Reference Number: INTAS-BELARUS-97-2028
INTAS logo Intelligent Neural System for Autonomous Control of a Mobile Robot
Home | Participans | Objectives | Expected results | Publications
Research activities | Scientific results | Summary of results

Project Summary

The purpose of this research is the development of on intelligent neural system for the control of a mobile transport robot.

Contents of work.

The following work packages need to be performed to develop an intelligent neural system for the management of the movement of a mobile robot. As sensor inputs, providing the source information for such a control system, the project will consider:

  • Video image of the future way from a video camera.
  • Diagram of environmental conditions from range sensor devices.
  • Dead reckoning based on wheel encoders (coordinates of initial and final point of robot movement is given)

On the basis of this information, the neural network should generate the direction and speed of movement. If necessary it should be able to correct the internal map of the environment during the movement. As a basis of such a control system, it is prepared to use the various neural nets for the different functionalities, which are to be combined in an intelligent system. In general the neural system should solve the following problems:

  • Navigation of the robot for movements in only partially known environments.
  • Formation of a region map during driving in the unknown area
  • Planning of an optimum route for the movement
  • Supervised training
  • Unsupervised training for self-organizing during the movement of the robot and update of the environment map
  • Capability for real time actions

As a result of the implementation of this project the following results are expected:

  • Research of the various concepts of autonomous control by the transport robot
  • Development and research of intelligent neural system for autonomous control by the transport robot
  • Realization of experiments and practical use of neural system for control by the transport robot

Designed by Andrey Dunets
The Laboratory of Artificial Neural Networks
Brest State Technical University, Belarus