WO2023174770A1

WO2023174770A1 - A controller for determining sensing outcome of a radio frequency-based sensing system and a method thereof

Info

Publication number: WO2023174770A1
Application number: PCT/EP2023/055832
Authority: WO
Inventors: Gerardus Wilhelmus Theodorus Van Der Heijden; Pieter Diederik DE VREEZE
Original assignee: Signify Holding B.V.
Priority date: 2022-03-18
Filing date: 2023-03-08
Publication date: 2023-09-21

Abstract

A method of determining sensing outcome of a radio frequency-based sensing system, wherein the system comprises at least three nodes arranged for transmitting and/or receiving radio frequency signals for radio frequency-based sensing, and wherein the at least three nodes form at least two sensing pairs having at least partially overlapping field of view, wherein each sensing pair comprises a transmitter node and a receiver node, wherein the method comprises assigning a first and a second sensing sensitivity to a first and a second sensing pair of the at least two sensing pairs respectively, determining a first and a second sensing outcome for the first and the second sensing pair respectively based on radiofrequency signals communicated between the transmitter node and the receiver node and further based on the assigned first and the second sensing sensitivity respectively, fusing, using a math operator, the first and the second sensing outcome based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency- based sensing system based on the fusion.

Description

A controller for determining sensing outcome of a radio frequency -based sensing system and a method thereof

FIELD OF THE INVENTION

The invention relates to a method of determining sensing outcome of a radio frequency-based sensing system. The invention further relates to a controller, a system, and a computer program product for determining sensing outcome of a radio frequency -based sensing system.

BACKGROUND

Radio frequency-based sensing is a sensing mechanism involving wireless transceivers (or transmitters/receivers) arranged for transmitting and receiving radiofrequency (RF) signals. These RF signals, which may also be used for radio communication, when passing through a sensing volume, are affected by presence/movement of a person within the sensing volume e.g., via reflection, absorption, scattering etc. The radiofrequency-based sensing uses such deviations of radiofrequency signals to infer presence/motion of the person. Radiofrequency-based sensing also extends to other applications such as location detection, fall detection, gesture detection, vital signs detection etc. which are also based on how radiofrequency signals are affected in the sensing volume.

US2018292520A1 relates to a method of occupancy detection, such that the received signal strength is analyzed using nonparametric online change-point detection analysis to determine change-points in the received signal(s). One or more statistical measures of the received signal(s), such as mean and variance, are used in conjunction with the change-point detection to determine a probability that the occupancy of the monitored space has changed.

US2005055568A1 relates to a system for detecting the presence of an intruder in a protected area utilizes a received signal strength indicator (RSSI) value of signals broadcast from transmitting stations deployed in the protected area.

US2019355242A1 relates to a method for detecting movements or a lack of movements of objects and/or living being in a Fresnel zone-related radio range which influence radio signals of at least one radio terminal transmitted on a number of radio channels being divided in at least one sub-channel, received by a local fixed radio device in the radio range.

SUMMARY OF THE INVENTION

The inventors have realized that a radio frequency-based sensing system may comprise multiple sensing pairs in an environment. The ‘final’ sensing outcome of the sensing system may comprise a combination of the individual sensing outcomes of the sensing pairs. The inventors have further realized that how these individual sensing outcomes are combined influence the reliability and latency of the radio frequency-based sensing system.

It is therefore an object of the present invention to improve performance of the radio frequency-based sensing system, e.g., in terms of reliability (for instance minimizing false positive/negative) and latency etc.

According to a first aspect, the object is achieved by a method of determining sensing outcome of a radio frequency-based sensing system, wherein the system comprises at least three nodes arranged for transmitting and/or receiving radio frequency signals for radio frequency -based sensing, and wherein the at least three nodes form at least two sensing pairs having at least partially overlapping field of view, wherein each sensing pair comprises a transmitter node and a receiver node, wherein the method comprises assigning a first and a second sensing sensitivity to a first and a second sensing pair of the at least two sensing pairs respectively, determining a first and a second sensing outcome for the first and the second sensing pair respectively based on radiofrequency signals communicated between the transmitter node and the receiver node and further based on the assigned first and the second sensing sensitivity respectively, fusing, using a math operator, the first and the second sensing outcome based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency -based sensing system based on the fusion.

