An integrated vision-guided robotic system for rapid vehicle inspection

This paper presents the design and integration of a vision-guided robotic system for automated and rapid vehicle inspection. The main objective of this work is to achieve a seamless and efficient integration of several sensors and robotic components to rapidly acquire RGB-D data over the surface of a vehicle in order to efficiently navigate a robotic manipulator along the vehicle's surface and within regions of interest that are selectively identified. An efficient and accurate integration of information from multiple RGB-D sensors is proposed to achieve fully automated and rapid 3D profiling of automotive vehicles of various types and shapes. The proposed integrated system merges all components while taking into consideration strict requirements in the context of vehicle security screening. Experimental results at the different processing stages are presented and analyzed.

[1]  Henry Fuchs,et al.  Encumbrance-free telepresence system with real-time 3D capture and display using commodity depth cameras , 2011, 2011 10th IEEE International Symposium on Mixed and Augmented Reality.

[2]  Lawrence Carin,et al.  Application of the theory of optimal experiments to adaptive electromagnetic-induction sensing of buried targets , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Pierre Payeur,et al.  Rapid 3D Modeling and Parts Recognition on Automotive Vehicles Using a Network of RGB-D Sensors for Robot Guidance , 2013, J. Sensors.

[4]  Ligang Liu,et al.  Scanning 3D Full Human Bodies Using Kinects , 2012, IEEE Transactions on Visualization and Computer Graphics.

[5]  Camillo J. Taylor,et al.  Dynamic Sensor Planning and Control for Optimally Tracking Targets , 2003, Int. J. Robotics Res..

[6]  Philip J. Noonan,et al.  The design and initial calibration of an optical tracking system using the Microsoft Kinect , 2011, 2011 IEEE Nuclear Science Symposium Conference Record.

[7]  C. Ascher,et al.  Adaptive path planning for a VTOL-UAV , 2008, 2008 IEEE/ION Position, Location and Navigation Symposium.

[8]  Howie Choset,et al.  Path Planning for Robotic Demining: Robust Sensor-Based Coverage of Unstructured Environments and Probabilistic Methods , 2003, Int. J. Robotics Res..

[9]  Peter Lindstrom,et al.  Out-of-core simplification of large polygonal models , 2000, SIGGRAPH.

[10]  P. Payeur,et al.  Calibration of a network of Kinect sensors for robotic inspection over a large workspace , 2013, 2013 IEEE Workshop on Robot Vision (WORV).

[11]  Y. Imamura,et al.  Design and characteristics of a parallel link compliant wrist , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[12]  Ana-Maria Cretu,et al.  Salient features based on visual attention for multi-view vehicle classification , 2011, 2011 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA) Proceedings.

[13]  Raul A. Romero,et al.  Athena Mars rover science investigation , 2003 .

[14]  Pierre Payeur,et al.  Trajectory planning for surface following with a manipulator under RGB-D visual guidance , 2013, 2013 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).