Sensor Fusion

Concept

A human being recognizes external environment by using many kinds of sensory information. By integrating these information and making up lack of information for each other, a more reliable and multilateral recognition can be achieved. The purpose of Sensor Fusion Project is to realize new sensing architecture by integrating multi-sensor information and to develop hierarchical and decentralized architecture for recognizing human beings further. As a result, more reliable and multilateral information can be extracted, which can realize high level recognition mechanism.

Research Topics

Sensory-Motor Fusion System

• High-speed Catching System (exhibited in National Museum of Emerging Science and Innovation since 2005)
• Lightweight High-Speed Multifingered Hand System (2002-)
• High-speed Manipulation System (2000-)
• Column Parallel Vision System (CPV) (2000-)

Grasping/Manipulation

• Dynamic Manipulation of a Linear Flexible Object with a High-speed Robot Arm (2009-)
• Catching a small object in high-speed motion (2009-)
• Throwing and Batting robot system (2009-)
• Knotting manipulation based on skill synthesis (2008-)
• Tool Manipulation by a Multifingered Hand Using a High-speed Vision (2007-)
• One Handed Knotting of flexible rope using a High-speed Multifingered Hand (2006-)
• High-speed Throwing Based on Wave Propagation (2006-)
• Ball Control in High-speed Batting Motion (2005-)
• Dynamic Regrasping using a High-speed Hand (2005-)
• Dynamic Pen Spinning using a High-speed Multifingered Hand (2005-)
• Dynamic Holding Using a High-speed Multifingered Hand (2004-)
• High-speed Batting (2003-)
• Soft Catching with a soft finger (2003-)
• Dynamic Active Catching Using High-speed Multifingered Hand (2002-)
• Dynamic Grasping Using High-speed Visual Feedback (2001-)

Robot Vision

• Pixel-parallel collision detection for safe human-robot-coexistence
• Visual Feedback System Using Multi-High-Speed Vision for High-Speed Manipulation (2003-)
• Real time 3D Shape Recognition Using Image Moment-Based Features (2003-)

Sensor Fusion/Sensory-Motor Fusion Theory

• Sensor Selection Method Considering Communication Delays (2003)
• Adjustment of Discount Rate Using Index for Progress of Learning (2003)
• Acquisition of Dynamics Matching in Sensory-Motor Fusion System (2001-2002)

Human Interface

• Portable Assist Tool with Visual and Force Feedback (2000)
• Touching an Object by Visual Information (1997-1998)

Research in the past