History and Abstract
- 1997
We propose the method for recognition and tracking of the 3D
position and posture of the hexapod in spite of the joint motion and
occlusion. By using 2D image matching, the body of the hexapod,
several legs and toes are recognized in turn. The position of the
body and toes are measured by the binocular-stereo and the angles of
the legs are obtained, which are used for motion recognition.
In addition, we propose motion recognition mechanism using
eigenspace, which can reduce the dimension for matching.
The effectiveness of these methods is tested through an experiment
using two hexapod robots.
-
- 1996
In order to assist the human operating robot, the autonomous robots
must recognize its motions in real time.
The vision is the most useful sensor for this purpose. But it is
difficult to recognize the motion of a robot which has a body and
multiple legs because of its high degrees of freedom, occlusion and so
on.
We propose a hierarchical method, in which a body is
recognized first, and each leg and its toe are recognized by using 3D
geometric constraints, respectively. The appearance based and minute
templates based matching is used in this method.
- 1995
The purpose of this research is to make multiple robots perform a
designated task according to the intentions of a human operator.
Since operating multiple robots simultaneously is difficult for a
human operator, we propose a cooperation style in which the human
operates one robot and the other autonomous robots assist it. In
order to assist the human operating robot, the autonomous robots must
recognize its motions in real time.
In this paper, we propose the same motion recognition mechanism
that is used in the human cognition model. We implement the motion
symbolization method and the motion recognition method using the fuzzy
filter and the template matching with predefined patterns. We
implement the "Task-Operation Model" to describe the motion of the
autonomous robot's assistance mechanism, and the ``Event Driven
Method'' to manage the execution of this motion. The effectiveness of
these methods is tested through an experiment in which two hexapod
robots lift a box in cooperation.
-
-
Movie
- An assistant robot acquired the position of the box which
a human operating robot grasped by vision. The assistant robot walked
to the work plase to assist this task.
- An assistant robot grasped the target box and lifted it
according to the motion of a human operating robot.
Photos of "T-Hexs"
Publications