Robot air purification and measurement

Abstract

Air purification and / or monitoring may be performed by a robot 1902. Fixed air quality sensors 1905 within a building detect air quality and based on air quality data, a decision is made whether to op

Description

TECHNICAL FIELD

[0001] The present invention relates to robot air purification and measurement. More particularly, the present invention relates to a method of controlling a robot for purifying air or measuring air quality within a building. The present invention further relates to a robot configured to implement the method and an air purifying or air quality measurement system for a building, the system comprising such a robot and a fixed air quality sensor. Embodiments of the present invention are built on, logically connected with, or otherwise associated to an Artificial Intelligence (Al) system or computing platform for performing the monitoring or control of a system within a building. Certain embodiments of the present invention are particularly directed to robot air purification a measurement within domestic premises such as houses and apartments - that is, homes. BACKGROUND

[0002] Buildings, including homes, offices and commercial or industrial premises, are becoming increasingly complex. A single building, for instance a single home, may include multiple separate building systems each linking together a range of devices. The devices include sensors providing sensor data indicative of a sensed parameter for the building or the building system and components forming part of the building system and providing component data indicative of a component state. As an example, a typical home Heating, Ventilation and Air Conditioning (HVAC) system may include an array of environment sensors, including for instance temperature and humidity sensors distributed through the home. A HVAC system may include an array of controllable components, for instance fans and valves for controlling ventilation, heating, and cooling sub-systems within the home. Clearly, there is a need for some form of control system to control the HVAC system components based on their component state and based on sensing data.

[0003] One particular type of HVAC system (or a component or sub-system within a HVAC system) is a Mechanical Ventilation with Heat Recovery (MVHR) system. MVHR is a type of mechanical ventilation system used in residential and commercial buildings to provide fresh air while recovering the heat from the outgoing air. Extracted stale air from the building passes through a first duct network to a heat exchanger which transfers the heat from the outgoing air to the incoming fresh air, which is then distributed back into the building through a separate duct network. This process helps to maintain a comfortable indoor temperature while reducing energy consumption and carbon emissions. The MVHR system also helps to improve indoor air quality by continuously exchanging stale air with fresh air, reducing the build-up of pollutants and excess moisture. It will be appreciated that an MVHR system requires a control system for its respective parts (which may include at a minimum pumps or fans and optionally control valves. A typical home may include numerous further building systems (or sub systems), for instance security systems, health care or health monitoring systems and energy supply and control systems, each with their own specific requirements for sensors, controllable components, and control mechanisms (though in some cases there may be overlap in terms of shared sensors).

[0004] Commercially deployed building control systems are often limited in terms of their performance. They may be relatively “dumb” in the sense that they are purely reactive. For instance, if the sensed temperature is below a set threshold, then a heating system may be turned up. Typically, there is no capability for building systems to learn and adapt to the specific attributes of a building, nor to adapt to the requirements of the building occupants.

[0005] There is an industry trend towards “smarter” buildings. Smarter in the sense of better able to react and adapt to the attributes of a building and to adapt to the needs of the building occupants. Al holds much promise for developing smarter buildings. Particularly the use of machine learning or deep learning to analyse real life data for a building and its building systems, to train suitable machine learning algorithms for the building systems and to apply those trained algorithms to provide for control of building systems that are better adapted to meet the needs of the building occupants. Al may improve building systems with the result that the buildings themselves are more energy efficient, secure, comfortable, or healthier for their occupants.

[0006] While the majority of modern buildings have an internet gateway provided by an Internet Service Provider (ISP), those gateways typically have no inbuilt Al inference acceleration capability. Neither is it commonplace for Al hardware capability to be separately provided within buildings (at least for homes - in commercial and industrial settings the use of Al to control building systems is more well established). With the rise of web 3.0 (also known as the “Semantic Web”) it is expected that the need for Al capability within the home will increase. Web 3.0 refers to the next evolution of the World Wide Web, in which data is interconnected and machine-readable, allowing for more intelligent and efficient use of information. Web 3.0 is also expected to provide greater privacy and security for users, as well as more personalized and relevant experiences for users.

[0007] In the interim, before widespread deployment of Al hardware capability to homes, any Al task or insight, including for the control of building systems, is normally carried out using cloud computing. Cloud computing refers to the delivery of computing services such as servers, storage, databases, software, and networking over the internet. These services are provided by remote servers that are maintained by a cloud service provider, allowing users to access and use them on-demand without needing to own and manage their own infrastructure. Cloud computing offers advantages such as cloud scalability, flexibility, and cost-efficiency. While cloud computing offers numerous benefits, there are some potential problems and challenges to consider, including: • Security: Storing data and applications in the cloud can potentially expose them to security risks, such as data breaches or unauthorized access, if the appropriate security measures are not implemented. For a home control system this data could include personally identifiable or sensitive information such as whether the building is occupied. • Availability: Cloud services depend on reliable internet connectivity, so disruptions to the internet or to the cloud service provider’s infrastructure can result in downtime. For instance, for control of a home HVAC system such interruption may be unacceptable. • Vendor lock-in: Switching cloud providers can be difficult and expensive, so customers may feel “locked in” to their current provider. • Cost: While cloud computing can be cost-efficient, the costs can add up overtime, especially if users are not careful to monitor and manage their usage. • Latency and bandwidth can potentially be a problem for cloud computing, depending on the specific application or use case.

[0008] As a result of these factors, particularly latency and bandwidth, cloud computing may not provide an acceptable Quality of Service (QoS) for Al based control of building systems.

[0009] Furthermore, indoor air pollution is an increasing concern in the modern world. Sources of indoor air pollution may be external or internal to a building. It is known to install air quality sensors within a building to measure air quality, and so to quantify indoor air pollution. Such sensors may measure one or more environmental parameters, such as levels of particulate matter in an air sample. It is also known to provide fixed devices within the building to seek to reduce levels of pollution or to maintain measured air quality within a predetermined acceptable range. Such fixed devices may include ventilation devices designed to extract polluted or stale air from a building. Ventilation devices may, for instance, include a MVHR system, a Positive Input Ventilation (PIV) device (which serves to draw in fresh air to push out stale air), extractor fans and window trickle vents. It is known for a building to be provided with a fixed air purifying device whereby a closed circuit is formed in which building air is drawn in, purified, and returned to the building (optionally in the same location or a different location). An air purifier may make use of a pre-filter, to capture larger particles such as dust, pet hair, and lint, and a main filter. The main filter may, for instance, be a HEPA (High-Efficiency Particulate Air) filter formed from densely packed fibres that can trap up to 99.97% of particles as small as 0.3 microns in size, or an activated carbon filter which may also be effective at removing odours, and Volatile Organic Compounds through a process of adsorption.

[0010] It will be appreciated that fixed ventilation or air purification devices are limited in that they can only directly improve air quality in their immediate vicinity and their effectiveness reduces with distance. Unless a building is provided with a dense network of fixed ventilation or air purification devices then there will be locations within the building in which air pollution is not adequately addressed: that is, ventilation or air purification dead spots.

[0011] It is known to use a robot to navigate a building and perform air purification in order to tackle indoor air pollution. For instance, US patent US-10443874-B2 discloses a method for multipoint purification by a robotic air purifier. The method comprises establishing a map of an area to be purified, moving the robotic air purifier within that area, measuring air quality, noting where a pollution threshold is exceeded, marking those locations on the map, and later returning to those locations to perform air purification. However, the method disclosed in US-10443874-B2 is inefficient in that it requires the whole building to be surveyed by the robot before locations where air purification is required can be identified and returned to.

[0012] It is an aim of certain examples of the present invention to solve, mitigate or obviate, at least partly, at least one of the problems and / or disadvantages associated with the prior art. Certain examples aim to provide at least one of the advantages described below. BRIEF SUMMARY OF THE INVENTION

[0013] Aspects of the invention provide a method of purifying air or measuring air quality within a building using a robot, a robot configured to implement the method and an air purifying or air quality measurement system for a building, the system comprising such a robot and a fixed air quality sensor (optionally, a plurality of distributed sensors), as claimed in the appended claims.

[0014] According to a first aspect of the present invention there is provided a method of controlling a robot, the method comprising: obtaining air quality data measured at a fixed air quality sensor within a building; and determining, based on the received air quality data, whether to operate the robot within the building; wherein operating the robot within the building comprises: navigating the robot within the building; and operating an air purifying device mounted on the robot to improve the air quality; or operating an air quality sensor mounted upon the robot to measure air quality.

[0015] An advantage of certain embodiments of the present invention is that by taking account of air quality data measured at a fixed air quality sensor, robotic air purification can be performed more efficiently. It may be that the robot is only operated if received air quality data from the fixed sensor is outside of an acceptable air quality range (for instance if measured pollution exceeds a threshold). It may be that if the building further includes fixed air purifying or ventilation devices then these may be operated in preference to operating the robot if it is expected that those devices can return the measured air quality to the acceptable range within an accepted time span. Certain embodiments provide further efficiency gains by optimising the navigation of the building based on the measured air quality data or based on sensed parameters such as the layout of a room.

[0016] An advantage of certain embodiments of the present invention is that by combining air quality measurements from fixed air quality sensors and measurements performed by a robot as it navigates the building, a more accurate picture of air quality within the building can be established.

[0017] Determining whether to operate the robot may further comprise inferring, based on the received air quality data, a first location within the building where air quality is outside of an air quality range indicating acceptable air quality; or inferring, based on the received air quality data, a second location within the building where the air quality is unknown.

[0018] Navigating the robot within the building may further comprise navigating the robot such that it traverses the first location or the second location.

[0019] Navigating the robot may further comprise inferring, based on the received air quality data, a third location within the building where air quality is within the air quality range; and navigating the robot to avoid the third location.

[0020] Determining whether to operate the robot may comprise forming a map of air quality within the building based on the received air quality data and corresponding measurement locations for the fixed air quality sensors; and using the map to infer the first location, second location or third location.

[0021] The method may further comprise supplementing the map with air quality data measured by the air quality sensor mounted on the robot and corresponding measurement locations.

[0022] The method may further comprise using the map to infer the second location by calculating a location remote from air quality measurement locations.

[0023] The method may further comprise updating the map to remove air quality data older than a first time threshold.

[0024] The method may further comprise interpolating air quality at locations between measurement locations.

[0025] Determining whether to operate the robot further may comprise: determining an estimated time to improve air quality at the first location such that the air quality is within the air quality range using a fixed air purifying or ventilation device within the building; comparing the estimated time to a second time threshold; and determining whether to navigate the robot and operate the robot’s air purifying device or whether to operate the fixed air purifying or ventilation device based on the result of the comparison.

[0026] Determining an estimated time may comprise processing received air quality data or air quality data measured by the robot using a trained predictive machine learning algorithm to determine an estimated time.

[0027] The method may further comprise processing received air quality data or air quality data measured by the robot using the trained predictive machine learning algorithm to infer a location within the building where future air quality will be outside of the air quality range.

[0028] The method may further comprise receiving the trained predictive machine learning algorithm from a fog computing device; and forwarding air quality data measured by the robot or data indicating operation of the robot air purifying device to the fog computing device fortraining or updating the training of the predictive machine learning algorithm.

[0029] The method may further comprise: processing received air quality data, air quality data measured by the robot, or data obtained from the fixed air purifying or ventilation device using a trained reinforcement machine learning algorithm to determine a preferred remedy to an inference of air quality outside of the air quality range; wherein determining whether to navigate the robot and operate the robot’s air purifying device or whether to operate the fixed air purifying or ventilation device is further based on the determined preferred remedy.

[0030] Navigating the robot within the building may comprise prioritising visiting: known regions of the building where air quality measurements have previously differed from measurements recorded at a fixed air quality sensor, those known regions being preprogramed or determined from previous operation of the robot; regions of the building where it is predicted that air quality measurements may differ from measurements recorded at a fixed air quality sensor, the prediction being based on operation of a camera mounted on the robot to determine a layout of the building or a room within the building or furniture or other obstacles located within the building indicative of low air circulation; or regions within the building that are a priority for maintaining air quality within the air quality range, including regions where people congregate, either preprogramed or determined using a camera mounted on the robot.

[0031] Navigating the robot within the building may comprise one or more of: providing the robot with a map indicating the layout of the building; using a camera mounted on the robot to determine a layout of the building or a room within the building; or using the camera mounted on the robot to detect furniture or other obstacles located within the building.

[0032] The map may indicate the locations of a fixed air quality sensor or fixed air purifying or ventilation devices; or the method further comprises using the camera mounted on the robot to detect the locations of fixed air quality sensors or fixed air purifying or ventilation devices.

[0033] Different air quality ranges may be applied in different regions of a building; or an air quality range applied in a region of the building where it is known or detected that people congregate may be indicative of cleaner air than an air quality range applied in a region of the building that is unoccupied.

[0034] The method further comprises determining sources of pollution through fixed or robot air quality measurements or through a camera mounted upon the robot and navigating the robot towards determined sources of pollution to perform air quality measurements or to perform air purification; or receiving a signal from a building occupancy sensor indicative of occupancy levels and adjusting the frequency of navigating the robot through the building according to detected occupancy levels.

[0035] According to a second aspect of the present invention there is provided a computer-readable storage medium having computer-readable program code stored therein that, in response to execution by a processor, causes the processor to control a robot perform the above method.

[0036] According to a third aspect of the present invention there is provided a robot comprising: propulsion means for navigating through a building; an air purifying device or an air quality sensor; a processor; and a memory storing executable instructions that, in response to execution by the processor, cause the processor to control the robot to perform the above method.

[0037] According to a fourth aspect of the present invention there is provided an air purifying or air quality measurement system for a building, the system comprising: a robot as described above, and a fixed air quality sensor configured to be located within the building and configured to measure air quality.

