Binocular Vision-Based Robot Control with Active Hand-Eye Coordination
Traditional eye-in-hand robotic systems are capable of performing versatile manipulation, but generally they can only observe a restricted workspace. As regards eye-to-hand configurations, tasks can be controlled within the field of view of the vision system with accuracy up to the pixel resolution of the vision system. In this paper, the robot workspace is further expanded by allowing cameras to be actively controlled by pan, tilt, and zoom motion. This configuration can be applied to a mobile robot equipped with a binocular vision system. The manipulator for visual servo control purpose can be either mounted on-board or in fixed configuration. To enable large and flexible workspace visual servoing with precision under such a configuration, active hand-eye coordination must be assured. The control strategy is successfully validated through convergence analysis and simulations.
KeywordsActive vision Binocular vision Hand-eye coordination Mobile robot Visual servoing Visual tracking
Unable to display preview. Download preview PDF.
- 2.Chang, W.C.: Vision-Based Control of Uncertain Systems. PhD thesis, Yale University, New Haven, CT (1997)Google Scholar
- 3.Asada, M., Tanaka, T., Hosoda, K.: Adaptive binocular visual servoing for independently moving target tracking. In: Proc. of the 2000 IEEE International Conference on Robotics and Automation, San Francisco, CA, U.S.A, IEEE Press, Los Alamitos (2000)Google Scholar
- 5.Chang, W.C.: Binocular vision-based trajectory following for autonomous robotic manipulation. Robotica. Published online by Cambridge University Press (2007), DOI:10.1017/s0263574707003505Google Scholar
- 6.Chang, W.C., Morse, A.S.: Six degree-of-freedom task encoding in vision-based control systems. In: Proc. of the 14th World Congress of IFAC. Volume B., Beijing, China, pp. 311–316. International Federation of Automatic Control (1999)Google Scholar