Neuromorphic self-driving robot with retinomorphic vision and spike-based processing/closed-loop control
Autor: | Andreas G. Andreou, Gaspar Tognetti, Valerie Rennoll, Philippe O. Pouliquen, Heather Romney, Laxaviera Elphage, John Rattray, Tobias E. Niebur, Alejandro Pasciaroni, Daniel R. Mendat, Garrick Orchard, Christos Sapsanis, Laura F. Campbell, Kate D. Fischl, Shamaria Walker |
---|---|
Rok vydání: | 2017 |
Předmět: |
Data stream
Artificial neural network Computer science business.industry 020208 electrical & electronic engineering 02 engineering and technology Convolutional neural network TrueNorth Neuromorphic engineering Asynchronous communication 0202 electrical engineering electronic engineering information engineering Robot 020201 artificial intelligence & image processing Spike (software development) Computer vision Artificial intelligence business |
Zdroj: | CISS |
DOI: | 10.1109/ciss.2017.7926179 |
Popis: | We present our work on a neuromorphic self-driving robot that employs retinomoprhic visual sensing and spike based processing. The robot senses the world through a spike-based visual system - the Asynchronous Time-based Image Sensor (ATIS) - and processes the sensory data stream using IBM's TrueNorth Neurosynaptic System. A convolutional neural network (CNN) running on the TrueNorth determines the steering direction based on what the ATIS “sees.” The network was trained on data from three different environments (indoor hallways, large campus sidewalks, and narrow neighborhood sidewalks) and achieved steering decision accuracies from 68% to 82% on development data from each dataset. |
Databáze: | OpenAIRE |
Externí odkaz: |