[0038] The system may further comprise: a fog computing device configured to train or to update the training of the predictive machine learning algorithm for execution by the robot.

[0039] There is further disclosed a computer implemented method of monitoring or controlling a system within a building, the method comprising: training a machine learning algorithm using device data from at least one device relating to the building or forming part of a building system at a fog computing device associated with the building; receiving device data from the at least one device at an edge computing device associated with the building; and processing the received device data at the edge computing device using the trained machine learning algorithm to generate an output signal relating to the building system or a control signal for the building system.

[0040] Advantageously, that control or monitoring of building systems (particularly for a smart home) may be improved using an Al distributed architecture in which training of a machine learning algorithm is performed by a fog computing device and execution of the trained algorithm is performed by an edge computing device. The principle advantage of this is that the Al distributed architecture is scalable and extensible: the more complex / expensive fog computing device can perform training for multiple machine learning algorithms associated with different building systems, while the trained machine learning algorithm for each building system (for instance, air quality, security or health monitoring) can be executed on a respective edge device which communicates with an appropriate set of devices such as sensors and controllable system components to receive data, make predictions and / or control devices.

[0041] This split between fog computing and edge computing gives benefits in terms of cost reduction (where there are multiple systems in a building needing separate control), extensibility / scalability through the ability to add additional edge computing devices to expand to control additional building systems, while leveraging the investment in a single (or reduced number) of fog computing devices to provide Al algorithm training, future proofing by permitting as yet unanticipated future building systems to be controlled through the same Al distributed architecture, cost effectiveness, security, privacy and the ability to additionally communicate with cloud computing services due to the edge / fog implementation (for instance, for data collection, fault reporting, communication with other external systems).

[0042] Advantageously, the Al distributed architecture allows for more efficient control of building systems compared to conventional alternatives. As an example, for a HVAC building system (or particularly an MVHR system) controlled as described above, the heating of the building may be optimised to the predicted occupancy level of the building thereby reducing excess heating (for instance when it is predicted that the building will be empty) which can reduce the carbon intensity of the building. A further example is that when it is predicted that the building will be occupied at a future time point then the building may be preferentially heated during time periods when the electricity supply is anticipated to be predominantly supplied by renewable or low carbon energy sources, or when there is typically overcapacity on the electricity supply network (which may also correspond to periods of reduced cost electricity supply).

[0043] The at least one device may comprise at least one of: a sensor providing sensor data indicative of a sensed parameter for the building or the building system; or a component forming part of the building system and providing component data indicative of a component state. There is no limitation to any particular type of device: each device may be anything which can provide device data indicative of a sensed parameter within a building or within or part of a building system, or a device forming part of a building system able to provide data indicative of a device state. Existing or newly deployed devices within a building may be used to obtain data indicative of how a building or system functions or operates.

[0044] The output signal may comprise at least one of: an output message or alert to a user indicating a state of the building or the building system or if the state or the building or the building system is outside of a defined range; or a prediction of a current or future state of the building or the building system. There is no limitation to any particular type of output, nor any particular delivery mechanism for an output signal.

[0045] The control signal may comprise a signal instructing a component setting or change of operation for a component forming part of the building system either immediately or a future point in time. Advantageously, not only can building systems be monitored, but they can also be directly controlled (for instance in response to a predicted building or system state) so as to permit the building system to run more effectively. Effective building control can include energy efficiency, improving the comfort and health of building occupants and control that prolongs the lifespan of a building system by avoiding operating the system when it is unnecessary.

[0046] The method may further comprise: the edge computing device storing device data received from the at least one device. Where device data is stored, this may be for the purpose of its later use when executing a trained Al model (such that the model may process both live device data and historic device data).

[0047] The method may further comprise: the edge computing device forwarding device data received from the at least one device to the fog computing device fortraining the machine learning algorithm or updating the training of the machine learning algorithm. There is no limitation to any specific routing or topology for distributing data around the distributed Al architecture.

[0048] The method may further comprise: the edge computing device storing device data received from the at least one device and periodically forwarding stored device data to the fog computing device.

[0049] The method may further comprise: the fog computing device training the machine learning algorithm using a training set of device data received from the at least one device, the training set of device data being received directly from the at least one device or via the edge computing device. The volume of device data required to form an effective training set may be context dependent for the building system being observed and the building within which it is deployed.

[0050] The method may further comprise updating the training of the machine learning algorithm at the fog computing device using device data received from the at least one device; and providing an updated trained machine learning algorithm to the edge computing device for use in processing further received device data. Advantageously this allows the fog computing device to learn how effectively building systems are controlled or monitored and build this feedback into the training of an updated model.

[0051] Updating of the training of the machine learning algorithm may further use the training set of device data or previously received device data.

[0052] Updating of the training of the machine learning algorithm may be performed continuously as device data is received from the at least one device, the updated trained machine learning algorithm being provided to the edge computing device either continuously or periodically; or wherein updating of the training of the machine learning algorithm is performed intermittently or periodically using device data received from the at least one device.

[0053] The trained machine learning algorithm may comprise at least one of: a predictive machine learning model adapted to provide a prediction of a current or future state for the building or the building system; or an inference machine learning model adapted to provide a control signal instructing a component setting or a change of operation for a component forming part of the building system either immediately or a future point in time to control or adjust a predicted state for the building system. The trained machine learning algorithm may further comprise an observational or reinforcement learning model that takes account of feedback concerning operation of the models for controlling or monitoring building systems.

[0054] Alternatively, both a predictive machine learning model and an inference machine learning model may be implemented at the edge computing device; the predictive machine learning model provide a prediction of a current or future state for the building system and the inference machine learning model provides an output to a component forming part of the building system to control or adjust the building system according to the prediction from the predictive machine learning model.

[0055] The at least one device may comprise a sensor providing sensor data indicative of a sensed parameter for the building or the building system; wherein at least one component forming part of the building system provides component data indicative of a component state to the fog computing device or to the edge computing device; and wherein the machine learning algorithm is trained at the fog computing device using sensor data and component data.

[0056] The machine learning algorithm may comprise an inference machine learning model adapted to provide a control signal instructing a component setting or a change of operation for the at least one component forming part of the building system either immediately or a future point in time to control or adjust a predicted state for the building system.

[0057] The method may further comprise the fog computing device storing sensor data received from the at least one sensor or component data from the at least one component.

[0058] Both a predictive machine learning model and an inference machine learning model may be implemented at the edge computing device; and the predictive machine learning model may provide a prediction of a current or future state for the building system and the inference machine learning model may provide an output to the at least one component forming part of the building system to control or adjust the building system according to the prediction from the predictive machine learning model.

[0059] The edge computing device may comprise a sensing edge computing device receiving sensor data from the at least one sensor within or associated with the building; wherein the method may further comprise a system edge computing device communicating with the at least one component to receive component data; wherein the sensing edge computing device processes the received sensor data using a predictive machine learning algorithm, trained by the fog computing device, to provide a prediction of a current or future state for the building or the building system and to provide an output to the system edge computing device if the prediction is outside of a defined range; and wherein the system edge computing device processes received component data and the output received from the sensing edge computing device using an inference machine learning algorithm, trained by the fog computing device, to provide a control signal instructing a component setting or a change of operation either immediately or a future point in time to control or adjust a predicted state for the building system.

[0060] The method may further comprise: the system edge computing device observing building system state data or control data, and providing this data to the fog computing device; the fog computing device training an observational or reinforcement learning model and providing the trained model to the system edge; and the system edge executing the trained observational or reinforcement learning model to adjust at least one threshold or range fora prediction output for the predictive model.

[0061] Advantageously, the observational or reinforcement learning model observes and records the states and actions of components of the building system, for instance a ventilation system, and the states and actions of the building occupants. The observational or reinforcement model determines what patterns exist within the data, but is not responsible for controlling the building system components devices itself to effect system change. This permits context awareness or situational awareness by adjusting the parameters of the predictive model based on real-time observations of the control of the building system which is fed back to the operation of the predictive model. It may be assumed that if building occupants do not override any such changes through a feedback mechanism, then implicitly those changes are approved.

[0062] The method may further comprise: the system edge computing device observing building system state data or control data, and providing this data to the fog computing device; the fog computing device training an observational or reinforcement learning model and providing the trained model to the system edge; and the system edge executing the trained observational or reinforcement learning model to adjust at least one threshold or range for a prediction output for the predictive model.

[0063] That is, the functions of Al prediction and Al inference may be separated out. The sensing edge may be responsible for monitoring the building system and forming prediction of future states for the building or the building system. The system edge may be responsible for building system control: adjusting control data sent to components within the building system, optionally based on feedback on predictions from the sensing edge.

[0064] For an example application of monitoring air quality and controlling a ventilation system to ensure that air quality stays within defined limits, the sensing edge computing device may comprise an environment sensing edge computing device receiving environment sensor data from at least one environment sensor within or associated with the building. The system edge computing device may comprise a ventilation system edge computing device communicating with at least one component forming part of a building ventilation system to receive component data indicative of a ventilation system component state; wherein the environment sensing edge computing device processes the received environment sensor data using a predictive machine learning algorithm, trained by the fog computing device, to provide a current or a future air quality prediction for the building and to provide an output to the system edge computing device if the prediction is outside of a defined range; and wherein the system edge computing device processes received ventilation system state data and the output received from the environment sensing edge computing device using an inference machine learning algorithm, trained by the fog computing device, to provide a control signal instructing a ventilation system component setting or change of operation either immediately or a future point in time to control or adjust a predicted state for the ventilation system.

[0065] The at least one environment sensor may comprise one or more of: a temperature sensor; a humidity sensor; a particulate matter sensor; a gas sensor; or a pressure sensor. This should not be considered to be an exhaustive list of available environment sensors that may yield data relevant to air quality.

[0066] The environment sensing edge computing device may further configured to receive sensor data from one or more of: an occupancy sensor; or a camera. The skilled person will be aware of other ways in which occupancy may be monitored and other sources of external data that may prove relevant to monitoring and controlling air quality.

[0067] The at least one ventilation system component may comprise one or more of: a ventilation fan; a ventilation valve; a heating control or valve; or an air conditioning control or valve. This is not an exhaustive list of components of a HVAC system that may be controlled and may provide data indicative of a system state.

[0068] The edge computing device may comprise a first edge computing device processing received device data using a first trained machine learning algorithm to generate an output signal or a control signal for a first building system; wherein the method further comprises at least one further edge computing device processing received device data from at least one device relating to the building or forming part of a further building system using a further trained machine learning algorithm to generate an output signal, relating to the building or the further building system, or a control signal for the further building system; and wherein both the first machine learning algorithm and the further machine learning algorithm are trained using device data at the fog computing device. Accordingly, the benefits of scalability and extensibility provided by the distributed Al architecture may be provided by deploying further edge computing devices for monitoring or controlling further building systems.

[0069] Each of the first and further building systems may comprise separate building systems selected from a group including: a building ventilation system; a building heating and ventilation system; a building heating, ventilation, and air conditioning system; a building security system; a building energy use monitoring and control system; or a healthcare system.

[0070] For at least one further building system a machine learning algorithm trained by the fog computing device may be executed on the fog computing device for processing device data received by the fog computing device. That is, while the primary function of the distributed Al architecture is to separate the roles of model training and model executing, in some cases particularly for complex multi-system deployments it may be more efficient for at least one model to be executed as well as trained by the fog computing device.

[0071] The method may further comprise at least one edge computing device or fog computing device: receiving device data from at least one controllable device within or associated with the building; processing the device data using a control algorithm; and returning a control signal to the controllable device. That is, while the distributed Al architecture serves to control or monitor complex building systems, the available computing power may also be leveraged to control simpler devices or appliances within a building.

[0072] The at least one controllable device may comprise at least one of: a kitchen appliance, for instance an oven, microwave, refrigerator, freezer, or dishwasher; ora utility appliance, for instance a clothes washing machine or tumble drier; a home entertainment device, for instance a television or other audio or visual device. This is not an exhaustive list.

[0073] At least one edge computing device or fog computing device may receive data from a system external to the building for processing using a trained machine learning algorithm together with device data, or for use in training a machine learning algorithm at the fog computing device.

[0074] The data from the system external to the building may comprise at least one of: current or predicted meteorological information; and current or predicted location information for building occupants. Other pertinent external data sources will be readily apparent to the skilled person from consideration of a particular building system to be monitored or controlled.

[0075] Current or predicted location information for building occupants may be derived from at least one of: calendar information; and mobile device location services.

[0076] The output signal may be provided through at least one of: a local area network portal; a mobile device application; ora display or touchscreen device within the building.

[0077] Each edge computing device, the fog computing device, and any devices, sensors or system components may be communicatively coupled either through a wired network within the building or wirelessly.

[0078] Communications between each edge computing device, the fog computing device, and any devices, sensors or system components may be compliant with the Matter protocol. This is only one example of a suitable communication protocol, albeit one that permits the use of Matter compatible commercially available sensors and system components.

[0079] Wireless communications may be transmitted through a Thread network, particularly where Matter compatible devices are to be used.

[0080] The building may comprise a domestic premise. While certain disclosed embodiments are broadly applicable to any building, as discussed below in connection with figures 7a and 7b they may be particularly suitable for monitoring or controlling building systems within a home.

[0081] There is further disclosed a computer-readable storage medium having computer-readable program code stored therein that, in response to execution by a processor forming part of an edge computing device and a processor forming part of a fog computing device, cause the edge computing device and the fog computing device to perform the method of any one of the preceding claims.

[0082] There is further disclosed a system for monitoring or controlling a system within a building, the system comprising: at least one device relating to the building or forming part of a building system and configured to provide device data; an edge computing device configured to receive device data from the at least one device and process the received device data using a trained machine learning algorithm to generate an output signal relating to the building system ora control signal for the building system; and a fog computing device configured to train the machine learning algorithm.

