1
Positioning, 2011, 2, 65-77 doi:10.4236/pos.2011.22007 Published Online May 2011 (http://www.SciRP.org/journal/pos)
Machine Perception Through Natural Intelligence Rostyslav Sklyar Verchratskogo st. 15-1, Lviv 79010 Ukraine Email: sklyar@tsp.lviv.ua Received December 30th , 2010; revised March 1st , 2011; accepted April 20th, 2011.
ABSTRACT The sensing organs are exponentially better than any of analogous artificial ones. That is why using them in full scale is a perspective trend to the efficient (advanced) machine perception. On the other hand, limitations of sensing organs could be replaced by the perfect artificial ones with the subsequent training the nervous system on their output signals. An attempt to lay down the foundations of biosensing by natural sensors and in addition to them by the artificial transducers of physical quantities, also with their expansion into space arrays and external/implantable functioning in relation to the nervous system is performed. The advances in nanotechnology are opening the way to achieving direct electrical contact of nanoelectronic structures with electrically and electrochemically active neurocellular structures. The transmission of the sensors’ signals to a processing unit has been maintaining by an electromagnetic transistor/memristor (externally) and superconducting transducer of ionic currents (implantable). The arrays of the advanced sensors give us information about the space and direction dynamics of the signals' spreading.The measuring method and necessary performance data of the sensor for the robot’s orientation in the ambient magnetic field with living being-machine interaction in order to obtain input and output signals from brain and motor nerves to the measurement system and vice versa are introduced. The range of applied sensors differs from an induction sensor to superconducting induction magnetometer. The analytical expressions for arrangements of the head sensors in differential and vector (3D) relative positions are deduced. Sensitivity of the perception method makes it possible to recognize the linear translation of 10!2 m and disposal in space of 10!3 m3. Interaction between living beings and robotic equipment is given analytical treatment. Keywords: Magnetic Field, Induction Sensor, SuFET, Nerve Impulses, Interface, Gradiometer, Sensing Area
1. Introduction. Artificial Sensors with the Human Machine Interface Electronic Nose is a smart instrument that is designed to detect and discriminate among complex odours using an array of sensors. The array of sensors consists of a number of broadly tuned (non-specific) sensors that are treated with a variety of odour-sensitive biological or chemical materials [1]. This instrument provides a rapid, simple and noninvasive sampling technique, for the detection and identification of a range of volatile compounds. The key function of an electronic nose is to mimic human olfactory system. Typically an electronic nose consists of three elements: a sensor array which is exposed to the volatiles, conversion of the sensor signals to a readable format and software analysis of the data to produce characteristic outputs related to the odour encountered. The main parts of a typical biosensor are shown in Figure 1. The artificial tactile sensor integrates a micro electro-mechanical system (MEMS) array having a number
of sensing elements (16 channels in about 20 mm2) similar to the innervation density of mechanoreceptors in the hand (about 1 unit/ mm2). The technological approach is based on a 3D MEMS core unit with a soft and compliant packaging. The microsensor can be integrated with a packaging architecture resulting in a robust and compliant tactile sensor for application in artificial hands, while sensitive enough to detect slip events, showing that silicon based tactile sensors can go beyond laboratory practice [2]. The tactile sensor array, depicted in Figure 2, had 16 channels as total tactile sensor outputs. The measurement of magnetic fields (MFs) is an important task for the majority of autonomous missions. The distribution of permanent and the value of periodical MFs give the data about placement of ferromagnetic objects and sources of EM radiation respectively. On the other hand, these signals will be a reference point and guiding line for a walking robot (Figure 3). Detection of some magnetic anomalies of the Earth’s MF and their variations is provided by fluxgate sensors
Copyright © 2011 SciRes.!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!POS
IOP PUBLISHING
MEASUREMENT SCIENCE AND TECHNOLOGY
doi:10.1088/0957-0233/23/11/115101
Meas. Sci. Technol. 23 (2012) 115101 (7pp)
Position and movement sensing at metre standoff distances using ambient electric field H Prance, P Watson, R J Prance and S T Beardsmore-Rust Sensor Technology Research Centre,Department of Engineering and Design, University of Sussex, Falmer, Brighton, BN1 9QT, UK E-mail: r.j.prance@sussex.ac.uk
