RADIO FREQUENCY BASED SENSING FOR DENSE NODE ARRANGEMENTS

Abstract

The present invention regards performing RF-based sensing in RF system (100) comprising multiple nodes (10, 27, 28, 29, 30) of which at least two nodes (10) are included a dense node arrangement (26). A first group of nodes including at least one node (10) of the dense node arrangement (26) and a second group including the at least one node of the first group and at least one additional node of the dense node arrangement are formed. RF-based sensing is performed by the first group in a first sensing area for detecting a first sensing event indicating a presence of an object (32) in the first sensing area. If the first sensing event is detected, RF-based sensing is performed by the second group in a second sensing area (60) at least partially overlapping with the first sensing area for recognizing a second sensing event indicating an activity of the object.

Claims

1. A radio frequency system comprising multiple nodes for performing radio frequency based sensing, wherein at least two of the multiple nodes are included in a dense node arrangement, wherein the dense node arrangement comprises a multi-node device and/or a group of densely packed nodes; and wherein the radio frequency system is configured: for forming a first group of nodes including at least one node of the dense node arrangement, for forming a second group of nodes including the at least one node of the first group and at least one additional node of the dense node arrangement, for performing radio frequency based sensing by the first group in a first sensing area for detecting a first sensing event indicating a presence of an object in the first sensing area, and wherein if the first sensing event is detected, the radio frequency system is further configured: for performing radio frequency based sensing by the second group in a second sensing area at least partially overlapping with the first sensing area for recognizing a second sensing event indicating an activity of the object.

2. The radio frequency system according to claim 1, wherein the radio frequency system is configured for forming the first group of nodes such that the first group includes the at least one node of the dense node arrangement and at least one node which is not included in the dense node arrangement.

3. The radio frequency system according to claim 1, wherein upon detecting the first sensing event, the radio frequency system is configured for performing radio frequency based sensing in a third sensing area by at least the at least one node of the first group for detecting a third sensing event indicating a location of the object within proximity of the dense node arrangement, the third sensing area at least partially overlapping with the first sensing area and the second sensing area, and wherein the radio frequency system is configured for performing the radio frequency based sensing by the second group at the location of the object for recognizing the second sensing event if the first sensing event is detected and upon detecting the third sensing event.

4. The radio frequency system according to claim 3, wherein the radio frequency system is configured for forming the second group upon detecting the third sensing event and based on the location of the object.

5. The radio frequency system according to claim 1, wherein the radio frequency system is configured for adjusting a message frequency for transmitting radio frequency messages by the nodes of the radio frequency system for performing radio frequency based sensing, a directionality of radio frequency message transmissions, or both the message frequency for transmitting radio frequency messages by the nodes of the radio frequency system for performing radio frequency based sensing and the directionality of the radio frequency message transmissions, based on which sensing event is to be detected or recognized by the nodes.

6. The radio frequency system according to claim 1, wherein the radio frequency system is configured while performing radio frequency based sensing by the second group in the second sensing area for recognizing the second sensing event, to stop performing radio frequency based sensing for detecting any other sensing events in the second sensing area.

7. The radio frequency system according to claim 1, wherein the radio frequency system is configured for performing radio frequency based sensing by the second group in the second sensing area for recognizing the second sensing event until a stopping condition is fulfilled including one or more of that the second event is recognized, that a stopping event is detected, that a predetermined duration has passed since the second group started radio frequency based sensing in the second sensing area for recognizing the second sensing event, and that an inactivity of the object is recognized.

8. The radio frequency system according to claim 1, wherein the radio frequency system is configured for performing radio frequency based sensing for detecting the first sensing event or the third sensing event when the second group stops performing radio frequency based sensing for detecting the second sensing event.

9. The radio frequency system according to claim 1, wherein the radio frequency system is configured for performing an action based on the detected first sensing event, the detected third sensing event, the recognized second sensing event, and/or contextual information.

10. A radio frequency super-system including two or more radio frequency systems according to claim 1 such that the RF super-system includes two or more dense node arrangements at different locations.

11. A method for performing radio frequency based sensing in a radio frequency system comprising multiple nodes for performing radio frequency based sensing, wherein at least two of the multiple nodes are included in a dense node arrangement, wherein the dense node arrangement comprises a multi-node device and/or a group of densely packed nodes; wherein the method comprising the steps: forming a first group of nodes including at least one node of the dense node arrangement, forming a second group of nodes including the at least one node of the first group and at least one additional node of the dense node arrangement, performing radio frequency based sensing by the first group in a first sensing area for detecting a first sensing event indicating a presence of an object in the first sensing area, and wherein if the first sensing event is detected, the method comprises the step of— performing radio frequency based sensing by the second group in a second sensing area at least partially overlapping with the first sensing area for recognizing a second sensing event indicating an activity of the object.

