CAEPIA 2005: Current Topics in Artificial Intelligence pp 470-479 | Cite as
Training and Analysis of Mobile Robot Behaviour Through System Identification
Abstract
In this paper we describe a new procedure to obtain the control code for a mobile robot, based on system identification: Initially, the robot is controlled by a human operator, who manually guides it through a desired sensor-motor task. The robot’s motion is then “identified” using the NARMAX system identification technique. The resulting transparent model can subsequently be used to control the movement of the robot.
Using a transparent mathematical model for robot control furthermore has the advantage that the robot’s motion can be analysed and characterised quantitatively, resulting in a better understanding of robot-environment interaction.
We demonstrate this approach to robot programming in experiments with a Magellan Pro mobile robot, using the task of door traversal as a testbed.
Keywords
Mobile Robot Robot Controller Mobile Robotic Sonar Sensor Robot ProgrammingPreview
Unable to display preview. Download preview PDF.
References
- 1.Korenberg, M., Billings, S., Liu, Y.P., McIlroy, P.J.: Orthogonal parameter estimation algorithm for non-linear stochastic systems. International Journal of Control 48, 193–210 (1988)MATHCrossRefMathSciNetGoogle Scholar
- 2.Nehmzow, U., Iglesias, R., Kyriacou, T., Billings, S.: Task identification and characterization in mobile robotics. In: Proceedings of TAROS 2004 - Towards Autonomous Robotic Systems (2004)Google Scholar
- 3.Nehmzow, U., Iglesias, R., Kyriacou, T., Billings, S.: Robot programming through a combination of manual training and system identification. In: 2nd European Conference on Mobile Robots (2005)Google Scholar
- 4.Iglesias, R., Kyriacou, T., Nehmzow, U., Billings, S.: Cross-platform programming through system identication. In: Proceedings of TAROS 2004 - Towards Autonomous Robotic Systems (2004)Google Scholar
- 5.Iglesias, R., Nehmzow, U., Kyriacou, T., Billings, S.: Self-localisation through system identification. In: 2nd European Conference on Mobile Robots (2005)Google Scholar
- 6.Billings, S., Chen, S.: The determination of multivariable nonlinear models for dynamical systems. In: Leondes, C. (ed.) Neural Network Systems, Techniques and Applications, pp. 231–278. Academic press, London (1998)Google Scholar
- 7.Sobol, I.M.: Sensitivity estimates for nonlinear mathematical models. Mathematical Modelling and Computational Experiment 1, 407–414 (1993)MATHMathSciNetGoogle Scholar