A real-time Model Based Visual Servoing application for a differential drive mobile robot using Beaglebone Black embedded system

This paper presents a Model Based Visual Servoing (MBVS) control strategy for a differential drive mobile robot navigation using single camera attached on the robot platform. Four points image features are used to compute the angular velocities of the right wheel and the left wheel. The model based visual servoing scheme was simulated using visual servoing platform (ViSP) libraries. The simulation results show the effectiveness of the designed control law. The control law performances are measured both in the image space and in the control input space. The effectiveness of the MBVS has also been verified in real-time experiments using Beaglebone Black as the main hardware controller.

[1]  T. Martin McGinnity,et al.  A position based visual tracking system for a 7 DOF robot manipulator using a Kinect camera , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[2]  Rs Roel Pieters,et al.  Visual Servo Control , 2012 .

[3]  Sonya Coleman,et al.  Image-Based Visual Servoing of a 7-DOF Robot Manipulator Using an Adaptive Distributed Fuzzy PD Controller , 2014, IEEE/ASME Transactions on Mechatronics.

[4]  L. Behera,et al.  A computationally efficient approach for Jacobian approximation of image based visual servoing for joint limit avoidance , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[5]  François Chaumette,et al.  Visual servo control. I. Basic approaches , 2006, IEEE Robotics & Automation Magazine.

[6]  Ashok K. Turuk,et al.  Dead Reckoning Localization Technique for Mobile Wireless Sensor Networks , 2015, ArXiv.

[7]  Ashok K. Turuk,et al.  Dead reckoning localisation technique for mobile wireless sensor networks , 2015, IET Wirel. Sens. Syst..

[8]  Giuseppe Oriolo,et al.  A position-based visual servoing scheme for following paths with nonholonomic mobile robots , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Lawrence Wai-Choong Wong,et al.  A Novel Map-Based Dead-Reckoning Algorithm for Indoor Localization , 2014, J. Sens. Actuator Networks.

[10]  Patrick Rives,et al.  Visual Servoing Based on a Task Function Approach , 1989, ISER.

[11]  Éric Marchand,et al.  ViSP for visual servoing: a generic software platform with a wide class of robot control skills , 2005, IEEE Robotics & Automation Magazine.

[12]  Carlos Sagüés,et al.  Pose-estimation-based visual servoing for differential-drive robots using the 1D trifocal tensor , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Alexander Zelinsky,et al.  Range and pose estimation for visual servoing of a mobile robot , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[14]  Alexander Rudolph,et al.  Quantification and Estimation of Differential Odometry Errors in Mobile Robotics with Redundant Sensor Information , 2003, Int. J. Robotics Res..