Radio frequency sensing orchestration

Abstract

An orchestration system and method may be provided for orchestrating radio frequency (RF)-based wireless data transmissions of devices for RF sensing. The orchestration system and method may access device location data, receive a target physical location for RF sensing, use the device location data to select one or more devices of which the physical location is within a neighborhood of the target physical location, and instruct said selected one or more devices, or an auxiliary device which controls data communication of the selected one or more devices, to adjust the data transmission of the selected one or more devices in order to regulate an efficacy of the RF sensing at the target physical location. This way, the orchestration system and method may provide an abstraction layer for RF sensing, enabling network entities to request measurements by specifying a target location without needing to handle the technical intricacies of RF sensing nor having to possess knowledge about the relationship between data transmission properties and RF sensing efficacy.

Description

[0001] RADIO FREQUENCY SENSING ORCHESTRATION

[0002] TECHNICAL FIELD

[0003] The presently disclosed subject matter relates to an orchestration system and a computer-implemented method for orchestrating wireless data transmissions of devices for radio frequency sensing. The presently disclosed subject matter further relates to a device configured for wireless data communication, to a computer- implemented method performed at the device, and to a transitory or non-transitory computer-readable medium comprising instructions, which when executed by a processor system, cause the processor system to perform any of the methods.

[0004] BACKGROUND

[0005] Radio frequency (RF) sensing refers to a sensing technique that may leverage existing RF-based wireless transceivers in the environment to gather sensor data without requiring additional dedicated sensors. Specifically, RF sensing may involve inferring one or more environmental characteristics based on the influence of environmental conditions on wireless data transmissions. For example, environmental conditions such as the presence of objects, human movement, or open and closed doors may influence wireless signals, resulting in signal characteristics such as signal attenuation, phase shifts, or changes in channel state information. These signal characteristics may then be analyzed for specific sensing tasks to infer environmental characteristics, such as the number of people in a room for occupancy estimation or gestures of people caused by hand movements, all using existing wireless communication infrastructure. For example, studies have demonstrated that Wi-Fi sensing can detect human presence, motion, and even breathing patterns by analyzing disruptions in Wi-Fi signals [1], Similarly, other wireless communication techniques, such as cellular data communication (e.g., using 5G, 6G, or next-generation networks), Bluetooth, Zigbee, LoRa, and other types of electromagnetic radiofrequency-based wireless communication techniques, may also be suitable for RF sensing.

[0006] An advantage of such RF sensing may be its energy efficiency, as it may repurpose signals already present in the environment. For example, existing data transmissions between devices may be reused for RF sensing [2],

[0007] Another advantage may arise in scenarios where utilizing sensors is difficult, for example due to a lack of infrastructure or insufficient sensor coverage. In such cases, RF sensing may provide a viable alternative. For example, RF sensing may be employed to keep a digital twin updated. A digital twin may in this context refer to a digital replica or model of a real-world system or object that may be updated with real-time data from its physical counterpart. Digital twins may enable simulations, forecasts, and analytics to be conducted in real time, facilitating monitoring, control, and optimization of complex systems without disrupting their operations. However, ensuring that a digital twin remains up-to-date may be challenging, for example due to the aforementioned lack of infrastructure or insufficient sensor coverage. RF sensing may address this issue, either alone or by operating alongside traditional sensors to achieve comprehensive data acquisition. Other application examples of RF sensing may include, but are not limited to, smart factories, smart homes, healthcare monitoring, and security systems.

[0008] Despite its advantages, RF sensing may face challenges because the signals it repurposes may not be inherently optimized for sensing purposes. Consequently, their performance may be reduced under certain conditions or events. For example, it is known that the efficacy of RF sensing may be influenced by the type of data transmission between devices [2], Moreover, current implementations may rely on rigid, hardcoded arrangements that may lack flexibility and scalability. These limitations may make them unsuitable for broader deployment, particularly in dynamic or heterogeneous environments. Therefore, there may be a need to improve both the accessibility and efficacy of RF sensing across various scenarios.

[0009] References

[0010] [1] C. Wu, B. Wang, O. C. Au, and K. J. R. Liu, 'Wi-Fi Can Do More: Toward Ubiquitous Wireless Sensing,' IEEE Communications Standards Magazine, vol. 6, no. 2, pp. 42-49, June 2022, doi: 10.1109 / MCCMSTD.0001.2100111.

[0011] [2] A. Sharma, J. Li, D. Mishra, S. Jha, and A. Seneviratne, 'Towards Energy Efficient Wireless Sensing by Leveraging Ambient Wi-Fi Traffic,' Energies, vol. 17, no. 2, p. 485, 2024, doi: 10.3390 / en 17020485.

[0012] SUMMARY

[0013] In accordance with a first aspect of the presently disclosed subject matter, a computer-implemented method is provided for orchestrating radio frequency (RF)- based wireless data transmissions of devices for RF sensing. The method may comprise: - accessing device location data, wherein the device location data may be indicative of a physical location of a respective device;

[0014] - receiving a target physical location for RF sensing;

[0015] - using the device location data, selecting one or more devices of which the physical location may be within a neighborhood of the target physical location;

[0016] - instructing said selected one or more devices, or an auxiliary device which controls data communication of the selected one or more devices, to adjust the data transmission of the selected one or more devices in order to regulate an efficacy of the RF sensing at the target physical location.

[0017] In accordance with a further aspect of the presently disclosed subject matter, an orchestration system is provided for orchestrating radio frequency (RF)- based wireless data transmissions of devices for RF sensing. The orchestration system may comprise:

[0018] - a network interface to a network, wherein the devices may be reachable via the network;

[0019] - a processor subsystem configured to, using the network interface: access device location data, wherein the device location data may be indicative of a physical location of a respective device; receive a target physical location for RF sensing; using the device location data, select one or more devices of which the physical location may be within a neighborhood of the target physical location; instruct said selected one or more devices, or an auxiliary device which controls data communication of the selected one or more devices, to adjust the data transmission of the selected one or more devices in order to regulate an efficacy of the RF sensing at the target physical location.

[0020] In accordance with a further aspect of the presently disclosed subject matter, a computer-implemented method is provided for being performed at a device configured for radio frequency (RF)-based wireless data communication. The method may comprise:

[0021] - providing, to an orchestration system, a schedule of data transmissions of the device;

[0022] - receiving an instruction from the orchestration system to regulate an efficacy of RF sensing in a neighborhood of the device by adjusting a data transmission of the device; and - in response to the instruction, adjusting the data transmission by modifying at least one of: a timing, transmission power, frequency, or communication band, of the data transmission.

[0023] In accordance with a further aspect of the presently disclosed subject matter, a device is provided which may be configured for radio frequency (RF)-based wireless data communication with at least one other device. The device may comprise:

[0024] - a wireless interface for the wireless data communication;

[0025] - a processor subsystem configured to, using the wireless interface: provide, to an orchestration system, a schedule of data transmissions of the device; receive an instruction from the orchestration system to regulate an efficacy of RF sensing in a neighborhood of the device by adjusting a data transmission of the device; and in response to the instruction, adjust the data transmission by modifying at least one of: a timing, transmission power, frequency, or communication band, of the data transmission.

[0026] In accordance with a further aspect of the presently disclosed subject matter, a computer program is provided comprising instructions which, when executed by a processor system, cause the processor system to perform any single method or any combination of methods as described in this specification.

