Kyouichi Tatsuno

An experimental robot system for power distribution line maintenance robots - System architecture and bolt insertion experiment -

We are developing a conceptual design for a power distribution line maintenance robot system using a CG (computer graphics) simulator and an experimental robot system. This system is a semi-autonomous robot system that performs tasks using task-level instructions. An operator directs the tasks, for example inserting a bolt into a hole, and clicks the work objects ldquoBoltrdquo and ldquoHolerdquo in the picture on the display with a mouse.

An example of open robot controller architecture

In this paper, we propose an architecture for easy construction of an open robot controller. The controller is a multi-agent system which has six agents: the man-machine interface, task planner, motion planner, arm controller, tool controller and CG display. The controller also has two databases: the task knowledge database and the robot/environment database. Based on this controller architecture, we are constructing a CG simulator for a power distribution line maintenance robot and are executing simulations of the maintenance tasks.

Conceptual Design of a Power Distribution Line Maintenance Robot Using a Developed CG Simulator and Experimental Robot System

We have been developing a conceptual design for a power distribution line maintenance robot system using a CG (Computer Graphics) simulator and an experimental robot system. This system is a semi-autonomous robot system which performs - tasks with task level instructions. We developed the design while during construction of the CG simulator. We believe that we demonstrate a possible solution to working up a semi-autonomous robot system.

Vision for a Power Distribution Line Maintenance Robot -Environments Input

This paper describes a vision system for a power distribution line maintenance robot. The robot will perform a task, for example, a switch gear installation task automatically. To perform the task, 3D model of work environments are constructed in a computer. Target positions for robot commands are generated using the work environment 3D model. We investigated three methods to superimpose 3D frame models of working environment parts on the photographs: 1) Manually superimposing method by a mouth, 2) Manually pointing method, and 3) Automatically superimposing method.

The work environment input for a power distribution line maintenance robot

This paper describes two methods to input work environments around an electric pole by a vision system for a power distribution line maintenance robot. One is to superimpose 3D frame models on images of components in the environments by an operation. Other is to superimpose 3D frame models on images of components in the environments automatically. We can make the work environment input by the manual and automatical superimposing method.