
  2010-11-04
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] 腱駆動2足歩行ロボットの開発と腰軌道および腱張力の強化学習2010
- Author(s)
  黒田聖弥、日野雄太、岡島勇也、田中純夫、兵頭和人、小林博明
- Organizer
  第53回自動制御連合講演会
- Place of Presentation
  高知市高知城ホール
- Year and Date
  2010-11-04
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] 腱駆動2足歩行ロボットの開発と腰軌道および腱張力の強化学習-その2010
- Author(s)
  伊藤昌樹、宮崎和光、小林博明
- Organizer
  第53回自動制御連合講演会
- Place of Presentation
  高知市高知城ホール
- Year and Date
  2010-11-04
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] 改良型罰回避政策形成アルゴリズムへの罰基底度決定機構の導入と評価2010
- Author(s)
  小林諒平, 宮崎和光, 小林博明
- Organizer
  日本機械学会関東支部第16期総会講演会
- Place of Presentation
  明治大学アカデミーコモン
- Year and Date
  2010-03-10
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] 腱駆動2足歩行ロボットの開発と腰軌道および腱張力の強化学習2010
- Author(s)
  黒田聖也, 平野晃一郎, 小林博明, 田中純夫
- Organizer
  日本機械学会関東支部第16期総会講演会
- Place of Presentation
  明治大学アカデミーコモン
- Year and Date
  2010-03-10
- Data Source
  KAKENHI-PROJECT-21560275
[Presentation] 罰基底度閾値の学習機能を有する改良型罰回避政策形成アルゴリズムの提案2009
- Author(s)
  小林諒平, 宮崎和光, 小林博明
- Organizer
  第52回自動制御連合講演会
- Place of Presentation
  大阪大学基礎工学研究科
- Year and Date
  2009-11-22
- Data Source
  KAKENHI-PROJECT-21560275

1. HYODO Kazuhito (10271371)

# of Collaborated Projects: 3 results

# of Collaborated Products: 1 results
2. TANAKA Sumio (40287884)

# of Collaborated Projects: 2 results

# of Collaborated Products: 3 results
3. MIYAZAKI Kazuteru (20282866)

# of Collaborated Projects: 1 results

# of Collaborated Products: 18 results
4. NOBORISAKA Hirokazu

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
5. OZAWA Ryuta

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results

KOBAYASHI Hiroaki 小林 博明

Research Projects

Research Products

Co-Researchers

Reinforcement Learning of Action Strategies and Joint Stiffness of Tendon-driven Biped RobotPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

INTELLIGENT CONTROL OF TENDON-DRIVEN ROBOTIC MECHANISMS.Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

DEVELOPMENT OF A ROBOTIC ARM DRIVEN WITH REDUNDANT TENDONS TO WORK COOPERATIVELY WITH HUMANS.Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

[Journal Article] Evaluation of the Improved Penalty Avoiding Rational Policy Making Algorithm in Real World Environment2012

Author(s)

Journal Title

DOI

ISBN

Data Source

[Journal Article] Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot2012

Author(s)

Journal Title

Data Source

[Journal Article] Evaluation of the Improved Penalty Avoiding Rational Policy Making Algorithm in Real World Environment2012

Author(s)

Journal Title

Data Source

[Journal Article] Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot2012

Author(s)

Journal Title

Data Source

[Journal Article] Threshold Learning in the Improved Penalty Avoiding Rational Policy Marking Algorithm2010

Author(s)

Journal Title

Data Source

[Journal Article] Threshold Learning in the Improved Penalty Avoiding Rational Policy Marking Algorithm2010

Author(s)

Journal Title

Data Source

[Journal Article] A New Improved PenaltyAvoiding Rational Policy Making Algorithm for Keepaway with Conti-nuous State Spaces2009

Author(s)

Journal Title

Data Source

[Journal Article] A New Improved Penalty Avoiding Rational Policy Making Algorithm for Keepaway with Continuous State Spaces2009

Author(s)

Journal Title

Data Source

[Journal Article] 腱駆動ロボットの作業に適した関節剛性のGAによる学習2006

Author(s)

Journal Title

NAID

Data Source

[Journal Article] Joint Stiffness Optimization of Robotic Arms with Adjustable Joint Elasticity for Force/Position Hybrid Control2006

Author(s)

Journal Title

Description

Data Source

[Journal Article] Joint Stiffness optimization of Robotic Arms with Adjustable Joint Elasticity for Force/Position Hybrid Control2006

Author(s)

Journal Title

Description

Data Source

[Journal Article] Optimization of Tendon-Driven Robot Joint Stiffness using GA-based Learning2006

Author(s)

Journal Title

NAID

Description

Data Source

[Journal Article] 腱駆動ロボットの作業に適した関節剛性のGAによる学習2006

Author(s)

Journal Title

KOBAYASHI Hiroaki 小林博明