12. The method according to claim 11, wherein the first group is formed such that the first group includes the at least one node of the dense node arrangement and at least one node which is not included in the dense node arrangement.

13. The method according to claim 11, comprising one or more of the steps: upon detecting the first sensing event, performing radio frequency based sensing in a third sensing area by at least the at least one node of the first group for detecting a third sensing event indicating a location of the object within proximity of the dense node arrangement, the third sensing area at least partially overlapping with the first sensing area and the second sensing area, and wherein the radio frequency based sensing performed by the second group is performed at the location of the object for recognizing the second sensing event if the first sensing event is detected and upon detecting the third sensing event, forming the second group upon detecting the third sensing event and based on the location of the object, forming the first group by selecting the nodes to be included in the first group based on one or more radio frequency system parameters and/or the second sensing event to be recognized by the second group, forming the second group by selecting the at least one additional node of the dense node arrangement to be included in the second group in addition to the nodes of the first group based on one or more radio frequency system parameters and/or the second sensing event to be recognized by the second group, adjusting a message frequency for transmitting radio frequency messages by the nodes of the radio frequency system for performing radio frequency based sensing based on which sensing event is to be detected or recognized by the nodes, adjusting a directionality of radio frequency messages by the nodes of the radio frequency system for performing radio frequency based sensing based on which sensing event is to be detected or recognized by the nodes, while performing radio frequency based sensing by the second group in the second sensing area for recognizing the second sensing event, stop performing radio frequency based sensing for detecting any other sensing events in the second sensing area, performing radio frequency based sensing by the second group in the second sensing area for recognizing the second sensing event until a stopping condition is fulfilled, wherein the stopping condition includes one or more of that the second event is recognized, that a stopping event is detected, that a predetermined duration has passed since the second group started radio frequency based sensing in the second sensing area for recognizing the second sensing event, and that an inactivity of the object is recognized, performing radio frequency based sensing for detecting the first sensing event or the third sensing event when the second group stops performing radio frequency based sensing for detecting the second sensing event, and performing an action based on the detected first sensing events, the detected third sensing event, the recognized second sensing event, and/or contextual information.

14. A computer program product for performing radio frequency based sensing in a radio frequency system comprising multiple nodes for performing radio frequency based sensing, wherein at least two of the multiple nodes are included in a dense node arrangement, wherein the computer program product comprises program code means for causing a processor to carry out the method according to claim 11, when the computer program product is run on the processor.

15. A computer readable medium having stored the computer program product of claim 14.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In the following drawings:

[0083] FIG. 1 shows schematically and exemplarily a node of a RF system;

[0084] FIG. 2 shows schematically and exemplarily an embodiment of the RF system performing presence detection;

[0085] FIG. 3 shows schematically and exemplarily an embodiment of the RF system performing proximity detection;

[0086] FIG. 4 shows schematically and exemplarily an embodiment of the RF system performing activity recognition;

[0087] FIG. 5 shows schematically and exemplarily an embodiment of a RF super-system; and

[0088] FIG. 6 shows an embodiment of the method for performing RF-based sensing in an RF system with a dense node arrangement.

DETAILED DESCRIPTION OF EMBODIMENTS

[0089] FIG. 1 shows schematically and exemplarily a node 10 of a RF system, e.g., connected lighting (CL) system 100 presented in FIGS. 2 to 4 or CL system 400 or 400′ presented in FIG. 5. The node 10 is a luminaire that provides lighting and that is used for performing RF-based sensing.

[0090] In the CL system, the nodes can for example be routers, bridges, lights, luminaires, switches, or sensors. This allows using the wireless infrastructure of the CL system to perform RF-based sensing, increasing the functionality of the CL system. The nodes may perform their functions, such as providing light and receiving control commands and additionally perform RF-based sensing. RF-based sensing can, for example, be used for presence detection and for activity recognition, such as breathing rate measurements, heart rate measurements, gesture recognition, fall recognition, or for performing other sensing applications.

[0091] The node 10 comprises a control unit 12, a transceiver unit 14, an antenna array 16, and a function unit in form of a lighting unit 17. Instead of an antenna array, a single antenna may also be included in the node.