[0083] The system described above may be further configured to execute any part of the above-described methods of monitoring or controlling a building.

[0084] There is further disclosed a computer implemented method of operating an edge computing device to monitor or control a system within a building, the method comprising: receiving device data from at least one device relating to the building or forming part of a building system at the edge computing device, the edge computing device being associated with the building; and processing the received device data at the edge computing device using a trained machine learning algorithm to generate an output signal relating to the building system ora control signal for the building system; wherein the machine learning algorithm is trained using device data at a fog computing device associated with the building.

[0085] The edge computing device may be further configured to perform any part of the above-described methods of monitoring or controlling a building.

[0086] There is further disclosed a computer-readable storage medium having computer-readable program code stored therein that, in response to execution by a processor forming part of an edge computing device, cause the edge computing device to perform the above-described method of operating an edge computing device.

[0087] There is further disclosed an edge computing device comprising a processor and a memory storing executable instructions that, in response to execution by the processor, cause the edge computing device to perform the above-described method of operating an edge computing device.

[0088] There is further disclosed a computer implemented method of training a machine learning algorithm for monitoring or controlling a system within a building, the method comprising: receiving device data from at least one device relating to the building or forming part of a building system; forming a training data set from the device data; and training a machine learning algorithm using the training data set; wherein the trained machine learning algorithm is provided to an edge computing device for processing received device data at the edge computing device to generate an output signal, relating to the building or the building system, ora control signal for the building system.

[0089] Training the machine learning algorithm using device data at the fog computing device may comprise processing a training set of device data using machine learning or deep learning, including one or more steps from a group including: classification; segmentation; correlation; and prediction.

[0090] There is further disclosed a computer-readable storage medium having computer-readable program code stored therein that, in response to execution by a processor forming part of a fog computing device, cause the fog computing device to perform the above-described method of training a machine learning algorithm.

[0091] There is further disclosed a fog computing device comprising a processor and a memory storing executable instructions that, in response to execution by the processor, cause the fog computing device to perform the above-described method of training a machine learning algorithm.

[0092] Embodiments of the disclosure are described in connection with controlling or monitoring building systems, and the term “building” should be broadly construed to mean any structure defining a space which is wholly or partially contained. The term “building" includes industrial, commercial, retail and office buildings or structures as well as domestic premises including houses and apartments (hereinafter referred to as “homes”). However, as will become apparent from the following description, certain embodiments of the disclosure are particularly suited to monitoring or controlling building systems within homes. This is because, as noted above, up until now homes have not typically been provided with Al hardware capability (particularly, Al inference acceleration capability), resulting in home systems being reliant on cloud computing for advanced system control functions. Furthermore, context awareness and situational awareness are facilitated as part of Al control of building systems. As but one example, account may be taken of current and predicted future occupancy information when controlling a building system so that the building system may be optimised to meet the needs of the building occupants (both fortotal occupancy levels and for the specific requirements of identified occupants). That is, the behaviour of occupants of a building can be observed and predicted and considered when controlling a building system. For instance, for controlling a building ventilation system, it may be observed that certain occupants cook food or use bathrooms at certain times of day, meaning that it can be predicted that the air quality within the home may be affected at a future point in time and the ventilation system controlled to address this predicted reduction in air quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] Examples of the invention are further described hereinafter with reference to the accompanying drawings, in which:

[0094] Figure 1 is a process flow diagram for a distributed Al architecture comprising an edge computing device and a fog computing device for monitoring or controlling a building system;

[0095] Figure 2 is a process flow diagram comprising a modification to the distributed Al architecture of figure 1 in which both a predictive machine learning model and an inference machine learning model are executed upon the edge computing device;

[0096] Figure 3 is a process flow diagram comprising a modification to the distributed Al architecture of figure 1 in which both sensor data and data from a component forming part of a building control system are processed;

[0097] Figure 4 is a process flow diagram comprising a modification to the distributed Al architecture of figure 2 in which both sensor data and data from a component forming part of a building control system are processed;

[0098] Figure 5 is a process flow diagram comprising a modification to the distributed Al architecture of figure 4 in which the distributed Al architecture further comprises both a sensing edge computing device which executes a predictive machine learning model and system edge computing device which executes an inference machine learning model, the edge computing devices processing both sensor data and data from a component forming part of a building control system;

[0099] Figure 6 is a process flow diagram corresponding to the distributed Al architecture of figure 5 for the example of monitoring or controlling a ventilation system;

[00100] Figure 7a is a perspective view and figure 7b is a cross section plan view of a domestic premise, particularly a home (specifically a home constructed as a hybrid building) incorporating a distributed Al architecture;

[00101] Figure 8 is a flow chart illustrating a process of training and implementing a machine learning algorithm for monitoring or controlling a building system where a distributed Al architecture is deployed within a building;

[00102] Figure 9 is a modification to the flow chart of figure 8 further illustrating a method of updating the training of a machine learning algorithm for monitoring or controlling a building system;

[00103] Figure 10 is a modification to the flow chart of figure 8 further illustrating a more detailed method of training of a machine learning algorithm for monitoring or controlling a building system;

[00104] Figure 11 is a flow chart illustrating a method of operating an edge computing device for monitoring or controlling a building system;

[00105] Figure 12 is a flow chart illustrating a method of operating a fog computing device fortraining a machine learning algorithm for monitoring or controlling a building system;

[00106] Figure 13 is a network topology diagram for a distributed Al architecture;

[00107] Figure 14 illustrates an edge computing device forming part of a distributed Al architecture;

[00108] Figure 15 illustrates a fog computing device forming part of a distributed Al architecture;

[00109] Figure 16 illustrates a building or building system sensor device configured to communicate sensor data to a distributed Al architecture;

[00110] Figure 17 illustrates a building system component configured to communicate component data to a distributed Al architecture;

[00111] Figure 18 is a process flow diagram corresponding to a modified form of the distributed Al architecture of figure 6 for the example of monitoring or controlling a ventilation system;

[00112] Figure 19 illustrates a floor plan fora building within which the methods of figures 19 to 22 may be implemented;

[00113] Figure 20 schematically illustrates a robot adapted to perform the methods of figure 19 to 22;

[00114] Figure 21 is a process flow diagram for a method of purifying air within a building according to an embodiment of the present invention;

[00115] Figure 22 is a process flow diagram for a method of purifying air within a building according to a further embodiment of the present invention;

[00116] Figure 23 is a process flow diagram for a method of purifying air within a building according to a yet further embodiment of the present invention; and

[00117] Figure 24 is a process flow diagram for a method of measuring air quality within a building according to an embodiment of the present invention.

[00118] In the following description of the drawings, where corresponding features are shown, the same reference numbers are used. DETAILED DESCRIPTION

[00119] There is disclosed herein a novel distributed Al architecture for monitoring or controlling a building system in which a machine learning model training is performed by a fog computing device and execution of the trained machine learning algorithm is performed by an edge computing device. In particular, but not exclusively, this Al distributed architecture may be deployed within a smart home interacting with a broad range of devices including sensors for sensing parameters of the building such as environmental parameters. The devices may further comprise system components, such as controllable system actuators, capable of providing sensor information or component state information. In some cases, the components may also be configured to receive control signals output from the trained machine learning algorithm for controlling the building system.

[00120] As previously noted, while it is known for building systems to be controlled through cloud computing, it has been identified that particularly latency and bandwidth issues relating to conventional implementations of cloud computing may not provide an acceptable quality of service for monitoring or controlling building systems. Edge computing addresses at least some of the issues associated with cloud computing by bringing data processing closer to the sources of data.

[00121] Edge computing is a distributed computing paradigm that involves processing and analysing data at or near the edge of the network, where the data is generated, rather than relying solely on a centralized cloud computing infrastructure. This enables faster response times, reduced network bandwidth, improved reliability, and enhanced security and privacy for applications and services that require real-time or low-latency processing.

[00122] This may mean processing building system data to provide output signals and control signals for the building system using an edge computing device in or associated with the home. An edge computing device used as described herein as part of a distributed Al architecture may comprise a relatively low-cost computing device that has the capacity to receive and process device data by executing a trained machine learning algorithm (also referred to herein as a trained Al model or simply trained model or model). The edge computing device may receive data from one or a plurality of devices, process the data and generate an output signal or a control signal. In particular, the edge computing device may incorporate the Al acceleration (particularly, in some embodiments, Al inference acceleration) hardware capability that is necessary to execute a trained Al model. As noted above, conventionally most buildings, especially homes, lack such Al acceleration hardware capability. However, an edge computing device according may lack the computational capacity to train a machine learning algorithm in order to generate a trained Al model.

[00123] Fog computing is a distributed computing paradigm that extends the capabilities of edge computing by adding an intermediate layer of computing and storage resources between the edge devices and the cloud. The fog layer is typically located closer to the edge devicesthan the cloud, and provides more powerful computing resources and storage than the edge devices. This allows for more complex processing and analysis of data at the edge. Fog computing is especially useful in applications where data must be processed and analysed in real-time, or where there are limitations on network bandwidth or latency.

[00124] A fog computing device is provided in or associated with the home and communicates with one or more edge computing devices. The fog computing device may be a relatively high-cost computing device that provides the capability fortraining machine learning algorithms for each edge computing device. The fog computing device may also provide orchestration and coordination services for the distributed Al architecture. Each edge computing device may be responsible for processing device data using a trained Al model fora separate building system. Each edge computing device may be responsible for monitoring or controlling a single building system, or potentially a relatively small number of building systems. The devices supplying device data to each edge computing device may be unique to each building system or there may be overlap with a device supplying device data for use in monitoring or controlling two or more building systems (on one or more edge computing devices). This use of a single, powerful fog computing device with a plurality of edge computing devices to monitor or control disparate building systems provides a scalable distributed Al architecture computing platform that may be extended through the provision of additional edge computing devices as required as new building systems are added or expanded.

[00125] Referring now to figure 1, this illustrates a device 101 and a distributed Al architecture comprising an edge computing device 102 and a fog computing device 103. For simplicity of explanation, in figures 1 to 6 only a single edge computing device 102 is illustrated. That is, these figures illustrate simplified deployment scenarios in which only a single building system is to be controlled or monitored using a single edge computing device 102. However, from the discussion above it will be apparent to the skilled person how this is scalable to the fog computing device 103 communicating with and providing machine learning algorithm training for multiple edge computing devices 102 associated with multiple building systems.

[00126] The edge computing device 102 communicates with at least one device 101 in order to receive device data. For instance, a device 101 may comprise a sensor, in which case the edge computing device 102 may be referred to as a sensing edge computing device 102. A sensor 101 may provide sensor data indicative of a sensed parameter for the building or the building system. In figure 1 for simplicity the edge computing device 102 is labelled simple Edge. A sensor 101 may for instance be an environment or air quality sensor 101, in which case the edge computing device may be referred to as an environment sensing edge computing device 102 (discussed in greater detail below in connection with figure 6). As is illustrated in figure 1, there may be only a single device 101 sending device data to the edge computing device 102. However, there may be a plurality of devices 101 providing separate device data to the edge computing device 102, as indicated by the dashed box Device x.

[00127] Figure 1 (and also figures 2 to 6 and 18, described below) are process flow diagrams in which system components (particularly the distributed Al architecture comprising the edge computing device 102 and the fog computing device 103) are illustrated at the top and by descending vertical lines. The exchange of information between system components is illustrated by interconnecting lines. Processes happening at each system component are illustrated upon the descending lines. These process flow diagrams may also be referred to as ladder diagrams. It should not be assumed that the exchange of information and processing illustrated define a strict chronology descending downwards, except where this is required or made apparent in the following description.

[00128] As well or instead, at least one device 101 may be a building system component. For instance, the building system may be ventilation system. It will be understood that in the context of the present document the term ventilation system is intended to encompass building systems including one or more element of heating and air conditioning as well as ventilation. A HVAC system, including an MVHR system, remains a ventilation system. A component of a ventilation system may include a fan arranged to provided component state information such as fan speed or airflow to the edge computing device. In some cases, as will be discussed below, such a system component may be configured to receive a control signal from the edge computing device operating a trained machine learning algorithm, particularly an inference model that has identified the component as an influence for the building system and seeks to control the building system through controlling the component. Where the device 101 comprises a system component the device data may comprise component data indicative of a component state. The component may include a sensor providing the component state information. The component state may indicate a setting or mode of operation for the sensor.

[00129] Where a plurality of devices is supplying device data for monitoring or controlling a building, the devices may include both sensors (for instance, supplying data indicating an environment parameter for the building) and system components relating to the building system being controlled or monitored. Examples of this are presented below in connection with figures 3 to 6.

[00130] As already noted, the edge computing device 102 receives device data from the at least one device 101 as indicated by arrows 104 (with the optional supply of device data from further devices indicated by dashed line 104). Only a single transfer of device data 104 is illustrated. However, it will be appreciated that the devices 101 may continuously, regularly, or periodically transfer device data to the edge computing device 102, and this may continue in parallel (that is, simultaneously or concurrently) to the other processes described below. This device data 104 is processed by the edge computing device 102 using a trained machine learning model that executes at step 109 on the edge computing device 102 to provide a model output, for instance an alert or message to a building occupant, or a control signal, for instance to control a component such as a fan. As will be well understood by the skilled person, a machine learning algorithm operates to map an input (or a series of inputs) to an output (for instance, a prediction of a future building state). Particularly, the trained machine learning algorithm executed by the edge computing device to process the received device data may be one or typically both of a predictive machine learning model and an inference machine learning model. Deep learning is a particular subfield of machine learning (and both are subsets of Al) that involves training artificial neural networks, which are composed of layers of interconnected nodes, to learn from vast amounts of data. Deep learning algorithms are typically used for tasks such as image recognition, natural language processing, and speech recognition, where they have achieved state-of-the-art results. Deep learning models are more complex than traditional machine learning models and require large amounts of data and computational power to train effectively. For the control of building systems, the present inventor has identified that deep learning is particularly suited, however in this document the generic term machine learning is used.

