eMorph: Towards Neuromorphic Robotic Vision

Abstract The eMorph project aims at introducing a new concept for vision in the field of humanoid robotics. The system that is currently being developed is inspired by the biology of mammalian visual systems, introducing concepts such as stimulus-driven signal acquisition and processing, together with space-variant sensor design coupled with active vision. This approach is leading to the realization of a system that goes beyond current thinking in robotic vision.

[1]  Giacomo Indiveri,et al.  A serial communication infrastructure for multi-chip address event systems , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[2]  Giulio Sandini,et al.  Object-based Visual Attention: a Model for a Behaving Robot , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[3]  Tobi Delbrück,et al.  A 128$\times$ 128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor , 2008, IEEE Journal of Solid-State Circuits.

[4]  Giorgio Metta,et al.  Towards long-lived robot genes , 2008, Robotics Auton. Syst..

[5]  Michael Hofstätter,et al.  A SPARC-compatible general purpose address-event processor with 20-bit l0ns-resolution asynchronous sensor data interface in 0.18μm CMOS , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[6]  Chiara Bartolozzi,et al.  Attentive motion sensor for mobile robotic applications , 2011, 2011 IEEE International Symposium of Circuits and Systems (ISCAS).

[7]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.