Advantageously, the object of the present invention is achieved by a method of determining sensing outcome of a radio frequency-based sensing system, wherein the system comprises at least three nodes arranged for transmitting and/or receiving radio frequency signals for radio frequency-based sensing, and wherein the at least three nodes form at least two sensing pairs having at least partially overlapping field of view, wherein each sensing pair comprises a transmitter node and a receiver node, wherein the method comprises assigning a first and a second sensing sensitivity to a first and a second sensing pair of the at least two sensing pairs respectively, determining within a time window a first and a second sensing outcome for the first and the second sensing pair respectively based on radio frequency signals communicated between the transmitter node and the receiver node and further based on the assigned first and the second sensing sensitivities respectively, fusing, using a math operator, the first and the second sensing outcome based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency -based sensing system based on the fusion.

The method relates to radio frequency-based sensing system. The system may be arranged for determining an activity state or a characteristic of an object. The activity state or characteristic may comprise, presence, motion, vital signs, location etc. The object may comprise living objects such as human, animals etc. and/or non-living objects such as cars, atmospheric conditions etc. The determination may be based on how the radiofrequency signal is affected by the object in an environment compared to a baseline (initial values defined for the environment).

The radio frequency-based sensing system may comprise at least three nodes arranged for transmitting and/or receiving radio frequency signals for radio frequency-based sensing. For radio frequency -based sensing in general, the system requires at least two nodes, i.e., a transmitter node and a receiver node. Such combination of a transmitter node and a receiver node forms a sensing pair. In case when the system comprises three nodes, e.g., two transmitter nodes and a receiver node, the system may comprise two sensing pairs formed by two transmitter-receiver pairs. In other words, each transmitter-receiver pair may form a sensing pair. A transmitter or receiver may be comprised in more than one sensing pair. The at least two sensing pairs may have at least partially overlapping field of view, e.g., depending on the location of the transmitter-receiver pair.

Preferably, the at least two sensing pairs are configured to detect a same event with an improved reliability, such as a reduced miss detection and/or false alarm probability. Since the first sensing outcome and the second outcome are triggered by a same event, there is both spatial and temporal correlation between the first and second outcome. The spatial correlation is achieved by configing the at least two sensing pairs having at least partially overlapping field of view. The temporal correlation is achieved by obtaining the first and the second sensing outcome within a same time window. The size of the time window may be predefined according to a type of the activity state or characteristic of an object to be detected, a detection latency of the at least two sensing pairs.

The method comprises assigning a first and a second sensing sensitivity to a first and a second sensing pair of the at least two sensing pairs respectively. The sensing sensitivity may comprise a sensing threshold. For instance, when the deviation in the received radio frequency signals is above such a sensing threshold, the sensing pair may conclude that the sensing event has occurred. For example, a highly sensitivity sensing pair (which implies a sensing pair with a low sensing threshold) renders sensing outcome to be more sensitive to any changes in the radiofrequency signals such that a small change may trigger sensing outcome (e.g., motion of a user), alternatively a low sensitivity sensing pair (which implies a sensing pair with a high threshold) may render sensing outcome to be less sensitive to changes in the radiofrequency signals. A highly sensitive sensor (e.g., with a low sensing threshold) may have less latency but may suffer from reliability issues such as false positives, whereas a low sensitive sensor (e.g., with a high sensing threshold) may be more reliable (less false positives) but may have high latency.

The method further comprises determining a first and a second sensing outcome for the first and the second sensing pair respectively based on radiofrequency signals communicated between the transmitter node and the receiver node and further based on the assigned first and the second sensing sensitivity respectively. The sensing may be based on an effect on a characteristic of the communicated radiofrequency signals, e.g., effect on Received Signal Strength Indicator (RSSI), or Channel State Information (CSI) of the communicated signal, wherein the communicated radiofrequency signals are communicated between the transmitter and receiver node of the respective sensing pair. Each sensing pair may determine a sensing outcome based on comparing the RSSI and/or CSI value with a respective baseline and sensing sensitivity threshold, and determine a sensing outcome, e.g., presence, absence, motion etc.