[0027] The disclosed measures may involve orchestrating the data transmissions of devices to regulate the efficacy of RF sensing. In this context, ‘RF sensing’ may refer to inferring environmental characteristics based on the influence of environmental conditions on wireless data transmissions. In this context, ‘data transmissions’ may refer to the exchange of data through a wireless transceiver which uses RF signals (also referred to as a wireless interface) and may primarily serve purposes other than RF sensing. For example, these RF data transmissions may serve primary purposes such as enabling communication between devices (e.g., peer-to-peer or client-server coordination), exchanging application data (e.g., streaming, file sharing, or control commands), supporting network functionality (e.g., signaling, authentication, or updates), or for transmitting other sensor data unrelated to RF sensing. The wireless data transmissions utilized for the RF sensing may be RF-based, for example using cellular, Wi-Fi, Bluetooth, Zigbee, LoRa, or other RF-based communication technologies. RF sensing may be known under a term which refers to the specific type of communication technology, for example Wi-Fi sensing for Wi-Fi, etc. It is noted that RF sensing may also be known as ambient sensing and that the measures described in this specification equally apply to ambient sensing and its orchestration.

[0028] To orchestrate the data transmissions, the orchestration system and method may access device location data. The device location data may be indicative of the physical location of a respective device, for example by comprising a geographic location specified in terms of longitude and latitude, or by referencing other identifiers such as a room number in a building or a specific zone within a facility. The physical location may for example be specified as, or be resolvable to, a two-dimensional geolocation, such as the aforementioned longitude and latitude, but may in some cases also include height information to provide a three-dimensional representation of the physical location. The device location data may be obtained from various sources. For example, devices may report their location directly to an entity which maintains the device location data, or an entity may estimate the device location, e.g., based on signaling. In the context of 3GPP standards, examples of entities which may provide access to device location data include, but are not limited to, an Access and Mobility Management Function (AMF) that determine location based on signaling, a Location Management Function (LMF), or a Network Data Analytics Function (NWDAF). The device location data may for example be accessed by accessing a database, or by querying a network function. It should be noted that device location data may be indicative rather than definitive, as the accuracy of device location data may not be guaranteed at all times and may occasionally deviate from the actual physical location.

[0029] The orchestration system and method further receive a target physical location for RF sensing as input. The target physical location may for example be provided by an entity seeking to perform RF sensing, such as an entity managing a digital twin or conducting environmental monitoring. The target physical location may be specified in various ways. For example, the target physical location may be expressed in the same or a similar manner as the device location data, for example as a geographic location specified in terms of longitude and latitude. The target physical location may also be specified in other forms, such as by identifying a device whose physical location can be determined from the device location data, or as an area or volume of interest, which may correspond to a specific room in a building, a zone in a factory, or another defined space where RF sensing is intended to be performed.

[0030] Based on the target physical location and the device location data, the orchestration system may identify a set of one or more devices that are within a neighborhood of the target physical location. For example, the orchestration system and method may search the device location data for devices located within a predetermined vicinity of the target physical location, or the target physical location may be used as a query term with a network function that reports back the device(s) in the neighborhood. In this context, the term ‘neighborhood’ may be defined in various ways. For example, ‘neighborhood’ may refer to devices within a specified distance from the target physical location, devices located in the same area or volume of interest, such as a room in a building or a specific zone, or devices that are expected to contribute to RF sensing at the target physical location based on specific metrics. Such metrics may for example include the strength or range of wireless signals at the target physical location or the potential impact of these devices on sensing efficacy. Here, 'sensing efficacy' may refer to the ability of RF sensing to successfully perform or fulfill a specific sensing task, such as the estimation of occupancy, gesture detection, etc.

[0031] The orchestration system and method may further instruct the selected device(s) to adjust their data transmissions to regulate the efficacy of RF sensing at the target physical location. In this context, a data transmission ‘of’ a device may refer to any transmission in which the device is involved, whether as a sender, receiver, or intermediary. Additionally or alternatively, an auxiliary device associated with the data transmission of one or more selected devices may be instructed to adjust the data transmission of the selected device(s). Examples of auxiliary devices may include intermediate devices that facilitate the data transmission of a selected device, such as switches, routers, or other network components, as well as upstream or downstream devices, such as data sources or data destinations, in cases where the selected devices themselves are not the original source or ultimate destination of the transmitted data. For example, an auxiliary device may adjust the data transmission of another device through actions such as throttling or delaying a data transmission. As explained elsewhere, the instructed adjustments may, in general, take various forms and may involve modifications to one or more properties of the data transmission, including but not limited to the timing, transmission power, frequency, or communication band.

[0032] The orchestration system and method may generate the instructions to regulate the efficacy of RF sensing at the target physical location. In this context, the term ‘regulate’ may include enabling, improving, or even disrupting or disabling the RF sensing, depending on the requirements of the requesting entity or the specific use case, while the term ‘efficacy’ may refer to a measure of the quality, accuracy, spatial resolution, reliability, or overall effectiveness of the RF sensing in achieving its intended purpose. Such regulation may be based on known effects of data transmission properties on RF sensing efficacy, for example as described in [2], For example, increasing transmission power or communication bands may enhance RF sensing efficacy in certain scenarios, while reducing activity in certain communication bands may improve the signal-to-noise ratio of the RF sensing.

[0033] The disclosed measures provide an orchestration system and method that, based on a target physical location, take specific actions to regulate the efficacy of RF sensing at that location. This allows entities, such as those managing digital twins or performing other monitoring tasks, to obtain the required measurements by specifying the target location. Such entities may not need to concern themselves with the technical intricacies of RF sensing. For example, the orchestration system may be implemented as a network entity, such as a network function, providing an abstraction layer for RF sensing. This abstraction may make RF sensing more accessible to network entities, as they can request measurements without needing to manage the underlying processes. Additionally, the orchestration system and method may be configured with knowledge about the relationship between RF sensing efficacy and data transmission properties. This knowledge may allow the orchestration system and method to, through instructions to selected and / or auxiliary devices, effectuate appropriate adjustments to data transmissions without requiring the devices involved in the communication or the requesting entities to possess such knowledge themselves. For example, the orchestration system and method may be configured with knowledge of how the data type of a data transmission, such as the protocol, application, payload characteristics, traffic type (e.g., streaming, real-time communication, or bulk data transfer), or transmission priority, affects the efficacy of RF sensing. This way, the orchestration system and method may improve both the accessibility and efficacy of RF sensing across various scenarios.

[0034] It is noted that the devices whose data transmissions are adjusted are typically those whose transmissions are subject to the RF sensing process, such as signal analysis. As such, the selection of devices for adjustment of their data transmission may reflect the selection of devices of which their data transmission is used for the RF sensing. The RF sensing itself, including processes like signal analysis, may be performed by the orchestration system and method, thereby also functioning as the RF sensing system and method, or by another entity. In cases where another entity performs the RF sensing, the selection of devices may align with the orchestration system’s selection but may also differ depending on specific requirements or constraints. In some examples, the orchestration system and method may communicate with the RF sensing system and method, for example to exchange information such as the device selection or other relevant parameters. The following refers to embodiments of the orchestration method. These embodiments are equally applicable as embodiments of the orchestration system by reflecting a configuration of the processor subsystem of the orchestration system to perform the corresponding step(s), and may also denote corresponding features or limitations in the devices being instructed by the orchestration system or method.

[0035] In an embodiment, the method further comprises:

[0036] - receiving a timestamp representing a target time for the RF sensing; and

[0037] - adjusting a timing of the data transmission of the selected one or more devices so that the data transmission coincides with the target time.