[0092] The control unit 12 includes a processor 18 and a computer readable medium in form of memory 20.

[0093] In this embodiment, the transceiver unit 14 includes a WiFi transceiver 22 and a BLE transceiver 24. The WiFi transceiver 22 uses a WiFi communication technology according to one or more of the WiFi standards, e.g., IEEE 802.11ax, IEEE 802.11ay, and/or any other communication protocol in this embodiment. The BLE transceiver 24 uses BLE communication technology. In this embodiment, the BLE transceiver 24 can be operated with multiple different frequency channels. In other embodiments, various other communication technologies may be used, such as Zigbee, cellular radio, Thread, or any other communication technology.

[0094] The transceiver unit 14 uses the antenna array 16 for transmitting RF signals to nodes and receiving RF signals from nodes of the CL system for exchanging data wirelessly between the nodes and for performing RF-based sensing. RF signals transmitted from one node to another node are disturbed by objects within a specific volume between the nodes. The RF signals disturbed by an object in the specific volume can be analyzed in the control unit 12. The RF signals can use the WiFi communication technology or the BLE communication technology. In other embodiments, the transceivers of the transceiver unit can be used for performing RF-based sensing by transmitting RF signals into a specific volume and by receiving and analyzing reflected RF signals from the specific volume by the same node. The RF signals can also be transmitted into the specific volume by one node and disturbed and/or reflected RF signals can be received and analyzed by another node.

[0095] The lighting unit 17 includes a driver and a light source, e.g., an light emitting diode (LED) array, for providing light.

[0096] The memory 20 of the control unit 12 stores a computer program product for performing RF-based sensing. The computer program product includes program code means for causing processor 18 to carry out a method for performing RF-based sensing when the computer program product is run on the processor 18, e.g., the method as presented in FIG. 6. The memory 20 further includes a computer program product for operating the node 10 and optionally also the CL system, e.g., for controlling the functions of the node and controlling the functions of the nodes of the CL system, for example, in order to provide lighting as well as for performing RF-based sensing.

[0097] Furthermore, the memory 20 stores RF system parameters including, for example, a location of the nodes, areas of interest in which a sensing event is expected, a distance between the nodes, or any other RF system parameter. Additionally, the memory 20 stores settings of RF-based sensing parameters used for performing RF-based sensing, e.g., frequency channels, message frequencies, sensing areas, groups or any other RF-based sensing parameters.

[0098] FIG. 2 shows the CL system 100 performing presence detection. The CL system 100 comprises multiple nodes 10, 27, 28, 29, and 30 for performing RF-based sensing. Five nodes 10 of the multiple nodes are included in a dense node arrangement in form of chandelier 26. The nodes 10 in the chandelier 26 have a node density of 10 nodes per square meter. In other embodiments, the node density in the dense node arrangement may also be, for example, at least 5 nodes per square meter or above 10 nodes per square meter. Chandelier 26 is furthermore connected to an external server 200. The CL system 100 is arranged in a room in a building (not shown). In other embodiments, the CL system may also, for example, be arranged in an open space, such as a part of a streetlight system.

[0099] The external server 200 controls the CL system 100 in this embodiment, i.e., controlling the normal operation of the nodes of the CL system, e.g., providing lighting, as well as the RF-based sensing. RF messages are transmitted via RF signals 34 between the nodes. The RF messages can include RF data messages and RF sensing messages. The RF data messages, such as control commands, serve for activating or deactivating a function, such as providing lighting of a node. The RF sensing messages are used for performing RF-based sensing. In this embodiment, RF sensing messages are not exchanged between the nodes of the dense node arrangement, but only between other nodes and the nodes of the dense node arrangement. In other embodiments, RF sensing messages may also be exchanged between each of the nodes. The CL system 100 performs RF-based sensing for various sensing applications, for example, in order to detect a presence of an object in form of a user 32.

[0100] RF-based sensing requires a different number of nodes and different message frequencies in dependence of the sensing application, such as presence detection, proximity detection, or activity recognition as different sensing applications require different levels of precision. For example, recognizing an activity of the user 32, such as a gesture, requires more nodes and a higher message frequency than detecting presence of the user 32 or a proximity of the user 32 to the dense node arrangement, e.g., the chandelier 26. Higher message frequencies and more nodes transmitting RF messages may lead to wireless interference between activity recognition and the normal operation of the CL system, e.g., data exchange for controlling the nodes of the CL system. In order to keep wireless interference low, the number of nodes performing RF-based sensing at the same time should be kept to a minimum required for performing the respective sensing application. The CL system is therefore calibrated and additional nodes are only activated for performing RF-based sensing in order to improve resolution, e.g., required for activity recognition, when needed. The calibration of the CL system includes finding an optimal number, physical location and configuration of nodes for presence and proximity detection, as well as activity recognition. This allows maintaining a timely and accurate detection resulting in a desired low-latency control of the nodes. The CL system is thus able to react on control commands transmitted via RF data messages, such as activating a lighting scene using a switch, or changing a color of a luminaire using a device running a respective app.

