Controller for configuring radio frequency (RF)-based sensing system and method thereof

Abstract

A method of configuring a radio frequency (RF)-based sensing system, where the RF sensing system comprises a plurality of nodes comprising a transmitter and / or a receiver arranged for transmitting and / or receiving an RF signal for sensing an object in an environment, wherein the method comprises clustering the plurality of nodes into two or more clusters based on proximity of the plurality of nodes, determining suitability of the plurality of nodes in each of the two or more clusters for transmitting and / or receiving RF signals for RF sensing, one or more nodes are selected from each of the two or more clusters to act as a transmitter and / or receiver of the RF sensing system based on the determined suitability, and the selected one or more nodes are instructed to act as the transmitter and / or receiver of the RF sensing system.

Description

Technical Field

[0001] The present invention relates to a method of configuring a radio frequency (RF) based sensing system. The present invention also relates to a controller, a system and a computer program product for configuring a radio frequency (RF) based sensing system. Background Art

[0002] Radio frequency based sensing is a sensing mechanism involving a wireless transceiver (or transmitter / receiver) arranged to transmit and receive radio frequency (RF) signals. These RF signals - which may also be used for radio communications - are affected by the presence / movement of people within the sensing volume as they pass through the sensing volume, e.g., via reflection, absorption, scattering, etc. Radio frequency based sensing uses such deviations in the radio frequency signals to infer the presence / movement of people. Radio frequency based sensing also extends to other applications such as position detection, fall detection, posture detection, vital sign detection, etc., which are also based on how the radio frequency signals are affected in the sensing volume.

[0003] US2021 / 185485 A1 discloses a system for selecting one or more devices in a wireless network to transmit, receive and / or process radio frequency signals for presence and / or location detection, the system comprising at least one processor configured to: determine the suitability of each of a plurality of devices for transmitting, receiving and / or processing radio frequency signals for presence and / or location detection; select a subset of devices from the plurality of devices based on the suitability determined for each of the plurality of devices; and instruct at least one of the subset of devices to act as a device for transmitting, receiving and / or processing radio frequency signals for presence and / or location detection. Summary of the invention

[0004] The inventors have realized that selecting all nodes in the environment as part of RF sensing will flood the network with RF signals transmitted and received by the nodes. The inventors have also realized that selecting all nodes will also consume more power and utilize more internal resources because all nodes need to communicate, collect data and process all information.

[0005] It is therefore an object of the present invention to optimize the selection of nodes in sensing areas within an environment.

[0006] According to a first aspect, the object is achieved by a method for configuring a radio frequency (RF)-based sensing system, wherein the RF sensing system includes a plurality of nodes, the plurality of nodes including a transmitter and / or a receiver arranged to transmit and / or receive radio frequency (RF) signals to sense objects in an environment, wherein the method includes: clustering the plurality of nodes into two or more clusters based on proximity of the plurality of nodes; determining the suitability of a plurality of nodes in each of the two or more clusters to transmit and / or receive RF signals for RF sensing; based on the determined suitability, selecting a first subset of nodes from a first cluster of the two or more clusters and selecting a second subset of nodes from a second cluster of the two or more clusters to act as transmitters and / or receivers of the RF sensing system; instructing the nodes from the selected first subset and second subset to act as transmitters and / or receivers of the RF sensing system.

[0007] The method relates to an RF sensing system. The system may be arranged to sense an activity state or characteristic of an object. The activity state or characteristic may include presence, motion, vital signs, posture, fall, position, etc. The object may include a living object such as a person, an animal, and / or a non-living object such as a car, atmospheric conditions, etc. The sensing may be based on how objects in the environment affect the radio frequency signal compared to a baseline (initial value defined for the environment).

