Ibaraki University's
College of Engineering
Department of Intelligent Systems Engineering

顔写真
Lecturer

INOUE Kousuke


Career

  1. 東京大学 人工物工学研究センター 研究期間研究員 2002/04-2002/04
  2. 茨城大学 工学部 システム工学科・助手 2002/05/01-2007/03/31
  3. Research Associate: Dept. of Intelligent Systems Engineering, Ibaraki University 2007/04/01-Present
  4. 茨城大学 工学部 知能システム工学科 講師 2010/04/01-Present

Academic background

  1. The University of Tokyo Faculty of Engineering Department of Precision Machinery Engineering 1996 Graduated
  2. The University of Tokyo Graduate School, Division of Engineering Department of Precision Machinery Engineering Master course 1998 Completed
  3. The University of Tokyo Graduate School, Division of Engineering Department of Precision Machinery Engineering Doctor course 2002 Completed

Academic degrees

  1. Master degree (Engineering) The University of Tokyo 1998/03/31
  2. Doctor (Engineering) The University of Tokyo

Current state of research and teaching activities

Study on Intelligent Artifacts by Bio-mimetics
Behind the living creatures surviving in natural environments, there is a principle of intelligence that has not been dealt with in previous engineering field. Our study aims at novel intelligent artifacts based on bio-mimetics.

Research Areas

  1. Computer Science
  2. Intelligent Informatics
  3. Intelligent Mechanics and Machine System
  4. System Engineering

Research keywords

  1. bio-mimetic robotics, multi-robot cooperation, robot learning

Subject of research

  1. Control of cooperative iterative transportation by multiple mobile robots We proposed control methods to realize cooperative iterative transportation of many objects by multiple robots in unknown or dynamic environments. 1996/04-Present
  2. Behavior acuisition by a mobile robot in partially observable environments. We propose a framework for a mobile robot to acquire behavior in environments that can be modeled as Partially Observable Markov Decision Processes. 1998/04-Present
  3. Acquisition of Generalized Knowledge for Ontogenetic Development of a Robot We propose a framework to acceralate learning process by accumulating generalized knowledges in iterative learning processes. 1999/04-Present
  4. Decentralized adaptive control of meandering locomotion of a snake-like robot based on CPGs Based on models of CPGs, that control rhythmic locomotion of animals, we realized a decentralized controller of a snake-like robot with adaptability to environments. 2003/04-Present
  5. Development of a snake-like robot with viscoelasticity By utilizing pneumatic actuators as artificial muscles, we developed a snake-like robot with body dynamics similar to living snakes. 2005/04-Present

Bibliography

  1. 知の創成-身体性認知科学への招待- (原著: R. Pfeifer, C. Scheier: Understanding Intelligence, MIT Press, (1999)) R. Pfeifer, C. Sheier著, 石黒 章夫, 小林 宏, 細田 耕 監訳 共立出版 2001/11
  2. Insect Mimetics Handbook Eds: Tateo SHIMODATE, Takahiko HARIYAMA NTS Press 2009

Papers

  1. Research paper (scientific journal) Joint Iterative Transportation by Multiple Mobile Robots Considering Unknown Obstacles Kousuke INOUE, Jun OTA, Tamio ARAI Journal of Robotics and Mechatronics 21/ 2 2009/02
  2. Research paper (scientific journal) Joint Behavior Acquisition for Multiple Tasks in a Partially Observable Environment Kousuke INOUE, Jun OTA, Tamio ARAI Trans. SICE 38/ 7, 641-648 2002/07 This paper proposes a method for acquisition of behavior capable of multiple tasks by an agent with non-predesigned and continuous observation space in partially observable environment. In the proposed method, the agent discriminates the ongoing task from other tasks using experience acquired in acquisition process of behaviors corresponding to the tasks, and applies knowledge for the corresponding task. In order to cope with lack of clues for task-identi.cation and bad in.uence on the task-execution behavior by the task-identifying behavior, additional learning process is executed as the need arises. Simulation results shows the proposed method can build a suitable behavior for multiple tasks in a simple partially observable grid-environment.
  3. (MISC) Introduction and explanation (international conference proceedings) Joint CPG-based Control of a Simulated Snake-like Robot Adaptable to Changing Ground Friction Kousuke INOUE, Takaaki SUMI, Shugen MA Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2007) 1957-1962 2007/10
  4. (MISC) Introduction and explanation (international conference proceedings) Joint Neural Oscillator Network-Based Controller for Meandering Locomotion of Snake-Like Robots Kousuke INOUE, Shugen MA, Chenghua JIN Proceedings of 2004 IEEE International Conference on Robotics and Automation (ICRA2004) 5064-5069 2004/04
  5. Research paper (scientific journal) Joint Acceleration of Reinforcement Learning by a Mobile Robot using Generalized Rules Kousuke INOUE, Jun OTA, Tomohiko KATAYAMA, Tamio ARAI Proceedings of 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2000) 885-890 2010/04 One very fundamental problem in behavioral learning by an agent is that it takes quite a long time to acquire optimal behavior. In order to solve this problem, in this paper, we propose an approach to make learning processes more efficient by the use of generalized knowledge. In this approach, the agent repeats learning processes for different tasks and extracts behavioral rules that are commonly harmful to task execution by the use of statistical method. After sufficient experience is accumulated, the generalized rules are extracted from the experience and are applied to subsequent learning processes, and, consequently, the learning processes are accelerated by inhibiting commonly harmful behaviors. In order to achieve generality of rule expression, the description of the rules is based on egocentric information, namely, raw data of observations and actions experienced by the agent. In order to avoid a perceptual aliasing problem, the rule expression includes information on sequential experience and a mechanism is introduced to control the balance of utility and generality of the rules. The proposedmethod is examined in navigation tasks by amobile robot in grid environments as an example of application. The results show that the proposed method accelerates learning processes.

Research presentations

  1. Oral presentation(invited, special) エンジニアがやる生物学 ─ 長い動物の自律分散制御メカニズムの解明に向けて ─ SICE中部支部 制御理論研究委員会・組込みシステムと制御研究委員会 合同研究会 2014/12/17

Prizes

  1. 平成12 年度 IMS (Intelligent Manufacturing Systems) 論文賞 Jun OTA, Tamio ARAI, Kousuke INOUE, Ryousuke CHIBA, Tomokazu HIRANO: Flexible Transport System by Cooperation of Conveyer-Loaded AGVs, Proceedings of 2000 IEEE International Conference on Robotics and Automation (ICRA2000), pp.1144-1150, (2000/10) 2000/11

Alloted class

  1. Introduction to Intelligent Systems
  2. Introduction to Intelligent Systems
  3. Industrial Mechanics
  4. Inductrial Mechanics
  5. Algorithms and Data Structures

Memberships of academic societies

  1. 計測自動制御学会 2002/01-Present
  2. 日本ロボット学会 1997/04-Present