[0101] In the following the functionality of the CL system 100 is explained with respect to FIGS. 2 to 4.

[0102] In a nutshell, the CL system 100 first calibrates groups for performing RF-based sensing for a specific sensing application in a sensing area associated to the respective group. A first group detects presence of an object in a first sensing area in FIG. 2. Optionally performing presence detection is stopped, and a third group detects proximity of the object of the dense node arrangement and optionally determines a current location of the object to the dense node arrangement in FIG. 3. Presence detection and proximity detection are then stopped and a second group recognizes an activity of the object in FIG. 4. When activity recognition is not needed anymore, the activity recognition is stopped and presence detection or optionally proximity detection is performed again. An action can be performed by the CL system 100 upon detecting the first sensing event, the third sensing event and/or upon recognizing the second sensing event. The action performed by the CL system 100 may depend on the sensing event, e.g., when presence of the user is detected, lighting may be activated, when presence of the user is not detected anymore, lighting may be deactivated, and when a gesture is recognized a respective lighting scene may be activated. Additionally, contextual information may be considered for the action.

[0103] In the following we explain the steps performed by the CL system 100 in more detail.

[0104] At first, the CL system 100 performs a calibration by selecting nodes to be added to the respective groups for performing RF-based sensing for detecting or recognizing a respective sensing event. In this embodiment, three groups are formed, namely, a first group for presence detection, a third group for proximity detection, and a second group for activity recognition. In other embodiments, a different number of groups may be formed, e.g., two groups.

[0105] The first group is optimized for presence detection. Nodes are included in the first group that allow optimal presence detection as shown in FIG. 2. In this embodiment, a center node of the chandelier 26 is included in the first group and the nodes 27, 28, 29, 30 which are not included in the chandelier 26, i.e., the first group includes one node of the dense node arrangement and several nodes which are not included in the dense node arrangement. In other embodiments, the RF system may also form the first group of nodes such that it includes only one or more nodes of the dense node arrangement, i.e., not including nodes which are not included in the dense node arrangement. Furthermore, settings of RF-based sensing parameters of the nodes of the first group are adjusted, such as directionalities, frequency channels and message frequencies used by the nodes for performing RF-based sensing in order to optimize the nodes of the first group for presence detection. Finally, a first sensing area 40 associated to the first group is defined. In this embodiment, the first sensing area 40 depends on the location of the nodes included in the first group.

[0106] Nodes of the third group are selected in order to optimize proximity detection, e.g., detecting a location of the user within proximity of the dense node arrangement. In this embodiment, the third group includes the nodes of the first group and additionally two further nodes of the chandelier 26 as shown in FIG. 3. In other embodiments, other nodes may be included in the third group. Furthermore, the settings of RF-based sensing parameters of the nodes of the third group are adjusted in order to optimize them for proximity detection. Finally, a third sensing area 50 associated to the third group is defined which depends on the location of the nodes included in the third group.

[0107] The second group is optimized for recognizing activities. The second group includes all nodes of the first group and additionally all nodes of the chandelier 26 as shown in FIG. 4. The second sensing group is thus a superset of the first group. In other embodiments, other nodes may be included in the second group. The nodes to be included in the second group may be selected based on various parameters, such as the sensing application, as well as a distance of the user to the dense node arrangement. Furthermore, settings of RF-based sensing parameters of the nodes of the second group are adjusted in order to optimize activity recognition. Finally, a second sensing area 60 associated to the second group is defined. In this embodiment, the second sensing area depends on the location of the nodes included in the second group and in particular on the location of the dense node arrangement. The second sensing area is defined such that it is located in proximity to the dense node arrangement in order to optimally cover an area of interest in which the activities of the user will be performed.

