Adaptive control algorithm of flexible robotic gripper by extreme learning machine. (February 2016)

• Record Type: Journal Article
• Authors: Petković, Dalibor; Seyed Danesh, Amir; Dadkhah, Mehdi; Misaghian, Negin; Shamshirband, Shahaboddin; Zalnezhad, Erfan; Pavlović, Nenad D.
• Is Part Of: Robotics and computer-integrated manufacturing. Volume 37(2016)
• Page Start: 170
• Page End: 178
• Publication Date: 2016-02
• Subjects: Flexible gripper -- Sensors -- Object detection -- Soft computing; Robots, Industrial -- Periodicals; Computer integrated manufacturing systems -- Periodicals; Robotics -- Periodicals; Robots industriels -- Périodiques; Productique -- Périodiques; Robotique -- Périodiques; 670.285
• DOI: 10.1016/j.rcim.2015.09.006
• Languages: English
• ISSNs: 0736-5845

Abstract

Abstract: Adaptive grippers should be able to detect and recognize grasping objects. To be able to do it control algorithm need to be established to control gripper tasks. Since the gripper movements are highly nonlinear systems it is desirable to avoid using of conventional control strategies for robotic manipulators. Instead of the conventional control strategies more advances algorithms can be used. In this study several soft computing methods are analyzed for robotic gripper applications. The gripper structure is fully compliant with embedded sensors. The sensors could be used for grasping shape detection. As soft computing methods, extreme learning machine (ELM) and support vector regression (SVR) were established. Also other soft computing methods are analyzed like fuzzy, neuro-fuzzy and artificial neural network approach. The results show the highest accuracy with ELM approach than other soft computing methods. Highlights: Controlling input displacement of a new adaptive compliant gripper. This design of the gripper with embedded sensors as part of its structure. To build an effective prediction model of input displacement of gripper. The impact of the variation in the input parameters.