[0008] A plurality of nodes are (physically) located in an environment. The environment may be: an indoor environment, such as an office, a home, an arena, etc.; or an outdoor environment, such as a street, a parking lot, etc. The method includes clustering a plurality of nodes into two or more clusters based on the proximity of the plurality of nodes. In one example, the proximity may be only an indication based on, for example, RSSI signal strength, changes in RSSI signal data, etc. The proximity may also be represented by a room name and the nodes in the room, but may also be represented by similar names, etc. The environment may include any number of nodes. For example, in a larger space, there may be a plurality of nodes, such as 50, 100 or even more nodes. The nodes may be clustered in subgroups based on the distance between the nodes. For example, a subset of nodes that are close to each other may be clustered or grouped in a cluster. In one example, the cluster size of different clusters may vary based on the arrangement of the nodes in the environment.

[0009] The method also includes determining the suitability of a plurality of nodes in each of the two or more clusters to transmit and / or receive RF signals for RF sensing. The suitability is based on the overall performance of the RF sensing system and / or network communications. In one example, suitability is determined for each of the plurality of nodes in each of the two or more clusters. Alternatively, suitability is determined for a subset of nodes in each of the two or more clusters.

[0010] Since the method also includes selecting a first subset of nodes from a first cluster of two or more clusters and a second subset of nodes from a second cluster to act as a transmitter and / or receiver of the RF sensing system based on the determined suitability, and also includes instructing the selected one or more nodes to act as a transmitter and / or receiver of the RF sensing system, the selection of nodes in the sensing area is optimized within the environment taking into account the overall performance of the RF sensing system and / or (network) communication. By not selecting unsuitable or less suitable nodes, network traffic is minimized, which improves the overall RF sensing performance. In addition, the nodes that are not selected have more time for network communication and therefore do not waste resources for network communication.

[0011] The first cluster may include the selected first subset and unselected subsets of other nodes. Therefore, the total number of nodes in the first cluster is the sum of the selected first subset and the unselected subsets of other nodes. Similarly, the second cluster may include the selected second subset and unselected subsets of other nodes. Therefore, the total number of nodes in the second cluster is the sum of the selected second subset and the unselected subsets of other nodes. The subset may include one node or more than one node. In one example, the number of nodes in the subset is less than the total number of nodes.

[0012] In one embodiment, determining at least in part the suitability of a node among the plurality of nodes may be based on evaluating at least one of: hardware capabilities of the node, one or more RF characteristics of the node, mounting orientation of the node, wireless interference in the vicinity of the node.

[0013] The selection criteria may include hardware capabilities, for example, selecting nodes with the required RF sensing capabilities. One or more RF characteristics may include, for example, radiation pattern, antenna directivity, transmit power, and / or receive sensitivity. Wireless interference may hinder performance by reducing the reception of RF signals, and therefore, the selection may be based on wireless interference close to the node. The selection may be dynamic, as wireless interference may change over time. Using these selection criteria, the performance of the RF sensing system is further improved.

[0014] In one embodiment, at least partial determination of suitability of a node among the plurality of nodes may be based on historical data associated with the node and / or by evaluating conditions of the spatial location and / or environment of the node.

[0015] As an example of the latter, if the node is a garden light located in an outdoor environment and arranged to perform RF sensing, a lighting device in sunlight may have a different sensitivity than a lighting device in the shadow, for example due to expansion of the substrate resulting in changes in the tracking antenna length and thermal drift of component values ​​like the RF matching circuit and crystal, which results in, for example, a deviation of the carrier frequency relative to the center frequency of the selected frequency band. The environmental conditions may be, for example, weather conditions.

[0016] In one embodiment, at least a partial determination of suitability of a node among the plurality of nodes may be based on a type of detection performed by the RF sensing system.

[0017] RF sensing may be arranged to perform one or more of presence detection, motion detection, vital sign detection (such as breathing rate, heart rate, etc.), fall detection, sleep monitoring, location detection, people counting, people tracking, gesture detection, etc. In this advantageous embodiment, a node is selected based on the type of detection, e.g., a node that is more suitable for the type of detection.

[0018] In one embodiment, the steps of clustering, determining, and selecting may be performed as part of initializing the plurality of nodes to join the network and / or after initializing the plurality of nodes to join the network.