[0038] In addition to receiving a target physical location, the orchestration system and method may receive a target time for RF sensing, such as the time when an event is scheduled to occur and RF sensing is desired. This target time may represent a specific moment, such as the start of the event, or may define a time window together with another specified time. When the target time is known, the data transmissions of the selected devices may be adjusted to regulate the efficacy of RF sensing at the required time. By utilizing the target time, the impact of adjustments to the data transmissions may be limited to the relevant period while avoiding unnecessary changes at other times. For example, to improve sensing efficacy, the orchestration system and method may adjust the timing of data transmissions to ensure that a suitable transmission occurs at the target time. If no data transmission is ongoing, or if the data being transmitted is unsuitable, for example by being highly erratic or inconsistent, the efficacy of RF sensing may be diminished. By aligning suitable data transmissions with the target time, the orchestration system and method may enhance the efficacy of RF sensing. Conversely, if the desire is to reduce efficacy, the orchestration system and method may adjust the timing to ensure that no suitable data transmission occurs during the target time. The required timing adjustments may vary depending on the situation, and may range from changes on the order of milliseconds or seconds to broader adjustments spanning minutes or more, particularly in cases where the exact timing of the data transmission is not critical for the completion and for the primary purpose of the data transmission itself.

[0039] In an embodiment, the method further comprises:

[0040] - obtaining a data transmission schedule indicative of data transmissions of the devices; and

[0041] - selecting the one or more devices based on the data transmission schedule, for example based on the data transmissions of said devices aligning with, or being capable of adjustment to, the target time for the RF sensing. Data transmissions of devices may be known or estimated in advance and represented in a schedule. In this context, a 'schedule' may refer to data indicating a data transmission that is either definitively planned or estimated, for example based on the device's past data transmission patterns. By obtaining such a schedule for the devices, the orchestration system and method may determine which devices are expected to perform data transmissions and at what times. The selection of devices for regulating the efficacy of the RF sensing may then be informed by this schedule. For example, devices may be selected if they have scheduled data transmissions that align with the target time for RF sensing or if their data transmissions, although not aligned, can be rescheduled to align with the target time. Thereby, the orchestration system and method are enabled to make a suitable selection of devices for RF sensing. In particular, the adjustments required for the selected devices may be smaller in magnitude or at least feasible, compared to devices with scheduled data transmissions that are not aligned with the target time and / or not reschedulable.

[0042] In an embodiment, obtaining the data transmission schedule comprises at least one of:

[0043] - predicting the data transmission schedule for a respective device based on past data transmissions, for example using a machine learning model; and

[0044] - requesting the data transmission schedule from a respective device.

[0045] The data transmission schedule may be obtained in various ways, for example through prediction, by requesting the schedule directly from a device, or through a combination of these approaches. It is noted that the orchestration system and method may provide and maintain the schedule, or alternatively, another entity may provide and maintain the schedule, with the orchestration system and method subsequently accessing the schedule. The prediction of the data transmission schedule may, for example, take into account historical data of past transmissions. In a specific example, a machine learning model trained on past data transmissions may be used to predict future transmissions. The machine learning model may be periodically or even continuously (re)trained on newly observed data transmissions, allowing the machine learning model to refine and improve its prediction capabilities over time.

[0046] In an embodiment, adjusting the timing of the data transmission of the selected one or more devices comprises delaying or advancing a scheduled data transmission. For example, the timing of a data transmission may be adjusted to align with the target time by delaying a scheduled data transmission, for example if the transmission is non-urgent, or by advancing it to occur earlier than originally planned.

[0047] In an embodiment, the method further comprises: - obtaining an estimate of a data type associated with the data transmissions of the devices; and

[0048] - selecting the one or more devices based on the data type, for example based on a preference list for data types.

[0049] The type of data involved in the data transmission, which may elsewhere also be referred to as ‘data type’, may be relevant to the efficacy of RF sensing, as demonstrated in [2], In this context, ‘data type’ may refer to a characterization of the data transmission, for example in terms of protocol, application, payload characteristics, traffic type (e.g., streaming, real-time communication, or bulk data transfer), and / or transmission priority. Different data types may have different impacts on the efficacy of RF sensing. Based on knowledge of these impacts, the orchestration system and method may select the devices accordingly. In a specific example, a preference may be given to certain data types, and the selection of devices may be based on this preference. This may ensure that the devices whose data transmissions are to be adjusted have data types that may optimally support the desired regulation of the efficacy of the RF sensing. For example, if it is desired to improve the efficacy of RF sensing, devices may be selected that have data transmissions, ongoing or scheduled, which are well-suited to support RF sensing.

[0050] In an embodiment, the RF sensing is performed using machine learning models, wherein a plurality of machine learning models is provided for different data types, and wherein the method comprises selecting the one or more devices based on supported data types and / or a preference for data types among the plurality of machine learning models. RF sensing may be performed using machine learning models. These models may, similar to non-machine learning based RF sensing processes, take metadata characterizing the data transmission as input. Examples of such metadata may include received signal strength (RSS), channel state information (CSI), for example with amplitude and phase data, timing parameters such as delay and jitter, signal attenuation, phase shifts, frequency changes, multipath profiles, etc. Different machine learning models may have been trained for different data types to optimize their performance in processing data transmissions for RF sensing. For example, specific models may be trained to handle real-time communication, streaming data, or bulk data transfer and thereby adapt to the characteristics of each data type. However, the number of machine learning models available for use may be limited, and the performance of these models may vary due to a difference in suitability of the data type for RF sensing. To address this, the selection of devices for RF sensing may be based on the availability of machine learning models that support the data types of their data transmissions. For example, preference may be given to devices whose data transmissions are compatible with available models, particularly when these models are expected to perform well with the corresponding data types. Additionally, the selection of devices may be prioritized based on a preference for certain data types that better support the desired regulation of the efficacy of RF sensing, enabling the orchestration system to optimize sensing performance.

[0051] In an embodiment, the method further comprises:

[0052] - obtaining an estimate of a direction of the data transmission of the devices, the direction being for example upstream or downstream with respect to a network topology; and

[0053] - selecting the one or more devices based on the direction of data transmission of a respective device, for example based on a directional preference.

[0054] The direction of data transmission may influence the suitability for RF sensing, e.g., as demonstrated by [2], and may therefore be considered in the device selection. In some cases, data communication may be bidirectional, but the primary purpose of the communication, such as streaming, may predominantly occur in one direction. In this context, the ‘direction’ may refer to the primary flow of data in the data communication. It will be appreciated, however, that even when the primary data flow is in one direction, such as downstream, the data flow in the opposite direction, such as upstream, may also be used for RF sensing. For example, upstream control or signaling information may contribute to RF sensing efficacy.

[0055] In an embodiment, adjusting the data transmission comprises adjusting a communication path for the data transmission of the selected one or more devices, for example by routing the data through a third device in the neighborhood of the target physical location. By rerouting the data transmission, the physical transmission path of the wireless signals may also be altered. Such adjustments may be performed to better align the transmission path with the target physical location, for example to enhance coverage of a target area or target volume or establish a primary line of sight through the target physical location. The rerouting, for example via a third device, may thus modify the actual path of the electromagnetic signals represented by the wireless signals, and thereby affect the efficacy of RF sensing. For example, the data transmission may be rerouted to improve the sensing accuracy at the target physical location or, in certain cases, rerouted to intentionally degrade the sensing accuracy.

[0056] In an embodiment, adjusting the data transmission comprises adjusting at least one of: transmission power, frequency, or communication band, of the data transmission. The transmission power, frequency, and communication band may represent transmission parameters which, in addition to or as an alternative to timing adjustments, may influence the efficacy of RF sensing and may therefore be adjusted to achieve the desired regulation of the RF sensing, e.g., the improvement or degradation. In this context, ‘transmission power’ may refer to the level of power used to transmit the wireless signal, which may affect the signal's range and penetration. ‘Frequency’ may refer to the specific radio frequency at which the signal is transmitted, potentially influencing factors such as signal propagation and susceptibility to interference. ‘Communication band’ may refer to the broader spectrum or range of frequencies used for the transmission, which may for example include 2.4 GHz, 5 GHz, and 6 GHz bands for Wi-Fi, as well as low-band (e.g., 600 MHz), mid-band (e.g., 3.5 GHz), and high-band (e.g., 28 GHz) spectrums for 5G. For example, the data transmission of devices may be adjusted to occur at a higher frequency and / or within a higher communication band to enhance spatial resolution in RF sensing.