Received 14 June 2012, in final form 17 August 2012 Published 8 October 2012 Online at stacks.iop.org/MST/23/115101 Abstract We describe a system for the measurement of changes in electric field which occur as a result of the movement of people, or objects, in ambient electric fields with standoff distances of several metres. A passive sensor system is used to measure the changes in electric field which are due to several different mechanisms. From this we are able to extract presence, movement and position information with a positional accuracy of âˆź10 cm. Furthermore, by examining the disturbances in ambient ac fields, such as those created by domestic electricity networks, we show that it is possible to recover static field information with a sensor that lacks dc sensitivity. In this way, we demonstrate that tracking of individuals within large room-scale spaces is possible. As a simple, passive, undetectable technique, with no line of sight requirement, these measurements open up new possibilities in security, telehealth and human computer interfacing applications. Keywords: sensors, movement, electrometer, security, telehealth
(Some figures may appear in colour only in the online journal)
1. Introduction
obscured by objects, walls and poor visibility. Moreover, video imaging systems generate extremely large data sets which are complex to analyse and may contain significantly more information than is required for the application, frequently leading to the additional burden of anonymizing the data. In order to meet the requirement for movement sensing systems capable of operating in environments where line of sight is not available, such as in the presence of walls or debris, substantial work has taken place [7, 8]. To date, however, much of this work has focused on the use of RF radar techniques for identifying movement through walls and debris [9, 10]. These techniques, while clearly effective, are active, which presents limitations when considering applications requiring covert surveillance or extended use. By contrast in this paper we describe a new passive method which combines the use of ambient electric fields as the excitation signal with a unique electric field sensing technology. The electric potential sensor (EPS), developed and patented at the University of Sussex, can be described as a laboratory grade
The applications for movement sensing and tracking systems are wide ranging and include security, offender management [1], search and rescue, and the military, as well as the care of the elderly [2, 3]. In a number of these applications, it is sufficient to be aware when a given space is occupied by an individual or individuals and to obtain information about their movements around, into and out of the space. In such cases, there is often a requirement for long term, unattended, surveillance systems which do not generate excess data or false alarms [4, 5]. Passive techniques for the detection of subjects and monitoring or tracking their movement, have several clear advantages over active techniques. These include compatibility with a need for covert surveillance, removal of potential hazards due to irradiation, light weight construction, lower power requirements and the capability for extended use. However, existing passive techniques tend to focus on either optical or infrared sensors [6, 3]. Both types of sensor can be 0957-0233/12/115101+07$33.00
1
Š 2012 IOP Publishing Ltd
Printed in the UK & the USA
Table. The similar fragments which are highlighted in two attached articles. R Sklyar “Machine Perception Through Natural Intelligence”
#
H Prance, P Watson, R J Prance and S T Beardsmore-Rust “Position and movement sensing at metre standof distances using ambient electric feld”
1
title- Machine Perception ...
title- Position and movement sensing ...
2
abstract- a)The measuring method and necessary performance data of
abstract- a)We describe a system for the measurement of changes in
electric feld which occur as a result of the movement of people, or objects, in ambient electric felds ... b) The range of applied sensors differs from an induction sensor to b) A passive sensor system is used to measure the changes in electric feld superconducting induction magnetometer. c) Sensitivity of the perception method makes it possible to recognize the which are due to several different mechanisms. c) From this we are able to extract presence, movement and position linear translation of 10^(−2) m and disposal in space of 10^(−3) m^3. information with a positional accuracy of ∼10 cm. d) The arrays of the advanced sensors give us information about the space d) Furthermore, by examining the disturbances in ambient ac felds, such as and direction dynamics of the signals' spreading. those created by domestic electricity networks, we show that it is possible to f)The analytical expressions for arrangements of the head sensors in recover static feld information with a sensor that lacks dc sensitivity. differential and vector (3D) relative positions are deduced. f)In this way, we demonstrate that tracking of individuals within large roomscale spaces is possible. the sensor for the robot’s orientation in the ambient magnetic field ...