[0019] The node may be selected after using multiple nodes or after receiving information from a similar building space elsewhere (e.g., from another floor or another building). During the network initialization process, some nodes may be marked as more or less suitable for sending functions than other nodes. For example, the suitability of a node may be determined based on how critical the node is for routing messages. The latter is an indication of how much additional resources / bandwidth the node will leave for additional RF-based sensing. Alternatively or additionally, the suitability of a device may be determined, for example, based on how much non-routed or non-rebroadcast traffic the node needs to send (sensor) or receive (actuator, such as a light), as the associated latency requirements may affect the determination of suitability.

[0020] In one embodiment, the plurality of nodes may include at least one lighting device. For this example, the determination of at least a portion of the suitability of the lighting devices of the plurality of nodes may be based on evaluating the expected and / or past use of the lighting and / or network functions of the nodes and / or any other expected and / or past use of the nodes.

[0021] The plurality of nodes may include at least one lighting device. Lighting devices are increasingly equipped with wireless transceivers to enable intelligent functionality and are typically located in large numbers and at locations well suited for RF sensing applications (e.g., presence detection, motion detection, etc.). For example, a lighting device that is always on may be better than a lamp whose on / off state changes frequently. In this example, an off condition may include that the lighting device may be powered but does not provide lighting (e.g., in sleep mode). The intended use of the lighting functionality may be derived from the floor plan or from other devices in similar situations (e.g., from devices on a floor in the same building where wireless lighting is already installed).

[0022] When evaluating the usage of network functions, it is also possible to evaluate how such usage is performed. For example, a node that is frequently used to route messages between two other nodes and successfully relays messages 100% of the time will behave differently than a node that does the same routing but is only successful 70% of the time. The latter may be an indication of some external factor that is affecting the operation of the node (regardless of the level of usage). The performance of network functions such as routing messages and proxying nodes for flows can also potentially result in a visible impact (although not necessarily on the device itself, but on the nodes it serves), and such usage of the device can also be evaluated.

[0023] In one embodiment, at least partial suitability determination of lighting devices for multiple nodes can be based on whether the lighting devices are operated by a battery operated wall switch or by a conventional wall switch, occupancy sensor, motion sensor, sensor bundle, blind controller, and / or mains powered wireless switch.

[0024] Lights controlled by traditional wall switches may be considered less suitable because the light switch cuts power to the light, rendering it unable to perform RF-based sensing. If the light is equipped with a sensor beam, but the sensor beam output is not used for the purpose of real-time adjustment of the light output of other lighting devices (e.g., some wireless lights map the temperature and humidity of an entire room without any dynamic lighting control (e.g., emergency lighting fixtures)) and / or is not used for real-time adjustment of the lighting device that houses the sensor beam, then latency will generally not be critical. The sensor beam may include, for example, a CO2 sensor, a humidity sensor, a microphone (for sound analysis), a volatile organic component sensor, and / or a temperature sensor. Sensors using ultra-wideband (UWB) and LiFi sensor technology may also be used.

[0025] In one embodiment, the method may also include assigning a transmitter role to a first node in a first cluster of the two or more clusters, and assigning a receiver role to a second node in a second cluster of the two or more clusters. The assignment of transmitter and / or receiver roles may be based on criteria for selecting the first and / or second subsets of nodes. In other words, criteria such as hardware capabilities, installation orientation, etc., used to select the first and second subsets may also be used to assign (select) transmitter and / or receiver roles.

[0026] In one embodiment, the method may further include determining a communication quality between a transmitter-receiver pair; and wherein determining at least in part the suitability of a node of the plurality of nodes is based on the determined communication quality between the pair.

[0027] In one example, a first cluster includes transmitters and a second cluster includes receivers. The quality of communication between a transmitter-receiver pair can be determined and compared to a threshold. If the determination is negative, e.g., the quality is below a threshold, the pair is determined to be unsuitable. The quality of communication typically depends on whether there are obstacles blocking the RF-based sensing path. RF-based sensing methods do not necessarily require direct line of sight between nodes. However, wireless signals cannot penetrate certain obstacles. For example, if an end user rearranges a large piece of metal furniture (e.g., a bookshelf), the RF sensing path between the nodes may be compromised.