[00131] A predictive machine learning model is a type of machine learning model that uses historical data to make predictions or forecasts about future events or trends. These models use algorithms to analyse large amounts of data, identify patterns and correlations, and create a mathematical model that can be used to make predictions based on new data. An inference machine learning model is a machine learning model that has been trained on a dataset to learn to identify patterns and correlations in the data that allow it to identify factors within a system that influence a system state. Either or both of a predictive machine learning model (referred to herein for simplicity as a predictive model) and an inference machine learning model (referred to herein for simplicity as an inference model) may be executed by an edge computing device 102 for processing device data to monitor or control a building system. Figure 2 presents an example in which a single edge computing device implements both predictive and inference machine learning models and figure 5 presents an example in which the respective model types are implemented by separate edge computing devices.

[00132] A predictive machine learning model executed by the edge computing device 102 may process received device data 104 in order to make a prediction of a current or future building system state. An inference machine learning model executed by the edge computing device 102 may process received device data, including building system component state information and identify how building system components should be controlled in order to influence a predicted system state (for instance, a prediction of a current or future system state provided by a predictive machine learning algorithm). In its broadest sense however, the edge computing device 102 may operate a generic trained machine learning algorithm capable of providing a prediction ora control signal for an influencing a system state, and the distinction between predictive and inference machine learning algorithms may be arbitrary or not apparent.

[00133] Prior to execution 109 of a trained model, the fog computing device 103 performs the training of the machine learning algorithm. This training process is based upon a training data set of device data. As illustrated in figure 1, the edge computing device 102 may pass through the device data to the fog computing device 103 at step 106. Optionally (as indicated by the dashed box 105) the edge computing device 102 may also store the device data, particularly in the event that later execution 109 of the trained machine learning algorithm makes use of historic as well as current device data.

[00134] As illustrated, each device 101 associated with a particular building system provides device data at step 104 to the edge computing device 102, and this passes the device data through to the fog computing device 103 as required at step 106. This pass through of the device data may occur in real time - that is the edge computing device 102 forwards the device data to the fog computing device 103 substantially as it is received. In other embodiments, the transfer of device data may occur intermittently, for instance once a predetermined buffer of device data is filled. In some embodiments device data may only be provided to the fog computing device 103 in order to form a training data set. Once the machine learning algorithm is trained it may be that no further device data is provided to the fog computing device 103. However, especially where the fog computing device 103 periodically updates the training of the machine learning algorithm, the supply of device data from the edge computing device 102 to the fog computing device 103 may be an ongoing process.

[00135] It will be appreciated that the arrangement illustrated in figure 1 whereby for monitoring or control of a single building system the associated devices 101 communicate only with the respective edge computing device 102, which in turn forwards device data to the fog computing device advantageously provides a simple network topology. This is readily extendable to additional building systems whereby the fog computing device 10 need only communicate with a relatively small number of edge computing devices. However, there is no restriction to this particular network topology. Each device 101 may also communicate its device data directly to the fog computing device 103 in addition to the edge computing device 102. Optionally, in some examples or for some devices, device data may be sent to the fog computing device 103 and forwarded to the edge computing device 102 as required. There may be a blend by which some devices 101 communicate primarily with the edge computing device and some devices 102 communicate primarily with the fog computing device 103, or both (an example of which is presented in figure 3).

[00136] In one embodiment data collection is implemented by the edge computing device 102 whereby device data is sent to the edge computing device 102 until a given threshold of data records is reached, at which point a data transfer to the fog computing device 103 occurs and training may commence.

[00137] Once a sufficient training data set of device data is built up at the fog computing device 103 (not specifically illustrated in figure 1) then machine learning or deep learning techniques are applied by the fog computing device 103 at step 107 to train or generate a trained machine learning algorithm. The process of training the machine learning algorithm is described in greater detail below in connection with figures 8 to 10. It will be appreciated that the volume of training data required may be specific to the type of building system, the particular deployment scenario, or the selected machine learning algorithm. Once the model is trained, it is provided to the edge computing device 102 at step 108 for processing device data.

[00138] The received trained model is executed at step 109. The executing trained Al model receives and process device data received at steps 104 from the or each device 101. As an example, a device 101 may be configured to periodically send device data to the edge computing device 102 according to a duty cycle or as new data becomes available (or data may be buffered and transmitted periodically). The executing trained Al model uses newly received device data as well as, optionally, previously received device data, which may also include the training set of device data noted above. Outputs from the executing trained Al model including control signals as appropriate are output at step 110. Execution of the model at step 109 will be dependent on the nature of the selected and trained machine learning algorithm, as will be apparent to the skilled person. The model output 110 may comprise an output message or alert to a user indicating a state of the building or the building system or if the state or the building or the building system state is outside of a defined range. Alternatively, or additionally, the model output 110 may comprise a prediction of a current or future state for of the building or the building system. Alternatively, or additionally, the model output 110 may comprise a signal instructing a component setting or change of operation for a component forming part of the building system either immediately or a future point in time. The component may comprise one of the devices 101 that supplies device data to the edge computing device for processing using the trained model, or it may be a separate device. A model output may be provided through a local area network portal, a mobile device application or a display or touchscreen device within the building.

[00139] As hinted at above, and indicated by the dashed lines, in some cases device data may continue to be supplied at step 111 to the fog computing device 103 (indicated as via the edge computing device 102, though it could be direct) for updating the training of the machine learning algorithm at step 112. The updated training may be continuous or periodic. The model update may take account of the training set of device data, previously received device data and / or newly received device data. The updated model is supplied to the edge computing device 102 at step 113 which may then substitute the updated model for the previously received model for processing further device data (not illustrated).

[00140] Advantageously, the edge computing device can execute a predictive machine learning and / or an inference machine learning algorithm without relying on cloud computing, with all the associated disadvantages that entails, as set out above. Furthermore, while only a single edge computing device associated with a single building system is illustrated in figure 1, the solution is scalable in that a relatively low cost edge computing device may be associated with each building system and executing a respective trained machine learning algorithm, while a single (or smaller number) fog computing device may perform the more computationally expensive but less frequently required task of training the respective machine learning algorithms. In a test system established by the present inventor, an edge computing device was implemented on hardware costing under £100, while a fog computing device was implemented on hardware costing around £500 (2022 prices).

[00141] The range of device data that may be collected by an edge computing device may be extended to enable context awareness and situation awareness. In particular, sensors or other data sources capable of providing an indication of building occupancy (or the whereabouts of normal building occupants) greatly enhance the ability of a building system to be responsive to the needs of the building’s users.

[00142] Context awareness refers to a system’s ability to understand the context in which it is operating, such as the user’s location, preferences, and behaviour, as well as the state of the system and its environment. The goal of context awareness is to provide users with a more personalized and relevant experience, by adapting to their needs and preferences. Situation awareness, on the other hand, refers to a system’s ability to understand the current situation or environment in which it is operating. This includes being aware of the current state of the system and its environment, as well as any potential threats or hazards. As an example, an air quality monitoring and control system implemented may take account of the number (and optionally identity) of predicted building occupants when determining whether a predicted air quality measure is acceptable or whether it must be changed by control of ventilation system components.

[00143] Further examples of context awareness or situational awareness could include learning behavioural usage patterns of simple appliances like lighting, music, heating, ventilation, hot water, and even garden sprinklers. These behavioural models are not controlling the devices directly, rather the devices are observers, with habits learnt and improvements to the ecosystem proposed to other inference models. A further example could include computer vision inference being used to extend security or support a healthcare requirement like stopping someone falling down the stairs in an inference situational awareness model. Situational awareness involves not only understanding the behaviours and environment but also the situations itself. This could be a burglar breaking in with intent to harm, a potential fire, someone at harm doing DIY in the garden on a ladder that is not positioned correctly.

[00144] Referring now to figure 2, this is a process flow diagram comprising a modification to the distributed Al architecture of figure 1 in which both a predictive machine learning model and an inference machine learning model are executed upon the edge computing device 102. For figure 2, and also for figures 3 to 6 discussed below, where steps are the same as presented and described for an earlier figure, the same reference numbers are used, and the description is not repeated.

[00145] Figure 2 differs from figure 1 in that on receipt of the device data at step 106 the fog computing device 103 trains two machine learning algorithms to generate two trained models at step 201. Both a trained predictive model and a trained inference model are supplied to the edge computing device 102 at steps 202 and 203. Both trained models are executed by the edge computing device 102 at step 204 and one or both models may generate model outputs at step 205.

[00146] Particularly, the predictive machine learning model may be adapted to provide a prediction of a current or future state for the building or the building system. The inference machine learning model may be adapted to provide a control signal instructing a component setting or a change of operation for a component forming part of the building system either immediately or a future point in time to control or adjust a predicted state for the building system. In some embodiments the prediction from the predictive machine learning algorithm may comprise an input to the inference machine learning algorithm (optionally, along with device data relating to sensors or system components). The inference machine learning model allows for the identification of system components that influence a building or building system state and which may be controlled to adjust a prediction of a future state. Advantageously, the distributed Al architecture of figure 2 allows both a prediction of a current or future system state to be generated (which may or may not be provided to a user or building occupant) and the building system to be controlled to adjust the system state, for instance if the predicted system state falls outside of a predetermined range.

[00147] Referring now to figure 3, this is a process flow diagram comprising a modification to the distributed Al architecture of figure 1 in which both sensor data and data from a component 301 forming part of a building control system are processed to train a machine learning algorithm (or processed when the trained model is executed, or both) for monitoring or controlling a building system.

[00148] Accordingly, figure 3 illustrates at least one (optionally, plural as indicated by the dashed lines) sensors 101 providing sensor data to the edge computing device 102 at step 104 and at least one (optionally, plural as indicated by the dashed lines) system components 301 providing system component state data to the fog computing device 103 at step 302. Although not explicitly illustrated, in some embodiments the fog computing device 103 may provide the system component data to the edge computing device in an analogous way to the supply of sensor data from the edge computing device 102 to the fog computing device 103 at step 106. A further alternative is for the system components 301 to communicate systems component data to both the fog computing device 103 and the edge computing device 102, or primarily to the edge computing device. Optionally, the system component data may be stored by the fog computing device 103 at step 303. More generally, either of the edge computing device 102 and the fog computing device 103 or both may store any portion of data from the sensors 101 and the system components 301 for use in model training or model execution. Irrespective of the network topology, at step 107 the training of the machine learning algorithm may be based on a training data set comprising data from both sensors 101 and system components 301.

[00149] At step 109, as before the trained Al model processes data received from the devices 101 at step 104. Additionally, the trained Al model may process data received from the system components 301 at step 302 (either directly or via the fog computing device 103). That is, both the devices 101 and the system components 301 send data to the edge computing device 102 that is processed using the trained machine learning model at step 109 to generate model outputs.

[00150] At step 110, as before the trained machine learning model generates model outputs. Those outputs may comprise one or more control signals for controlling one or more of the system components 301. That control may be responsive to a prediction of a current or future system state.

[00151] Although not specifically illustrated, updating of the trained model at step 112 may also take account of further received system component data.

[00152] Figure 4 is a further refinement to the process flow diagram of figure 3 in which the fog computing device 103 trains both a predictive machine learning model and an inference machine learning model, as for figure 2, on the basis of both sensor data and system component data. As for figure 2, both trained models are provided to the edge computing device which may execute both models, processing received sensor data and / or system component data to provide model outputs (which may include control signals or data controlling the system components 301).

[00153] Figure 5 is a process flow diagram comprising a modification to the distributed Al architecture of figure 4 in which the distributed Al architecture further comprises both a sensing edge computing device 501 which executes a predictive machine learning model and a system edge computing device 502 which executes an inference machine learning model. The edge computing devices 501,502 both form part of a distributed Al architecture for monitoring or controlling a single building system. Each edge computing device 501, 502 may process both sensor data from sensors 101 and system component data from a component 301 forming part of a building control system. More generally, it may be that each edge computing device 501, 502 processes part or the whole of the available sensor and component data.

[00154] For clarity, in figure 5 (and also figure 6) the processing of updating the training of the machine learning models is not illustrated, though the skilled reader will appreciate that this process is analogous to that illustrated for figure 4.

[00155] As for figure 4 the distributed Al architecture includes a single fog computing device 103 which is responsible for machine learning algorithm training to generate both predictive and inference machine learning models at step 201, using part or the whole of the available sensor and component data. However, differing from figure 4, at step 503 the trained predictive model is supplied to the sensing edge computing device 501 and the trained inference model is supplied to the system edge computing device 502 at step 504.

[00156] Figure 5 illustrates an example embodiment in which the sensing edge computing device executes the predictive model at step 505 processing sensor data received from one or more sensors 101. The supply of device data to the executing predictive model at step 505 is not illustrated for clarity in figure 5. At step 506 the predictive model generates a model output, for instance a prediction of a current or future state of the building or the controlled building system based on the sensor data. However, in certain other embodiments the predictive model may also accept as inputs data from one or more system components 301. The output at step 506 may be a value for a current or future system state. Alternatively, the output may be an indication that a predicted value exceeds a threshold or falls outside of a predefined range. At step 507 either an indication that a threshold or range will be breached, ora predicted current or future value of the building system state (or both) is transmitted from the sensing edge 501 to the system edge 502 where it forms an input to the executing inference machine learning model at step 508.