The method further comprises fusing, using a math operator, the first and the second sensing outcome based on the assigned first and the second sensitivity. The fusion may comprise combining the first and the second sensing outcome. The math operator may comprise basic operations that act on numbers and other math constructs. For example, math operators take between one and two numbers as input and return a number as output. Examples of math operator includes arithmetic operators such as addition operator, subtraction operator etc., algebraic operators such as absolute value operator, square root operator etc., Boolean logic operator such as logical AND operator, logical OR operator etc. The method combines the sensing outcomes of the sensing pairs based on the respective assigned sensitivities using a math operator, e.g., using Boolean logic operators or arithmetic operators.

Since the method further comprises determining the sensing outcome for the radio frequency -based sensing system based on the fusion, the performance of the radio frequency-based sensing system, e.g., in terms of reliability (for instance low false positive/negative), latency in sensing outcome etc. is improved.

In an example, the method may further comprise determining a first sensing likelihood of the first sensing outcome, and a second sensing likelihood for the second sensing outcome, fusing, using a math operator, the first and the second sensing likelihood based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency -based sensing system based on the fusion.

Alternatively, and/or additionally, the method may fuse (combine) sensing likelihood for determining the sensing outcome of the radio frequency-based sensing system. Sensing likelihood may be determined based on historical data. The sensing likelihood may be one-dimensional time series indicating the likelihood. The fusion of sensing likelihood further increases the performance of the radio frequency-based sensing system.

In an example, the sensing sensitivity may comprise a sensing threshold, and if the assigned first and/or the second sensitivity do not exceed a predetermined threshold level, the method may further comprise fusing, using a math operator, the first and the second sensing likelihood, wherein the math operator is an arithmetic addition operator, determining a fused sensing sensitivity, determining the sensing outcome for the radio frequency -based sensing system based on the fusion and on the fused sensing sensitivity.

The sensing sensitivity may comprise a sensing threshold, which e.g., is a value, level etc. The sensing outcome of the sensing pair is based on such a sensing threshold. If the deviation in the received radiofrequency signals exceeds the sensing threshold, the sensing pair then may conclude that the sensing event has occurred. The predetermined threshold level may be defined based on a criterion which determines whether the sensing pair is highly sensitive or not. For instance, sensing pairs with the sensing threshold below the predetermined threshold level are considered as highly sensitive sensing pairs. In case, when the first and the second sensing pair are highly sensitivity, i.e., if they are sensitive to small changes, the sensing likelihoods may be fused using an arithmetic addition operation. For example, when the likelihoods are added, slopes in the likelihood are also added and becomes steeper. This results in reduction of latency for overall sensing. A fused sensing threshold for added likelihood may be determined and the final sensing outcome may be then based the determined fused sensitivity threshold and the added likelihood. Similarly, for the case when any one of the sensing pairs is highly sensitivity, the likelihoods may be added. Such a fusion will increase the performance of the radio frequency -based sensing system in view of reduction of latency in sensing outcome. The thresholds (e.g., predetermined threshold level and/or the fused sensing threshold) may be predetermined, based, e.g., on user’s input, environmental contextual parameters, baselines etc.

In another example, the sensing sensitivity may comprise a sensing threshold, and if the assigned first and/or the second sensitivity do not exceed a predetermined threshold level, the method may further comprise fusing, using a math operator, the first and the second sensing outcome, wherein the math operator is a Boolean logical OR operator.

In this example, since the sensing threshold does not exceed the predetermined threshold level, the sensing pairs may be considered as highly sensitive. In this example, for both the cases when the first and the second sensing pair are highly sensitive or at least one of the sensing pairs is highly sensitivity, the fusion may be based on a Boolean logical OR operation of the first and the second sensing outcome from the first and the second sensing pair respectively. The Boolean logic operators operate on Boolean expressions - values that are either true or false. For example, for the case of presence sensing, ‘true’ may comprise ‘presence’ and ‘false’ may comprise ‘no presence (absence)’. The logical "or" operator returns true if either the left side expression evaluates to true or the right-side expression evaluates to true, otherwise returns false. In this case, if any of the sensing pair has the positive outcome (e.g., have detected presence), then the sensing outcome for the radio frequency-based sensing system is also positive (e.g., have detected presence). Such a fusion will increase the performance of the radio frequency -based sensing system in view of reduction of latency in the sensing outcome.

In an example, wherein the sensing sensitivity comprises a sensing threshold, and if the assigned first and the second sensitivity exceed a predetermined threshold level, the method may further comprise fusing, using a math operator, the first and the second sensing outcome, wherein the math operator is a Boolean logical AND operator.

