Header menu link for other important links
A Novel Image-based Path Planning Algorithm for Eye-in-Hand Visual Servoing of a Redundant Manipulator in a Human Centered Environment
D. Raina, P. Mithun, , S. Kumar
Published in Institute of Electrical and Electronics Engineers Inc.
This paper presents a novel image-based path-planning and execution framework for vision-based control of a robot in a human centered environment. The proposed method involves applying Rapidly-exploring Random Tree (RRT) exploration to perform Image-Based Visual Servoing (IBVS) while satisfying multiple task constraints by exploiting robot redundancy. The methodology incorporates data-set of robot's workspace images for path-planning and design a controller based on visual servoing framework. This method is generic enough to include constraints like Field-of-View (FoV) limits, joint limits, obstacles, various singularities, occlusions etc. in the planning stage itself using task function approach and thereby avoiding them during the execution. The use of path-planning eliminates many of the inherent limitations of IBVS with eye-in-hand configuration and makes the use of visual servoing practical for dynamic and complex environments. Several experiments have been performed on a UR5 robotic manipulator to demonstrate that it is an effective and robust way to guide a robot in such environments. © 2019 IEEE.
About the journal
JournalData powered by Typeset2019 28th IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2019
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.
Open AccessNo