[00157] Figure 5 illustrates an example embodiment in which the system edge computing device 502 executes the inference model at step 508 processing system component data received from one or more system components 301. The supply of system component state data to the executing inference model at step 508 is not specifically illustrated for clarity. However, in certain other embodiments the inference model may also accept as inputs data from one or more sensors 101. Furthermore, the inference model receives as an input a prediction of a system state or an indication that this falls outside of a predefined range from the predictive model executing on the sensing edge 501. The executing inference model generates an output at step 509. The outputs from the inference model comprise control data 510 that is supplied to system components 301 at step 510.

[00158] The control data output 510 comprises settings or instructions for control of building system components 301 to maintain the state of the system within normal operational bounds. The provision of a separate system edge computing device 502 allows for closer integration between the control of the building system and the building system components 301. Such improved control may include Digital Signal Processing (DSP) based control of system components, for instance a ventilation fan, as opposed to conventional digital control whereby components are typically only switched on or off.

[00159] Furthermore, where a prediction or indication that a prediction falls outside of a defined range is received by the inference model at step 508, the close integration between the system edge and the system components allows for more flexible control of the system components 301 to adjust the system to ensure that the system state remains in a predefined range. An example of this is presented in figure 6. Figure 6 is like figure 5 for the specific example of an air quality monitoring and control system based on the same distributed Al architecture of figure 5. Sensors 101 are now identified specifically as environment sensors, for instance temperature, pressure, humidity, particulate matter, and certain gases. This sensor data is processed by an environment sensing edge 501. The building system is specifically a ventilation system. In one example, this may be an MVHR system, which may be referred to as a “smart MVHR system” through its integration with a ventilation system edge 502. The ventilation system components 301 may include fans, valves, heaters, and other conventional components of a ventilation system. The ventilation system components 301 may be configured to provide data indicative of a setting or state such as a fan speed, airflow or whether a valve is open, and to receive control data to control those states.

[00160] At step 505 the environment sensing edge executes a predictive model based on sensor data (and optionally state data for components of the ventilation system). It forms a prediction at step 506 fora current or future measure of air quality for the building. If this falls outside of accepted bounds then at step 507 an output is passed to the inference model executing on the smart MVHR, which is adapted to adjust the operation of the ventilation system components so as to prevent the air quality falling outside of the accepted bounds. As an example, if it is predicted that air quality will reduce at a future time, then in advance of that time point the ventilation system may be adjusted to increase the supply of fresh air into the home.

[00161] Although not specifically illustrated in figure 6, as well as sensor data the predictive model may also receive data from other sources. For instance, occupancy sensors, for instance cameras may detect how many people (and optionally, which particular people) are present in a home at a given time. Through observation of typical occupancy patterns the training of the predictive model may take account of how many people and which people are typically present within a home at different times of day and days of the week. This may be correlated during the training process with observed fluctuations in air quality which may correspond to activities within the home, for instance showering or cooking at "normal" times of day. This information about occupancy enables a degree of situational awareness to be built into the building system monitoring and control: a prediction of a future reduction in air quality may result from a prediction that based on observed behavioural patterns for building occupants it is likely that the activities of the building occupants within the home will lead to a drop in air quality at a future time.

[00162] Furthermore, the operation of the inference model may be optimised to not only address a predicted drop in air quality, but to do so in an efficient manner (for instance, adjusting heating or ventilation components such that they operate in advance of the predicted low air quality during times where energy prices are lower or where electricity is predominantly supplied by low carbon sources.

[00163] The predictive model may be further trained and respond to other data sources. For instance, particularly for the example of an air quality monitoring and control system, weather forecast data may be received through a network connection (as described below in connection with figure 13), which may affect how the ventilation system is to be controlled to remain within acceptable bounds. Information received from outside of the home may also include occupancy information, for instance mobile device location data indicating the whereabouts of frequent building occupants and calendar information indicating the likely future whereabouts of frequent building occupants.

[00164] Referring now to figures 7a and 7b, as noted previously, while the presently described techniques are applicable to buildings in general, they are particularly to suited to domestic premises such as houses and apartments (referred to generically in this document as homes). Partly this is because the daily routines of people within a home and the range of activities that take place within a home are significantly more complex than for industrial, retail, or commercial premises, with the result that the ability to implement situational awareness functions described above taking account of building occupancy are especially beneficial. Figure 7a is a perspective view of one particular form of home, and figure 7b illustrates a cross section plan view of such a home incorporating a distributed Al architecture for monitoring or controlling air quality.

[00165] Figures 7a and 7b, show a home 700 which is constructed as a hybrid building 700 (which may also be referred to as a modular building). The hybrid building 700 comprises a first building section 701 and a second building section 702. The first building section 701 can take the form of a dock. The term “dock” is used to describe a building section to which another building section may be docked, installed, connected, or attached. The first building section 701 is an on-site construction at a final location of the building 700, which may be a fixed, on-site location. That is, the building 700 has a final, fixed, on-site location. In this exemplary embodiment, said final, fixed, on-site location is determined by construction plans and fixed by virtue of building foundations. The term “on-site location” is used to refer to the building site, which will be understood to refer to the immediate proximity of the building 700 and the entire building site, including housing estate, on which the building 700 is to be built. It will be understood that the site may be a large building / construction site comprising a plurality of plots, the final location for the building 100 being provided by one of said plots.

[00166] The second building section 702 can take the form of a module. The term “module” is used to describe a building section which may be docked to another building section or is installable, connectable, or attachable to another building section, particularly a first building section in the form of a dock. The second building section 702 is transportable to the final location in a substantially assembled form.

[00167] During construction of the first building section 701 at the on-site location, the first building section 701 is preconfigured to receive the second building section 702. That is, the first building section 702 is constructed with the knowledge and design that a second building section is to be subsequently connected, and the first building section 701 is thus preconfigured for connection and receipt of the second building section. The second building section 702 may be removable. This could relate to the shaping of the first building section 701, through to sealing and connection features. The second building section 702 is connected to the first building section 701 at the final location of the building 700, thereby to provide said building 700 at the final, fixed, on-site location.

[00168] The first building section 701 further includes a services hub 703, which may include part or the whole of certain building systems. For instance, for a ventilation system, the services hub 703 may include ventilation system components such as the pumping and heat exchange elements of an MVHR.

[00169] Figure 7b shows the system edge computing device 502 and the fog computing device 103 located within the services hub along within at least one system component 301, though it will be understood that this location is merely exemplary, and the system edge 502 and the fog computing device 103 may be located at any convenient location. Similarly, the sensing edge computing device 501 is shown located within the first building section 701, though it may be located at any convenient location. Figure 7b shows a range of sensors 101 and system components 301 distributed through the first and second building sections 701,702. It will be understood that their locations are determined according either to optimal placement for sensing or where required to form an effective part of the building system. The sensors 101, system components 301, fog computing device 103 and edge computing devices 501,502 may be connected wirelessly, as will be described in greater detail below in connection with figure 13.

[00170] Referring now to figure 8, this is a flow chart illustrating a process of training and implementing a machine learning algorithm for monitoring or controlling a building system where a distributed Al architecture is deployed within a building. As an example, this may relate to the air quality monitoring and control of figure 6. Figure 8 specifically relates to an example in which a machine learning model for monitoring and controlling air quality has been previously established but is to be newly deployed within a building such as the hybrid home of figures 7a and 7b. It will be understood that the behaviour of a specific building regarding patterns of air quality must first be observed during a training process.

[00171] At step 801 the fog computing device 103 collects device data relating to the environment sensors 101 and the ventilation system components 301. As previously described, this data may be received via the sensing or system edge computing devices 501,502 or directly from the sensors 101 or ventilation system components 301. Data is collected until a sufficiently large training data set is established. The size of that data set may be dependent on a particular building, but for instance may comprise a period of several days, weeks or months. It will be understood that during that time the ventilation system may be controlled by the ventilation system edge 502 according to a default or less fully featured control algorithm.

[00172] At step 802 once the training data set is established then the machine learning algorithm or algorithms may be trained, for instance using machine learning or specifically deep learning techniques. This may include, for instance, Exploratory Data Analysis (EDA), clustering machine learning techniques such k-means for correlation matching, machine learning gradient descent fit regression algorithms and deep learning Long Short-Term Memory (LSTM) to generate trained predictive and inference models. This training process is described in greater detail in connection with figure 10, below. The trained model or each of a predictive model and an inference model are supplied to the edge computing device 102 or respective edge computing devices 501,502.

[00173] At step 803 the edge computing device 102 or each of the edge computing devices 501, 502 receive device data from sensors and / or system components and at step 804 the edge computing devices 501,502 implement the trained models. Appropriate model outputs such as alerts, or control signals are generated at step 805.

[00174] Figure 9 is a modification to the flow chart of figure 8 further illustrating a method of updating the training of a machine learning algorithm for monitoring or controlling a building system. Specifically, figure 9 illustrates a feedback loop whereby in addition to the collected device data at step 803 being supplied to the edge computing device for implementing the machine learning algorithm at step 804, it is further supplied to the fog computing device 103 for updating the machine learning algorithm at step 901. Once an updated machine learning algorithm is generated then the updated algorithm is implemented at step 804.

[00175] Figure 10 is a modification to the flow chart of figure 8 further illustrating a more detailed method of training of a machine learning algorithm for monitoring or controlling a building system. The training method of figure 10 may be applicable to training a machine learning model for the first time, though it will be understood that part or the whole of the method of figure 10 may be applicable when deploying a previously identified model algorithm for the first time in a new building.

[00176] As for figures 8 and 9, the method of figure 10 begins with the collection of device data at step 801. Particularly where a new type of building system is considered for model development, it may be that a considerable period of data collection may be required to generate a training data set for model development, for instance over a period of days, weeks, or months. It may be that the data collection phase comprises collecting data from a large number of devices including sensors and system components, whereas during model development it may be that some data sources may be excluded as not being significant influences on the building system or not generating significant data for the generation of model outputs such as predictions and control signals. Step 801 may further include removing missing values, handling outliers, normalizing the data, and encoding categorical variables.

[00177] At step 1001 algorithm type may be evaluated. This may be a largely manual process, or it may be at least partially automated through analysis of the device data and an understanding of type of monitoring or control outputs that are required. Essentially step 1001 comprises selection of a suitable machine learning algorithm for us in the building system. It may be that more than one algorithm is evaluated and tested, or trained, before the most suited algorithm is selected. Particularly, deep learning algorithms based on exploitation of a neural network may be evaluated and selected for model development. The skilled person will be aware of suitable machine learning algorithms that may be deployed. However, suitable examples include linear regression, logistic regression, decision tree, SVM algorithm, naive Bayes algorithm, KNN algorithm, K-means, random forest algorithm, dimensionality reduction algorithms, gradient boosting algorithms, gradient descent fit algorithms, Long Short-Term Memory (LSTM) and the AdaBoost algorithm.

[00178] At step 1002 data types are prepared. This comprises a process of identifying the data sources from the collected device data at step 801, identifying the data format including the precision and update frequency of the collected data, and defining data types to be provided to the algorithm type or types evaluated at step 1001. Step 1001 may further include transforming the data into a format that can be used by the machine learning algorithm. This may involve removing missing values, handling outliers, normalizing the data, and encoding categorical variables.

[00179] At step 1003 Exploratory Data Analysis (EDA) is performed based on the collected device data. Exploratory data analysis (EDA) in machine learning refers to the process of analysing and understanding data to extract insights, patterns, and trends. During EDA, the data is analysed for missing values, outliers, skewness, and other data quality issues. Data distributions and correlations are explored using summary statistics and visualization techniques, such as histograms, box plots, scatter plots, and heatmaps. EDA also involves the identification of potential features and the formulation of hypotheses that can be tested through machine learning models. EDA is an essential step in machine learning because it helps to identify the distribution and characteristics of the data, understand relationships between variables, detect outliers and anomalies, and ultimately prepare data for modelling. EDA typically involves techniques such as data visualization, statistical analysis, and data summarization. The goal of EDA is to gain a better understanding of the data and inform decisions about feature engineering, model selection, and other important aspects of the machine learning process. Ultimately, EDA helps to ensure that machine learning models are trained on high-quality data, which is critical for achieving accurate and reliable predictions.

[00180] At step 1004 the machine learning algorithm is built, taking account of the model selection and prepared data types from the preceding steps.

[00181] At step 802 the machine learning algorithm is trained. Training the model involves using the data to adjust the model parameters so that it can accurately make predictions or decisions. For instance, this may involve defining a loss function that measures the difference between the model predictions and the actual outcomes, and using an optimization algorithm to minimize this loss function. At step 1005 the machine learning algorithm is evaluated. Evaluation may involve testing the performance of the trained model on a separate dataset to determine how well it generalizes to new data. This may require the collection of further data, or it may be that the data collected at step 801 is partitioned into two parts, a first part for model training and a second part for model evaluation. This may involve computing various performance metrics, such as accuracy, precision, recall, and F1 -score.

[00182] At step 1006 the model may be fine-tuned, for instance if certain data sources or data types are found to not be influential in monitoring or controlling the building system they may be excluded. Or it may be that model prediction accuracy indicates that further data sources may be required. As an example, for a system modelling air quality within a home it may be identified that more environment sensors covering particular portions of the home may be required.

[00183] At step 1007 the model is deployed. For instance, this may comprise the step of supplying the trained model to an edge computing device as described above in connection with figures 1 to 6.

[00184] Turning now to figure 11, this is a flow chart illustrating a method of operating an edge computing device for monitoring or controlling a building system. In certain embodiments, the edge computing device serves to receive some or all the device data at step 1101, optionally store the device data step 1102 and supply the device data to the fog computing device at step 1103 for model training. However, as noted above, while this arrangement is logical and readily scalable for other building systems, if may be that some or all the devices supply data also or primarily to the fog computing device.

