Reference Number: INTAS-97-2028
INTAS logo Intelligent Neural System for Autonomous Control of a Mobile Robot
Scientific results
Home | Participans | Objectives | Expected results | Publications
Research activities | Scientific results | Summary of results
Scientific results
  • As a result of implementation of this project the following results were achieved:
    • Investigation of various concepts of autonomous control of a mobile robot
    • Neural networks for control of the robot on the basis of data from ultrasonic sensors and infrared scanner
    • Neural networks for building of the Global Route map
    • Neural Network Methods for Optimal Path Planning
    • Neural Networks for unsupervised training of the robot by means of interaction with environment
    • Intelligent Neural System which consists of different neural networks
    • Realisation of experiments and practical use of neural system for control of a mobile robot
  • The software for Neural System was transferred to hardware of the "Pioneer" (figure 1) and "Walter" (figure 2) mobile robots

    Figure 1. Pioneer mobile robot

    Figure 2. Walter mobile robot

    The experiments were performed using typical real-world environment and different kinds of obstacles. They showed capability for real-time reactions and good confirmation to the theoretical results. The robot was able to pass through narrow openings (e.g. doorways) or narrow corridors without collisions using inexact data from sensors.
  • The following papers resulted already directly from the project: click here.

Designed by Oleg Ignatiuk
The Laboratory of Artificial Neural Networks
Brest State Technical University, Belarus