19 February 1988 Artificial Neural-Net Based Intelligent Robotics Control
Author Affiliations +
Proceedings Volume 0848, Intelligent Robots and Computer Vision VI; (1988) https://doi.org/10.1117/12.942801
Event: Advances in Intelligent Robotics Systems, 1987, Cambridge, CA, United States
Fast real-time intelligent control of dynamic systems can be implemented with a combination of logic-based (higher level) strategies and automatic reflexive pattern driven responses generated with artificial neural-nets (ANN). In this paper we are concerned with the adaptive control of a robot manipulator with two degrees of freedom. The objective is to move the end effector of a two limbed manipulator towards a target point until the positions of two coincide. The task is to generate the control signals for movement of the arm through the use of ANN. Control algorithm is computationally simple and robust due to the exploitation of highly parallel information processing capabilities of multilayered neural-nets. Feasibility of obstacle avoidance is discussed also. The proposed approach was evaluated with a computer simulation. A feedforward neural-net was used for this purpose. The results are presented and discussed in this paper.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yoh-Han Pao, Yoh-Han Pao, Dejan J. Sobajic, Dejan J. Sobajic, "Artificial Neural-Net Based Intelligent Robotics Control", Proc. SPIE 0848, Intelligent Robots and Computer Vision VI, (19 February 1988); doi: 10.1117/12.942801; https://doi.org/10.1117/12.942801


Back to Top