[0028] In one embodiment, the method may also include: determining at a later time further suitability of multiple nodes (each of which) for transmitting and receiving radio frequency signals; based on the further determined suitability, selecting a first subset of nodes from a first cluster of two or more clusters and selecting a second subset of nodes from a second cluster of two or more clusters to act as transmitters and / or receivers of the RF sensing system; instructing the nodes from the selected first subset and second subset to act as transmitters and / or receivers of the RF sensing system.

[0029] In this example, the selection process may be a dynamic process, where the selection criteria may evolve, be evaluated, or be dynamically determined over time. For example, wireless interference may change over time, i.e., a node that suffers interference may become a suitable node later in time.

[0030] In one embodiment, the plurality of nodes may also be arranged to transmit and / or receive radio frequency (RF) signals for network communication, wherein nodes not selected in two or more clusters may be arranged for network communication.

[0031] The RF signals may also be advantageously used for network communications, for example, to carry network messages intended for communication between nodes. With regard to network communications, in order to optimize RF sensing system performance, non-selected nodes in the cluster may be arranged to perform network communications. This results in better utilization of available network resources.

[0032] In one embodiment, the proximity of multiple nodes may be determined based on characteristics of received RF signals.

[0033] In this advantageous embodiment, the distance between multiple nodes can be determined based on a characteristic of the received RF signal. In one example, the characteristic can be a received signal strength indication (RSSI). Additionally and / or alternatively, a (digital) floor plan can be used to determine the location and distance between nodes.

[0034] In one embodiment, clustering may be performed by utilizing a machine learning algorithm, preferably k-means clustering.In one embodiment, the method may further include determining a maximum number of clusters based on one or more of: the number of multiple nodes, the type and / or size of the environment, user input.

[0035] The number of clusters may be capped by some selection criteria. For example, it may be based on the number of available nodes, their distances relative to each other. The user may also be able to provide an input indicating the maximum number of clusters.

[0036] According to a second aspect, the object is achieved by a controller for configuring a radio frequency (RF) based sensing system, wherein the RF sensing system comprises a plurality of nodes, the plurality of nodes comprising a transmitter and / or a receiver arranged to transmit and / or receive radio frequency (RF) signals to sense objects in an environment, wherein the control device comprises a processor arranged to perform the steps of the method of the first aspect.

[0037] According to a third aspect, the object is achieved by a system for configuring a radio frequency, RF, based sensing system, wherein the RF sensing system comprises a plurality of nodes, the plurality of nodes comprising a transmitter and / or a receiver arranged to transmit and / or receive radio frequency, RF, signals to sense objects in an environment, wherein the system comprises the plurality of nodes and a controller according to the second aspect.

[0038] According to a fourth aspect, the object is achieved by a computer program product comprising instructions, which, when executed by a computer, cause the computer to perform the steps of the method of the first aspect. According to a fourth aspect, the object is achieved by a computer program product comprising instructions, which, when executed by a processor of a controller according to the second aspect, cause the processor to perform the steps of the method of the first aspect.

[0039] It should be understood that the computer program product, controller, and system may have similar and / or the same embodiments and advantages as the above-described method. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and 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 the systems, devices and methods with reference to the accompanying drawings, in which:

[0041] Figure 1 Schematically and exemplarily, an embodiment of a system for configuring a radio frequency (RF) based sensing system is shown,

[0042] Figure 2 Schematically and exemplarily, an embodiment of a controller for configuring a radio frequency RF based sensing system is shown,

[0043] Figure 3 A flow chart illustrating an embodiment of a method for configuring a radio frequency RF based sensing system is shown schematically and exemplarily.

[0044] All the figures are schematic, not necessarily to scale, and generally show only parts which are necessary in order to elucidate the invention, wherein other parts may be omitted or merely suggested. DETAILED DESCRIPTION

[0045] Figure 1 An embodiment of a system 100 for configuring a radio frequency RF-based sensing system 100 is schematically and exemplarily shown. The system 100 includes a plurality of nodes 110a-f. In this exemplary figure, the nodes are shown as lighting devices. Additionally and / or alternatively, the nodes may be one or more sensors, switches, smart plugs, etc.