[00185] At step 1104 the edge computing device receives one or more trained machine learning algorithms from the fog computing device for monitoring or controlling a building system. At step 1106 the trained algorithm is executed for processing device data received at step 1105, and model outputs are generated at step 1107. Optionally, though not illustrated in figure 11, device data received at step 1105 may be supplied to the fog computing device for updating the training.

[00186] Turning now to figure 12, this is a flow chart illustrating a method of operating a fog computing device fortraining a machine learning algorithm for monitoring or controlling a building system. Device data is received at step 1201, either via the edge computing device or directly (or a combination of both). At step 1202 the machined learning algorithm is trained, for instance according to the method of figure 10. At step 1203 the trained algorithm is supplied to the edge computing device for implementation.

[00187] At step 1204 the fog computing device receives further device data which is used for updating the training at step 1205 such that an updated trained algorithm may be supplied to the edge computing device at step 1206.

[00188] Figure 13 is a network topology diagram fora distributed Al architecture. Specifically, figure 13 is a network diagram showing a distributed Al architecture within a building such as a home. A single fog computing device 103 is illustrated. This is communicating with a sensing edge 501 and a system edge 502 according to the embodiment of figure 5, (for instance, for monitoring or controlling a building ventilation system as illustrated in figure 6). However, in some examples there may only be a single edge computing device 102 for controlling a building system (for instance according to the embodiments of figures 1 to 4).

[00189] Furthermore, as previously described, a key advantage of certain described embodiments is that it is scalable for controlling multiple building systems within a building, for instance a home, with a single fog computing device (or a low number of fog computing devices) providing machine learning algorithm training and providing those trained models to an array of edge computing devices associated with the multiple building systems. Each building system may be associated with one or more edge computing devices. In some cases, an edge computing device may execute trained machine learning models for more than one building system, particularly where there is overlap in the devices that provide data to be processed by those models, as discussed below. Accordingly, figure 13 illustrates this scalability by the representation of additional sensing edge computing devices 501 or system edge computing devices 502 indicated by dashed lines. Furthermore, the fog computing device 13 provides further orchestration and coordination services for the control of the multiple building systems.

[00190] Figure 13 further illustrates a variety of devices that provide device data for training a machine learning model or to be processed by a trained model. For instance, there may be at least one sensor 101 (and optionally multiple sensors as indicated by the dashed lines). Alternatively, or in addition, there may be at least one building system component 503 and optionally multiple building system components as indicated by the dashed lines). In some embodiments it may be that each sensor 101 or system component 503 is associated only with a single building system that is monitored or controlled by a single edge computing device 501,502. However, in other embodiments I may be that at least one sensor 101 or system component 503 is associated more than one building system, and those building systems may be monitored or controlled by one or more edge computing device 501,502. It will be understood that the arrangement of sensors 101, system components 503 and edge computing devices 501,502 will be context dependent for the particular building and building systems to be monitored or controlled. In particular, the precise way in which device data is communicated through the distributed Al architecture will be implementation specific.

[00191] The sensors 101, system components 503, edge computing devices 501,502 and fog computing device 103 communicate with one another through a building network 1301. This may a wired or a wireless network. The presently described embodiments are not limited to the nature of the network, nor the communication protocols used to communicate across the network. However, as one example, the Matter protocol, formerly known as Project CHIP (Connected Home over IP), is an open-source standard for smart home devices which may be used, at least for communicating device data from sensors 101 and system components 503 and optionally control data for the system components 503. The Matter protocol specification is defined by the Connectivity Standards Alliance and is available at the following URL: https: / / csa-iot.org / all-solutions / matter / . The goal of the Matter protocol is to create a unified, secure, and reliable standard for smart home devices, so that they can work seamlessly with each other and with different ecosystems. In certain examples the edge computing device and the fog computing device may be Matter compliant so as to be able to receive device data from standard Matter compatible smart home sensors and system components. In some cases, off-the-shelf Matter compatible home devices may be used to form sensors or system components, with the edge computing device or the fog computing device configured to receive the communicated information in addition to or in place of a conventional data end point for those off-the-shelf components.

[00192] The interoperability Matter protocol is designed to work with a variety of wired and wireless technologies, including Wi-Fi, Bluetooth Low Energy, and Thread. That is, the building network 1301 may suitably be any conventional wireless network. The Matter protocol defines a set of common communication physical layer protocols, security mechanisms, and different vendor device profiles that can be used by smart home devices to communicate with each other within a single ecosystem.

[00193] Thread is a low-power, wireless networking protocol designed for smart home and Internet of Things (loT) devices. Thread is based on the IEEE 802.15.4 standard for low-rate Wireless Personal Area Networks (WPANs). The Thread specification is defined by the Thread Group and is available at the following URL: https: / / www.threadgroup.Org / support#specifications. It uses a mesh networking architecture, which allows devices to communicate with each other directly or through other devices in the network. This means that Thread can provide a reliable and flexible network for smart home devices, even in environments with many devices and obstacles.

[00194] One of the key advantages of Thread is its low power consumption. Thread-enabled devices can operate on small batteries for months or even years, depending on the usage. This makes it ideal for smart home devices such as sensors and switches, which need to operate for long periods of time without requiring frequent battery replacements.

[00195] Figure 13 further illustrates a router 1302 coupled to the building network 1301. In some embodiments the router may control the building network 1301, for instance where the building network is a Wi-Fi network and the router 1302 acts as a Wi-Fi access point. The router 1302 links the distributed Al architecture to the internet, and particularly to cloud computing services indicated by cloud 1303. The fog computing device 103 may be combined with or implement the functionality of a router 1302 such that no separate router 1302 is required.

[00196] An edge computing device and a fog computing device comprise a distributed Al architecture for monitoring or controlling building systems such that building systems may be controlled more effectively without recourse to cloud computing to execute Al algorithms. That is, the edge computing layer and the fog computing layer do not require there to be an available cloud computing layer to implement the above described techniques. However, in some examples, coordination with cloud computing services may be desirable. As an example, data from building systems may be collected and stored in the cloud 1303. Data from multiple buildings (each implementing their own distributed Al architecture) may be aggregated which may allow for greater insights to be gathered in how building systems operate. This may in turn guide the development of enhanced building control algorithms in the future.

[00197] Furthermore, the presence of a router 1302 and access to cloud computing services allows for additional data to be collected for use in training and executing building control Al models. As noted previously, for monitoring or controlling a ventilation system it may be desirable to obtain information about forecast weather or occupancy information from an outside data source.

[00198] Figure 14 illustrates an edge computing device 102 (or 501,502) forming part of a distributed Al architecture. The edge computing device comprises a processor 1401, memory 1402 and some form of input / output device 1403 configured to communicate with other devices across a network, for instance the building network 1301 of figure 13. The memory 1402 stores executable instructions that, in response to execution by the processor 1401, cause the edge computing device to perform the method described above in connection with figure 11 or any of the other functions described above in connection with the other embodiments. The input / output device 1403 allows the edge computing device to communicate with devices such as sensors 101 and system components 503 for receiving device data and transmitting control data, as well as to communicate with the fog computing device 103. In particular, the edge computing device receives a trained Al model (or an update to the trained Al model) from the fog computing device, which is stored in the memory 1402. The processor 1401 executes the trained Al model and uses this to process device data.

[00199] According to certain embodiments, the edge computing device may be a relatively low cost computing device so long as it has the computational capacity to execute a trained Al model. For instance, for monitoring or controlling some building systems a Raspberry Pi computing device may be used, and is available from Raspberry Pi Ltd and described at the following URL: httrB: / / www.raspberwpi.com / . Advantageously, the edge computing device incorporates hardware support for predictive or inference Al acceleration.

[00200] Figure 15 illustrates a fog computing device 103 forming part of a distributed Al architecture. The fog computing device comprises a processor 1501, memory 1502 and some form of input / output device 1503 configured to communicate with other devices across a network, for instance the building network 1301 of figure 13. The memory 1502 stores executable instructions that, in response to execution by the processor 1501, cause the fog computing device to perform the method described above in connection with figure 12 or any of the other functions described above in connection with the other embodiments (particularly in relation to training a machine learning algorithm as described in connection with figures 8 to 10). The input / output device 1503 allows the fog computing device to communicate with devices, particularly edge computing devices 102, 501,502 and optionally communicate directly with sensors 101 and system components 503. In particular, the fog computing device receives device data to form a training data set and uses this to train a machine learning algorithm to then provide a trained Al model (or an update to the trained Al model) to an edge computing device.

[00201] According to certain embodiments, the fog computing device may be a relatively expensive computing device (relative to an edge computing device) in order to provide the computational capacity to train a machine learning algorithm in support of an edge computing device to execute the trained algorithm. For instance, suitably an NVIDIA Xavier computing device may be used, which is available from Nvidia Corporation and described at the following URL: https: / / www.nvidia.com / en-gb / autonomous-machines / embedded-systems / jetson-xavier-nx / . Nvidia Xavier computing devices provide for hardware Al acceleration allowing for machine learning algorithm training within the building. In some embodiments, Al acceleration (and in particular, Al inference acceleration) may be provided by leveraging multiple Graphics Processing Units (GPUs) within the fog computing device in parallel.

[00202] For at least one building system where a plurality of building control systems is monitored or controlled it may be that in addition to the fog computing device training a machine learning algorithm adapted for monitoring or controlling that system, the fog computing device also executes the trained Al model to process received device data. While a key advantage of certain described embodiments is scalability through the separation of training and prediction or inference execution, in some situations it may be desirable for the fog computing device to additionally be responsible for model execution.

[00203] In addition to their functions described above, at least one edge computing device or fog computing device may receive device data from at least one controllable device within or associated with the building, process the device data using a control algorithm, and return a control signal to the controllable device. In particular, techniques have been described suitable for controlling complex building system, including those with multiple sensor inputs and system components that influence system states, there may be relatively simple systems or single device that require a degree of control but may not require the use of Al. Spare computing capacity upon one of the devices within the distributed Al architecture may suitably be used to achieve that control. For instance, a relatively simple device that may require control may include a kitchen appliance, for instance an oven, microwave, refrigerator, freezer, or dishwasher; a utility appliance, for instance a clothes washing machine or tumble drier; or a home entertainment device, for instance a television or other audio or visual device.

[00204] Figure 16 illustrates a building or building system sensor device 101 configured to communicate sensor data to a distributed Al architecture. At a minimum the sensor device 101 comprises a sensor 1601 capable of generating sensor data indicative of at least one sensed parameter and some form of input / output device 1602 configured to communicate that sensor data to other devices (particularly, edge computing devices) across a network, for instance the building network 1301 of figure 13. The sensed parameter may be an air quality parameter, for instance temperature, humidity, CO2, and particulate matter (for instance, 2 nm, 2.5 or 10 nm particulate matter). It will be appreciated that in other embodiments the sensor device 101 may include further components, for instance memory configured to buffer sensor data for periodic transmission and a processor to control the other parts.

[00205] Figure 17 illustrates a building system component 301 configured to communicate component data to a distributed Al architecture. At a minimum the building system component 301 comprises an actuator 1701 capable of providing system data indicative of an actuator state and some form of input / output device 1702 configured to communicate that system data to other devices (particularly, edge computing devices) across a network, for instance the building network 1301 of figure 13. The input / output device 1702 may further receive control data to control the actuator 1701. The actuator may be part of a ventilation system, for instance a fan motor, such that system data provided by the action 1701 may be fan speed and the control data may instruct a change in fan speed. It will be appreciated that in other embodiments the building system component 301 may include further components, for instance memory configured to buffer system data for periodic transmission and a processor to control the actuator in response to received control data.

[00206] Turning now to Figure 18, this is a process flow diagram corresponding to a modified form of the distributed Al architecture of figure 6 for the example of monitoring or controlling a ventilation system. Specifically, as noted previously, context awareness and / or situation awareness can be provided as part of monitoring or controlling a building system. Figure 18 is one example of how this may be implemented.

[00207] Figure 18 corresponds to figure 6 except as noted below and those parts of the system and flows of information indicated by the same reference number should be considered to be the same, and so will not be described.

[00208] Figure 18 differs from figure 6 firstly in that the ventilation system components 301 do not provide component state information 302 to the fog computing device 103 for training the Al models, though in other variants of the embodiment of figure 18 training of the Al models may continue to be based in part on component state data in addition to sensor data, for the purposes of predicting air quality and controlling the ventilation system components.

[00209] As for figure 6, a predictive Al model is trained by the fog computing device 103 and executed by the environment sensing edge 501 at step 505 for the purpose of forming predictions relating to air quality within the building. As for figure 6, an inference Al model is trained by the fog computing device 103 and executed by the system sensing edge 502 at step 509 for the purpose of controlling components of the ventilation system which the trained model has learnt influence the output of the predictive Al model. Specifically, as for figure 6, the inference model receives as an input a prediction from the predictive model, for instance a prediction that a predicted air quality will fall outside of an air quality or system state range (that is, corrective action is required). The inference model generates control data outputs 510 that are provided to components of the ventilation system that influence the predictive model output to seek to ensure that predicted air quality does not exceed the state range (for instance, to ensure that air quality stays within safe limits).

[00210] Figure 18 differs from figure 6 in that as well as training predictive and inference models based on sensor data (and optionally ventilation system component data), the fog computing device 103 further trains an observational Al model or a reinforcement learning model that is executed by the system edge 502.

[00211] An observational Al model is a type of machine learning model that is designed to learn patterns and relationships in data, in this context the behaviour of a ventilation system by observing and analysing it, without any direct intervention or feedback from humans. Observational Al models are often used fortasks such as anomaly detection, prediction, and classification, where the model is trained on large amounts of data to identify patterns or relationships that can be used to make accurate predictions or classifications on new data. These models are typically trained using unsupervised learning methods, where the model is left to identify patterns in the data without being explicitly told what to look for.