[0057] In an embodiment, the selected one or more devices which are instructed to adjust their data transmission are network infrastructure devices, for example base stations and access points. The devices used for RF sensing may include, or exclusively consist of, network infrastructure devices, as such network infrastructure devices may typically be integrated into larger networks, such as Wi-Fi or cellular networks (e.g., 5G or 6G). The use of network infrastructure devices may allow existing network mechanisms to be leveraged so as to instruct these devices to adjust their transmissions and collaborate in the RF sensing process. For example, the orchestration system and method may form part of the same network infrastructure, facilitating the ability to control and coordinate the network infrastructure devices. Alternatively, or additionally, the selected one or more devices which are instructed to adjust their data transmission comprise or consists of User Equipment (UE) of a telecommunications network. The use of UEs may equally allow existing network mechanisms to be leveraged so as to instruct these devices to adjust their transmissions and collaborate in the RF sensing process.

[0058] In an embodiment, the method further comprises accessing preferred characteristics for the RF sensing and instructing the selected one or more devices or the auxiliary device to adjust the data transmission to increase the efficacy of the RF sensing based on the preferred characteristics. It may be known which data transmission characteristics are preferred for RF sensing. The data transmission may be adjusted to align with these characteristics to improve the efficacy of the sensing, for example in terms of spatial resolution, temporal stability, etc. In an embodiment, the method further comprises instructing the selected one or more devices or the auxiliary device to adjust the data transmission to disrupt the RF sensing, for example by accessing preferred characteristics for the RF sensing and using the preferred characteristics as an inverse reference for the adjustment. The data transmission may be deliberately adjusted to disrupt RF sensing, such as to safeguard privacy or prevent eavesdropping. For example, if preferred data transmission characteristics for RF sensing are known, these may be used as a basis for inverse adjustments, such as adjusting data transmissions in an opposing manner. For example, data transmissions may be delayed and / or rerouted to avoid occurring at the target physical location at a target time. Another example may comprise using a lower frequency and / or a lower communication band, thereby reducing spatial resolution and impairing the effectiveness of the RF sensing.

[0059] In an embodiment, the data transmissions comprise cellular data transmissions or Wi-Fi data transmissions. Cellular data transmissions, such as 5G and 6G transmissions at bands such 3.5 GHz or 28 GHz, as well as Wi-Fi transmissions, for example in the 5 GHz and 6 GHz bands, may be well-suited for RF sensing as they may allow RF sensing at a comparatively high spatial resolution.

[0060] In an embodiment, the data transmissions comprise network data transmissions. The devices may be part of a wireless network, such as a cellular access network or a Wi-Fi network, with the data transmissions occurring via this wireless network. In such cases, the devices may also receive instructions from the orchestration system and method via the same wireless network.

[0061] In an embodiment, the data transmissions comprise device-to-device (D2D) data transmissions. The data transmissions used for RF sensing may include D2D data communication, such as Wi-Fi Direct or similar protocols. In such cases, the devices may be instructed directly via D2D data communication or through a separate network in case the devices are capable of D2D data communication and have network connectivity.

[0062] It will be appreciated by those skilled in the art that two or more of the above-mentioned embodiments, implementations, and / or aspects of the invention may be combined in any way deemed useful.

[0063] Modifications and variations of any one of the above-mentioned entities (e.g., computer-implemented method, orchestration system, device, computer-readable medium), which correspond to the described modifications and variations of another one of these entities, may be carried out by a person skilled in the art on the basis of the present description. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] These and other aspects of the invention are apparent from and will be elucidated with reference to the embodiments described hereinafter. In the drawings,

[0065] Fig. 1 shows an orchestration system configured to orchestrate Wi-Fi data transmissions of device(s) by instructing the device(s) to adjust their Wi-Fi data communication to regulate an efficacy of RF sensing at a target physical location;

[0066] Fig. 2A shows an orchestration system configured to orchestrate cellular data transmissions of device(s) by instructing the device(s) to adjust their cellular data communication to regulate an efficacy of RF sensing at a target physical location;

[0067] Fig. 2B is similar to Fig. 2A and shows the orchestration system instructing the device(s) to adjust their D2D data communication, in addition or as an alternative to adjusting their cellular data communication, to regulate the efficacy of RF sensing;

[0068] Fig. 3 shows a method of orchestrating data transmissions of device(s) to regulate an efficacy of RF sensing at a target physical location;

[0069] Fig. 4 illustrates a data transmission of a device being delayed to coincide with a target time at which RF sensing is to be performed;

[0070] Fig. 5 shows a process flow diagram for the orchestration of data transmissions of device(s) to regulate an efficacy of RF sensing;

[0071] Fig. 6 shows a system which may be exemplary for a control system or other federated learning entity as described in this specification;

[0072] Fig. 7 shows a non-transitory computer-readable medium comprising data;

[0073] Fig. 8 shows an exemplary data processing system.

[0074] Reference signs list

[0075] The following list of references and abbreviations is provided for facilitating the interpretation of the drawings and shall not be construed as limiting the claims.

[0076] 100 orchestration system

[0077] 102 instructions

[0078] 110 network

[0079] 112 mobile telecommunications network

[0080] 120 device location database

[0081] 122 device location data

[0082] 130 sensing system

[0083] 140 target physical location (factory zone) 150 robotic arm

[0084] 160 device (Wi-Fi access point)

[0085] 162-166 device (Wi-Fi client)

[0086] 170 device (gNodeB)

[0087] 172-178 device (UE)

[0088] 180 wireless data communication (Wi-Fi)

[0089] 182 wireless data communication (cellular)

[0090] 184 wireless data communication (D2D)

[0091] 200 device location data

[0092] 202 target physical location data

[0093] 204 data transmission schedule data

[0094] 206 timestamp (target time) data

[0095] 208 method for orchestrating RF sensing

[0096] 210 accessing device location data

[0097] 220 receiving target physical location

[0098] 230 obtaining data transmission schedule

[0099] 240 receiving timestamp representing target time

[0100] 250 selecting devices within neighborhood

[0101] 260 instructing devices to adjust data transmission

[0102] 300 time (T)

[0103] 310 target time

[0104] 320 scheduled data transmission

[0105] 330 rescheduling (delaying)

[0106] 340 rescheduled (delayed) data transmission

[0107] 400 orchestration system

[0108] 402 data storage device

[0109] 404 processor subsystem

[0110] 410 upcoming transmission schedule

[0111] 412 transmission schedule

[0112] 414 device location

[0113] 416 device location data

[0114] 418 event schedule

[0115] 420 event data 422 trained models

[0116] 424 available trained models

[0117] 430 path selection algorithm

[0118] 432 opportunistic path list

[0119] 434 communication scheduler

[0120] 436 updated transmission schedule

[0121] 438 communications synchronisation algorithm

[0122] 440 transmission instructions

[0123] 450 sensing processor

[0124] 452 sensing output

[0125] 460 transceiver

[0126] 462 network node 1

[0127] 464 network node 2

[0128] 466 communications

[0129] 468 RF sensing data

[0130] 500 system

[0131] 520 network interface

[0132] 522 received data

[0133] 524 sent data

[0134] 540 processor subsystem

[0135] 560 data storage

[0136] 600 non-transitory computer-readable medium

[0137] 610 stored data

[0138] 1000 exemplary data processing system

[0139] 1002 processor

[0140] 1004 memory element

[0141] 1006 system bus

[0142] 1008 local memory

[0143] 1010 bulk storage device

[0144] 1012 input device

[0145] 1014 output device

[0146] 1016 network adapter

[0147] 1018 application DESCRIPTION OF EMBODIMENTS

[0148] Fig. 1 shows an orchestration system 100 configured to orchestrate wireless data transmissions of devices to regulate the efficacy of radio frequency (RF) sensing at a target physical location 140. In this example, the target physical location 140 may correspond to a factory zone, such as part of a manufacturing line in a factory. In this example, the factory zone may include a robotic arm 150, and it may be desired to perform RF sensing to measure or sense the pose of the robotic arm. The following refers to the target physical location 140 interchangeably as the factory zone or target zone, with the understanding that any remarks regarding the factory or target zone also apply, in general, to any other type of specified target physical location.

