Ishikawa Oku Laboratory (Ishikawa Watanabe Laboratory), University of Tokyo, Tokyo, Japan

[Administrator]

Website - ishikawa-vision.org

youtube.com/IshikawaLab

facebook.com/IshikawaLaboratory

twitter.com/IshikawaLab_e

linkedin.com/company/ishikawa-watanabe-laboratory

Projects:

ACHIRES, high speed bipedal robot running using high speed visual feedback

Baseball Robots: Throwing, Tracking, Batting, Running, Catching

Janken, rock-paper-scissors robot with 100% winning rate

 

[Administrator]

Ultra High-speed Robot Based on 1 kHz Vision System

Published on Dec 27, 2012

This video shows the historical overview of our research results on the robot system. This video was submitted to "2012 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems" and received Best IROS Jubilee Video Award. We have IEEE permission to upload this video on YouTube. Other research results except for the robot system are summarized as the video named "Dynamic Intelligent Systems Based on 1 kHz Vision System" and please also see it.

 

[Administrator]

Dynamic Intelligent Systems Based on 1 kHz Vision System

Published on Dec 27, 2012

This video shows the historical overview of our research results on the high-speed vision and its applications such as tracking of microorganisms, human interaction, virtual reality, et cetera. As for our research results regarding the robot system, these are summarized as the other video named "Ultra High-speed Robot Based on 1 kHz Vision System" and please also see it. You can understand the entire scope of our laboratory with two videos.

 

[Administrator]

Published on Apr 6, 2014

Anywhere Surface Touch: utilizing any surface as an input area with a wearable device
Anywhere Surface Touch allows any flat or curved surface in a real environment to be used as an input area. The interface uses only a single small camera and a contact microphone to recognize numerous kinds of interaction between the fingers of the user and the surface. The system recognizes which fingers are interacting and in which direction the fingers are moving. Additionally, the fusion of vision and sound allows the system to distinguish the contact conditions between the fingers and the surface.

 

[Administrator]

Toward the Dream of a Baseball Android

Published on Nov 5, 2014

This video shows an overview of our research about robotic systems individually achieving fundamental actions of baseball, such as throwing, tracking, batting, running and catching, while at the same time comparing these with humans performing the same actions. We achieved these tasks by controlling high-speed robots based on real-time visual feedback from high-speed cameras.
For more information, please see the following web page:
k2.t.u-tokyo.ac.jp/fusion/Baseball/index-e.html
We use footage of the University of Tokyo Baseball Club during their practice in this video, with their permission. Ishikawa Watanabe Lab is rooting for the University of Tokyo Baseball Club.

 

[Administrator]

3D Motion Sensing of any Object without Prior Knowledge

Published on Oct 20, 2015

We present a new 3D motion sensing system. Object motion information is being used in various applications, and the types of targets that can be sensed continue to diversify. Nevertheless, conventional motion sensing systems have low universality because they require some devices to be mounted on the target, such as accelerometers and gyro sensors, or because they are based on cameras, which highly depend on the target shape or texture and require high calculation costs. In particular, when the target has no texture on the surface and no distinctive structural features, the methods based on cameras inevitably fail. Our method solves this problem and enables noncontact, high-speed, deterministic measurement of the velocity of a moving target without any prior knowledge about the target shape and texture, and can be applied to any unconstrained, unspecified target. Using this technique and a prototype system that we developed, we also demonstrated a number of applications, including motion capture, video game control, and 3D shape integration with everyday objects.

"3D Motion Sensing of any Object by Using Multiplexed Lasers"

 

[Administrator]

Robot system for manipulating a randomly placed towel-like object

Jun 2, 2022

In recent years, there has been an increasing demand for robotic handling of towel-like objects in linen and laundry services. One such task involves picking up a towel randomly and aligning it to a predetermined position and posture. However, it is difficult for robots to handle these towel-like flexible objects because deformation occurs during robotic manipulation, and manipulation based on estimation of deformation status is rather challenging and unfeasible for most robotic systems. To solve this problem, in this research, we propose a method to continuously realize the object picking, the object spreading and the object alignment by robot arm system, aiming at further automation.

ishikawa-vision.org/fusion/TowelManipulation