[00212] A reinforcement learning Al model is a type of machine learning model that learns to make decisions based on trial and error through interacting with an environment. It involves an agent that is trained to take actions in an environment to maximize a cumulative reward signal, which is a scalar value that measures the agent's success in achieving its goals. In reinforcement learning, the agent learns by receiving feedback in the form of a reward signal based on its actions. The agent tries to maximize the cumulative reward overtime by choosing actions that lead to higher rewards and avoiding actions that lead to lower rewards.

[00213] In the embodiment of figure 18 it is specifically a reinforcement learning model that is executed by the system edge computing device. The purpose of the reinforcement model is to observe and record the states and actions of components of the building system, in this context the ventilation system, and the states and actions of the building occupants. Specifically, at step 1801 observations of the control data sent to the ventilation system components (and optionally the ventilation system component state data) are stored and transmitted to the fog computing device at step 1802. In some cases, this information may not be stored first. As previously described, the fog computing device 103 is also in receipt of environment sensing data indicative of air quality, and also occupancy information relating to the building occupants.

[00214] The purpose of the reinforcement model is to determine what patterns exist within the data, not to control the components devices itself. For the specific example of figure 18 the observations used to train the reinforcement model in relation to air quality and a ventilation system may include: • What air quality threshold or range is set. • Current and historic air quality data. • Algorithm banding for the reinforcement model. • When the occupants are present. • How long building occupants are present. • Time of day that building occupants are present. • How long the inference model and the control data to the ventilation system takes to achieve a desired level. • How much power is needed.

[00215] These metrics are indexed with a machine learning algorithm, classified and a decision discovery machine learning or deep learning algorithm applied.

[00216] The trained reinforcement model is provided to the system edge 502 at step 1803 and executed at step 1804. At step 1805 the executing reinforcement model provides an input to the predictive model. This enables the reinforcement model not only to consider the raw metrics but also behavioural perceptions. An example of this is the reinforcement model adjusts the air quality threshold within safe limits of the banding autonomously without any human intervention if the occupant does not disagree with the change, then the change becomes the threshold.

[00217] The reinforcement model not only considers the raw metrics of the building system component usage but can adjust thresholds autonomously through behavioural perceptions with a condition of safety limits or threshold banding. In the event that the occupant does not raise a concern to the change, the change becomes the new threshold.

[00218] Advantageously, this additional use of a reinforcement model allows for habits and preferences of specific building occupants to be learnt without human intervention, which create historic datasets for future usage and prediction. This can help to reduce energy consumption due to learning new occupant thresholds, for instance for a comfortable heating range.

[00219] There will now be described methods of addressing poor indoor air quality that can be combined with or built off the above described methods of controlling building systems.

[00220] Embodiments of the present invention address poor indoor air quality through a novel combination of one or more fixed air quality sensors that may be distributed through an indoor space such as a room or whole building and a robot that is able to navigate through the building either to perform localised air purification or to provide supplementary air quality measurements. Indoor air quality may be improved by performing air purification where it is most required, which may be at locations remote from fixed ventilation or air purification devices or close to sources of pollution. At the same time, a more efficient robotic air purification system is provided, for instance because the robot need only be operated when the fixed sensor network indicates that it is required. Furthermore, an improved understanding of the variance of indoor air quality may be provided by supplementing the fixed air quality sensor data with air quality data measured as the robot traverses the building.

[00221] Turning to figure 19, this illustrates a floorplan for a building 1900 within which a robot may be operated to perform air purification or to measure air quality. For simplicity, only a single room 1900 is illustrated though of course this is extensible to any building layout, for instance interconnected rooms. The building 1900 includes a plurality of objects 1901, such as furniture, internal room dividers or anything else around which a robot 1902 must navigate, as is expanded upon in the following description. The building 1900 further includes a fixed ventilation system comprising an air inlet 1903 at one side of the room and an air outlet 1904 upon another side of the room. It will be appreciated that this is only one example and any combination of known, fixed ventilation or air purification devices may be provided within the room, and which can be activated in the event that poor indoor air quality is detected. In the example of figure 19 the ventilation system may comprise part of an MVHR system, a PIV system (combined with an outlet), an air conditioning system or any other known ventilation system type. The present invention is not directly concerned with the nature of any fixed ventilation or air purification system, only whether one is provided within a building and whether it can be activated upon demand, as discussed below.

[00222] The room further includes first and second fixed air quality sensors 1905 which are shown mounted roughly upon diametrically opposite sides of the room. It will be appreciated that there may be any type, number, or distribution of air quality sensors within a building 1900, including the option for there to be only a single fixed air quality sensor. The air quality sensors 1905 may, for instance comprise particulate matter sensors, for instance adapted to measures levels of particulate matter in an air sample. Known particulate matter sensors can provide air quality data indicating levels of particulate matter down to a minimum particle size of 10 microns, 4 microns, 2.5 microns, or even 1 micron. Furthermore, the air quality sensors 1905 may be adapted to provide air quality data in respect of other environmental parameters, for instance level of gas such as CO2, temperature, humidity, or any other factor known to be used to characterise indoor air quality. The air quality sensors 1905 may further provide air quality data giving an indication of air quality based upon a combination of different sensed parameters. The present invention is not directly concerned with the nature of the air quality sensors or the type of air quality data that they can provide, only how this may be interpreted and used to control a robot, as discussed below. Figure 19 further shows an air quality data dead spot 190, roughly equidistant between the air quality sensors 1905. It will be appreciated that a dead spot comprises a region of the building 1900 remote from a fixed air quality sensor 1905 and / or for which it is possible that there could be a significant deviation from the air quality data measured at the fixed sensor 1905. That is, a dead spot comprises a location where the air quality is unknown. Depending upon the size, shape, and layout of a building, there may be multiple dead spots 1906 within a building. The number of dead spots 1906 may also depend on the number, type, and distribution of air quality sensors.

[00223] Figure 19 further shows robot 1902 and robot docking station 1907. An exemplary robot 1902 is shown in figure 20. The robot docking station 1907 may comprise a location to which the robot 1902 returns after use. It may provide power to the robot 1902, for instance through a wireless charging mechanism. In some examples there may be no such docking station. It will be appreciated that a robotic air purification system or air quality measurement system is not new, perse, for instance one is disclosed in US-10443874-B2 discussed in the background section above. Accordingly, the configuration of a robot and any docking station is not germane to the present invention and not further discussed beyond the schematic illustration of figure 20.

[00224] Figure 20 schematically illustrates the robot 1902. The robot 1902 comprises one or both of an air purification system 2000 and an air quality sensor 2001. These may be of any known type. The robot 1902 further comprises some form of propulsion 2002. This may be of any suitable type. For instance, the robot 1902 may be mounted on wheels that are electrically driven, in a manner that is well known for robots including in domestic settings, such as robot vacuum cleaners. The robot 1902 further comprises some form of power supply 2003, for instance a battery and a wireless charger to operate in connection with the robot docking station 2005. Robot 1902 further comprises a processor 2004 and a memory 2005 to store computer program code executed by the processor 2004 to control the various functions of the robot 1902.

[00225] Turning now to figure 21 a method of purifying air within a building using a robot according to an embodiment of the present invention will now be described. Figure 21 is a process flow diagram illustrating processes happening at robot 1902, and first and second air quality sensors 1905 within a building. The robot 1902 and the sensors 1905 may be the same as described above in connection with figure 19. However, of course, the method of figure 21 is not limited to the specific floor plan for figure 19. For instance, there may be any number of air quality sensors 15 throughout the building, including the option that there may only be a single air quality sensor 1905.

[00226] At step 2100 the robot 1902 scans a network to detect one or more air quality sensors 1905. For instance, the sensors 1905 may be configured to wirelessly broadcast their measured air quality data. Or the sensors 1905 may transmit air quality data only to the robot 1902 (directly or indirectly).

[00227] At steps 2101 and 2102 the robot 1902 requests air quality data from each respective air quality sensor 1905 detected through the network scan 2100. It will be appreciated that this process is only one example. In other embodiments of the invention the network scan 2100 may not be required (for instance, necessary if the robot 1902 is already in possession of this information), or not required everytime air quality data is to be requested. Furthermore, the air quality sensors 1905 may push the air quality data to the robot 1902 such that no specific request is required.

[00228] At steps 2103 and 2140 the robot 1902 receives air quality data measured at the or each fixed air quality sensor within the building 1900. The embodiment of figure 21 shows the air quality data being transmitted directly from each air quality sensor 1905 to the robot 1902. However, this is only one example. For instance, with reference to figure 6 which shows a distributed Al architecture including an environment sensing edge 501 and environment sensors 101, it will be understood that the air quality sensors 1905 may comprise examples of environment sensors 101 and that the robot 1902 may receive air quality data via the environment sensing edge computing device 501 (or optionally via fog computing device 103). The present invention is concerned more with how the robot 1902 processes air quality data from fixed air quality sensors and responds to the air quality data than with how the robot 1902 acquires the air quality data.

[00229] Once in possession of the air quality data, the robot 1902 determines whether it should operate (that is, to navigate through the building and purify air or perform air quality measurements at one or more locations). This determination of whether to operate may include at step 2105 comparing the received air quality data to an air quality range indicating acceptable air quality to determine at the robot whether air quality within the building is within or outside of the air quality range. The air quality range may comprise a threshold. For instance, where air quality data is indicative of the level of particulate matter in a sample, an upper threshold for the amount of particulate matter may be set, which if exceeded indicates that the indoor air quality is poor. Alternatively, the air quality data may be indicative of a combination of different sensed environmental factors, or otherwise indicative of overall air quality. It may be that a higher score is indicative of better or poorer air quality and so the air quality range may comprise a threshold and the comparison may be whether the air quality score is higher or lower than the threshold. The comparison at step 2105 may be performed separately in respect of air quality data for each sensor 1905. Alternatively, aggregate air quality data fora plurality of sensors may be compared to the air quality range. As an example, various government agencies have defined Air Quality Indexes (AQI) for various combinations of sensor data. Within the European Union a Common AQI (CAQI has been defined based on a combination of sensed NO2, O3 and particulate matter, with an index given between 0 and 100 (where a higher number indicates worse air quality). Within this, five bands are determined. The comparison at step 2105 may comprise determining which band the air quality data falls within, and the threshold may be set according to a maximum acceptable band.

[00230] In some embodiments, if it is determined that air quality within the building is outside of the air quality range, at step 2106 the method further comprises navigating the robot 1902 within the building and at step 2107 operating the air purifier 2000 mounted on the robot to improve the air quality within the building. However, in other embodiments described below, particularly in connection with figure 23, a determination of out of range air quality data may not be determinative of whether the robot should operate: other factors may also be considered. Step 2107 may comprise first measuring the air quality at the current location of the robot and only performing air purification if this is required. It may be that the robot will remain in each location for a variable period of time until air quality is restored to within the acceptable air quality range. If the received air quality is not outside of the air quality range (either overall, or for any one of the sensors) then it may be determined that the air quality within the building is acceptable and that there is no need to operate the robot. It will be appreciated that energy is expended in propelling the robot 1902 within the building and in operating the air purifier 2000. Accordingly, if the robot 1902 is able to determine that indoor air quality is acceptable then the robot need not be used for air purification. If on the other hand it is determined that there is a need for robotic air purification, then further efficiency gains may be made by considering which portions of the building should be visited by the robot based on the received air quality data, as discussed below.

[00231] The embodiment of figure 21 (and indeed the embodiments of certain of the following figures) is based upon the robot 1902 performing the required computation for itself (for instance, using processor 2004 of figure 20) to determine whether or not it is necessary to move within the building and perform air purification. However, in other embodiments of the invention it may be that the processing to determine whether the robot should act (and optionally where it should travel to within the building and where the air purifier should be operated) may be performed elsewhere. For instance, with reference to figure 6, it may be that the air quality data is processed at an environment sensing edge computing device 501, the fog computing device, in the cloud, or optionally a further edge computing device dedicated to controlling the operation of the robot. It will be appreciated that where processing takes place upon the robot 1902, in effect the robot 1902 is operating as an edge computing device (and may thus be referred to as a robot edge computing device). For clarity, the some or all of the processing indicated as taking place at the robot 1902 in each of figures 21 to 24 may occur elsewhere such that to some degree the robot 1902 is remotely controlled.

[00232] Turning now to figure 22, in some embodiments if the received air quality data indicates that there is or may be poor air quality detected at one or more air quality sensor then step 2106 of navigating the robot within the building is preceded by a process of affordance inference 2200 and route calculation 2201. Affordance inference 2200 comprises an inference at the robot, based on the received air quality data (or predicted air quality as discussed below), of one or more locations within the building where the air quality may be outside of the air quality range, and the necessary actions that the robot should perform including whether it should operate at all. In the context of robotics, an affordance is a relationship between an actor (i.e., robot), an action performed by the actor, an object on which this action is performed, and the observed effect. A robot able to discover and learn the affordances of an environment can autonomously adapt to it. The term “affordance” is discussed in detail in “Affordance Equivalences in Robotics: A Formalism”, M. Andries et al., Frontiers in Neurorobotics, 8 June 2018, and available at the following URL: https: / / www.frontjerain.org / articies / 10.3389 / fnbot.2018.00026 / full. For the purposes of this patent specification, affordance includes a process of inferring whether the robot 1902 should operate in response to the received air quality data. Affordance may include the comparison to the air quality range 2105 (shown separately in the figures for clarity). Affordance may include inferring one or more location within the building where the air quality is outside of the air quality range, or one or more locations where the air quality is unknown (that is, a dead spot). It may further include determining a location where the air quality is within the air quality range (including for instance a location where a fixed air quality sensor reports acceptable air quality). Affordance may include determining whether the robot navigate within the building and if so where it should travel to within the building and where the air purifier should be operated (though again for clarity, the step of calculating a route 2201 is shown separately).

