[61]Masaru Iida & Katsunari Shibata: (Almost the same as [43])
Direct-Vision-Based Reinforcement Learning in a Real Mobile Robot,
Artificial Life and Robotics, Vol. 7, pp. 102-106 (to appear) 2004
[Direct-Vision-Based Reinforcement Learning, Real Mobile Robot]
[60]Katsunari Shibata:
Discretization of Analog Communication Signals by Noise Addition in Communication Learning,
Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics),
Vol. 2, pp. 351-354, 2004. 1
[Symbol, Reinforcement Learning, Neural Network, Communication, Noise]
pdf File (4 pages, 249kB)
[59]Ryusuke Kurino, Masanori Sugisaka & Katsunari Shibata:
Growing Neural Network with Hidden Neurons,
Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics),
Vol. 1, pp. 144-147, 2004. 1
[Growing Neural Network, Hidden Neuron]
pdf File (4 pages, 191kB)
[58]Kazuyoshi Yuki, Masanori Sugisaka & Katsunari Shibata:
Learning of Reaching a Colored Object Based on Direct-Vision-Based
Reinforcement Learning and Acquired Internal Representation,
Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics),
Vol. 2, pp. 486-489, 2004. 1
[Direct-Vision-Based Reinforcement Learning, Neural Network, Color and Position]
pdf File (4 pages, 333kB)
[57]Masanobu Nakanishi, Masanori Sugisaka & Katsunari Shibata:
Occurrence of State Confusion in the Learning of Communication Using Q-leaning,
Proc. of The 9th AROB (Int'l Sympo. on Artificial Life and Robotics),
Vol. 2, pp. 663-666, 2004. 1
[Q-learning, State Confusion, Communication]
pdf File (4 pages, 155kB)
[56]Katsunari Shibata & Masaru Iida:
Acquisition of Box Pushing by Direct-Vision-Based Reinforcement Learning,
SICE (The Society of Instrument and Control Engineers) Annual Conf. 2003, 0324.pdf, pp. 1378-1383, 2003. 8
pdf File (6 pages, 644kB)
[55]Katsunari Shibata & Koji Ito:
Hidden Representation after Reinforcement Learning of Hand Reaching Movement
with Variable Link Length,
Proc. of IJCNN (Int'l Conf. on Neural Networks) 2003, 1475-674.pdf, pp.2619-2624, 2003.7
pdf File (6 pages, 764kB)
[54]Ryusuke Kurino, Masanori Sugisaka \& Katsunari Shibata:
Growing Neural Network for Acquisition of 2-layer Structure,
Proc. of IJCNN (Int'l Conf. on Neural Networks) 2003, 1455-703.pdf, pp.2512-2517, 2003.7
pdf File (6 pages, 160kB)
[53]Katsunari Shibata, Masahide Ueda and Koji Ito:
Emergence and Differentiation Model of Individuality and Sociality by Reinforcement Learning,
Trans. of SICE (The Society of Instrument and Control Engineers), Vol. 39, No. 5, pp.494--502, 2003.5 (in Japanese)
pdf File (9 pages, 186kB)
[52]Katsunari Shibata, Tsutomu Masaki \& Masanori Sugisaka:
Autonomous Learning of Reward Distribution in Not100 Game,
Proc. of AROB (Int'l Symp. on Artificial Life and Robotics) 8th, pp.78-81, 2003.1
pdf File (4 pages, 116kB)
[51]Masaru Iida, Masanori Sugisaka \& Katsunari Shibata:
Application of Direct-Vision-Based Reinforcement Learning to a Real Mobile Robot with a CCD camera,
Proc. of AROB (Int'l Symp. on Artificial Life and Robotics) 8th, pp.86-89, 2003.1
[50]Daiki Kiyosuke, Masanori Sugisaka \& Katsunari Shibata:
Body Growth Effect on Reinforcement Learning in a Simple Standing-up Task,
Proc. of AROB (Int'l Symp. on Artificial Life and Robotics) 8th, pp. 90-93, 2003.1
[49]Ryusuke Kurino, Masanori Sugisaka \& Katsunari Shibata:
Acquisition of 2-layer Structure in a Growing Neural Network,
Proc. of AROB (Int'l Symp. on Artificial Life and Robotics) 8th, pp. 391--394, 2003.1