[0149] There may be several devices configured for wireless communication, for example for radiofrequency (RF)- based wireless communication, in and near the target zone 140. For example, the devices within the target zone 140 may include a Wi-Fi access point 160 and Wi-Fi clients 162-166, while additional Wi-Fi clients (and Wi-Fi access points, although not shown in Fig. 1) may be located adjacent to the target zone 140. These devices may communicate with each other locally and may also communicate with entities in or via a remote network 110, such as the Internet. Both types of communication may take place via the Wi-Fi access point 160. Local communication between the Wi-Fi access point 160 and the Wi-Fi clients 162-166 may involve Wi-Fi data communication 180 via electromagnetic radio signals.

[0150] In the example of Fig. 1 , the orchestration system 100 is shown to be a network entity which is located remotely from the target zone 140. For example, the orchestration system 100 may be implemented by a network node belonging to or being connected to the network 110, such as a server, or in a distributed manner or a cloud-based manner by a plurality of network nodes. Data communication between the orchestration system and the devices 160-166 may occur via the network 110. Alternatively, the orchestration system 100 may be implemented locally, e.g., onsite by a local server, by one of the devices, or in a distributed manner across devices.

[0151] In order to orchestrate wireless data transmissions of devices for the purpose of regulating the efficacy of RF sensing in the target zone 140, the orchestration system 100 may access device location data 122. In the example of Fig. 1 , the device location data 122 is shown to be accessible from a device location database 120, which in turn is shown to be accessible via the network 110 and located remotely from the target zone, e.g., offsite. However, this is not a limitation, as the device location data 122 may also be obtained onsite, for example from a local server. The device location data 122 may be indicative of the physical locations of respective devices. For example, the data device location data 122 may specify the geographical locations or the relative locations of the devices with respect to the target zone 140. The device location data 122 may have been generated manually, for example based on an asset register or equipment inventory. Alternatively, the device location data 122 may have been generated automatically, for example through remote estimation of device locations or by the devices themselves reporting their estimated locations.

[0152] Using the device location data 122, the orchestration system 100 may identify the devices located within or near the target physical location 140. For example, the orchestration system may search for devices situated within the exact boundaries of the target zone 140 or for devices within a predetermined vicinity to the target zone 140, which predetermined vicinity may extend beyond the target zone or may be limited to the target zone. Additionally, or alternatively, the orchestration system may utilize a metric indicating the likelihood that a device can contribute to RF sensing in the target zone 140. The metric may use the physical location of the device relative to the target zone 140 as input. The orchestration system 100 may then identify devices that are likely able contribute to the RF sensing using the metric.

[0153] In the example of Fig. 1 , RF sensing may be performed using Wi-Fi signals. The RF sensing may therefore also be referred to as Wi-Fi sensing. The devices within the target zone 140 include the aforementioned Wi-Fi access point 160 and multiple Wi-Fi clients 162, 164, and 166. The orchestration system 100 may select any subset of these devices or all the devices within the target zone for RF sensing, or as discussed above, devices outside of the target zone which are still expected to be able to contribute to the RF sensing in the target zone 140.

[0154] The orchestration system 100 may instruct the selected devices to adjust their data communication parameters, for example by sending instructions 102 via the network 110 to the Wi-Fi access point 160. Such adjustments may include, but not be limited to, modifications to timing, transmission power, frequency, or communication band. The adjustments may be selected to achieve specific sensing objectives. For example, the orchestration system 100 may enhance the efficacy of RF sensing by optimizing the data transmissions of the devices based on preferred characteristics which indicate a relation between sensing efficacy and data transmission parameters. Conversely, the orchestration system 100 may disrupt or hinder the sensing process by using the preferred characteristics as an inverse reference for these adjustment.

[0155] A sensing system 130 may use metadata characterizing the data transmission(s) of the selected device(s) as input to generate sensor data which is indicative of the pose or movement of the robotic arm 150 in the target zone 140, or more generally, indicative of a sensed property in the target zone. Examples of such metadata may include received signal strength (RSS), channel state information (CSI), for example with amplitude and phase data, timing parameters such as delay and jitter, signal attenuation, phase shifts, frequency changes, multipath profiles. In the example of Fig. 1 , the sensing system 130 may analyze variations in Wi-Fi signal reflections caused by the adjusted data communications of the Wi-Fi access point 160 and the WiFi clients 162-166 to determine the pose or movement of the robotic arm 150.

[0156] As shown in Fig. 1 , the sensing system 130 may be implemented by a network node belonging to or being connected to the network 110, such as a server, or in a distributed manner or a cloud-based manner by a plurality of network nodes. Data communication between the sensing system and the devices 160-166 may occur via the network 110. Alternatively, the sensing system 130 may be implemented locally, e.g., onsite by a local server, by one of the devices, or in a distributed manner across devices. Moreover, in Fig. 1 , the sensing system 130 and the orchestration system 100 are depicted as separate entities. In such examples, the sensing system 130 and the orchestration system 100 may coordinate their operations. For example, the device selection performed by the orchestration system 100 may be communicated to the sensing system 130, which may then acquire metadata of the data communications of the selected devices to perform the RF sensing, for example via the network 110 and the Wi-Fi access point 160. In other examples, the sensing system 130 and the orchestration system 100 may be integrated into a single entity. In such examples, the functionality of both systems may be implemented by respective subsystems of a single system. Both subsystems may coordinate their operations, as elucidated above.

[0157] In some examples, only the network infrastructure device, such as the Wi-Fi access point 160, may be selected for the adjustment of the data transmission. Specifically, by instructing the Wi-Fi access point 160 to adjust its data transmissions, the orchestration system 100 may indirectly influence the communication of the connected Wi-Fi clients 162-166. It is noted that, although not shown in Fig. 1 , the WiFi access point 160 may even be located outside the target physical location 140 and still influence the Wi-Fi data transmissions within the zone. Alternatively, or additionally, the orchestration system 100 may directly instruct the Wi-Fi clients 162-166 via the WiFi access point 160 to adjust their data communication parameters in a manner consistent with the sensing objectives. Similarly, the sensing system 130 may obtain the metadata only from network infrastructure devices, such as the Wi-Fi access point 160, but also from Wi-Fi clients or the combination of both types of devices. Fig. 2A shows an orchestration system 100 configured to orchestrate cellular data transmissions of user equipment (UE) devices, hereinafter also referred to as ‘UE’, and / or access nodes such as base stations by instructing the UE and / or base stations to adjust their cellular data communication to regulate the efficacy of RF sensing at the target zone 140. Other access nodes that may be instructed include, but are not limited to, Integrated Access and Backhaul (IAB) nodes, Mobile Base Station Relays (MBSR), or Mobile gNBs with Wireless Access Backhauling (MWAB). In this example, the UE 172-176 are connected to a mobile telecommunications network 112, such as a 5G, 6G, or next-generation network, via a base station 170 (gNodeB). While the UE are depicted as mobile, screen-based devices such as smartphones and tablets, the UEs may include various other types of connected devices, such as loT devices and controllers. The gNodeB 170 is shown serving the area encompassing the target zone 140, enabling cellular data transmissions 182 to occur between the devices 172-176 and the gNodeB 170. In some examples, the orchestration system 100 may instruct the gNodeB 170 via instructions 102 to adjust the cellular data transmissions involving the UE 172-176. The gNodeB 170, even if located outside the target zone 140, may thereby influence the data transmissions within the target zone and regulate the efficacy of RF sensing. In other examples, the orchestration system 100 may directly instruct the UE 172-176 to adjust their cellular data transmissions, or may issue instructions to both the gNodeB 170 and the UE 172-176. The sensing system 130 may access metadata for RF sensing from either the gNodeB 170, the UE 172-176, or from both types of entities.