In the case when the first and the second sensing pair have low sensitivity, such that they are not very sensitive to changes in the communicated radiofrequency signals, the fusion may be based on a Boolean logical AND operator. The logical AND operator returns true if both the left side expression and the right side expression evaluate to true, otherwise the operator returns false. Therefore, if all the sensing pairs have the ‘true’ outcome (e.g., all have detected presence), only then the sensing outcome for the radio frequency-based sensing system will be ‘true’ (have detected presence). Such a fusion will increase the performance of the radio frequency -based sensing system in view of improvement of reliability in sensing outcome, e.g., false positives are reduced.

In an example, the assignment of the first and/or the second sensing sensitivity may be based on one or more of type of an environment wherein the sensing pairs are located, types of transmitter/receiver nodes, number of nodes in an environment, number of sensing pairs, location of the transmitter/receiver nodes in the environment with respect to each other and/or with respect to the environment.

The assignment of sensitivities to the first and the second sensing pair may be based on different contextual and node related parameters. For example, sensitivities may be assigned based on the location of the sensing pair, e.g., the sensing pair at the entrance of room may be suited with a low sensitivity such that the false positives can be avoided, whereas the sensing pair in the room may be suited with a high sensitivity such that the user does not have to move (e.g., if the sensing is arranged for detecting motion) to keep sensing pair detecting the user’s motion (and e.g., keeping the lights on). Furthermore, the environment type can be of importance also, e.g., a living room, or office you want to detect motion already when there is very limited motion, as such with a high sensitivity.

In an example, the assignment of the first and/or the second sensing sensitivity may be based on a user’s input.

In this example, a user may be provided with a user interface, e.g., a slider to adjust sensitivity. The user’s input, e.g., received via the user interface may be used to assign the sensitivities to the first and/or the second sensing pairs. The input of the user may be received via an audio signal, via user’s gesture etc.

In another example, the assignment of the first and/or the second sensing sensitivity may be based on a baseline for radio frequency -based sensing. A baseline may be initial values for the radiofrequency signals based on ‘disturbances’ caused by the environment. These are the null-state of the environment. The baseline may differ per environment. The sensitivity may be advantageously assigned based on the baseline which may vary over the day, history of the signals within a time-window, type of day (weekend, week-days).

In an example, the method may further comprise receiving a sensing outcome from another sensing modality, wherein the another sensing modality comprises at least partially overlapping field of view with at least one of the at least two sensing pairs, fusing, using a math operator, the first and the second sensing outcome and the received sensing outcome based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency -based sensing system based on the fusion.

The performance of the sensing outcome may be further improved by incorporating the sensing outcome of another sensing modality. For instance, the sensing outcome of a PIR sensor may be incorporated and fused with the sensing outcome of the first and the second sensing pair.

In another example, the assignment of the first and/or the second sensing sensitivity may be based on location of a user.

For example, if the users are not home, sensitivity overall can decrease, which will decrease the number of false positives (triggers by interference or other causes). The location of the user may be obtained, e.g., via a location detection system. Such an assignment will improve reliability of the radio frequency-based sensing system.

According to a second aspect, the object is achieved by a controller for determining sensing outcome of a radio frequency-based sensing system, wherein the controller comprises a processor arranged for executing (or at least controlling the execution of) the steps of the method according to the first aspect.

According to a third aspect, the object is achieved by a system for determining sensing outcome of a radio frequency-based sensing system, wherein the system comprises at least three nodes arranged for transmitting and/or receiving radio frequency signals for radio frequency -based sensing, and wherein the at least three nodes form at least two sensing pairs having at least partially overlapping field of view, wherein each sensing pair comprises a transmitting node and a receiving node, and a controller according to the second aspect.

The system may further comprise a user interface arranged for receiving an input indicative of a user selection for the first and/or the second sensing sensitivity.

According to a fourth aspect, the object is achieved by a computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method of the first aspect.

It should be understood that the computer program product, the controller, and the system may have similar and/or identical embodiments and advantages as the above- mentioned methods. Furthermore, the different embodiments can be combined.