[48]Katsunari Shibata, Tetsuo Nishino \& Yoichi Okabe: (Almost the same as [41])
Active Perception and Recognition Learning System Based on Actor-Q Architecture
Systems and Computers in Japan, Vol. 33, No. 14, pp. 12-22, 2002. 12
[47]Katsunari Shibata \& Koji Ito:
Effect of Force Load in Hand Reaching Movement Acquired by Reinforcement Learning,
Proc. of Int'l Conf. on Neural Information Processing Systems (ICONIP '02), Vol. 3, pp. 1444-1448, 2002.11
pdf File (5 pages, 200kB)
[46]Masaru Iida, Masanori Sugisaka \& Katsunari Shibata:
Application of Direct-Vision-Based Reinforcement Learning to a Real Mobile Robot,
Proc. of Int'l Conf. of Neural Information Processing Systems (ICONIP '02), Vol. 5, pp. 2556--2560, 2002. 11
pdf File (5 pages, 640AROB03kB)
[45]Katsunari Shibata and Masanori Sugisaka:
Dynamics of a Recurrent Neural Network
Acquired through the Learning of a Context-based Attention Task,
Proc. of AROB (Int'l Sympo. on Artificial Life and Robotics) 7th,
pp. 152-155, 2002.1
pdf File (4 pages, 126kB)
[44]Shin'ich Maehara, Masanori Sugisaka and Katsunari Shibata:
Effectiveness of Sensory Motion in the Learning of Capturing Task of a Moving Object
Proc. of AROB (Int'l Sympo. on Artificial Life and Robotics) 7th,
pp. 46-49, 2002.1
[43]Masaru Iida, Masanori Sugisaka and Katsunari Shibata:
Direct-Vision-Based Reinforcement Learning in a Real Mobile Robot,
Proc. of AROB (Int'l Sympo. on Artificial Life and Robotics) 7th, pp. 42-45, 2002.1
[42]Katsunari Shibata:
Formation of Attention and Associative Memory Based on Reinforcement Learning,
Proc. of ICCAS (Int'l Conf. on Control, Automation and Systems) 2001, pp. 9-12, 2001. 10
[Selective Attention, Associative Memory, Recurrent Neural Network, Reinforcement Learning]
pdf File (4 pages, 136kB)
[41]Katsunari Shibata, Tetsuo Nishino and Yoichi Okabe:
Active Perception Learning System Based on Actor-Q Architecture,
Trans. of IEICE (The Institute of Electronics, Information and Communication Engineers), Vol. J84-D-II, No. 9, pp.2121-2130, 2001. 9 (in Japanese)
[Actor-Q architecture, reinforcement learning, active perception,neural network]
pdf File (10 pages, 894kB)
[40]Munenobu Uchida, Katsunari Shibata, Xin-Zhi Zheng and Koji Ito:
An Adjustment Method of VIsco-elastic Parameters for Above-Knee Prosthesis based on Mechanical Models,
J. of Bio-Mechanism Society (SOBIN) Japan, Vol.25, No.2, pp.81-87, 2001. 5 (in Japanese)
[Above Knee Prosthesis, Energy Storing, Optimal Control Problem]
[39]Katsunari Shibata, Tetsuo Nishino, and Yoichi Okabe,
Actor-Q Based Active Perception Learning System,
Proc. of Int'l Conf. on Robotics and Automation (ICRA)2001, (to appear), 2001. 5
[Actor-Q architecture, reinforcement learning, active perception,neural network]
pdf File (6 pages, 833kB)
[38]Katsunari Shibata, Yoichi Okabe and Koji Ito:
Direct-Vision-Based Reinforcement Learning Using a Layered Neural Network
- For the Whole Process from Sensors to Motors -,
Trans. of SICE (The Society of Instrument and Control Engineers), Vol.37, No.2, pp.168-177, 2001.2 (in Japanese)
[reinforcement learning, neural network, visual sensor, hidden representation, localization]
pdf File (10 pages, 307kB)
[37]Katsunari Shibata, Masanori Sugisaka and Koji Ito:
Fast and Stable Learning in Direct-Vision-Based Reinforcement Learning,
Proc. of Int'l Sympo. on Artificial Life and Robotics (AROB) 6th, pp.200-203, 2001.1