[0108] The calibration may include acquiring feedback from the user 32 in order to optimize the groups for their respective sensing application. For example, the groups may be calibrated based on a physical configuration of the nodes, i.e., the positions of the nodes, and on the user preferences, e.g., which type of activities, e.g., cooking, training, playing a game, should be tracked or are expected to be performed by the user 32. The user 32 may support in calibrating the CL system 100 by providing feedback regarding a latency level that the user finds acceptable. Furthermore, the CL system may be trained to recognize the activity of the user based on activities performed by the user in different parts of the room. The user may generate training data in this manner. The training data may be labeled and provided as input data to an activity recognition algorithm, e.g., a machine learning (ML) algorithm, for example, including a neural network or the like. This may be used when adjusting the directionalities, frequency channels, and message frequencies as well as when selecting the nodes to be included in the respective groups to optimize the groups for performing RF-based sensing for a respective sensing application.

[0109] In other embodiments, the RF system may form the second group upon detecting the third sensing event and based on the location of the object, i.e., during operation of the CL system 100 or in other words on the fly while the CL system 100 performs RF-based sensing.

[0110] Once the CL system 100 is calibrated, it may be used for performing improved RF-based sensing.

[0111] Initially, the CL system 100 performs RF-based sensing by the first group in the first sensing area 40 for detecting the first sensing event indicating a presence of the user 32 in the first sensing area 40 as shown in FIG. 2. In this embodiment, the center node of the chandelier 26 and the nodes 27, 28, 29, and 30 perform RF-based sensing with a message frequency of 30 Hz sufficient for presence detection. This sensing application does not interfere with the normal operation of the CL system 100, i.e., providing lighting and controlling the CL system 100. In other embodiments, detecting presence may be a default operation mode for the RF system. Detecting presence may be used, for example, to activate a security alert or simply for automatically switching lights on and off, i.e., activating and deactivating a lighting function of the nodes.

[0112] When presence is detected, in this embodiment, the CL system 100 activates the function of the luminaires to provide lighting. In other embodiments, the RF system may also perform any other action upon detecting the first sensing event indicating presence of an object, e.g., the user. The RF system may be configured for performing an action based on the detected first sensing event and/or contextual information.

[0113] Furthermore, upon detecting the first sensing event, the CL system 100 performs RF-based sensing in the third sensing area 50 by the third group for detecting the third sensing event indicating a location of the user 32 within proximity of the dense node arrangement. The location may be a physical location, e.g., with a direction and distance from the dense node arrangement, or a direction such as north, east, south or west of the node arrangement. The third group has a higher node density than the first group as two additional nodes in the dense node arrangement are included. Proximity detection requires a slightly higher resolution than presence detection and can be enabled due to the higher node density of the third group compared to the first group. Furthermore, the third sensing area 50 partially overlaps with the first sensing area 40 and the second sensing area 60.

[0114] Proximity is detected if the user is within a certain distance of the dense node arrangement, e.g., within a distance of 4 m to an outer surface of the dense node arrangement or a center of the dense node arrangement, e.g., within a distance of 4 m to the center node of the chandelier 26.

[0115] In other embodiments, proximity detection may be leveraged to provide individual control of the nodes nearby the location of the user. For example, it may be used for physical controls, app, or voice type of commands. The RF system may be configured for performing an action upon detecting the third sensing event and/or based on the detected third sensing event.

[0116] In this embodiment, the second group performs RF-based sensing in the second sensing area 60 for recognizing the second sensing event indicating an activity of the user 32 upon detection of the third sensing event, i.e., if the location of the user is in proximity to the dense node arrangement. Since the proximity is detected also the first sensing event, i.e., presence of the user, is detected. The second group only performs RF-based sensing if the user 32 is in proximity to the dense node arrangement, i.e. chandelier 26 in this embodiment, since activity recognition requires a higher density of co-located nodes, i.e., the nodes in the dense node arrangement. Additionally, the message frequency for performing RF-based sensing by the second group is increased compared to the third group. This may allow recognizing activities, such as gestures of the user 32. Due to the higher message frequency, wireless interference may be higher. Therefore, the CL system 100 may coordinate or orchestrate transmissions of RF messages, including RF data messages for controlling the CL system 100, as well as RF sensing messages for performing RF-based sensing. This orchestrated transmission of the RF messages further allows reducing wireless interference. Furthermore, the second group only temporally, e.g., as short as possible, performs RF-based sensing in order to reduce or avoid wireless interference.

[0117] In this embodiment, the second group performs the RF-based sensing at the location of the user 32. The second sensing area 60 at least partially overlaps with the first sensing area 40.