BRIEF DESCRIPTION OF THE DRAWINGS The above, as well as additional objects, features and advantages of the disclosed systems, devices and methods will be better understood through the following illustrative and non-limiting detailed description of embodiments of systems, devices and methods, with reference to the appended drawings, in which:

Fig. 1 shows schematically and exemplary an example of a system for determining sensing outcome of a radio frequency-based sensing system,

Fig. 2 shows schematically and exemplary an example of a controller for determining sensing outcome of a radio frequency-based sensing system,

Fig. 3 shows schematically and exemplary a flowchart illustrating an example of a method for determining sensing outcome of a radio frequency-based sensing system, and Fig. 4 shows schematically an example of fusing sensing likelihood.

All the figures are schematic, not necessarily to scale, and generally only show parts which are necessary in order to elucidate the invention, wherein other parts may be omitted or merely suggested.

DETAILED DESCRIPTION OF EMBODIMENTS

Fig. 1 shows schematically and exemplary an example of a system 100 for determining sensing outcome of a radio frequency -based sensing system 100. The system 100 may be comprised in an environment 101. The environment 101 may be an indoor environment such as a house, an office, a shop, an animal barn etc., or may be an outdoor environment such as street, parking lot etc.

The system 100 comprises a plurality of lighting devices 1 lOa-d arranged for transmitting radiofrequency signals and/or receiving the transmitted radiofrequency signals. The lighting devices 1 lOa-d may comprise a transmitter, receiver or a transceiver (not shown). The wireless communication between the lighting devices 1 lOa-d may use a protocol of any suitable type, including for example Bluetooth, ZigBee or Wi Fi, thread, etc., with the lighting devices 1 lOa-d having appropriate corresponding circuitry for the protocol that is used.

A lighting device 1 lOa-d is a device or structure arranged to emit light suitable for illuminating an environment, providing or substantially contributing to the illumination on a scale adequate for that purpose. The system 100 may comprise any number of lighting devices 1 lOa-d. A lighting device 1 lOa-d comprises at least one light source or lamp, such as an LED-based lamp, gas-discharge lamp or filament bulb, etc., optionally any associated support, casing or other such housing. Each of the lighting devices 1 lOa-d may take any of a variety of forms, e.g., a ceiling mounted luminaire, a wall-mounted luminaire, a wall washer, or a free-standing luminaire (and the luminaires need not necessarily all be of the same type). In the exemplary figure, the lighting devices 1 lOa-c are ceiling mounted luminaires, and the lighting device 1 lOd is a standing lamp. Additionally, and/or alternatively, to the transmitter/receiver comprising lighting devices 1 lOa-d, the transmitter and/or receiver nodes may comprise a sensor, a gateway, a switch, or any other device capable of transmitting/receiving radiofrequency signals.

Radio frequency-based sensing is a sensing mechanism involving wireless transceivers (or transmitters/receivers) arranged for transmitting and receiving radiofrequency (RF) signals. These RF signals, which may also be used for radio communication, when passing through a sensing volume, are affected by an activity state or generally by a characteristic of an object, such as presence, motion, vital signs etc. The object may comprise a living object (e.g., human 120, animal etc.) or a non-living object such as cars. The objects are limited to only those objects which can affect the radiofrequency signals, e.g., via reflection, absorption, scattering etc., of the radiofrequency signals. The radio frequency-based sensing uses such deviations of the radiofrequency signals to infer a characteristic of the object, such as presence or motion of the object. Radio frequency -based sensing also extends to other applications such as location detection, fall detection, gesture detection, vital signs detection etc. which are also based on how radiofrequency signals are affected in the sensing volume.

For the radio frequency -based sensing, at least two nodes may be required, a transmitter node arranged for transmitting radio frequency signals and a receiver node arranged for receiving the transmitting radio frequency signals. Each transmitter node and receiver node may form a sensing pair. An environment 101 may comprise more than two nodes 1 lOa-d. Therefore, the radio frequency -based sensing system 100 comprised in the environment 101 may comprise more than one sensing pair, which may have at least overlapping field of view. For example, if there are 4 transmitter/receiver or transceiver nodes, then there may be (maximum) 6 sensing pairs in the environment. The (maximum) number of sensing pairs may depend on the number of transmitter nodes and the receiver nodes. The sensing outcome of the radio frequency -based sensing system 100 may be based on the individual sensing (outcome) of the sensing pairs. The system 100 may comprise a user interface 130 for user to interact with the radio frequency -based sensing system 100, e.g., to change properties of the system 100, read/see decisions/explanations of the decision of the radio frequency -based sensing system 100 etc. The user interface 130 may be in a form a portable mobile device, e.g., a mobile phone, a tablet etc. The user interface 130 may have a display.

