The FKIE Robot System for the European Land Robot Trial 2011

This paper presents technical details of the robot framework that is used by the FKIE team for the participation in the three scenarios Mule, Approach, and Camp Security of the ELROB 2011. Our navigation software used for both, the Mule and the Approach scenario, is based on a local navigation using motion patterns. Additionally, we employ a FastSLAM mapper taking a traversability analysis and virtual 2D scans of the environment as inputs. The built map will be used to return to the start point in areas with bad GPS reception. The Camp Security software is based on a people detector using image features.

[1]  G. Gilbreath,et al.  Accurate Waypoint Navigation using Non-Differential GPS , 2002 .

[2]  Bernt Schiele,et al.  Robust Object Detection with Interleaved Categorization and Segmentation , 2008, International Journal of Computer Vision.

[3]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[4]  Dirk Schulz,et al.  A Probabilistic Exemplar Approach to Combine Laser and Vision for Person Tracking , 2006, Robotics: Science and Systems.

[5]  Evangelos E. Milios,et al.  Globally Consistent Range Scan Alignment for Environment Mapping , 1997, Auton. Robots.

[6]  Armin B. Cremers,et al.  Adaptive real-time video-tracking for arbitrary objects , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Ross A. Knepper,et al.  Differentially constrained mobile robot motion planning in state lattices , 2009 .

[9]  Michael Himmelsbach,et al.  Driving with tentacles: Integral structures for sensing and motion , 2008 .

[10]  Luc Van Gool,et al.  Fast PRISM: Branch and Bound Hough Transform for Object Class Detection , 2011, International Journal of Computer Vision.

[11]  Dirk Schulz,et al.  Offroad Navigation Using Adaptable Motion Patterns , 2011, KI - Künstliche Intelligenz.

[12]  Jan Peters,et al.  Learning complex motions by sequencing simpler motion templates , 2009, ICML '09.

[13]  Wolfram Burgard,et al.  The dynamic window approach to collision avoidance , 1997, IEEE Robotics Autom. Mag..

[14]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[15]  Armin B. Cremers,et al.  Position Estimation of Mobile Robots Considering Characteristic Terrain Properties , 2018, ICINCO.

[16]  Oliver Brock,et al.  High-speed navigation using the global dynamic window approach , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[17]  Christoph H. Lampert,et al.  Beyond sliding windows: Object localization by efficient subwindow search , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.