[0118] While performing RF-based sensing by the second group in the second sensing area 60, the CL system 100 stops performing RF-based sensing for other sensing applications. In other embodiments, different sensing applications may be performed in parallel. Performing RF-based sensing for different sensing applications may include an orchestration of the transmission of different RF sensing messages included in the transmitted RF signals, such that wireless interference is reduced or avoided.

[0119] The CL system 100 processes recognized activities, such as gaits or gestures locally in the nodes in this embodiment. In other embodiments, the activities may also be recognized remotely, such as on server 200. Furthermore, different activities may be aggregated for a certain time before processing them. The aggregated activities may be processed together for recognizing them. The activities may be aggregated, e.g., in order to provide context information to the aggregated activities. For example, combinations of gestures may be recognized for allowing to provide complexer commands. The recognized activities may be used as a lookup key against a set of references. Artificial intelligence (AI)-based algorithms may enable a more accurate and complex recognition.

[0120] The RF system may be configured for performing an action based on the recognized second sensing event and possibly contextual information. For example, nodes may be dimmed up if a cooking action is detected or turned red if a romance action is detected. This allows to users to use simple gestures like waving to turn on the lights in a specific setting, e.g., color setting or dimming level. More complex context-aware actions may be performed based on additional contextual information. For example, more complex controls may be enabled by combining the recognized activities with contextual information obtained by other devices, e.g., a smartphone. If no user is detected to be at home, for example, due to contextual information in form of GPS information of the user's smartphone and opening of a main door is detected, an alarm signal may be triggered and provided to the smartphone of the user and/or to another external server, such as a security company.

[0121] In other embodiments, the nodes of the RF system may utilize directional antennas, e.g., for beamforming, for performing RF-based sensing in order to provide a narrower second sensing area 60.

[0122] The message frequency between the nodes of the dense node arrangement and the node closest to the user 32, e.g., node 29 may be higher than for the other nodes 27, 28, and 30. The message frequency between the nodes of the dense node arrangement and node 29 may be, for example, 1000 messages per second. The message frequency between the dense node arrangement and the other nodes 27, 28, and 30 may be, for example, 300 messages per second. This may allow to further improve the resolution in the area of interest, i.e., at the location of the user where activity of the user is expected.

[0123] The frequency channels of the nodes of the second group may also be adjusted. For example, frequency channels for WiFi, may be adjusted from 2.4 GHz to 5 GHz or 60 GHz. The higher frequencies may improve the activity recognition, such as gesture recognition.

[0124] In this embodiment, the second group performs RF-based sensing for recognizing the activity of the user only temporally, namely, until a stopping condition is fulfilled. The stopping condition is that the second event is recognized and that an additional stopping event is detected. The stopping event is that the user performs a certain stopping gesture and that this stopping gesture is recognized by the second group. In other embodiments, the stopping condition may also include, for example, one or more of that the second event is recognized, that a stopping event is detected, that a predetermined duration has passed since the second group started radio frequency based sensing in the second sensing area for recognizing the second sensing event, and that an inactivity of the object is recognized. The stopping event may be defined, for example, by the user, e.g., during calibration of the CL system 100. The stopping event may also be, for example, that the user leaves the second sensing area.

[0125] In this embodiment, the CL system 100 performs RF-based sensing for detecting the first sensing event, i.e., presence detection, upon the second group stopping to perform RF-based sensing for detecting the second sensing event. In other embodiments, the RF system may perform RF-based sensing for detecting the first sensing event or the third sensing event when the second group stops performing RF-based sensing for detecting the second sensing event. Whether the first group or the third group performs RF-based sensing for detecting the first sensing event or the third sensing event may depend on the stopping condition. For example, the user may leave the second sensing area. In this case, the first group may detect whether the user is still present in the first sensing area and the third group may subsequently detect whether the user comes back into proximity of the dense node arrangement. Alternatively, for example, the third group may detect whether the user is still in proximity to the dense node arrangement and if the user is not in proximity to the dense node arrangement, the first group may perform RF-based sensing to detect, whether the user is still in the first sensing area.

[0126] In other embodiments, in which the second group stopped performing RF-based sensing, the second group may only perform RF-based sensing again for recognizing the second sensing event if an additional restarting condition is fulfilled, e.g., that a predetermined duration has passed since the second group stopped performing RF-based sensing. This may allow to decrease wireless interference, as performing RF-based sensing by the second group may be avoided after the second sensing event is already recognized and the user is still in proximity to the dense node arrangement.