Fig. 2 shows schematically and exemplary an example of a controller 210 for determining sensing outcome of a radio frequency -based sensing system 100. The controller 210 may comprise an input unit 214 and an output unit 215. The input 214 and the output 215 units may be comprised in a transceiver (not shown) or input 214 may be comprised in a receiver and the output 215 is comprised in a transmitter, arranged for receiving (input unit 214) and transmitting (output unit 215) radiofrequency signals.

The controller 210 may further comprise a memory 212 which may be arranged for storing communication IDs of the lighting devices 1 lOa-d and/or of the user interface 130 etc. The controller 210 may comprise a processor 213 arranged for executing the steps or at least controlling the execution of the steps of the method according to the first aspect.

The controller 210 may be implemented in a unit separate from the lighting devices 1 lOa-d/user interface 130, such as wall panel, desktop computer terminal, or even a portable terminal such as a laptop, tablet or smartphone. Alternatively, the controller 210 may be incorporated into the same unit as the user interface 130 and/or the same unit as one of the lighting devices 1 lOa-d. Further, the controller 210 may be implemented in the environment 101 or remote from the environment (e.g. on a server); and the controller 210 may be implemented in a single unit or in the form of distributed functionality distributed amongst multiple separate units (e.g. a distributed server comprising multiple server units at one or more geographical sites, or a distributed control function distributed amongst the lighting devices 1 lOa-d or amongst the lighting devices 1 lOa-d and user interface 130). Furthermore, the controller 210 may be implemented in the form of software stored on a memory (comprising one or more memory devices) and arranged for execution on a processor (comprising one or more processing units), or the controller 210 may be implemented in the form of dedicated hardware circuitry, or configurable or reconfigurable circuitry such as a PGA or FPGA, or any combination of these.

To enable the controller 210, for example, to receive or transmit radiofrequency signals, the communication may be implemented in by any suitable wireless means such as a local (short range) RF network, e.g., a Wi-Fi, ZigBee or Bluetooth network; or any combination of these and/or other means.

Fig. 3 shows schematically and exemplary a flowchart illustrating an example of a method 300 for determining sensing outcome of a radio frequency -based sensing system 100. The method 300 may comprise assigning 310 a first and a second sensing sensitivity to a first and a second sensing pair of the at least two sensing pairs respectively. The sensing sensitivity may comprise a sensing threshold which is used to distinguish whether a sensing event has occurred or not, for instance if the presence of a user 120 has been detected or not. For example, if the signal deviation exceeds the sensing sensitivity (threshold), the system 100 decides that the sensing event has occurred. The sensing sensitivity may be assigned to each of the sensing pairs. The sensing sensitivity may be the same for some of or each of the sensing pairs or different. The assigning of the sensing sensitivity may be based on a user 120 input, e.g., via a user interface 130. In a simplest example, the user 120 is provided with a sensitivity slider via the user interface 130 to adjust sensing sensitivity. In an alternative example, the sensing sensitivity may comprise frequency of message transmission, e.g., the number of messages transmitted per minute.

Additionally, and/or alternatively, the assignment of the first and/or the second sensing sensitivity may be based on one or more of type of an environment 101 wherein the sensing pairs are located, types of transmitter/receiver nodes 1 lOa-d, a number of nodes 1 lOa-d, a number of sensing pairs, location of the transmitter/receiver nodes 1 lOa-d in the environment 101 with respect to each other and/or with respect to the environment 101. The assignment of the first and/or the second sensing sensitivity may further be based on location of a user 120.

The method 300 may further comprise determining 320 a first and a second sensing outcome for the first and the second sensing pair respectively based on radiofrequency signals communicated between the transmitter node 1 lOa-d and the receiver node 1 lOa-d and further based on the assigned first and the second sensing sensitivities respectively. Each sensing pair may make a sensing decision based on the affected radiofrequency signals communicated between the transmitter node 1 lOa-d and the receiver 1 lOa-d of the sensing pair. The sensing pair’s sensing outcome is based on the assigned sensing sensitivity. The sensing outcome is based on the sensing application/function assigned to the sensing pair. For example, sensing pair assigned for presence sensing will result in a sensing outcome of presence or no presence (absence), motion sensing will result in motion/no motion etc.

