Active Vision During Coordinated Head/Eye Movements in a Humanoid Robot

While looking at a point in the scene, humans continually perform smooth eye movements to compensate for involuntary head rotations. Since the optical nodal points of the eyes do not lie on the head rotation axes, this behavior yields useful 3-D information in the form of visual parallax. Here, we describe the replication of this behavior in a humanoid robot. We have developed a method for egocentric distance estimation based on the parallax that emerges during compensatory head/eye movements. This method was tested in a robotic platform equipped with an anthropomorphic neck and two binocular pan-tilt units specifically designed to reproduce the visual input signals experienced by humans. We show that this approach yields accurate and robust estimation of egocentric distance within the space nearby the agent. These results provide a further demonstration of how behavior facilitates the solution of complex perceptual problems.

[1]  Michele Rucci,et al.  Active 3D Vision through Gaze Relocation in a Humanoid Robot , 2009, Int. J. Humanoid Robotics.

[2]  Michael Kühl,et al.  An unexpected specialization for horizontal disparity in primate primary visual cortex , 2022 .

[3]  J. Demer,et al.  Human gaze stabilization during natural activities: translation, rotation, magnification, and target distance effects. , 1997, Journal of neurophysiology.

[4]  W MurrayDavid,et al.  Simultaneous Localization and Map-Building Using Active Vision , 2002 .

[5]  M. Guerraz,et al.  Influence of motion parallax in the control of spontaneous body sway , 2000, Experimental Brain Research.

[6]  Thomas S. Huang,et al.  Motion and Structure from Image Sequences , 1992 .

[7]  G. D. Paige,et al.  The primate vestibulo-ocular reflex during combined linear and angular head motion , 2004, Experimental Brain Research.

[8]  Olivier D. Faugeras,et al.  The geometry of multiple images - the laws that govern the formation of multiple images of a scene and some of their applications , 2001 .

[9]  Ehud Rivlin,et al.  Head Movements for Depth Perception: Praying Mantis versus Pigeon , 2005 .

[10]  Michele Rucci,et al.  Active estimation of distance in a robotic system that replicates human eye movement , 2007, Robotics Auton. Syst..

[11]  Mohan M. Trivedi,et al.  High-Speed Extraction of 3D Structure of Selectable Quality Using a Translating Camera , 1996, Comput. Vis. Image Underst..

[12]  Giulio Sandini,et al.  Active Tracking Strategy for Monocular Depth Inference over Multiple Frames , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  B Rogers,et al.  Motion Parallax as an Independent Cue for Depth Perception , 1979, Perception.

[14]  Alan Yuille,et al.  Active Vision , 2014, Computer Vision, A Reference Guide.

[15]  Michele Rucci,et al.  Motion parallax from microscopic head movements during visual fixation , 2012, Vision Research.

[16]  M. Rucci,et al.  Microsaccades Precisely Relocate Gaze in a High Visual Acuity Task , 2010, Nature Neuroscience.

[17]  Nicholas Ayache,et al.  Artificial vision for mobile robots - stereo vision and multisensory perception , 1991 .

[18]  Ray A. Jarvis,et al.  A Perspective on Range Finding Techniques for Computer Vision , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Yeung Sam Hung,et al.  A Kalman Filter Approach to Direct Depth Estimation Incorporating Surface Structure , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  A. A. Skavenski,et al.  Miniature eye movement. , 1973, Science.

[21]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Martina Poletti,et al.  Miniature eye movements enhance fine spatial detail , 2007, Nature.

[23]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[24]  Karl Kral,et al.  Behavioural–analytical studies of the role of head movements in depth perception in insects, birds and mammals , 2003, Behavioural Processes.

[25]  R. Bajcsy.  Active perception , 1988 .

[26]  Daniel Bullock,et al.  Integrating robotics and neuroscience: brains for robots, bodies for brains , 2007, Adv. Robotics.

[27]  David W. Murray,et al.  Simultaneous Localization and Map-Building Using Active Vision , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  R. W. DITCHBURN,et al.  Vision with a Stabilized Retinal Image , 1952, Nature.

[29]  Karl Kral,et al.  Motion parallax as a source of distance information in locusts and mantids , 2007, Journal of Insect Behavior.

[30]  Rama Chellappa,et al.  A Fast Bilinear Structure from Motion Algorithm Using a Video Sequence and Inertial Sensors , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Mandyam V. Srinivasan.  Distance Perception in Insects , 1992 .

[32]  Michele Rucci,et al.  Fixational eye movements, natural image statistics, and fine spatial vision , 2008, Network.

[33]  Hujun Bao,et al.  Consistent Depth Maps Recovery from a Video Sequence , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  J. Victor,et al.  Temporal Encoding of Spatial Information during Active Visual Fixation , 2012, Current Biology.

[35]  R. D. Watkins,et al.  THE OPTICAL SYSTEM OF THE EYE , 1970 .

[36]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[37]  Reinhold Necker,et al.  Head-bobbing of walking birds , 2007, Journal of Comparative Physiology A.

[38]  Yiannis Aloimonos,et al.  Estimating the heading direction using normal flow , 1994, International Journal of Computer Vision.

[39]  Lee W. Casperson,et al.  Head Movement and Vision in Underwater-Feeding Birds of Stream, Lake, and Seashore , 1999 .

[40]  Hermann Wagner,et al.  Depth generalization from stereo to motion parallax in the owl , 2002, Journal of Comparative Physiology A.