Claims:1. A sensor data fusing system comprising:
a memory storing instructions;
a processor communicatively coupled to said memory, wherein said processor is configured by said instructions to:
read and parse an adjacency floor matrix specific to a location to obtain physical knowledge, wherein said physical knowledge comprises one or more objects in said location;
compute one or more static weights for each of said one or more objects based on density of said one or more objects with reference to said adjacency floor matrix to obtain a set of static weights;
compute a dynamic weight using number of particles with respect to an inertial measurement obtained from an inertial sensor to obtain a first set of dynamic weights;
compute a received signal strength indicator (RSSI) for each of one or more access points obtained from a Wi-Fi sensor in said location;
compute a dynamic weight for said received signal strength indicator (RSSI) specific to said one or more access points obtained from said Wi-Fi sensor to obtain a second set of dynamic weights; and
fuse said first set of static weights, said first set of dynamic weights and said second set of dynamic weights to obtain a first coordinate and a second co-ordinate of a specific position of said one or more objects in said location:

2. The sensor data fusing system of claim 1, wherein said processor is further configured by said instructions to compute, for each cell in said location, a freedom quotient based on a number of accessible cells around said cell and a maximum number of adjacent cells.

3. The sensor data fusing system of claim 2, wherein said static weight for said one or more objects is computed based on said freedom quotient.


4. The sensor data fusing system of claim 1, wherein said dynamic weight computed for said received signal strength indicator (RSSI) specific to said one or more access points is based on number of valid access points and number of total access points.

5. The sensor data fusing system of claim 1, wherein said first co-ordinate and said second co-ordinate of said specific position in said location are obtained by averaging said first set of static weights, said first set of dynamic weights and said second set of dynamic weights.

6. A processor implemented sensor data fusing method comprising:
reading and parsing an adjacency floor matrix specific to a location to obtain physical knowledge, wherein said physical knowledge comprises one or more objects in said location;
computing one or more static weights for each of said one or more objects based on density of said one or more objects with reference to said adjacency floor matrix to obtain a set of static weights;
computing a dynamic weight using number of particles generated with respect to an inertial measurement obtained from an inertial sensor to obtain a first set of dynamic weights;
computing a received signal strength indicator (RSSI) for each of one or more access points obtained from a Wi-Fi sensor in said location;
computing a dynamic weight for said received signal strength indicator (RSSI) specific to said one or more access points obtained from said Wi-Fi sensor to obtain a second set of dynamic weights; and
fusing said first set of static weights, said first set of dynamic weights and said second set of dynamic weights to obtain a first coordinate and a second co-ordinate of a specific position of said one or more objects in said location.


7. The processor implemented sensor data fusing method of claim 6, further comprising computing, for each cell in said location, a freedom quotient based on a number of accessible cells around said cell and a maximum number of adjacent cells.


8. The processor implemented sensor data fusing method of claim 7, wherein said static weight for said one or more objects is computed based on said freedom quotient.


9. The processor implemented sensor data fusing method of claim 6, wherein said dynamic weight computed for said received signal strength indicator (RSSI) specific to said one or more access points is based on number of valid access points and number of total access points.


10. The processor implemented sensor data fusing method of claim 6, wherein fusing said first set of static weights, said first set of dynamic weights and said second set of dynamic weights comprises averaging said first set of static weights, said first set of dynamic weights and said second set of dynamic weights to obtain said first coordinate and said second co-ordinate of said specific position in said location.
, Description:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
SYSTEM AND METHOD FOR FUSING INERTIAL AND WI-FI SENSOR
DATA FOR LOCALIZATION

Applicant:
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the embodiments and the manner in which it is to be performed.
TECHNICAL FIELD
The embodiments herein generally relate to localization systems, and, more particularly, to system and method for fusing inertial and Wi-Fi sensor data for localization of one or more objects.

BACKGROUND
Indoor localization using both radio frequency (RF) and inertial sensors on a mobile device is a common approach. Localization and mapping are performed to compute the most probable location using sensors and control values (if any). Current solutions have considered both the techniques and methods of fusing them. Simultaneous Localization And Mapping (SLAM) is the computational problem (or technique) of constructing or updating a map of an unknown environment while simultaneously keeping track of one’s location within it. This technique uses image sensors that provide external information, and idiothetic sensors, which provide information related to the one’s motion in body reference frame, to construct a geometric or topological model of the environment and uses the model for navigation. This SLAM problem has been methodically prepared and solved as theoretical problem in various forms. However, issues remain in realizing general SLAM solutions in practice and notably in localization while using the above sensors. This has led to the use of extended Kalman filter (EKF) to solve the SLAM problem.
For example, the extended Kalman Filter (EKF) is an error probability based estimator for fusing sensor data. However, the fusion techniques are based on probabilistic models that do not consider how the sensors behave in different environments. Hence, the fusion method using extended Kalman Filter technique is often static, which does not converge to the best possible measurement estimation.

