AUTHOR=Jiang Zhuangyi , Bing Zhenshan , Huang Kai , Knoll Alois 

TITLE=Retina-Based Pipe-Like Object Tracking Implemented Through Spiking Neural Network on a Snake Robot

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 13 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2019.00029

DOI=10.3389/fnbot.2019.00029

ISSN=1662-5218

ABSTRACT=Target tracking ability based on vision is crucial to a bio-inspired snake robot for exploring
an unknown environment. However, the traditional vision modules of snake robots are difficult
to overcome the image blur resulting from the periodic swing. A promising approach is to use
the neuromorphic vision sensor (NVS) mimicking the biological retina to detect a target at the
higher temporal frequency and in the wider dynamic range. In this study, an NVS and a spiking
neural network (SNN) were performed on a snake robot for the first time to achieve pipe-like
object tracking. An SNN based on Hough Transform was designed to detect a target with an
asynchronous event stream fed by the NVS. Combining the state of snake motion analyzed by
the joint position sensors, a tracking framework was proposed. The experimental results obtained
from the simulator demonstrated the validity of our framework and the autonomous locomotion
ability of our snake robot. Comparing the SNN model performances respectively on CPUs, GPUs,
the SNN model showed the best performance on a GPU under a simplified and synchronous
update rule while it possessed higher precision on a CPU in an asynchronous way.