[reinforcement learning, neural network, visual sensor, localization]
pdf File (4 pages, 150kB)
[36]Shin'ichi Maehara, Masanori Sugisaka and Katsunari Shibata:
Reinforcement Learning Using Gauss-Sigmoid Neural Network,
Proc. of Int'l Sympo. on Artificial Life and Robotics (AROB) 6th, pp.562-565, 2001.1
[reinforcement learning, Gauss-Sigmoid neural network, hill-car problem]
[35]Katsunari Shibata, Masanori Sugisaka and Koji Ito:
Hand Reaching Movement Acquired through Reinforcement Learning,
Proc. of 2000 KACC (Korea Automatic Control Conference), 90rd (CD-ROM), 2000. 10
[Reinforcement Learning, Reaching Task, Hand Locus, Dynamics]
PDF File (186kB)
[34]Xin-Zhi Zheng, Wataru Inamura, Katsunari Shibata and Koji Ito:
Robotic Batting System --- An Architecture for Learning and Dynamic Pattern Generation ---,
Advanced Robotics Vol. 14, No. 5, pp.435-437, 2000. 10
[Batting, Dynamic Manipuation, Torque Output, Neural Network, Optimal Control]
[33]S. Morita, K. Shibata, X.-Z. Zheng and K. Ito:
Prosthetic Hand Control based on Torque Estimation from EMG Signals,
IROS 2000 (IEEE/RSJ Int'l Conf. on Intelligent Robotics and Systems), Vol.1, pp. 389-394, 2000.10
[Prosthetic Hand, EMG, Neural Network]
[32]E. A. Y. Murakami, K. Shibata, X.-Z. Zheng and K. Ito:
Human Control Characteristics in Bilateral Micro-Teleoperation System,
Proc. of IECON, 2000.10
[Micro-Teleoperation, Human Dynamics, Scaling, Master-Slave System, Transfer Function]
[31]S. Morita, K. Shibata, X.-Z. Zheng and K. Ito:
Human-EMG Prosthetic Hand Interface Using Neural Network,
IMEKO 2000 (Int'l Measurement Confederation XVI IMEKO World Congress), 2000. 9
[Prosthetic Hand, EMG, Neural Network]
[30]E. A. Y. Murakami, K. Shibata, X.-Z. Zheng and K. Ito:
Analysis of Human Dynamics in Micro-Teleoperation System,
IMEKO 2000 (Int'l Measurement Confederation XVI IMEKO World Congress), 2000. 9
[Micro-Teleoperation, Human Dynamics, Scaling, Master-Slave System, Transfer Function]
[29]Katsunari Shibata and Koji Ito:
Autonomous Learning of Reward Distribution for Each Agent
in Multi-Agent Reinforcement Learning,
Proc. of IAS6 (The 6th Int'l Conf. on Intelligent Autonomous Systems), pp. 495-502, 2000.7
pdf File (8 pages, 930kB)
[28]X.-Z. Zheng, W. Inamura, K. Shibata and K. Ito:
A Learning and Dynamic Pattern Generating Architecture for Skillful Robotic Baseball Batting System,
Proc. of ICRA 2000 (IEEE Int'l Conf. on Robotics and Automation), pp. 3227-3232, 2000. 4
[27]Katsunari Shibata, Masahide Ueda, and Koji Ito:
Emergence of Individuality and Sociality by Reinforcement Learning,
Proc. of Fifth of International Symposium on Artificial Life and Robotics (AROB)2000, Vol. 2, pp. 589 -- 592, 2000.1
[Individuality, Sociality, Reinforcement Learning, Multi-Agent Systems]
pdf File (4 pages, 119kB)
[26] Katsunari Shibata and Koji Ito:
Learning of Communication for Negotiation to Avoid Some Conflicts of Interests - Learning of Dynamic Communication Using Recurrent Neural Network -,
Trans. of SICE(The Society of Instrument and Control Engineers), Vol.35, No.11, pp.1346-1354, 1999.11
[dynamic communication, recurrent neural network, negotiation, individuality]
pdf File (10 pages, 214kB)
[25] K. Shibata and K. Ito:
Hand-Eye Coordination in Robot Arm Reaching Task by Reinforcement Learning Using Neural Networks,
IEEE SMC (Systems, Man, and Cybernetics) '99, Vol.V, pp. V-458 - 463, 1999.10