SUMMARY
The following presents a simplified summary of some embodiments of the disclosure in order to provide a basic understanding of the embodiments. This summary is not an extensive overview of the embodiments. It is not intended to identify key/critical elements of the embodiments or to delineate the scope of the embodiments. Its sole purpose is to present some embodiments in a simplified form as a prelude to the more detailed description that is presented below.
In one aspect, a sensor data fusing system for localization is provided. The system comprising: a memory storing instructions; a hardware processor communicatively coupled to the memory, wherein the hardware processor is configured by the instructions to: read and parse an adjacency floor matrix specific to a location to obtain physical knowledge, wherein the physical knowledge comprises one or more objects in the location; compute one or more static weights for each of the one or more objects based on density of the one or more objects with reference to the adjacency floor matrix to obtain a set of static weights; compute a dynamic weight using number of particles generated with respect to an inertial measurement obtained from an inertial sensor to obtain a first set of dynamic weights; compute a received signal strength indicator (RSSI) for each of one or more access points obtained from a Wi-Fi sensor in the location; compute a dynamic weight for each of the received signal strength indicator (RSSI) specific to the one or more access points obtained from the Wi-Fi sensor to obtain a second set of dynamic weights; and fuse the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain a first co-ordinate and a second co-ordinate of a specific position in the location. The first co-ordinate and the second co-ordinate of the specific position of the one or more objects in the location are obtained by averaging the first set of static weights, the first set of dynamic weights and the second set of dynamic weights.
The hardware processor is further configured by the instructions to compute, for each cell in the location, a freedom quotient based on a number of accessible cells around each said cell and a maximum number of adjacent cells. The static weight for the one or more objects is computed based on the freedom quotient. The dynamic weight computed for the received signal strength indicator (RSSI) specific to the one or more access points is based on number of valid access points and number of total access points.
In another aspect, a processor implemented sensor data fusing method for localization is provided. The processor implemented method comprising: reading and parsing an adjacency floor matrix specific to a location to obtain physical knowledge, wherein the physical knowledge comprises one or more objects in the location; computing one or more static weights for each of the one or more objects based on density of the one or more objects with reference to the adjacency floor matrix to obtain a set of static weights; computing a dynamic weight using number of particles generated with respect to an inertial measurement obtained from an inertial sensor to obtain a first set of dynamic weights; computing a received signal strength indicator (RSSI) for each of one or more access points obtained from a Wi-Fi sensor in the location; computing a dynamic weight for the received signal strength indicator (RSSI) specific to the one or more access points obtained from the Wi-Fi sensor to obtain a second set of dynamic weights; and fusing the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain a first co-ordinate and a second co-ordinate of a specific position of the one or more objects in the location. The fusing of the first set of static weights, the first set of dynamic weights and the second set of dynamic weights comprises averaging the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain the first co-ordinate and the second co-ordinate of the specific position in the location.
The computer implemented method further comprising computing, for each cell in the location, a freedom quotient based on a number of accessible cells around each said cell and a maximum number of adjacent cells. The static weight for the one or more objects is computed based on the freedom quotient. The dynamic weight computed for the received signal strength indicator (RSSI) specific to the one or more access points is based on number of valid access points and number of total access points.
In yet another aspect, one or more non-transitory machine readable information storage mediums comprising one or more instructions is provided, which when executed by one or more hardware processors causes reading and parsing an adjacency floor matrix specific to a location to obtain physical knowledge, wherein the physical knowledge comprises one or more objects in the location; computing one or more static weights for each of the one or more objects based on density of the one or more objects with reference to the adjacency floor matrix to obtain a set of static weights; computing a dynamic weight using number of particles generated with respect to an inertial measurement obtained from an inertial sensor to obtain a first set of dynamic weights; computing a received signal strength indicator (RSSI) for each of one or more access points obtained from a Wi-Fi sensor in the location; computing a dynamic weight for each of the received signal strength indicator (RSSI) specific to the one or more access points obtained from the Wi-Fi sensor to obtain a second set of dynamic weights; and fusing the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain a first coordinate and a second co-ordinate of a specific position of the one or more objects in the location. The fusing of the first set of static weights, the first set of dynamic weights and the second set of dynamic weights comprises averaging the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain the first co-ordinate and the second co-ordinate of the specific position in the location.
The instructions further causes computing, for each cell in the location, a freedom quotient based on a number of accessible cells around a cell and a maximum number of adjacent cells. The static weight for the one or more objects is computed based on the freedom quotient. The dynamic weight computed for the received signal strength indicator (RSSI) specific to the one or more access points is based on number of valid access points and number of total access points.
It should be appreciated by those skilled in the art that any block diagram herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computing device or processor, whether or not such computing device or processor is explicitly shown.