The method 300 may further comprise fusing 330, using a math operator, the first and the second sensing outcome based on the assigned first and the second sensitivity. The operators are function which acts on inputs and produce outputs. The examples of math operators are Arithmetic operators (addition, subtraction, division, multiplication), Algebraic operators (absolute value operator, square root operator, cross product operator, magnitude operator etc.), Calculus operators (limit notation, integral operator etc.), Boolean Logic operators (Logical AND, Logical OR, Logical Exclusive OR etc.) etc. The fusion 330 comprises combining the first and the second sensing outcome.

The choice of the math operator depends on the assigned sensing sensitivities. For example, for the low sensing sensitivity threshold case the math operator may be different from the high sensing sensitivity threshold case. In an example, if the assigned first and the second sensitivity threshold do not exceed a predetermined threshold, the fusion 330 may be based on combining the first and the second sensing outcome using a Boolean logical OR operator. Such that when the first and the second sensitivity threshold is low (does not exceed a predetermined threshold level), if any of the sensing pair has detected a sensing event, the system 100 concludes the sensing event to be true. Similarly, if any one of the sensing pair is assigned a low sensitivity threshold (do not exceed a predetermined threshold level), the fusion 330 may be based on combining the first and the second sensing outcome using a Boolean logical OR operator. The selection of the threshold may be based on a user’s 120 input, type of environment 101, location of the sensing pair etc.

Alternatively, if the assigned first and the second sensitivity threshold exceed a predetermined threshold, e.g., both the pairs have low sensitivity threshold, then the fusion 330 may be based on a Boolean logical AND operator such that if all of the pairs have detected the sensing event only then the sensing system 100 concludes the sensing event to be true. The threshold may be the same as in the previous example or different.

The method 300 further may comprise determining 340 the sensing outcome for the radio frequency -based sensing system 100 based on the fusion. The sensing outcome may be used e.g., for controlling the light output of the one or more lighting devices 1 lOa-d. For example, when presence is detected the one or more lighting devices 1 lOa-d are powered on.

The fusion 330 may additionally, and/or alternatively be based on combining sensing likelihoods. Now referring to Fig. 4, which shows schematically and exemplary an example of fusing sensing likelihood. A first sensing likelihood 410a and a second sensing likelihood 410b for the first and the second sensing outcome may be respectively determined. The sensing likelihood may be determined based on historical data. Such sensing likelihood may be fused 330, using a math operator, for determining the sensing outcome for the radio frequency -based sensing system 100. The likelihood can be derived of the disturbance in the signal. The disturbance of the signal can be a signal processing algorithm, e.g. median filter (to remove the outliers), a variance filter (to see level of changes in the signals), summing the CSI channel disturbances, normalising the disturbances etc. It would also be possible to use a different algorithm per channel, depending on the location etc. On all pairs it would indicate a likelihood of a sensing event, e.g., motion.

For example, if at least one of the assigned first or the second sensitivity threshold do not exceed a predetermined threshold level (for instance if any one of the first and the second sensing sensitivity threshold is assigned a low value), the first and the second sensing likelihood may be combined using an arithmetic addition operator. The added sensitivity is shown as a curve 420. The slopes are shown as dotted line. A fused sensing sensitivity threshold 430 may be determined, which may or may not be the same as the individual sensing sensitivities, and then the sensing outcome for the radio frequency -based sensing system 100 may be determined based on the fusion and on the fused sensing sensitivity 430.

The method 300 may be executed by computer program code of a computer program product when the computer program product is run on a processing unit of a computing device, such as the processor 213 of the controller 210.

In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. Use of the verb "comprise" and its conjugations does not exclude the presence of elements or steps other than those stated in a claim. The article "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer or processing unit. In the device claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Aspects of the invention may be implemented in a computer program product, which may be a collection of computer program instructions stored on a computer readable storage device which may be executed by a computer. The instructions of the present invention may be in any interpretable or executable code mechanism, including but not limited to scripts, interpretable programs, dynamic link libraries (DLLs) or Java classes. The instructions can be provided as complete executable programs, partial executable programs, as modifications to existing programs (e.g. updates) or extensions for existing programs (e.g. plugins). Moreover, parts of the processing of the present invention may be distributed over multiple computers or processors or even the ‘cloud’.

