Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE

Fernando Perez-Peña,Arturo Morgado-Estevez,Gabriel Jimenez-Moreno,Angel Jimenez-Fernandez,Juan Lopez-Coronado,Alejandro Linares-Barranco,Francisco Gomez-Rodriguez

doi:10.3390/s131115805

Fernando Perez-Peña, Arturo Morgado-Estevez + Show 5 more

Open Access

https://doi.org/10.3390/s131115805

Copy DOI

Abstract

In this paper we present a complete spike-based architecture: from a Dynamic Vision Sensor (retina) to a stereo head robotic platform. The aim of this research is to reproduce intended movements performed by humans taking into account as many features as possible from the biological point of view. This paper fills the gap between current spike silicon sensors and robotic actuators by applying a spike processing strategy to the data flows in real time. The architecture is divided into layers: the retina, visual information processing, the trajectory generator layer which uses a neuroinspired algorithm (SVITE) that can be replicated into as many times as DoF the robot has; and finally the actuation layer to supply the spikes to the robot (using PFM). All the layers do their tasks in a spike-processing mode, and they communicate each other through the neuro-inspired AER protocol. The open-loop controller is implemented on FPGA using AER interfaces developed by RTC Lab. Experimental results reveal the viability of this spike-based controller. Two main advantages are: low hardware resources (2% of a Xilinx Spartan 6) and power requirements (3.4 W) to control a robot with a high number of DoF (up to 100 for a Xilinx Spartan 6). It also evidences the suitable use of AER as a communication protocol between processing and actuation.

Highlights

Human beings, and their ancestors before them, have evolved throughout millions of years and obviously their systems to perform tasks too
Vector Integration to Endpoint (VITE) generates the trajectory to be followed by the joint, but in contrast to approaches which require the stipulation of the desired individual joint positions, the trajectory generator operates with desired coordinates of the end vector and generates the individual joint driving functions in real-time employing geometric constraints which characterize the manipulator
This section presents several results for the whole design. These results aim to show the evolution from the original VITE algorithm design by Grossberg [11], going through its translation into spikes (SVITE), to a real robotic platform

Summary

Introduction

Their ancestors before them, have evolved throughout millions of years and obviously their systems to perform tasks too. If we take a closer look in humans, we will find that the system involved in these tasks is the central nervous system (CNS) This system is a combination of the brain and the spinal cord and, simplifying, it consists of neuron cells and uses spikes or graduated potentials to transmit on the information across the anatomy [3]. The brain integrates the information from the spinal cord and motor cortex in order to plan, coordinate and execute the desired movements. Notice that VITE is the first layer involved in a planned arm movement It does not integrate any feedback from the end robot. Visual perception is composed of an AER Dynamic Vision Sensor (DVS) retina sensor and its spike-based processing elements for object detection and targeting.

Objectives

Results

Discussion

Conclusion