BRIEF DESCRIPTION OF THE DRAWINGS
The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:
FIG. 1 is a block diagram of a sensor data fusing system according to an embodiment of the present disclosure;
FIG. 2 is a flow diagram illustrating a processor implemented sensor data fusing method using the sensor data fusing system of FIG. 1 according to one or more embodiments of the present disclosure; and
FIG. 3A-3C illustrates experimental results comprising weights for inertial sensor data and Wi-Fi sensor data, averaging the weights based on measurement errors for localization using the sensor data fusing system FIG. 1 according to one or more embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The words “comprising,” “having,” “containing,” and “including,” and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items.
It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the preferred, systems and methods are now described.
Some embodiments of this disclosure, illustrating all its features, will now be discussed in detail. The disclosed embodiments are merely exemplary of the disclosure, which may be embodied in various forms.
Before setting forth the detailed explanation, it is noted that all of the discussion below, regardless of the particular implementation being described, is exemplary in nature, rather than limiting. For example, although selected aspects, features, or components of the implementations are depicted as being stored in memories, all or part of the systems and methods consistent with the apparel recognition and classification system and method may be stored on, distributed across, or read from other machine-readable media.
Referring now to the drawings, and more particularly to FIG. 1 through 3C, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
FIG. 1 is a block diagram of a sensor data fusing system 100 according to an embodiment of the present disclosure. The sensor data fusing system 100 comprises a memory 102, a hardware processor 104, and an input/output (I/O) interface 106. The memory 102 further includes one or more modules 108 (or modules 108). The memory 102, the hardware processor 104, the input/output (I/O) interface 106, and/or the modules 108 may be coupled by a system bus or a similar mechanism.
The memory 102, may store instructions, any number of pieces of information, and data, used by a computer system, for example the sensor data fusing system 100 to implement the functions (or embodiments) of the present disclosure. The memory 102 may include for example, volatile memory and/or non-volatile memory. Examples of volatile memory may include, but are not limited to volatile random access memory (RAM). The non-volatile memory may additionally or alternatively comprise an electrically erasable programmable read only memory (EEPROM), flash memory, hard drive, or the like. Some examples of the volatile memory includes, but are not limited to, random access memory, dynamic random access memory, static random access memory, and the like. Some example of the non-volatile memory includes, but are not limited to, hard disks, magnetic tapes, optical disks, programmable read only memory, erasable programmable read only memory, electrically erasable programmable read only memory, flash memory, and the like. The memory 102 may be configured to store information, data, applications, instructions or the like for enabling the sensor data fusing system 100 to carry out various functions in accordance with various example embodiments.
Additionally or alternatively, the memory 102 may be configured to store instructions which when executed by the hardware processor 104 causes the sensor data fusing system 100 to behave in a manner as described in various embodiments (e.g., computing static weights, computing dynamic weights periodically for localization). The memory 102 stores information for example, information comprising sensory information, for example, sensor data obtained from one or more inertial sensors, one or more Wi-Fi sensors, and combinations thereof.
The hardware processor 104 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Further, the hardware processor 104 may comprise a multi-core architecture. Among other capabilities, the hardware processor 104 is configured to fetch and execute computer-readable instructions or modules stored in the memory 102. The hardware processor 104 may include circuitry implementing, among others, audio and logic functions associated with the communication. For example, the hardware processor 104 may include, but are not limited to, one or more digital signal processors (DSPs), one or more microprocessor, one or more special-purpose computer chips, one or more field-programmable gate arrays (FPGAs), one or more application-specific integrated circuits (ASICs), one or more computer(s), various analog to digital converters, digital to analog converters, and/or other support circuits.
The hardware processor 104 thus may also include the functionality to encode messages and/or data or information. The hardware processor 104 may include, among other things, a clock, an arithmetic logic unit (ALU) and logic gates configured to support operation of the hardware processor 104. Further, the hardware processor 104 may include functionality to execute one or more software programs, which may be stored in the memory 102 or otherwise accessible to the hardware processor 104.