[0158] In general, the network 112 may represent a public network (e.g. a public land mobile network, PLMN) or a private network (e.g., a non-public network, NPN). While Fig. 2A depicts a single base station, the orchestration system 100 may also provide instructions to multiple base stations, which multiple base stations may be similarly instructed to adjust their data transmissions to regulate RF sensing.

[0159] Fig. 2B shows an orchestration system 100 similar to that depicted in Fig. 2A. However, unlike the Fig. 2A example, the UE 172-176 in Fig. 2B are shown to be capable of D2D data communication 184, which may involve technologies such as WiFi Direct, Bluetooth, or other short-range communication protocols. Such D2D data communication 184 may be used for RF sensing. The orchestration system 100 may instruct the UE to adjust their D2D data communication 184 to regulate the efficacy of RF sensing at the target zone 140. These adjustments may be made either as an alternative to adjustments to their cellular data communication, or together with adjustments to their cellular data communication, for example in cases where both D2D data communication and cellular data communication are used for RF sensing. As shown in Fig. 2B, instructions 102 from the orchestration system 100 may be provided via the telecommunications network 112 and its gNodeB 170. Alternatively, though not explicitly depicted in Fig. 2B, the orchestration system 100 may also send instructions directly to the devices through D2D data communication or through other forms of wireless data communication, such as via a Wi-Fi access point. In such cases, the devices participating in RF sensing may not necessarily be cellular UE.

[0160] Fig. 3 shows a method 208 for orchestrating data transmissions of devices to regulate the efficacy of RF sensing at a target physical location. The method shown in Fig. 3 may comprising accessing 210 device location data 200, where the device location data may be indicative of a current or predicted physical location of a respective device. The method may further comprise receiving 220 a target physical location for RF sensing, for example by accessing target physical location data 202. The method may further comprise, using the device location data 200, selecting 250 one or more devices of which the physical location may be within a neighborhood of the target physical location. The method may further comprise instructing 260 said selected one or more devices, or an auxiliary device which controls data communication of the selected one or more devices, to adjust the data transmission of the selected one or more devices in order to regulate an efficacy of the RF sensing at the target physical location. In some examples, the method may further comprise obtaining 230 a data transmission schedule that indicates the timing and characteristics of the data transmissions of the devices, for example by accessing data transmission schedule data 204. In this case, the selection of devices in step 250 may further comprise, based on the data transmission schedule, identifying those devices whose transmissions align with, or can be adjusted to, the target time 204 for the RF sensing.

[0161] With continued reference to the data transmission schedule, it is noted that such a schedule may be obtained through various approaches. For example, the data transmission schedule for a device may be predicted based on its past data transmission patterns. This prediction may for example be obtained from a machine learning model trained to analyze historical data and identify trends or recurring patterns. For example, a machine learning model may predict that a certain loT device in a factory typically transmits data every 10 minutes and predict future transmissions accordingly. Additionally, or alternative, the data transmission schedule may be directly requested from the respective device. Namely, devices may in some cases maintain, or at least be able to provide on request, a schedule of their planned or routine data transmissions. For example, a smart sensor in a factory may have a predefined schedule for transmitting measurements to a central server and may share this schedule when queried. By obtaining the data transmission schedule through either prediction or direct request, the orchestration system may effectively plan adjustments to these transmissions to optimize or regulate the efficacy of RF sensing.

[0162] It is noted that the method steps described with reference to Fig. 3 and elsewhere may correspond to operations performed by the orchestration system as described elsewhere in this specification. In particular, the processor subsystem of the orchestration system may be configured to execute these operations.

[0163] With continued reference to Fig. 3, it is noted that the method 208 may further include receiving 240 a timestamp representing a target time for the RF sensing, for example, by accessing timestamp data 206. In this case, the method may also involve, as part of step 260, adjusting the timing of the data transmissions of the selected devices so that the transmissions coincide with the specified target time.

[0164] Fig. 4 provides an example of such a timing adjustment. Along a time axis 300, a data transmission 320 of a device is initially scheduled to occur at a time preceding the target time 310. The orchestration system and method may adjust the timing of the data transmission 320 by, through instructions to the device, delaying 330 the transmission. This may result in a delayed data transmission 340, which now aligns with the target time at which RF sensing is to be performed. Although Fig. 4 illustrates an example involving the delaying of a transmission, it should be noted that data transmissions may also be advanced in time, depending on the requirements.

[0165] Fig. 5 shows a process flow diagram for the orchestration of data transmissions of device(s) regulate an efficacy of RF sensing. The process flow diagram shows an orchestration system 400 which may comprise a processor subsystem 404, a data storage device 402, and algorithms designed to perform the orchestration. The orchestration system 400 may represent a central entity, for example within a telecommunications network, for managing data transmissions related to RF sensing, and may be implemented in various ways, such as by a network node, e.g., a base station, or a network function, or as a distributed or temporarily designated entity within a decentralized network. The data storage device 402 within the orchestration system 400 may store several types of data for orchestration. For example, the data storage device 402 may store an upcoming transmission schedule 410, which may contain a transmission schedule 412 indicating future network communications. These communications may for example be labeled with transmission durations (e.g., specific timeframes or qualitative descriptors such as ‘long’ or ‘short’) and transmission windows, which specify the acceptable time period for a transmission to occur. For example, a periodic temperature sensor update may have a broad transmission window, whereas a live video stream may require a precise and immediate transmission. An event schedule 418, which may also be stored in the data storage device, may comprise event data 420 describing events that may require RF sensing. Event data may for example include event time, event duration, event location, and sensing criteria, such as high accuracy or reliability. For example, the event data may specify that a robotic arm is scheduled to move at a factory location at 16:00 for five seconds, requiring high-accuracy sensing. The event data may represent a specific example of a target time as described elsewhere in this specification.

[0166] The data storage device may also comprise trained models 422, also referred to as available trained models 424, which may be machine learning models configured and trained for processing RF sensing data. These machine learning models may be associated with specific activities (e.g., gesture recognition, occupancy sensing), data types (e.g., sensor uploads, video streams), and communication paths (e.g., uplink or downlink traffic). Each model may also have performance metrics, referred to as model performance, indicating its reliability or accuracy for particular tasks. A path selection algorithm 430 may use the event data 420, device location data 416 as described elsewhere in this specification, and the upcoming transmission schedule 410 to identify suitable communication paths for RF sensing. These paths, referred to as opportunistic paths, may be stored in an opportunistic path list 432. An opportunistic path may represent a communication path that aligns with the spatial, temporal, and other criteria of the event, making it suitable for RF sensing. For example, the path selection algorithm 430 may determine whether a communication path intersects with the event location using techniques such as ray tracing or line-of- sight calculations. The path selection algorithm 430 may also ensure that the event time falls within the transmission window of the identified path. If needed, the path selection algorithm 430 may assign transmission delays to align data communications with the event time or group multiple paths to cover an event duration.

