Real-time robot vision for collision avoidance inspired by neuronal circuits of insects

A real-time vision sensor for collision avoidance was designed. To respond selectively to approaching objects on direct collision course, the sensor employs an algorithm inspired by the visual nervous system in a locust, which can avoid a collision robustly by using visual information. We implemented the architecture of the locust nervous system with a compact hardware system which contains mixed analog- digital integrated circuits consisting of an analog resistive network and field-programmable gate array (FPGA) circuits. The response properties of the system were examined by using simulated movie images, and the system was tested also in real- world situations by loading it on a motorized car. The system was confirmed to respond selectively to colliding objects even in complicated real-world situations.

[1]  P. Simmons,et al.  Seeing what is coming: building collision-sensitive neurones , 1999, Trends in Neurosciences.

[2]  Tetsuya Yagi,et al.  An analog VLSI chip emulating sustained and transient response channels of the vertebrate retina , 2003, IEEE Trans. Neural Networks.

[3]  Richard Stafford,et al.  A bio-inspired visual collision detection mechanism for cars: Optimisation of a model of a locust neuron to a novel environment , 2006, Neurocomputing.

[4]  F C Rind,et al.  Intracellular characterization of neurons in the locust brain signaling impending collision. , 1996, Journal of neurophysiology.

[5]  G. Linan,et al.  A bioinspired collision detection algorithm for VLSI implementation , 2005, SPIE Microtechnologies.

[6]  N. Franceschini,et al.  From insect vision to robot vision , 1992 .

[7]  S. Bermudez i Badia,et al.  A collision avoidance model based on the Lobula giant movement detector (LGMD) neuron of the locust , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[8]  G. Laurent,et al.  Elementary Computation of Object Approach by a Wide-Field Visual Neuron , 1995, Science.

[9]  G. Linan,et al.  A bioinspired vision chip architecture for collision detection in automotive applications , 2005, SPIE Microtechnologies.

[10]  Paul F. M. J. Verschure,et al.  Collision avoidance using a model of the locust LGMD neuron , 2000, Robotics Auton. Syst..

[11]  A. Borst,et al.  A look into the cockpit of the fly: visual orientation, algorithms, and identified neurons , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[12]  Barbara Webb,et al.  Robots in invertebrate neuroscience , 2002, Nature.

[13]  Tetsuya Yagi,et al.  Bio-Inspired Real-Time Robot Vision for Collision Avoidance , 2008, J. Robotics Mechatronics.

[14]  F. Rind,et al.  Neural network based on the input organization of an identified neuron signaling impending collision. , 1996, Journal of neurophysiology.

[15]  W Reichardt,et al.  Visual control of orientation behaviour in the fly: Part I. A quantitative analysis , 1976, Quarterly Reviews of Biophysics.

[16]  G Indiveri,et al.  Neuromorphic Vision Sensors , 2000, Science.

[17]  Tetsuya Yagi,et al.  An image pre-processing system employing neuromorphic 100 /spl times/ 100 pixel silicon retina [robot vision applications] , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[18]  Michael O'Shea,et al.  The anatomy and output connection of a locust visual interneurone; the lobular giant movement detector (LGMD) neurone , 1974, Journal of comparative physiology.

[19]  Nicolas Franceschini,et al.  Visual guidance based on optic flow: a biorobotic approach , 2004, Journal of Physiology-Paris.