The hardware processor 104 is configured by the instructions stored in the memory 102. The hardware processor 104 when configured by the instructions to read (and/or analyse) and parse an adjacency floor matrix specific to a location to obtain physical knowledge. The physical knowledge comprises one or more objects in the location (e.g., an indoor facility with one or more inertial sensors, and one or more Wi-Fi sensors). Each of the Wi-Fi sensors can have one or more access points. The hardware processor 104 computes one or more static weights for each of the one or more objects based on density of the one or more objects with reference to the adjacency floor matrix to obtain a set of static weights. The hardware processor 104 additionally computes a freedom quotient based on the number of accessible cells around each said cell and a maximum number of adjacent cells for each cell in the location. The static weight for the one or more objects is computed based on the freedom quotient. The hardware processor 104 further computes a dynamic weight using number of particles generated with respect to an inertial measurement obtained from an inertial sensor (e.g., the one or more inertial sensors) to obtain a first set of dynamic weights.
The hardware processor 104 is further configured by the instructions to compute a received signal strength indicator (RSSI) for each of one or more access points obtained from a Wi-Fi sensor (e.g., the one or more Wi-Fi sensors) in the location. The hardware processor 104 further compute a dynamic weight for each of the received signal strength indicator (RSSI) specific to the one or more access points obtained from the Wi-Fi sensor to obtain a second set of dynamic weights. The dynamic weight that is computed for the received signal strength indicator (RSSI) specific to the one or more access points is based on number of valid access points and number of total access points.
The hardware processor 104 finally fuses the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain a first coordinate and a second co-ordinate of a specific position of the one or more objects (e.g., one or more users) in the location. More specifically, the first coordinate and the second co-ordinate of the specific position in the location are obtained by averaging the first set of static weights, the first set of dynamic weights and the second set of dynamic weights. The first coordinate and the second co-ordinate of the specific position in the location are indicative of localization of the one or more users.
Alternatively, the sensor data fusing system 100 may execute the modules 108 comprising a floor matrix parsing module that when executed by the hardware processor 104 reads (and/or analyses) and parses the adjacency floor matrix specific to the location to obtain physical knowledge. Similarly, the modules 108 further comprises a static weight calculator that the static weights based on the adjacency floor matrix based environment modeling. In one embodiment, the static weight calculator computes one or more static weights for each of the one or more objects based on density of the one or more objects with reference to the adjacency floor matrix to obtain the set of static weights as described above.
Similarly, the modules 108 comprises an error weight calculator which computes another part of the static weights based on the aggregate performance of both the techniques. The modules 108 further comprises a dynamic weight calculator which computes dynamic weights directly from measurement errors of the individual sensors (e.g., the one or more inertial sensors and the one or more Wi-Fi sensors). In one embodiment, the dynamic weight calculator computes a dynamic weight using number of particles generated with respect to an inertial measurement obtained from an inertial sensor to obtain the first set of dynamic weights. Similarly, the dynamic weight calculator computes the dynamic weight for each of the received signal strength indicator (RSSI) specific to the one or more access points obtained from the Wi-Fi sensor to obtain the second set of dynamic weights. The modules 108 further comprises a fusing module that fuses the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain (or derive/determine) the first coordinate and the second co-ordinate of the specific position in the location, thus localizing an object (e.g., a user). The fusing module fuses the above weights by averaging the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain the co-ordinates for localizing the specific position. The modules for example, the floor matrix parsing module, the static weight calculator, the error weight calculator, the dynamic weight calculator, and the fusing module are implemented as at least one of a logically self-contained part of a software program, a self-contained hardware component, and/or, a self-contained hardware component, with a logically self-contained part of a software program embedded into each of the hardware component that when executed perform the above method described herein, in one embodiment.