[hand-eye coordination, reinforcement learning, neural network, internal representation]
[24] X-Z Zheng, W. Inamura, K. Shibata and K. Ito:
Task Skill Formation via Motion Repetition in Robotic Dynamic Manipulation,
IEEE SMC (Systems, Man, and Cybernetics) '99, Vol.IV, pp. IV-1001 - 1006, 1999.10
[neural network, optimal control, generalization, hitting task]
[23] K. Shibata and K. Ito:
Gauss-Sigmoid Neural Network,
IJCNN (International Joint Conference on Neural Networks) '99, #747 (6pages), 1999. 7
[neural network, localization, integration, RBF, learning]
[22]K. Shibata and K. Ito :
Emergence of Communication for Negotiation By a Recurrent Neural Network,
Proc. of ISADS (International Symposium on Autonomous Decentralized System) '99, pp.294-301, 1999.3
[dynamic communication, recurrent neural network, reinforcement learning, individuality, negotiation, multi-agent system]
[21]K. Shibata and K. Ito :
Reconstruction of Visual Sensory Space on the Hidden Layer in a Layered Neural Networks,
Proc. of ICONIP'98, Vol. 1, pp.405-408, 1998.10
[neural network, generalization, visual sensor, spatial recognition, integration]
pdf File (4 pages, 162kB)
[20]K. Shibata, K. Ito and Y. Okabe :
Simple Learning Algorithm for Recurrent Networks to Realize Short-Term Memories,
Proc. of IJCNN'98, pp. 2367-2372, 1998.5
[recurrent neural network, supervised learning algorithm, back propagation (BP)]
(PSfile(gzip) 196kB A4 6 pages)
[19]K. Shibata, Y. Okabe and K. Ito :
Direct-Vision-Based Reinforcement Learning in "Going to an Target" Task with an Obstacle and with a Variety of Target Sizes,
Proc. of NEURAP(Neural Networks and their Applications)'98, pp.95-102, 1998.3
[reinforcment learning, visual sensor, neural network, obstacle avoidance, stereo vision, mobile robot]
PS File (8 pages, 318kB)
[18]Katsunari Shibata, Yoichi Okabe:
Temporal Smoothing Learning,
Trans. IEE (The Institute of Electrical Engineers) of Japan, Vol. 117-C, No. 9, pp.1291-1299, 1997.9
[neural network, temporal smoothing learning, mapping from space to time, local sensory signal integration, reinforcement learning]
[17]K. Shibata and Y. Okabe :
Reinforcement Learning When the Visual Signals are Directly Given as Inputs,
Proc. of ICNN'97 Houston, Vol. 3, pp.1716-1720, 1997.6
[reinforcement learning, neural network, visual sensor, hidden neuron, mobile robot]
PS File (5 pages, 236kB)
[16]Katsunari Shibata:
Autonomous Learning System Using Neural Networks,
Doctor Thesis, The Univ. of Tokyo, 1997. 3 (in Japanese)
[15]Katsunari Shibata, Tetsuo Nishino & Yoichi Okabe:
Learning of Active Perception Based on Reinforcement Learning,
J. of JNNS(Japan Neural Network Society), Vol. 3, No. 4, pp.126-134, 1996.12 (in Japanese)
[active perception, reinforcement learning, neural network, visual sensor, sensory motion]
[14]Katsunari Shibata & Yoichi Okabe:
Integration of Local Sensory Signals and Extraction of Spatial Information Based on Temporal Smoothing Learning,
J. of JNNS(Japan Neural Network Society), Vol. 3, No. 3, pp.98-105, 1996. 9 (in Japanese)
[neural network, temporal smoothing learning, local sensory signal integration, mapping from space to time]
[13]Katsunari Shibata & Yoichi Okabe:
Unsupervised Learning of the Spatial Recognition Ability Using the Correlated Information Extracting Neural Network,
J. of JNNS(Japan Neural Network Society), Vol. 3, No. 1, pp.11-16, 1996. 5 (in Japanese)
