Koji Shimojima

About

Koji Shimojima is a pioneering researcher in intelligent robotic systems, whose work bridges fuzzy logic, neural networks, and reinforcement learning to create adaptive, autonomous machines. His most influential contribution is the development of self-scaling reinforcement learning algorithms for fuzzy logic controllers, first introduced in his 1999 paper (45 citations), which enables robots to generate continuous real-valued actions without weight overshooting—a critical advance for motion control in complex tasks like brachiation. Shimojima has also made significant strides in multisensor integration, using fuzzy inference and neural networks to fuse data for industrial applications, such as curved metal surface cutting (37 citations). His visionary work on multimedia tele-surgery (35 citations) leverages high-speed optical fiber networks for intravascular neurosurgery, demonstrating robotic-assisted remote operations. Additionally, he proposed the Micro Autonomous Robotic System (MARS) with a biologically inspired immune swarm strategy (32 citations) for multi-agent coordination. With over 250 total citations across his top papers, Shimojima’s research has profoundly impacted robotics, from factory automation to minimally invasive surgery, establishing him as a key figure in intelligent, sensor-rich robotic systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Self-scaling reinforcement learning for fuzzy logic controller-applications to motion control of two-link brachiation robot

   45 citations · 1999
2. 2
   Multisensor integration system based on fuzzy inference and neural network

   37 citations · 1993
3. 3
   Multimedia tele-surgery using high speed optical fiber network and its application to intravascular neurosurgery - system configuration and computer networked robotic implementation

   35 citations · 2002
4. 4
   Micro autonomous robotic system and biologically inspired immune swarm strategy as a multi agent robotic system

   32 citations · 2002
5. 5
   Motion planning for a robotic system with structured intelligence

   20 citations · 2002
6. 6
   Reinforcement learning method for generating fuzzy controller

   19 citations · 2002
7. 7
   Self scaling reinforcement learning for fuzzy logic controller

   16 citations · 2002
8. 8
   Sensor Fusion System Using Recurrent Fuzzy Inference

   15 citations · 1998
9. 9
   Multi-sensor integration system based on fuzzy inference and neural network for industrial application

   15 citations · 2003
10. 10
    Navigation system based on ceiling landmark recognition for autonomous mobile robot -position/orientation control by landmark recognition with plus and minus primitives

    15 citations · 2002

Key Collaborators

Contact & Links