Humanoid localization and navigation using a visual memory

A visual memory (VM) is a topological map in which a set of key images organized in form of a graph represents an environment. In this paper, a navigation strategy for humanoid robots addressing the problems of localization, visual path planning and path following based on a VM is proposed. Assuming that the VM is given, the main contributions of the paper are: 1) A novel pure vision-based localization method. 2) The introduction of the estimated rotation between key images in the path planning stage to benefit paths with enough visual information and with less effort of robot rotation. 3) The integration of the complete navigation strategy and its experimental evaluation with a Nao robot in an unstructured environment. The humanoid robot is modeled as a holonomic system and the strategy might be used in different scenarios like corridors, uncluttered or cluttered environments.

[1]  Olivier Stasse,et al.  Humanoid Locomotion Planning for Visually Guided Tasks , 2012, Int. J. Humanoid Robotics.

[2]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Michel Dhome,et al.  Monocular Vision for Mobile Robot Localization and Autonomous Navigation , 2007, International Journal of Computer Vision.

[4]  Andrei Herdt,et al.  Online Walking Motion Generation with Automatic Footstep Placement , 2010, Adv. Robotics.

[5]  Tsukasa Ogasawara,et al.  Indoor Navigation for a Humanoid Robot Using a View Sequence , 2009, Int. J. Robotics Res..

[6]  Marilena Vendittelli,et al.  Vision-based maze navigation for humanoid robots , 2017, Auton. Robots.

[7]  Marilena Vendittelli,et al.  Humanoid odometric localization integrating kinematic, inertial and visual information , 2016, Auton. Robots.

[8]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[9]  Gustavo Arechavaleta,et al.  Visual servo walking control for humanoids with finite-time convergence and smooth robot velocities , 2016, Int. J. Control.

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

[11]  Philippe Martinet,et al.  Autonomous Navigation of Vehicles from a Visual Memory Using a Generic Camera Model , 2009, IEEE Transactions on Intelligent Transportation Systems.

[12]  Bill Triggs,et al.  Autocalibration from Planar Scenes , 1998, ECCV.

[13]  Seth Hutchinson,et al.  Visual Servo Control Part I: Basic Approaches , 2006 .

[14]  Gustavo Arechavaleta,et al.  Visual path following using a sequence of target images and smooth robot velocities for humanoid navigation , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[15]  Cancelling the sway motion of dynamic walking in visual servoing , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Claire Dune,et al.  Vision-guided motion primitives for humanoid reactive walking: Decoupled versus coupled approaches , 2015, Int. J. Robotics Res..

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

[18]  Masayuki Inaba,et al.  Visual navigation using view-sequenced route representation , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[19]  Oussama Kanoun,et al.  Real-time prioritized kinematic control under inequality constraints for redundant manipulators , 2011, Robotics: Science and Systems.

[20]  François Chaumette,et al.  2 1/2 D Visual Servoing with Respect to Unknown Objects Through a New Estimation Scheme of Camera Displacement , 2000, International Journal of Computer Vision.

[21]  Laurent George,et al.  Humanoid robot indoor navigation based on 2D bar codes: application to the NAO robot , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[22]  G. Schmidt,et al.  Vision-Guided Walking in a Structured Indoor Scenario , 2005 .

[23]  Carlos Sagüés,et al.  Visual navigation of wheeled mobile robots using direct feedback of a geometric constraint , 2014, Auton. Robots.