[correlated information, neural network, spatial recognition, unsupervised learning, mutual information]
[12]K. Shibata and Y. Okabe :
Some Learning Models of Visual System based on Local Sensor Signal Integration Learning,
Proc. of ICNN '95 Perth, IV, pp.1986-1990, 1995.11
[neural network, temporal smoothing learning, local sensory signal integration, vestibulo-ocular reflex, head-invariant perception, smooth pursuit]
PS File (60kB)
[11]K. Shibata, T. Nishino and Y. Okabe :
Active Perception based on Reinforced Learning
Proc. of WCNN '95 Washington, II, pp. 170-173, 1995.7
[active perception, reinforcement learning, neural network, visual sensor, sensory motion]
[PS file (4 pages, 155kB)]
[10]K. Shibata and Y. Okabe :
Unsupervised Learning Method to Extract Object Locations from Local Visual Signals
Proc. of ICNN '94, Orlando, Vol. 3, pp.1556-1559, 1994.7
[correlated information, neural network, spatial recognition, unsupervised learning, mutual information]
PS File (39kB)
[9]K. Shibata and Y. Okabe :
A Robot that Learns an Evaluation Function for Acquiring of Appropriate Motions,
Proc. of WCNN '94 San Diego, Vol.2, pp. II-29 - II-34, 1994. 6
[reinforcement learning, neural network, temporal smoothing learning, mobile robot]
PS File (6 pages, 157kB)
[8]K. Shibata :
A Neural-Network to get Correlated Information among multiple Inputs
Proc. of IJCNN'93 NAGOYA, Vol.3, pp. 2532-2535, 1993.10
[neural network, correlated information, unsupervised learning]
PS File (4pages, 50kB)
[7]K. Shibata :
Spatial Recognition Model by Extracting Correlated Information between Vision and Motion Information using Neural-Network
Proc. of IJCNN'93 NAGOYA, Vol.3, pp.2536-2539, 1993.10
[spatial recognition, neural network, correlated information]
PS File (4pages, 46kB)
[6] Yuji Sato, et. al:
Development of a High-Performance, General Purpose Neuro-Computer Composed of 512 Digital Neurons,
Proc. of IJCNN'93 NAGOYA, Vol.2, 1967-1970, 1993.10
[neuro computer, learning, back propagation(BP), SIMD type parallel computer, broadcast architecture]
[5] Moritoshi Yasunaga, el. al :
A Self-Learning Digital Neural Network Using Wafer-Scale LSI,
IEEE Journal of Solid-State Circuits, Vol.28, No.2, pp.106-114, 1993.2
[wafer-scale LSI, neuro computer, learning, back propagation(BP), broadcast architecture]
[4] Moritoshi Yasunaga, Mitsuo Asai, Katsunari Shibata & Minoru Yamada:
Self-Organiztion Capability for Eliminating Defective Neurons in Neural Network LSIs,
Trans. of IEICE (The Institute of Electronics, Information and Communication Engineers), Vol.J75-D-I¡¤No.11¡¤pp.1099-1108¡¤1992.11
[neural network, fault tolerance, LSI, learning]
[3] Minoru Yamada, et. al:
A Neural Network on Wafer Scale Integrations,
Proceedings of the IEEE International Conference on Wafer-Scale Integration, pp.231- ,1992
[wafer scale integration, neuro computer, learning, back propagation(BP), broadcast architecture]
[2] M. Yasunaga et. al :
A Self-Learning Neural Network Composed of 1152 Digital Neurons in Wafer-Scale LSIs
IJCNN'91 Singapore, Vol.3, pp1844-1849, 1991.11
[wafer scale integration, neuro computer, learning, back propagation(BP), broadcast architecture]
[1] Katsunari Shibata:
Research on Robot Learning Based on Back Propagation,
Master Thesis, The Univ. of Tokyo, Faculty of Engineering, Dept. of Mechanical Engineering, 1983.3 (in Japanese)