[0046] The lighting devices 110a-f are devices or structures arranged to emit light suitable for illuminating the environment 101, which provide or substantially contribute to illumination on a scale sufficient for that purpose. The lighting devices 110a-f include at least one light source or lamp (not shown), such as an LED-based lamp, a gas discharge lamp, or an incandescent bulb, plus any associated brackets, housings, or other such enclosures. Each of the lighting devices 110a-f can take any of a variety of forms, such as a ceiling-mounted fixture, a wall-mounted fixture, a wall washer, or a free-standing fixture (and the fixtures need not necessarily all be of the same type).

[0047] Multiple nodes 110a-f include a transmitter and / or a receiver, which is arranged to transmit and / or receive radio frequency RF signals for sensing objects in the environment 101. The transmitter and / or the receiver may be included in a transceiver. For example, nodes 110a-f may include a radar sensor, wherein the transmitter and the receiver are included in the same node. The radar sensor may be a Wifi radar, a millimeter wave (60GHz) and / or a UWB radar, etc. Multiple nodes 110a-f include appropriate circuits (not shown) to transmit and receive RF signals using any communication protocol such as Zigbee, Bluetooth, Wifi, Thread, etc. The RF signal may include any radio frequency bandwidth, such as 2.4GHz, 5GHz, 24GHz, 60GHz, etc.

[0048] Multiple nodes 110a-f can be clustered in at least two clusters / groups 115a-b. The formation of clusters 115a-b can be based on the proximity of multiple nodes 110a-b. The proximity of multiple nodes 110a-f can be determined based on characteristics of received RF signals (e.g., RSSI, channel state information (CSI), etc.). For example, RSSI can be evaluated to determine the distance of nodes relative to each other. Additionally and / or alternatively, proximity information can be obtained from a floor plan, user input, etc. Any other source of proximity information can be used.

[0049] In this illustrative example, two clusters 115a-b are shown. There may be n clusters, where n may be 5, 10, 100, etc. Clusters 115a-b may include nodes 110a-f of the same type or nodes 110a-f of different types. The number of nodes 110a-f in a cluster or the maximum number of nodes 110a-f may be based on the number of multiple nodes available in the environment, the type and / or size of the environment, user input, etc. User 120 may provide input via a user device 130 such as a mobile phone, laptop, tablet, etc.

[0050] The suitability of multiple nodes 110a-f (each of) in each of two or more clusters 115a-b to transmit and / or receive RF signals for RF sensing can be determined. In this example, node 110a from cluster 115a and node 110e from cluster 115b are determined to be suitable for transmitting and / or receiving RF signals for RF sensing. Then, these two nodes 110a, 110e are selected and instructed to act as transmitter and / or receiver roles of RF sensing systems. In this example, based on hardware capabilities, wireless interference, installation orientation, etc., the role of transmitter can be assigned to node 110a, and the role of receiver can be assigned to 110e, or it can be vice versa.

[0051] Figure 2 Schematically and exemplarily, an embodiment of a controller 210 for configuring a radio frequency RF based sensing system 100 is shown. The controller 210 may include an input unit 214 and an output unit 215. The input unit 214 and the output unit 215 may be included in a transceiver (not shown), or the input unit 214 may be included in a receiver and the output unit 215 in a transmitter, which is arranged for receiving (input unit 214) and transmitting (output unit 215) RF signals.

[0052] The controller 210 may further comprise a memory 212 which may be arranged to store communication IDs of lighting devices 110a-f and / or user devices 130 etc. The controller 210 may comprise a processor 213 arranged to execute steps or at least control execution of steps of the method according to the first aspect.

