Intelligent feedforward control and payload estimation for a two-link robotic manipulator

• Published in: IEEE/ASME transactions on mechatronics 2003-06, Vol.8 (2), p.277-282
• Main Authors: Nho, H.C., Meckl, P.
• Format: Article
• Language: English
• Subjects: Applied sciences; Architecture; Articulated; Artificial intelligence; Computer science; control theory; systems; Control theory. Systems; Drives; Exact sciences and technology; Intelligent control; Intelligent robots; Learning and adaptive systems; Linkage mechanisms, cams; Manipulator dynamics; Manipulators; Mechanical engineering. Machine design; Multi-layer neural network; Neural networks; Payloads; PD control; Proportional control; Robot control; Robotics; Robots; Torque control; Tracking; Trajectory; Uncertainty
• ISSN: 1083-4435; 1941-014X
• DOI: 10.1109/TMECH.2003.812847

Conventional model-based computed torque control fails to produce a good trajectory tracking performance in the presence of payload uncertainty and modeling error. The challenge is to provide accurate dynamics information to the controller. A new control architecture that incorporates a neural-network, fuzzy logic and a simple proportional-derivative (PD) controller is proposed to control an articulated robot carrying a variable payload. An off-line trained feedforward (multilayer) neural network takes payload mass estimates from a fuzzy-logic mass estimator as one of the inputs to represent the inverse dynamics of the articulated robot. The effectiveness of the proposed architecture is demonstrated by experiment on a two-link planar manipulator with changing payload mass. Experimental results show that this control architecture achieves excellent tracking performance in the presence of payload uncertainty.