Storage media suitable for storing computer program instructions include all forms of nonvolatile memory, including but not limited to EPROM, EEPROM and flash memory devices, magnetic disks such as the internal and external hard disk drives, removable disks and CD-ROM disks. The computer program product may be distributed on such a storage medium, or may be offered for download through HTTP, FTP, email or through a server connected to a network such as the Internet.

Claims

CLAIMS:

1. A method of determining sensing outcome of a radio frequency -based sensing system, wherein the system comprises at least three nodes arranged for transmitting and/or receiving radio frequency signals for radio frequency-based sensing, and wherein the at least three nodes form at least two sensing pairs having at least partially overlapping field of view, wherein each sensing pair comprises a transmitter node and a receiver node, wherein the method comprises assigning a first and a second sensing sensitivity to a first and a second sensing pair of the at least two sensing pairs respectively, determining within a time window a first and a second sensing outcome for the first and the second sensing pair respectively based on radio frequency signals communicated between the transmitter node and the receiver node and further based on the assigned first and the second sensing sensitivities respectively, fusing, using a math operator, the first and the second sensing outcome based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency -based sensing system based on the fusion.

2. The method according to claim 1, wherein the method further comprises: determining a first sensing likelihood of the first sensing outcome, and a second sensing likelihood for the second sensing outcome, fusing, using a math operator, the first and the second sensing likelihood based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency -based sensing system based on the fusion.

3. The method according to claim 2, wherein the sensing sensitivity comprises a sensing threshold, and if the assigned first and/or the second sensitivity do not exceed a predetermined threshold level, the method further comprises fusing, using a math operator, the first and the second sensing likelihood, wherein the math operator is an arithmetic addition operator, determining a fused sensing sensitivity, wherein the fused sensing sensitivity comprises a fused sensing threshold, determining the sensing outcome for the radio frequency -based sensing system based on the fusion and on the fused sensing sensitivity.

4. The method according to any of the preceding claims, wherein the sensing sensitivity comprises a sensing threshold, and if the assigned first and/or the second sensitivity do not exceed a predetermined threshold level, the method further comprises: fusing, using a math operator, the first and the second sensing outcome, wherein the math operator is a Boolean logical OR operator.

5. The method according to any of the preceding claims, wherein the sensing sensitivity comprises a sensing threshold, and if the assigned first and the second sensitivity exceed a predetermined threshold level, the method further comprises: fusing, using a math operator, the first and the second sensing outcome, wherein the math operator is a Boolean logical AND operator.

6. The method according to any of the preceding claims, wherein the assignment of the first and/or the second sensing sensitivity is based on one or more of type of an environment wherein the sensing pairs are located, types of transmitter/receiver nodes, number of nodes, a number of sensing pairs, location of the transmitter/receiver nodes in the environment with respect to each other and/or with respect to the environment.

7. The method according to any of the preceding claims, wherein the assignment of the first and/or the second sensing sensitivity is based on a user’s input.

8. The method according to any of the preceding claims, wherein the assignment of the first and/or the second sensing sensitivity is based on a baseline for radiofrequencybased sensing.

9. The method according to any of the preceding claims, wherein the method further comprises receiving a sensing outcome from another sensing modality, wherein the another sensing modality comprises at least partially overlapping field of view with at least one of the at least two sensing pairs, fusing, using a math operator, the first and the second sensing outcome and the received sensing outcome based on the assigned first and the second sensitivity, and determining the sensing outcome for the radio frequency -based sensing system based on the fusion.

10. The method according to any of the preceding claims, wherein the assignment of the first and/or the second sensing sensitivity is based on location of a user.

11. A controller for determining sensing outcome of a radio frequency -based sensing system, wherein the controller is communicatively connected to the at least three nodes and the controller comprises a processor arranged for executing the steps of the method according to any of the preceding claims.

12. A system for determining sensing outcome of a radio frequency-based sensing system, wherein the system comprises at least three nodes arranged for transmitting and/or receiving radio frequency signals for radio frequency-based sensing, and wherein the at least three nodes form at least two sensing pairs having at least partially overlapping field of view, wherein each sensing pair comprises a transmitting node and a receiving node, a controller according to claim 11.

13. A system according to claim 12, wherein the system further comprises a user interface arranged for receiving an input indicative of a user selection for the first and/or the second sensing sensitivity.

14. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method of any one of claims 1-10.