[0053] The controller 210 may be implemented in a unit separate from the lighting devices 110a-f / user devices 130, such as a wall panel, a desktop computer terminal, or even a portable terminal such as a laptop, tablet computer, or a smart phone. Alternatively, the controller 210 may be incorporated into the same unit as the user device 130 and / or in the same unit as one of the lighting devices 110a-f. Furthermore, the controller 210 may be implemented in the environment 101 or remotely from the environment 101 (e.g., on a server); and the controller 210 may be implemented in a single unit, or in the form of a distributed function distributed among multiple independent units (e.g., a distributed server including multiple server units at one or more geographic locations, or a distributed control function distributed among the lighting devices 110a-f or among the lighting devices 110a-f and the user device 130). In addition, the controller 210 can be implemented in the form of software stored on a memory (which includes one or more memory devices) and arranged to be executed on a processor (which includes one or more processing units), or the controller 210 can be implemented in the form of a dedicated hardware circuit, or a configurable or reconfigurable circuit such as a PGA or FPGA, or any combination of these.

[0054] To enable the controller 210 to, for example, receive or transmit RF signals, communication may be achieved via any suitable wireless means, such as a local (short-range) RF network, e.g., Wi-Fi, ZigBee, Bluetooth, or Thread network; or via any combination of these and / or other means.

[0055] Figure 3A flow chart illustrating an embodiment of a method 300 for configuring a radio frequency RF-based sensing system 100 is schematically and exemplarily shown. The method 300 may include clustering 310 a plurality of nodes 110a-f into two or more clusters 115a-b based on the proximity of the plurality of nodes 110a-f. A threshold may be defined so that if the proximity of the nodes is within a threshold distance, they are clustered in one cluster. Clustering 310 may be based on an area in the environment 101, for example, in a living room, nodes around a TV may be clustered in one group. Clustering may be performed by utilizing a machine learning algorithm (preferably k-means clustering). Other algorithms for clustering known in the art are not excluded. K-means clustering is a vector quantization method that aims to divide n observations into k clusters, where each observation belongs to a cluster with the nearest mean (cluster center or cluster centroid), serving as a prototype of the cluster. Clusters 115a-b may have different types of nodes 110a-f, different numbers of nodes 110a-f, and the like. Clusters 310 may change over time.

[0056] The method 300 may also include determining 320 the suitability of a plurality of nodes in each of the two or more clusters 115a-b to transmit and / or receive RF signals for RF sensing. The suitability may be determined such that the selection of the plurality of nodes 110a-f to perform RF sensing is optimized. The selection may be based on consideration of network communications such that network traffic is minimized. As previously described, the selection of the plurality of nodes 110a-f may be determined considering different selection criteria.

[0057] The method 300 may also include selecting 330 a first subset of nodes 110a-f from a first cluster of two or more clusters 115a-b, and selecting 330 a second subset of nodes 110a-f from a second cluster of two or more clusters 115a-b to act as a transmitter and / or receiver of the RF sensing system 100 based on the determined suitability. In one example, the subset includes only a single node, and in other examples, the subset includes more than one node. In another example, not all nodes are included in the subset, so that for each cluster, there is always a subset of nodes that are not selected. In other words, some nodes are excluded from the selected first and / or second subsets. Different clusters 115a-b may have different numbers of nodes 110a-f selected in the clusters 115a-b. In one example, the transmitter and receiver are included in the same node so that the transmitted RF signal is received back by the same node.

[0058] The method 300 may further comprise instructing 340 the selected one or more nodes 110a-f to act as a transmitter and / or receiver of the RF sensing system 100. The controller 210 and / or the user equipment 130 may be arranged to instruct the selection of the one or more nodes 110a-f to act as a transmitter and / or receiver of the RF sensing system 100.

[0059] The method 300 may be performed by computer program code of a computer program product when the computer program product is executed on a processing unit of a computing device, such as the processor 213 of the controller 210 .

[0060] It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims.

[0061] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The 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 a 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.

[0062] Aspects of the present 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 that may be executed by a computer. Instructions of the present invention may be any interpretable or executable code mechanism, including but not limited to scripts, interpretable programs, dynamic link libraries (DLLs) or Java classes. Instructions may be provided as complete executable programs, partial executable programs, as modifications (e.g., updates) of existing programs, or as extensions (e.g., plug-ins) of existing programs. In addition, partial processing of the present invention may be distributed over multiple computers or processors or even "clouds".