Since, inertial sensor data is based on tracking, and Wi-Fi sensor data is based on positioning, fusing is performed based on one or more criteria. The one or more criteria include: fusing to be performed (i) each time user comes to rest position, and (ii) when a noisy inertial window is determined (or obtained) due to ambient noise such as “above a threshold magnetic field”, or “usage of communication device (noisy window)” (e.g., a mobile communication device being using within the indoor facility where the one or more inertial sensors and the one or more Wi-Fi sensors are positioned to obtain inertial sensor data and Wi-Fi sensor data. If neither of the criteria occur, then the sensor data fusing system 100 fuses for every pre-determined time period (e.g., for every 30 seconds), based on a timer expiry.
For better understanding of the embodiments described in the present disclosure, computation of static and dynamic weights is discussed by way of examples: First level static weight is computed based on a map, wherein dense regions gives better accuracy for inertial and sparse regions for Wi-Fi. Similarly, second level static weight is computed based on number of access points. Higher the number of access points provides an improved accuracy in trilateration. Likewise, third static weight is computed based on an average accuracy of both systems, for example 2 meters for inertial sensor and 3 meters for Wi-Fi sensor. The static weights are computed during map pre-processing and is indicative of property of every cell where the user is localized. However it may be same for a region or zone. Whereas, dynamic weight is computed on the fly for every position or trajectory.
Below discussion describes computation of static weights that provides a better understanding of the embodiments.
For every valid cell in a zone of a map, the following are computed:
Freedom quotient = number of accessible cells around the cell/ maximum number of adjacent cells possible (8). So,
Fq = number of accessible cells/8
(1 – Freedom quotient) is the first weight component for inertial position:
W1i = (1-Fq)
Freedom quotient will be the first weight component for Wi-Fi.
W1w = Fq
The second weight component for Wi-Fi is the number of useable access points AP (as per geometry) and a maximum number of access points so,
W2w = number of AP/maximum number of supported AP
For inertial, the second weight component can be the preciseness of the map, which may be a score between 0 to 1, where 1 denotes highly precise
W2i = Map Precision quotient (manual)
The final weight is based on average accuracy so,
W3i = cumulative accuracy of inertial location/(cumulative accuracy of inertial location + cumulative accuracy of Wi-Fi location),
W3w = cumulative accuracy of Wi-Fi location/(cumulative accuracy of inertial location + cumulative accuracy of Wi-Fi location)
Below discussion describes computation of static weights that provides a better understanding of the embodiments. A measure like trajectory segments with high ratio of rejected particles and total number of particles has lesser accuracy of location. In other words, measure like trajectory segments with high ratio of rejected particles divided by total number of particles has lesser accuracy of location.
The first dynamic weight component for inertial is computed in accordance with the following relationship (or equation)
W4i = (1- number of rejected particles) and number of total particles, or
when rewritten is expressed as:
W4i = (1- number of rejected particles) divided by number of total particles
Similarly a dynamic measure can be number of access points giving sane readings [-90, -60] of all available access points
W4w = number of valid access points and Number of total access points, or
when rewritten is expressed as:
W4w = number of valid access points divided by Number of total access points
The sensor data fusing system 100 then finally performs fusing of weights for localizing, which is done by weighted average and expressed as below:
Xf = ?_(k=1)^m¦?(?_(i=1)^(n_k)¦?W_i^(k ))X^k/?_(k=1)^m¦?_(i=1)^(n_k)¦W_i^k ??
Yf = ?_(k=1)^m¦?(?_(i=1)^(n_k)¦?W_i^(k ))Y^k/?_(k=1)^m¦?_(i=1)^(n_k)¦W_i^k ??
Xf, and Yf are the fused X and Y coordinates (e.g., the first co-ordinate and the second co-ordinate) of the specific location respectively. ‘nk’ is the number of weights for technique “n” and “m” are the total number of such techniques for determining position.
FIG. 2, with reference to FIG. 1, is a flow diagram illustrating a processor implemented sensor data fusing method using the sensor data fusing system 100 of FIG. 1 according to one or more embodiments of the present disclosure. The method comprising, reading and parsing (202), an adjacency floor matrix specific to a location to obtain physical knowledge, wherein the physical knowledge comprises one or more objects in the location; computing (204) one or more static weights (e.g., multiple static weights) for each of the one or more objects based on density of the one or more objects with reference to the adjacency floor matrix to obtain a set of static weights; computing (206), a dynamic weight using number of particles generated with respect to an inertial measurement obtained from an inertial sensor to obtain a first set of dynamic weights; computing (208), a received signal strength indicator (RSSI) for each of one or more access points obtained from a Wi-Fi sensor in the location; computing (210), a dynamic weight for then received signal strength indicator (RSSI) specific to the one or more access points obtained from the Wi-Fi sensor to obtain a second set of dynamic weights; and fusing (212), the first set of static weights, the first set of dynamic weights and the second set of dynamic weights to obtain a first coordinate and a second co-ordinate of a specific position in the location.