3
(page 69)
A PC (pickup coil) realizing the oscillatory−forward movement along both AC industrial interferences and quasi-DC natural (Earth) environmental MFs (magnetic fields). These fields are distributed on a surface and in space roughly according to Figure 3.
(page 2) The new technique described in this paper takes a different
approach to detecting electric feld signals occurring as a result of presence and movement. While the measurement remains passive, with all the associated benefts, it is based on the detection of disturbances to the ambient ac electric feld. This new approach has many advantages, in (page 70) Magnetic induction BPC of AC MF with the frequency ωlimb of particular the ability to determine presence and location, even in the event limbs' oscillations produce an e.m.f. in PC ... that a subject remains stationary. The ambient 50 Hz (or 60Hz) feld, which As a result, an output signal receiving spontaneously, during twooccurs as a result of the mains electrical supply, is used as the excitation dimensional travel of a walking robot in quasi-DC MF. Moreover, by picking signal and the variation in the amplitude of this ac signal in response to the up the signals from both horizontal and vertical parts of the limbs, the robot subject is measured. The technique is still passive, and the power and covert derives its’ directional information from the axial course of the field lines advantages associated with this approach remain. and their inclination (defined as the angle between the direction of the field lines and the horizontal) in space.
4
(page 71-72)
2) Measuring of the MF signal in a triaxial arrangement (page 4) Figure 3. Experimental arrangement for monitoring movement and The vector of the industrial or household man-made AC MF (noise) ω can be position within a well defned space. (b) Elevation showing x axis sensors
and camera.
measured during the complete pass of the robot’s walking. Placing of the PC’s triplets (the three orthogonal components at each location) on the respective limbs give the necessary data for the triaxial MF determination according to the geometrical summation. In such a case, the frequency of the limb’s oscillations is much lower than ambient MF noise.
5
6
7
(page 71)
The finite distance d between the magnetic sensors for detecting the field difference is used to get an expression for the estimate of the exact magnetic gradient, adjusted by the function of the field distance, ΔBz = .., as follows ...
(page 4) For small deviations about the origin the product 2VAVB is
(page 71)
Figure 12. The variations of measured MF strength H DC, HAC: 1oscillations of a PC modulated by variations of external MF; 2- an envelope of sensor's output voltage UDC as the appropriate quasi-DC MF along the walking way; 3-changing of an AC industrial MF interference into the travel space; 4-the integral output voltage U AC which determines changing of the interference's power by a distance.
(page 6) In this paper we have demonstrated the ability to estimate and
(page 72)
(page 6) Three-dimensional imaging is also possible which is probably of
The basic scenario is shown in Figure 16. As a result living beings control drives by previously translated biosignals. In the other variant, biosignals from organs of the senses or brain transduce directly into intelligent or robotic systems which, in such a way, pick up environmental information.
approximately constant as a function of the target position, and so the proportionality can be simplifed; so that the differential output voltage is directly related to the target position. This simple relation may be implemented in low-cost sensor systems where only low precision is required. track the position of an individual human subject within a space using perturbations in the ambient 50 Hz electric feld. A simple differential subtraction model was used to extract position from electric feld amplitude for movement in one dimension, but does not accurately represent the true measurement scenario. more use for machine interfacing applications, by using additional sensors in the vertical z axis direction. Accurate assessment of gait, for gait recognition purposes,would require the use of multiple camera systems for a direct comparative study.