[0167] A communication scheduler 434 may use the opportunistic path list 432, the available trained models 424, the event data 420, and the upcoming transmission schedule 412 to generate an updated transmission schedule 436. This schedule may prioritize the most effective paths and models for RF sensing while minimizing disruptions to other network transmissions. For example, paths without suitable models or those failing to meet the event’s sensing criteria may be excluded, and the schedule may be adjusted to balance sensing requirements with overall network efficiency. A communications synchronization algorithm 438 may use the updated transmission schedule 436 along with the original transmission schedule 412 to generate transmission instructions 440. These instructions may specify how devices, such as network node 1 (462) and network node 2 (464), should adjust their data transmissions 466 to align with the updated transmission schedule. For example, if a specific communication path has been identified as suitable for sensing, the instructions may direct all involved devices to reschedule or modify their transmissions to match the requirements of that path. Such transmission instructions 440 may be delivered to the devices 462, 464 through a transceiver 460, which may, for example, be an access point, base station, or other network-connected communication node.

[0168] A sensing processor 450, which may represent an example of a sensing system as described elsewhere in this specification and which in this example is shown to be an internal component of the orchestration system 400, may use RF sensing data 468 obtained during events to produce a sensing output 452, such an estimated occupancy, a detected gesture, etc. The sensing processor 450 may select the most suitable trained model 424 based on the updated transmission schedule 436 and process the RF sensing data 468, which may include processing signal characteristics such as received signal strength, phase, or timing. For example, the sensing processor 450 may estimate occupancy, detect gestures, etc.

[0169] In some examples, the orchestration system and method may obtain an estimate of the data type associated with the data transmissions of the devices. As elucidated elsewhere, ‘data type’ in this context may refer to a characterization of the data transmission, for example in terms of protocol, application, payload characteristics, traffic type (e.g., streaming, real-time communication, or bulk data transfer), and / or transmission priority. For example, the data type may identify whether the data transmission comprises streaming media, potentially including the type (e.g., s video or audio, or specifically YouTube or Spotify traffic), or structured data uploads, such as periodic sensor readings from loT devices. The data type may be obtained in various ways, e.g., by packet inspection or by being identified in the data transmission schedule, etc. Once an estimate of the data type is obtained, the orchestration system and method may select the one or more devices based on this information. This selection may involve consulting a preference list for data types which may prioritize certain types of data transmissions. For example, video streams may be prioritized for sensing tasks that require high data volumes and consistent transmission.

[0170] In some examples, RF sensing may be performed using machine learning models, where a plurality of models is provided, each tailored to specific data types and / or different types of sensing tasks. The orchestration system and method may select the one or more devices based on the data types supported by these models and / or a preference for certain data types among the available machine learning models and / or the sensing task at hand. For example, if a sensing task requires realtime activity recognition, the system may select devices transmitting data types that align with a machine learning model optimized for this activity. For example, a model trained on high-resolution video data might lead the orchestration system to select devices transmitting video streams over those sending other data types.

[0171] In some examples, the orchestration system and method may obtain an estimate of the direction of the data transmission of the devices. The direction may refer to whether the data is flowing upstream (e.g., from a device to the network, such as uploading a file or sensor data) or downstream (e.g., from the network to the device, such as streaming content). Based on the direction of the data transmission, the orchestration system may select the one or more devices. For example, if a sensing task benefits from upstream traffic, the orchestration system may prioritize devices with consistent upstream activity. Conversely, if the sensing task benefits from downstream traffic, the orchestration system may favor devices primarily receiving data.

[0172] In some examples, the orchestration system and method may adjust the data transmission by altering the communication path of the selected one or more devices. This adjustment may involve routing the data through a third device located in the vicinity of the target physical location. For example, if a sensing task is being performed in a specific room within a building, the system may route the data transmissions of selected devices through a nearby access point, relay, or router located within or adjacent to the physical location. Such routing may ensure that the data transmissions pass through the physical location, enabling more effective RF sensing. For example, a security camera in a room may route its data uploads through a neighboring device, ensuring the wireless signals provide additional coverage or spatial resolution in the target location, thereby enhancing the sensing process.

[0173] Fig. 6 shows a system 500 which may represent or embody any of the entities described in this specification, such as an orchestration system or a device configured for wireless data communication. The system 500 may comprise a network interface 520 for network data communication, e.g., to receive data 522 and to send data 524. The network interface 520 may for example be a wired communication interface, e.g., a fiberoptic interface or an Ethernet interface, or specifically for the device, a wireless communication interface, e.g., a cellular radio interface or a Wi-Fi radio interface. The system 500 may further comprise a processor subsystem 540 which may be configured, e.g., by hardware design or software, to perform the operations described in this specification pertaining to the embodied entity.

[0174] In general, the processor subsystem 540 may be embodied by a single Central Processing Unit (CPU), such as a x86 or ARM-based CPU, but also by a combination or system of such CPUs and / or other types of processing units. As also shown in Fig. 6, the system 500 may comprise a data storage 560, which may comprise non-volatile memory such as flash memory, a solid-state drive, etc., and which may be used for long-term storage of data. Although not shown in Fig. 6, the system 500 may further comprise volatile memory for temporary storage of data.

[0175] In general, each entity described in this specification may be embodied as, or in, a device or apparatus. The device or apparatus may comprise one or more (micro) processors which execute appropriate software. The processor(s) of a respective entity may be embodied by one or more of these (micro)processors. Software implementing the functionality of a respective entity may have been downloaded and / or stored in a corresponding memory or memories, e.g., in volatile memory such as RAM or in non-volatile memory such as Flash. Alternatively, the processor(s) of a respective entity may be implemented in the device or apparatus in the form of programmable logic, e.g., as a Field-Programmable Gate Array (FPGA). Any input and / or output interfaces may be implemented by respective interfaces of the device or apparatus. In general, each functional unit of a respective entity may be implemented in the form of a circuit or circuitry. A respective entity may also be implemented in a distributed manner, e.g., involving different devices or apparatus.

[0176] It is noted that any of the methods described in this specification, for example in any of the claims, may be implemented on a computer as a computer implemented method, as dedicated hardware, or as a combination of both. Instructions for the computer, e.g., executable code, may be stored on a computer-readable medium 600 as for example shown in Fig. 7, e.g., in the form of a series 610 of machine-readable physical marks and / or as a series of elements having different electrical, e.g., magnetic, or optical properties or values. The executable code may be stored in a transitory or non-transitory manner. Examples of computer-readable mediums include memory devices, optical storage devices, integrated circuits, servers, online software, etc. Fig. 7 shows by way of example a memory card 600.

[0177] Fig. 8 is a block diagram illustrating an exemplary data processing system 1000 that may be used in the embodiments described in this specification. Such data processing systems include data processing entities described in this specification, including but not limited to an orchestration system or a device configured for wireless data communication. The data processing system 1000 may include at least one processor 1002 coupled to memory elements 1004 through a system bus 1006. As such, the data processing system may store program code within memory elements 1004. Furthermore, processor 1002 may execute the program code accessed from memory elements 1004 via system bus 1006. In one aspect, data processing system may be implemented as a computer that is suitable for storing and / or executing program code. It should be appreciated, however, that data processing system 1000 may be implemented in the form of any system including a processor and memory that is capable of performing the functions described within this specification. The memory elements 1004 may include one or more physical memory devices such as, for example, local memory 1008 and one or more bulk storage devices 1010. Local memory may refer to random access memory or other non-persistent memory device(s) generally used during actual execution of the program code. A bulk storage device may be implemented as a hard drive, solid state disk or other persistent data storage device. The data processing system 1000 may also include one or more cache memories (not shown) that provide temporary storage of at least some program code in order to reduce the number of times program code is otherwise retrieved from bulk storage device 1010 during execution.