[0127] In yet other embodiments, in which the second group stopped performing RF-based sensing, the second group may perform RF-based sensing again for recognizing the second sensing event based on the second sensing event. For example, if the second sensing event indicates an activity in form of a gesture command such as “turn on entertainment lights” for turning on nodes in form of lights using a specific lighting scene or “go to sleep” for turning of nodes in form of lights, it is unlikely that there will be a subsequent second sensing event to be recognized. If, for example, a user arrives at home and enters the building, multiple sensing events may be expected. For example, a first gesture may be recognized for turning on lights in the entrance, followed by a second gesture pointing towards the living room for turning on lights in the living room. In another example, a user may enter the bathroom. In this case a “turn on” gesture is likely to be followed after a few minutes by a “turn off” gesture.

[0128] FIG. 5 shows a RF super-system 1000 including two RF systems in form of CL systems 500 and 500′ with two dense node arrangements in form of chandeliers 26 and 26′ at different locations.

[0129] CL system 500 includes chandelier 26 and nodes 29 and 30. CL system 500′ includes chandelier 26′ and node 27. In this embodiment, the nodes of the RF super-system 1000 exchange data, e.g., RF messages, such as RF data messages and RF sensing messages for performing RF-based sensing. Chandelier 26 is furthermore connected to an external server 200. The external server 200 can be used for controlling the RF super-system 1000. Alternatively, the nodes of the RF super-system 1000 may also be locally controlled, e.g., via switches or remote control (not shown). The CL systems 500 and 500′ have a similar functionality as described with respect to the embodiment of the CL system 100 shown in FIGS. 2 to 4.

[0130] FIG. 6 shows an embodiment of the method 600 for performing RF-based sensing in a RF system comprising multiple nodes for performing RF-based sensing, e.g., the CL system 100 shown in FIGS. 2 to 4. At least two of the multiple nodes are included in a dense node arrangement. At first the method calibrates the RF system and therefore forms groups of nodes.

[0131] In step 602, a first group of nodes is formed. In this embodiment, the first group includes at least one node of the dense node arrangement and at least one node which is not included in the dense node arrangement. In other embodiments, the first group may also include only at least one node of the dense node arrangement. The first group is formed by selecting the nodes to be included in the first group based on one or more radio frequency system parameters. In other embodiments, the nodes may additionally, or alternatively be selected based on a second sensing event to be recognized by the second group. The nodes of the first group are configured by adjusting their directionality, frequency channels and message frequencies used for performing RF-based sensing based on the first sensing event, i.e., presence detection. Furthermore, a first sensing area is defined. In this embodiment, the first sensing area depends on the location of the nodes of the first group.

[0132] In step 604, a second group of nodes is formed. The second group of nodes includes the nodes of the first group and at least one additional node of the dense node arrangement. The second group is formed by selecting the at least one additional node of the dense node arrangement to be included in the second group in addition to the nodes of the first group based on one or more radio frequency system parameters. In other embodiments, the nodes may additionally, or alternatively be selected based on the second sensing event to be recognized by the second group. The nodes of the second group are configured by adjusting their directionality, frequency channels and message frequencies used for performing RF-based sensing based on the second sensing event to be recognized. Furthermore, a second sensing area is defined.

[0133] In step 606, the first group performs RF-based sensing in a first sensing area for detecting a first sensing event. The first sensing event indicates a presence of a user in the first sensing area. In other embodiments, the first sensing event may also indicate presence of any other object in the first sensing area. Step 606 is performed until the first sensing event is detected, i.e., until a user is detected. Step 606 is then stopped, i.e., presence detection is stopped and optionally step 608 is performed or step 610 is performed.

[0134] In step 608, upon detecting the first sensing event, RF-based sensing is performed in a third sensing area by the nodes of the first group for detecting a third sensing event. The third sensing event indicates a location of the user within proximity of the dense node arrangement. The third sensing area at least partially overlaps with the first sensing area. In other embodiments, additional nodes, e.g., nodes of the second group, may be added to the first group for improving the resolution. A third group may be formed for performing RF-based sensing for detecting the third sensing event. Upon detecting the location of the user to be within proximity of the dense node arrangement, here within a certain distance, such as 4 m from a center of the dense node arrangement, step 608 is stopped, i.e., proximity detection is stopped.

[0135] Step 608 is optional. Instead step 610 may be performed upon detecting presence of the user in the first sensing area.

[0136] In other embodiments, the second group is formed or adjusted upon detecting the third sensing event and based on the location of the object.

