Bio-inspired rough terrain contact patch perception

We present a new bio-inspired system for automatically finding foot-scale curved surface patches in rough rocky terrain. These patches are intended to provide a reasonable set of choices for higher-level footfall selection algorithms, and are pre-filtered for several attributes - including location, curvature, and normal - that we observed humans to prefer. Input is from a 640 × 480 depth camera augmented with a 9-DoF inertial measurement unit to sense the direction of gravity. The system is capable of finding approximately 700 patches/second on commodity hardware, though the intention is not to find as many patches as possible but to reasonably sample upcoming terrain with quality patches. Sixty recordings of human subjects traversing rocky trails were analyzed to give a baseline for target patch properties. While the presented system is not designed to select a single foothold, it does find a set of patches for possible footholds which are statistically similar to the patches humans select.

[1]  A. Patla,et al.  Visual information from the lower visual field is important for walking across multi-surface terrain , 2008, Experimental Brain Research.

[2]  Daniel Maier,et al.  Integrated perception, mapping, and footstep planning for humanoid navigation among 3D obstacles , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Nicholas Roy,et al.  Collision detection in legged locomotion using supervised learning , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Masahiro Fujita,et al.  Stair climbing for humanoid robots using stereo vision , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[5]  Aftab E. Patla,et al.  Review article Understanding the roles of vision in the control of human locomotion , 1997 .

[6]  Tuan Q. Pham.  Non-maximum Suppression Using Fewer than Two Comparisons per Pixel , 2010, ACIVS.

[7]  Reid G. Simmons,et al.  Perception, Planning, and Control for Autonomous Walking With the Ambler Planetary Rover , 1996, Int. J. Robotics Res..

[8]  Christopher K. Rhea,et al.  Control of adaptive locomotion: effect of visual obstruction and visual cues in the environment , 2006, Experimental Brain Research.

[9]  David W. Jacobs,et al.  Mesh saliency , 2005, ACM Trans. Graph..

[10]  Marsette Vona,et al.  Moving Volume KinectFusion , 2012, BMVC.

[11]  Daisuke Kihara,et al.  Salient critical points for meshes , 2007, Symposium on Solid and Physical Modeling.

[12]  Stefan Schaal,et al.  Learning, planning, and control for quadruped locomotion over challenging terrain , 2011, Int. J. Robotics Res..

[13]  Heiko Hirschmüller,et al.  Stereo-vision-based navigation of a six-legged walking robot in unknown rough terrain , 2012, Int. J. Robotics Res..

[14]  Michael A. Greenspan,et al.  On the Repeatability of 3D Point Cloud Segmentation Based on Interest Points , 2012, 2012 Ninth Conference on Computer and Robot Vision.

[15]  Nassir Navab,et al.  Adaptive neighborhood selection for real-time surface normal estimation from organized point cloud data using integral images , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  David Wettergreen,et al.  Dante II: Technical Description, Results, and Lessons Learned , 1999, Int. J. Robotics Res..

[17]  Markus H. Gross,et al.  Efficient simplification of point-sampled surfaces , 2002, IEEE Visualization, 2002. VIS 2002..

[18]  Gabriel Taubin,et al.  An improved algorithm for algebraic curve and surface fitting , 1993, 1993 (4th) International Conference on Computer Vision.

[19]  Marsette Vona,et al.  Sparse surface modeling with curved patches , 2013, 2013 IEEE International Conference on Robotics and Automation.

[20]  Wolfram Burgard,et al.  A Bayesian regression approach to terrain mapping and an application to legged robot locomotion , 2009, J. Field Robotics.

[21]  A E Patla,et al.  Where and when do we look as we approach and step over an obstacle in the travel path? , 1997, Neuroreport.

[22]  Andrew Y. Ng,et al.  Stereo vision and terrain modeling for quadruped robots , 2009, 2009 IEEE International Conference on Robotics and Automation.

[23]  Satoshi Kagami,et al.  Autonomous navigation of a humanoid robot over unknown rough terrain using a laser range sensor , 2012, Int. J. Robotics Res..

[24]  Jorge Dias,et al.  Relative Pose Calibration Between Visual and Inertial Sensors , 2007, Int. J. Robotics Res..

[25]  A. E. Patla,et al.  Gaze fixation patterns for negotiating complex ground terrain , 2007, Neuroscience.

[26]  Hyo-Kyung Lee,et al.  Foot Placement Selection Using Non-geometric Visual Properties , 2005, Int. J. Robotics Res..

[27]  Marsette Vona,et al.  Curved surface contact patches with quantified uncertainty , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[28]  M. Hollands,et al.  Visually guided stepping under conditions of step cycle-related denial of visual information , 1996, Experimental Brain Research.

[29]  Frédo Durand,et al.  A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach , 2006, International Journal of Computer Vision.

[30]  Olivier Stasse,et al.  Toward Reactive Vision-Guided Walking on Rough Terrain: An Inverse-Dynamics Based Approach , 2014, Int. J. Humanoid Robotics.

[31]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[32]  Takeo Kanade,et al.  Footstep Planning for the Honda ASIMO Humanoid , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[33]  Andrew W. Fitzgibbon,et al.  KinectFusion: Real-time dense surface mapping and tracking , 2011, 2011 10th IEEE International Symposium on Mixed and Augmented Reality.

[34]  Kevin Blankespoor,et al.  BigDog, the Rough-Terrain Quadruped Robot , 2008 .

[35]  Alfred A. Rizzi,et al.  Autonomous navigation for BigDog , 2010, 2010 IEEE International Conference on Robotics and Automation.