[0178] Input / output (I / O) devices depicted as input device 1012 and output device 1014 optionally can be coupled to the data processing system. Examples of input devices may include, but are not limited to, for example, a microphone, a keyboard, a pointing device such as a mouse, a game controller, a Bluetooth controller, a VR controller, and a gesture-based input device, or the like. Examples of output devices may include, but are not limited to, for example, a monitor or display, speakers, or the like. Input device and / or output device may be coupled to data processing system either directly or through intervening I / O controllers. A network adapter 1016 may also be coupled to data processing system to enable it to become coupled to other systems, computer systems, remote network devices, and / or remote storage devices through intervening non-public or public networks. The network adapter may comprise a data receiver for receiving data that is transmitted by said systems, devices and / or networks to said data and a data transmitter for transmitting data to said systems, devices and / or networks. Radios, modems, cable modems, and ethernet cards are examples of different types of network adapter that may be used with data processing system 1000. As shown in Fig. 8, memory elements 1004 may store an application 1018.

[0179] It should be appreciated that data processing system 1000 may further execute an operating system (not shown) that can facilitate execution of the application. The application, being implemented in the form of executable program code, can be executed by data processing system 1000, e.g., by processor 1002. Responsive to executing the application, the data processing system may be configured to perform one or more operations to be described herein in further detail.

[0180] For example, data processing system 1000 may represent an orchestration system. In that case, application 1018 may represent an application that, when executed, configures data processing system 1000 to perform the functions described with reference to the orchestration system. In another example, data processing system 1000 may represent a device configured for wireless data communication. In that case, application 1018 may represent an application that, when executed, configures data processing system 1000 to perform the functions described with reference to the device configured for wireless data communication.

[0181] An abstract for the present specification may read as follows: An orchestration system and method may be provided for orchestrating radio frequency (RF)-based wireless data transmissions of devices for RF sensing. The orchestration system and method may access device location data, receive a target physical location for RF sensing, use the device location data to select one or more devices of which the physical location is within a neighborhood of the target physical location, and instruct said selected one or more devices, or an auxiliary device which controls data communication of the selected one or more devices, to adjust the data transmission of the selected one or more devices in order to regulate an efficacy of the RF sensing at the target physical location. This way, the orchestration system and method may provide an abstraction layer for RF sensing, enabling network entities to request measurements by specifying a target location without needing to handle the technical intricacies of RF sensing nor having to possess knowledge about the relationship between data transmission properties and RF sensing efficacy.

[0182] 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.

[0183] 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 stages 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. Expressions such as “at least one of” when preceding a list or group of elements represent a selection of all or of any subset of elements from the list or group. For example, the expression, “at least one of A, B, and C” should be understood as including only A, only B, only C, both A and B, both A and C, both B and C, or all of A, B, and C. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. 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.

Claims

CLAIMSClaim 1. A computer-implemented method for orchestrating radio frequency (RF)- based wireless data transmissions of devices for RF sensing, comprising: accessing device location data, wherein the device location data is indicative of a physical location of a respective device; receiving a target physical location for RF sensing; using the device location data, selecting one or more devices of which the physical location is within a neighborhood of the target physical location; instructing said selected one or more devices, or an auxiliary device which controls data communication of the selected one or more devices, to adjust the data transmission of the selected one or more devices in order to regulate an efficacy of the RF sensing at the target physical location.Claim 2. The method according to claim 1 , further comprising: receiving a timestamp representing a target time for the RF sensing; and adjusting a timing of the data transmission of the selected one or more devices so that the data transmission coincides with the target time.Claim 3. The method according to claim 2, further comprising: obtaining a data transmission schedule indicative of data transmissions of the devices; and selecting the one or more devices based on the data transmission schedule, for example based on the data transmissions of said devices aligning with, or being capable of adjustment to, the target time for the RF sensing.Claim 4. The method according to claim 3, wherein obtaining the data transmission schedule comprises at least one of: predicting the data transmission schedule for a respective device based on past data transmissions, for example using a machine learning model; and requesting the data transmission schedule from a respective device.Claim 5. The method according to any one of claims 2 to 4, wherein adjusting the timing of the data transmission of the selected one or more devices comprises delaying or advancing a scheduled data transmission.Claim 6. The method according to any one of claims 1 to 5, further comprising: obtaining an estimate of a data type associated with the data transmissions of the devices; and selecting the one or more devices based on the data type, for example based on a preference list for data types.Claim 7. The method according to any one of claims 1 to 6, wherein the RF sensing is performed using machine learning models, wherein a plurality of machine learning models is provided for different data types, and wherein the method comprises selecting the one or more devices based on supported data types and / or a preference for data types among the plurality of machine learning models.Claim 8. The method according to any one of claims 1 to 7, further comprising: obtaining an estimate of a direction of the data transmission of the devices, the direction being for example upstream or downstream with respect to a network topology; and selecting the one or more devices based on the direction of data transmission of a respective device, for example based on a directional preference.Claim 9. The method according to any one of claims 1 to 8, wherein adjusting the data transmission comprises adjusting a communication path for the data transmission of the selected one or more devices, for example by routing the data through a third device in the neighborhood of the target physical location.Claim 10. The method according to any one of claims 1 to 9, wherein adjusting the data transmission comprises adjusting at least one of: transmission power, frequency, or communication band, of the data transmission.Claim 11. The method according to any one of claims 1 to 10, further comprising accessing preferred characteristics for the RF sensing and instructing the selected one or more devices or the auxiliary device to adjust the data transmission to:increase the efficacy of the RF sensing based on the preferred characteristics; or disrupt the RF sensing, for example by using the preferred characteristics as an inverse reference for the adjustment.Claim 12. A computer-implemented method performed at a device configured for radio frequency (RF)-based wireless data communication, the method comprising: providing, to an orchestration system, a schedule of data transmissions of the device; receiving an instruction from the orchestration system to regulate an efficacy of RF sensing in a neighborhood of the device by adjusting a data transmission of the device; and in response to the instruction, adjusting the data transmission by modifying at least one of: a timing, transmission power, frequency, or communication band, of the data transmission.Claim 13. A computer program comprising instructions which, when executed by a processor system, cause the processor system to perform the method according to any one of claims 1 to 12.Claim 14. An orchestration system for orchestrating radio frequency (RF)-based wireless data transmissions of devices for RF sensing, comprising: a network interface to a network, wherein the devices are reachable via the network; a processor subsystem configured to, using the network interface: access device location data, wherein the device location data is indicative of a physical location of a respective device; receive a target physical location for RF sensing; using the device location data, select one or more devices of which the physical location is within a neighborhood of the target physical location; instruct said selected one or more devices, or an auxiliary device which controls data communication of the selected one or more devices, to adjust the data transmission of the selected one or more devices in order to regulate an efficacy of the RF sensing at the target physical location.Claim 15. A device configured for radio frequency (RF)-based wireless data communication with at least one other device, the device comprising: a wireless interface for the wireless data communication; a processor subsystem configured to, using the wireless interface: - provide, to an orchestration system, a schedule of data transmissions of the device; receive an instruction from the orchestration system to regulate an efficacy of RF sensing in a neighborhood of the device by adjusting a data transmission of the device; and - in response to the instruction, adjust the data transmission by modifying at least one of: a timing, transmission power, frequency, or communication band, of the data transmission.

Images