AER Neuro-Inspired interface to Anthropomorphic Robotic Hand

Jiménez-Moreno

Linares-Barranco

et al. 2012

Sensors

In this paper we present a neuro-inspired spike-based close-loop controller written in VHDL and implemented for FPGAs. This controller has been focused on controlling a DC motor speed, but only using spikes for information representation, processing and DC motor driving. It could be applied to other motors with proper driver adaptation. This controller architecture represents one of the latest layers in a Spiking Neural Network (SNN), which implements a bridge between robotics actuators and spike-based processing layers and sensors. The presented control system fuses actuation and sensors information as spikes streams, processing these spikes in hard real-time, implementing a massively parallel information processing system, through specialized spike-based circuits. This spike-based close-loop controller has been implemented into an AER platform, designed in our labs, that allows direct control of DC motors: the AER-Robot. Experimental results evidence the viability of the implementation of spike-based controllers, and hardware synthesis denotes low hardware requirements that allow replicating this controller in a high number of parallel controllers working together to allow a real-time robot control.

Section: Experimental Platform: the Aer-robotmentioning

confidence: 99%

A Neuro-Inspired Spike-Based PID Motor Controller for Multi-Motor Robots with Low Cost FPGAs

Jiménez-Moreno

Linares-Barranco

et al. 2012

Sensors

“…These systems process the information into a continuous way, without discretization into frames. Hardware implementations of these systems are usually composed of several steps: sensors [6], filters [13], convolutions [3], actuators [14], etc… Engineers found a great problem at this point because they need to communicate thousands of neurons from one chip to the next chip, but they have a limitation in the number of pins. Address-Event-Representation solves this problem [4].…”

Section: Visitors Experiencementioning

confidence: 99%

Live demonstration: On the distance estimation of moving targets with a Stereo-Vision AER system

Domínguez-Morales

2012 IEEE International Symposium on Circuits and Systems

Paz-Vicente

et al. 2012

Self Cite

Distance calculation is always one of the most important goals in a digital stereoscopic vision system. In an AER system this goal is very important too, but it cannot be calculated as accurately as we would like. This demonstration shows a first approximation in this field, using a disparity algorithm between both retinas. The system can make a distance approach about a moving object, more specifically, a qualitative estimation. Taking into account the stereo vision system features, the previous retina positioning and the very important Hold&Fire building block, we are able to make a correlation between the spike rate of the disparity and the distance. Whole system with two DVS128 retinas (left), two USB-AER boards (middle-left), a Virtex-5 FPGA (middle-right) and the USBminiAER2 (right)

“…6). This new platform is an improved version of a prototype designed to control an anthropomorphic AER hand [6]. The platform is designed around a Spartan 3 400 FPGA with 4 parallel AER connectors (2 input and 2 output), 4 power stages to manage 4 DC motors with two encoder channels and 4 hall effect current sensor to measure the power consumption of the motors.…”

Section: Aer Cpgmentioning

confidence: 99%

“…The experiment that we present in this paper is based on connecting the AER output of the TmpDiff128 retina [5] to the USB-AER platform [7] and from there to the AER-Robot platform [6]. The USB-AER FPGA has been programmed with a new visual filter based on the architecture of the frame-grabber tool in [7].…”

Section: Introductionmentioning

confidence: 99%

Using FPGA for visuo-motor control with a silicon retina and a humanoid robot

Linares-Barranco

Gómez-Rodríguez

2007 IEEE International Symposium on Circuits and Systems (ISCAS)

et al. 2007

Self Cite

Abstract-The address-event representation (AER) is a neuromorphic communication protocol for transferring asynchronous events between VLSI chips. The event information is transferred using a high speed digital parallel bus. This paper present an experiment based on AER for visual sensing, processing and finally actuating a robot. The AER output of a silicon retina is processed by an AER filter implemented into a FPGA to produce a mimicking behaviour in a humanoid robot (The RoboSapiens V2). We have implemented the visual filter into the Spartan II FPGA of the USB-AER platform and the Central Pattern Generator (CPG) into the Spartan 3 FPGA of the AER-Robot platform, both developed by authors.