[0063] Storage media suitable for storing computer program instructions include all forms of non-volatile memory, including but not limited to EPROM, EEPROM and flash memory devices, magnetic disks such as internal and external hard drives, removable disks and CD-ROM disks. The computer program product may be distributed on such storage media or may be provided for download via HTTP, FTP, email or through a server connected to a network such as the Internet.

Claims

1. A method of configuring a radio frequency (RF) based sensing system, wherein the RF sensing system comprises a plurality of nodes, the plurality of nodes comprising transmitters and / or receivers arranged to transmit and / or receive radio frequency (RF) signals to sense objects in an environment, wherein the method comprises: - cluster multiple nodes into two or more clusters based on their proximity, - determining the suitability of a plurality of nodes in each of two or more clusters for transmitting and / or receiving RF signals for RF sensing, - based on the determined suitability, selecting a first subset of nodes from a first cluster of the two or more clusters and selecting a second subset of nodes from a second cluster of the two or more clusters to act as transmitters and / or receivers of the RF sensing system, - Instructing nodes from the selected first and second subsets to act as transmitters and / or receivers of the RF sensing system.

2. A method according to claim 1, wherein the determination of at least part of the suitability of a node among the multiple nodes is based on evaluating at least one of the following: hardware capabilities of the node, one or more RF characteristics, the installation orientation of the node, and wireless interference in the vicinity of the node.

3. A method according to any of the preceding claims, wherein the determination of at least part of the suitability of a node among the plurality of nodes is based on historical data related to the node and / or by evaluating the conditions of the spatial position and / or environment of the node.

4. A method according to any one of the preceding claims, wherein the determination of at least part of the suitability of a node in the plurality of nodes is based on a type of detection performed by an RF sensing system.

5. The method according to any one of the preceding claims, wherein the steps of clustering, determining and selecting are performed as part of and / or after initializing the plurality of nodes to join the network.

6. The method according to any of the preceding claims, wherein the plurality of nodes comprises at least one lighting device.

7. The method according to any one of the preceding claims, wherein the method further comprises: - assigning a transmitter role to a first node in a first cluster of the two or more clusters and assigning a receiver role to a second node in a second cluster of the two or more clusters.

8. The method according to claim 7, wherein the method further comprises - determining a quality of communication between a transmitter-receiver pair; and wherein the determination of at least part of the suitability of a node of the plurality of nodes is based on the determined quality of communication between the pair.

9. The method according to any one of the preceding claims, wherein the method further comprises: - determining at a later time the further suitability of the plurality of nodes for transmitting and receiving radio frequency signals, - based on the further determined suitability, selecting a first subset of nodes from a first cluster of the two or more clusters and selecting a second subset of nodes from a second cluster of the two or more clusters to act as transmitters and / or receivers of the RF sensing system, - Instructing nodes from the selected first and second subsets to act as transmitters and / or receivers of the RF sensing system.

10. A method according to any one of the preceding claims, wherein the plurality of nodes are further arranged to transmit and / or receive radio frequency (RF) signals for network communications, wherein non-selected nodes in two or more clusters are arranged for network communications.

11. A method according to any preceding claim, wherein the proximity of the plurality of nodes is determined based on characteristics of the received RF signals.

12. The method of any one of the preceding claims, wherein the method further comprises determining the maximum number of clusters based on one or more of: the number of the plurality of nodes, the type and / or size of the environment, user input.

13. A controller for configuring a radio frequency (RF) based sensing system, wherein the RF sensing system comprises a plurality of nodes, the plurality of nodes comprising transmitters and / or receivers arranged to transmit and / or receive radio frequency (RF) signals to sense objects in an environment, wherein the control device comprises a processor arranged to perform the steps of the method according to any one of the preceding claims.

14. A system for configuring a radio frequency (RF) based sensing system, wherein the RF sensing system comprises a plurality of nodes, the plurality of nodes comprising transmitters and / or receivers arranged to transmit and / or receive radio frequency (RF) signals to sense objects in an environment, wherein the system comprises: - multiple nodes, - A controller according to claim 13.

15. A computer program product comprising instructions which, when executed by a processor of a controller according to claim 13, cause the processor to perform the steps of the method according to any one of claims 1 to 12.

Images