Linear-Quadratic Regulator Control for Human Following Robot in Straight Path
Chetan Naik J1, S. L. Pinjare2, Jharna Majumdar3
1Chetan Naik J, Final Year M.Tech, Department of ECE, Nitte Meenakshi Institute of Technology, Bangalore India.
2S.L. Pinjare, Professor & Head, Department of ECE PG, Nitte Meenakshi Institute of Technology, Bangalore India.
3Jharna Majumdar, Dean R&D, Professor & Head, Department of CSE PG, Nitte Meenakshi Institute of Technology, Bangalore India.
Manuscript received on 10 July 2014 | Revised Manuscript received on 20 July 2014 | Manuscript Published on 30 July 2014 | PP: 65-67 | Volume-4 Issue-2, July 2014 | Retrieval Number: B1742074214/14©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The paper presents the design of controller for wheeled mobile robots (WMRs) which continuously follows humans indoors in straight path only. This task uses computer vision in the controller feedback loop and is referred to as vision-based control or visual servo control. Typically, visual servo techniques can be categorised into image based visual servoing (IBVS) and position-based visual servoing (PBVS). The paper discusses Image based visual servoing approaches for following human in an indoor environment.The Robotics system used here consists of camera for extracting the image features. A suitable control law is developed which can learn the robot behaviour policy and autonomously improve its performance to achieve the smooth and efficient travel path towards the object of interest.
Keywords: Embedded Computer Vision, Target Tracking, Correlation Based Template Matching, Particle Filters, Distance Measures, Re-Sampling, ARM, Beagleboard-Xm, Linux.
Scope of the Article: Robotics