[0137] In step 610, the second group performs RF-based sensing in a second sensing area for recognizing a second sensing event indicating an activity of the user. In this embodiment, the second sensing area is a subset of the first sensing area and narrowed down by beamforming to an area around the location of the user. In other embodiments, the second sensing area may at least partially overlap with the first sensing area and optionally with the third sensing area if proximity detection is performed. Furthermore, the second group may perform RF-based sensing at the location of the object for recognizing the second sensing event if the first sensing event was detected and upon detecting the third sensing event. In this embodiment, the activity to be recognized is a gesture of the user for controlling the RF system. Different gestures may allow activating different lighting scenes.

[0138] In this embodiment, no other RF-based sensing is performed for detecting other sensing events while RF-based sensing is performed by the second group in the second sensing area for recognizing the second sensing event.

[0139] The second group performs RF-based sensing in the second sensing area for recognizing the second sensing event until a stopping condition is fulfilled. In this embodiment, the stopping condition is that the second event is recognized, i.e., the gesture of the user for controlling the RF system is recognized, and that additionally a stopping event is recognized. In this embodiment, the stopping event is either that the user left the first sensing area or the location of the user is not within the proximity of the dense node arrangement anymore. Leaving of the user of the first sensing area may be detected, for example, if no presence of the user is detected in the first sensing area by performing RF-based sensing by the first group and detecting that the location of the user is not within the proximity of the dense node arrangement anymore may, for example, be detected by performing RF-based sensing in the third sensing area by at least the at least one node of the first group. In other embodiments, the stopping condition may, for example, include that a predetermined duration has passed since the last gesture has been recognized. In other embodiments, the stopping condition may include one or more of that the second event is recognized, that a stopping event is detected, that a predetermined duration has passed since the second group started radio frequency based sensing in the second sensing area for recognizing the second sensing event, and that an inactivity of the object is recognized.

[0140] If step 610 is stopped, either RF-based sensing for detecting the first sensing event, i.e., step 606, or the third sensing event, i.e., step 608, is performed. Which step is performed, depends on the stopping condition fulfilled, e.g., if the user leaves the first sensing area, step 606, i.e., presence detection is performed. If the user is still present in the first sensing area, but her location is not in proximity of the dense node arrangement anymore, step 608, i.e., proximity detection is performed.

[0141] In step 612, an action is performed upon and based on the detected second sensing event, namely a lighting scene is activated in dependence of the recognized gesture. Step 610 may be performed in parallel to step 612 if it has not been stopped, i.e., several gestures may be recognized subsequently for adjusting the lighting scene. In other embodiments, other actions may be performed based on the detected first sensing events, the detected third sensing event, the recognized second sensing event, and/or contextual information. The other actions may also be performed, for example, upon detecting the first sensing event, the third sensing event and/or the contextual information and/or recognizing the second sensing event.

[0142] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments. For example, it is possible to operate the invention in an embodiment wherein the RF system is a heating ventilating air-conditioning (HVAC) system, or any other smart home or building managing system (BMS).

[0143] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0144] In the claims, the word “comprising” and “including” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude a plurality.

[0145] A single unit, processor, or device may fulfill the functions of several items recited in the claims. 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.

[0146] Operations like forming a first group of nodes including at least one node of the dense node arrangement, forming a second group of nodes including the at least one node of the first group and at least one additional node of the dense node arrangement, performing RF-based sensing by the first group in a first sensing area for detecting a first sensing event indicating a presence of an object in the first sensing area, performing RF-based sensing by the second group in a second sensing area at least partially overlapping with the first sensing area for recognizing a second sensing event indicating an activity of the object if the first sensing event is detected, et cetera performed by one or several units, nodes, or devices can be performed by any other number of units, nodes, or devices. These operations and/or the method can be implemented as program code means of a computer program and/or as dedicated hardware.

[0147] A computer program product may be stored/distributed on a suitable medium, such as an optical storage medium, or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet, Ethernet, or other wired or wireless telecommunication systems.

[0148] Any reference signs in the claims should not be construed as limiting the scope.

[0149] The present invention regards performing RF-based sensing in a RF system comprising multiple nodes of which at least two nodes are included a dense node arrangement. A first group of nodes including at least one node of the dense node arrangement and a second group including the at least one node of the first group and at least one additional node of the dense node arrangement are formed. RF-based sensing is performed by the first group in a first sensing area for detecting a first sensing event indicating a presence of an object in the first sensing area. If the first sensing event is detected, RF-based sensing is performed by the second group in a second sensing area at least partially overlapping with the first sensing area for recognizing a second sensing event indicating an activity of the object.