FIG. 3A-3C, with reference to FIG. 1 and 2, illustrates experimental results comprising weights for inertial sensor data and Wi-Fi sensor data, averaging the weights based on measurement errors for localization using the sensor data fusing system 100 according to one or more embodiments of the present disclosure. In order to validate the embodiments (and the experimental results) of the present disclosure, a subject (or the user) is / was allowed to move around an indoor premise with a device (e.g., a mobile communication device) having both inertial and RF/Wi-Fi sensors. The location using inertial, RF/Wi-Fi and fused methods as described above have been computed for pre-measured test points. The test point locations are measured (such as manual measurements) using a laser range finder. In other words, the test point locations are manually measured and obtained using a laser range finder. Following this, when the user reaches point T1 with actual location X1, Y1, the user’s inertial location Xi1, Yi1; RF/Wi-Fi based location as Xr1,Yr1 are computed using respective methods as described above. Fusion technique is performed using mentioned and described method to arrive at Xf1,Yf1. The error is computed using measure of Euclidian distance given by E_T= v(?(X_m-X_a)?^2+?(Y_m-Y_a)?^2 ), where Xm, Ym are the measured X and Y and Xa, Ya are the actual X and Y for the location. ET is the error measure for technique T. It was found that the mean error for fused location estimates are better than the same arrived using both inertial and RF/Wi-Fi alone in terms of accuracy and computation. This proves the effectiveness of fusion technique/method as described above. More specifically, FIG. 3A illustrates measurement errors for inertial sensors. Similarly, FIG. 3B illustrates trilateration errors for Wi-Fi sensors. FIG. 3C illustrates fusing technique for fusing the static weights, dynamic weights of sensor data, and the fusion errors respectively.
The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
The embodiments of the present disclosure provide a sensor data fusing system 100 and a method for combining inertial and Wi-Fi sensors for localization using the error models for measurements from both the sensors as shown in FIGS. 3A-3C. As can be seen from the experimental results, less weightage is given to a sensor that is expected to perform poorly in the given scenario. Unlike conventional systems where there is no consideration of physical knowledge due to which the conventional systems are prone to errors, the sensor data fusing system 100 has knowledge of environmental factors that affect radio frequency (RF) channels and also factors that control drifts of inertial sensors and deviations of the magnetometer readings. Using such physical models/knowledge, the sensor data fusing system 100 and the method work with comparable degree of accuracy across multiple types of environments.
It is, however to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software modules located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. Examples of a computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM), a read-only memory (ROM), a rigid magnetic disk and an optical disk. Current examples of optical disks include compact disk-read only memory (CD-ROM), compact disk-read/write (CD-R/W) and DVD.
A data processing system suitable for storing and/or executing program code will include at least one processor coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution.
Input/output (I/O) devices (including but not limited to keyboards, displays, pointing devices, etc.) can be coupled to the system either directly or through intervening I/O controllers. Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.
A representative hardware environment for practicing the embodiments may include a hardware configuration of an information handling/computer system in accordance with the embodiments herein. The system herein comprises at least one processor or central processing unit (CPU). The CPUs are interconnected via system bus to various devices such as a random access memory (RAM), read-only memory (ROM), and an input/output (I/O) adapter. The I/O adapter can connect to peripheral devices, such as disk units and tape drives, or other program storage devices that are readable by the system. The system can read the inventive instructions on the program storage devices and follow these instructions to execute the methodology of the embodiments herein.
The system further includes a user interface adapter that connects a keyboard, mouse, speaker, microphone, and/or other user interface devices such as a touch screen device (not shown) to the bus to gather user input. Additionally, a communication adapter connects the bus to a data processing network, and a display adapter connects the bus to a display device which may be embodied as an output device such as a monitor, printer, or transmitter, for example.
The preceding description has been presented with reference to various embodiments. Persons having ordinary skill in the art and technology to which this application pertains will appreciate that alterations and changes in the described structures and methods of operation can be practiced without meaningfully departing from the principle, spirit and scope.