[00233] For a conventional robot adapted to operate within a building, such a robot vacuum cleaner or the robot air purifier disclosed in US-10443874-B2, affordance may typically comprise no more than how to navigate a floor map to avoid objects (for instance, objects 1901 shown in figure 19), for instance through the use of Light Detection And Ranging (LiDAR), or through the use of Bluetooth beacons. It will be appreciated that this may form part of the affordance process for robot 1902 also.

[00234] For embodiments of the present invention, affordance inference may take account not only of actual air quality data received from the air quality sensors 1905 but also an air quality predictive model (which may be running upon the robot edge computing device or elsewhere) that seeks to predict future air quality deterioration so that the robot may take action sooner (for instance to perform air purification even before the air quality falls outside of the acceptable air quality range). The air quality prediction model may operate substantially as described before, for instance in connection with figure 6, and so a full explanation is not repeated here. However, in summary, the robot (or another computing device within a system such as that of figure 6) may process received air quality data or air quality data measured by the robot using a first trained predictive machine learning algorithm to provide a current or a future air quality prediction for the building or a region within the building. This prediction may be used to navigate the robot within the building and to operate the robot’s air purifying device to improve the air quality within the building if the current or future air quality prediction is outside of the air quality range. The trained predictive machine learning algorithm may be received from a fog computing device such as fog computing device 103 of figure 6. In some embodiments air quality data measured by the robot (and / or air quality data from fixed air quality sensors) or data indicating operation of the robot air purifying device may be provided to the fog computing device for training or updating the training of the first predictive machine learning algorithm.

[00235] As briefly noted above, a further affordance extension in accordance with certain examples of the present invention is that the locations of the air quality sensors 1905 may be considered along with their reported air quality data. An example is that if one sensor reports poor air quality but for a second sensor the air quality is acceptable then the robot may determine that it is not necessary to navigate to the location of the second sensor. It may also be determined that there is no need to navigate to within a predetermined distance of an air quality sensor that is reporting acceptable air quality. In some embodiments that predetermined distance may be proportional to the air quality data: for example, for an air quality sensor that reports acceptable air quality, but close to the limits of the acceptable air quality range, then the predetermined distance may be smaller than for a further air quality sensor that reports excellent air quality.

[00236] Accordingly, the process of affordance 2200 can be summarised as a process of determining whether a robot should operate, if so which regions of the building should be visited by the robot 1902, and what action should be taken in those regions according to actual or predicted air quality. Optionally, the process of affordance 2200 may encompass the prioritisation of particular regions of a building where air purification may be required, as discussed in greater detail below. This results in greater power efficiency for the robot, and reduce response time for addressing actual or predicted poor air quality.

[00237] Following the step of affordance inference 2200, the step of route calculation 2201 may comprise a process of calculating an optimal route to visit the locations identified by the affordance processing. In some cases, route calculation may be considered to form part of the affordance inference itself. Suitable route calculation algorithms will be well known to the skilled person.

[00238] Figure 22 further includes step 2202 of recording results. This may comprise measuring the air quality at the robot 1902 within the building at locations where there is not a fixed air quality sensor. This may comprise measuring air quality before and after air purification has been performed by the robot 1902. These measurements may be used to supplement a map of air quality data within the building. They may further be used to train or update the training of a predictive machine learning algorithm used as part of the affordance processing, as discussed below, or as part of the training of a reinforcement machine learning algorithm operating for instance on a fog computing device, as discussed below in connection with figure 23. The training data may also include information about the operation of the air purifying device mounted on the robot, for instance locations and times for which the device was activated.

[00239] The process of affordance inference 2200 may further comprise forming at the robot 1902 a map of air quality within the building based on the received air quality data and corresponding measurement locations for the fixed air quality sensors 1905. Such a map may be used to determine a location within the building where the air quality may be outside of the air quality range. The map may be supplemented with air quality data measured by the robot 1902 as it navigates within the building and corresponding measurement locations (step 2202 of figure 22). One use for the map may be to determine a dead spot location within the building spaced apart from known measurement locations. An example dead spot 1906 is shown in figure 19, lying equidistant between a pair fixed air quality sensors 1905. It will be appreciated that as more measurement locations are added to the map (both fixed sensors and recent air quality measurements performed by the robot 1902) then dead spots may be determined more accurately as being equidistant between two or more measurement locations. Similarly, to the affordance technique noted above, whereby a radius about sensors reporting good air quality is determined, it may be that dead spots are determined to comprise regions outside of a known or assumed good quality zone about recent air quality measurements. As more measurement locations are plotted, the size of a dead spot region may be reduced. Accordingly, a more efficient route may be calculated through the building for the robot to navigate in which less space needs to be investigated for possible air purification.

[00240] In some embodiments, the map may be interpolated to determine estimated air quality data at intermediate locations between measurement locations in order to determine regions of the building where it is expected that air quality falls outside of the acceptable range.

[00241] In a further extension, in some embodiments the map may be updated to remove air quality data older than a first time threshold. That is, the reliability of air quality data may be assumed to degrade with time and a threshold may be established beyond which it is not considered to be reliable enough to be of use in determining whether the robot should operate at all (step 2105) or for affordance inference (step 2200) or route calculation (step 2201).

[00242] Turning now to figure 23, this illustrates an alternative implementation option in which the robot 1902 communicates with a fog computing device 2300 (which may be the same as fog computing device 103 shown in figure 6, for instance) instead of directly communicating with the air quality sensors 1905. The air quality sensors 1905 provide air quality data to the fog computing device 2300 at steps 2301 and 2302. At step 2303 the robot 1902 requests this air quality data from the fog computing device 2300 along with a map of air quality within the building that has been established by the fog computing device 2300 and location data for the air quality sensors 1905.

[00243] As discussed previously, a predictive machine learning algorithm may be operating upon the robot to predict current and future air quality data within the building. This is shown in figure 23 as step 2305. The trained predictive machine learning algorithm may be received from the fog computing device 2300. Additionally, the predictive machine learning algorithm at the robot 1902 may also determine based on the received air quality data an estimated time for a fixed ventilation or purifying system to return an out of acceptable range air quality measurement to the acceptable range. This may be used during the affordance inference 2200 as part of determining whether the robot should operate, for instance if the time exceeds a second time threshold.

[00244] Furthermore, a reinforcement machine learning algorithm 2306 is implemented upon the fog computing device 2300. In an alternative embodiment the processes described here at the fog computing device 2300 may be performed elsewhere, for instance at a ventilation system edge 502 as illustrated in figure 6. The fog computing device 2300 may be connected to one or more components of a building ventilation or fixed air purifying system, such as inlets and outlets 1903,1904 shown in figure 19. Accordingly, the fog computing device 2300 may in possession of data concerning the operation and performance of one or more parts of a ventilation or fixed air purifying system, such as a PIV, MVHR, window trickle vent or any other type of actuator. In the event that air quality data received at the fog computing device 2300 indicates that air quality has fallen outside of the acceptable air quality range, the reinforcement machine learning algorithm 2306 also determines an estimated time to improve air quality within the building or at a determined first location such that the air quality is within the air quality range using one or more of the fixed air purifying or ventilation devices within the building. This estimation is determined separately to the robot’s estimation. The reinforcement inference at step 2306 is a determination of a most suitable remedy to a detected instance of poor indoor air quality, which may be to use a fixed building system, the robot, or both. The robot 1902 queries the fog at step 2307 and at step 2308 the fog responds with the result of the reinforcement inference.

[00245] At step 2200 the affordance inference of whether the robot should operate, and if so where within the building it should navigate and what action should take place is also based in part of the fog response 2308. That is, the robot 1902 considers not only its own processing of the received air quality data (for instance, an inference of one or more locations where the air quality is unacceptable or unknown, or its own estimate of the time to remedy that poor air quality using fixed building systems) but also the remedy determined by the fog. In some cases, the robot 1902 may defer to the action instructed by the fog. In other cases, it may have the autonomy to select a different operation. It may be that the robot is only instructed to navigate the building and perform air purification if the estimated time (its own estimate or that estimated by the reinforcement inference at the fog) exceeds the second time threshold. Accordingly, more efficient operation of the robot is enabled by only using the robot when existing building ventilation or air purification systems do not suffice to address detected poor air quality. If the second time threshold is not exceeded, then the fog computing device 2300 may directly control or active one or more ventilation or fixed purification device to address the detected low air quality.

[00246] If the second time threshold is exceeded, then in some cases the determination of route and dead spots to investigate by the robot may be instructed directly by the fog computing device. The results recorded by the robot at step 2202, including information about how the robot has been operated, may be supplied to the reinforcement algorithm operating upon the fog computing device for reinforcement training. As an example, prior to the robot 1902 acting it queries the fog computing device to determine the best option. If a first sensor 1905 has provided air quality data indicating air quality within the acceptable range and a second sensor 1905 is borderline, the fog computing device may determine that the best course of action is to switch on a building ventilation system for a predetermined period of time to remedy the situation. In a second example if two sensors indicate acceptable air quality it may still be determined that the robot should operate to investigate determined dead spots. On completion of the advised best option from the fog computing device the operation of the robot is recorded and returned to the fog computing device for future learning. In a further extension, any detected deviation from air quality predicted at step 2305 may also be recorded for future learning.

[00247] Reinforcement learning may also be used to improve the determination of dead spots, for instance by identifying locations where air quality is detected by the robot to significantly deviate from measurements performed by the fixed air quality sensors.

[00248] Turning now to figure 24, this illustrates a method of measuring air quality within a building in accordance with an embodiment of the present invention. The focus of the method of figure 24 is on use of a robot to supplement air quality data from fixed sensors with roving measurements performed by the robot 1902. Steps 2100 to 2104 are as described previously for figure 21. At step 2400 the robot 1902 navigates within the building. This navigation may be the same as previously described for step 2106 however it need not be predicated on comparison of received air quality data to an acceptable air quality range. In some cases, a determination is first made whether the robot should operate based on the received air quality data. For instance, if all fixed sensors report good air quality, the robot may determine to take no action. In some cases, the robot may periodically traverse the building. At step 2401 air quality is measured at the robot 1902 within the building at locations where there is not a fixed air quality sensor. In some examples this measurement process may be combined with or performed simultaneously with the previously described air purification processes. Advantageously, the air quality measurements by the robot allow a more detailed picture of air quality within a building to be established.

[00249] In some embodiments, a map of air quality within the building may be formed based on air quality data received from the fixed air quality sensors at steps 2103 and 2104 and corresponding measurement locations for the fixed air quality sensors. This map may then be supplemented with air quality data measured by the robot 1902 at step 2401 and corresponding measurement locations.

[00250] As previously discussed, the map may be updated to remove air quality data older than a first time threshold. Also, forming a map may further comprise interpolating air quality at locations between measurement locations. The map may be used to determine a location within the building where the air quality may be outside of an air quality range.

[00251] For the previously described embodiments of the invention, navigating the robot through the building comprises may comprise prioritising visiting some portions of the building over visiting other portions. Prioritised portions of the building may include known regions of the building where air quality measurements have previously differed from measurements recorded at the fixed air quality sensors, those known regions being preprogramed or determined from previous operation of the robot. This may be on the basis that regions of the building that have previously shown poor air quality may be expected to be more likely to suffer from poor air quality in the future. Furthermore, regions of the building where it is predicted that air quality measurements may differ from measurements recorded at the fixed air quality sensors may be prioritised to be visited again. This may be based upon a reinforcement learning model whereby repeated operation of the robot allows a picture to be built up of where air quality deterioration may go undetected. As well or instead, the prediction may be based on operation of a camera mounted on the robot to determine a layout of the building or a room within the building or furniture or other obstacles located within the building indicative of low air circulation. Furthermore, in some cases regions within the building that are a priority for maintaining air quality within the air quality range, may be visited more often, including regions where people congregate, either preprogramed or determined using a camera mounted on the robot.

[00252] Where the robot navigates within the building this may comprise one or more of: providing the robot with a map indicating the layout of the building; using a camera mounted on the robot to determine a layout of the building or a room within the building; or using the camera mounted on the robot to detect furniture or other obstacles located within the building. Particularly, the camera mounted on the robot may be used to determine a layout of the building or a room within the building by receiving image data from the camera and classifying received image data according to detected object type.

[00253] Where a map is initially provided to the robot, the map may indicate the locations of fixed air quality sensors or fixed air purifying or ventilation devices. As well or instead, the method may further comprise using the camera mounted on the robot to detect the locations of fixed air quality sensors or fixed air purifying or ventilation devices.

[00254] The previously described embodiments of the invention may make use of a single air quality range throughout the building. Alternatively, different air quality ranges may be applied in different regions of a building. For instance, an air quality range applied in a region of the building where it is known or detected that people congregate is indicative of cleaner air than an air quality range applied in a region of the building that is unoccupied.

[00255] According to some embodiments, the robot may be configured to determine sources of pollution through fixed or robot air quality measurements or through a camera mounted upon the robot. If a pollution source is detected, then the robot may be navigated towards the pollution source to perform air quality measurements or to perform air purification.

[00256] Embodiments of the invention may further comprise receiving a signal from a building occupancy sensor indicative of occupancy levels. This may for instance be received directly or indirectly from a sensor such as a motion sensor or camera system. If a signal is received indicating that the building is occupied, then the robot may navigate through the building to perform air purification or air quality measurements more frequently.

[00257] In some embodiments if it is determined that air quality has fallen outside of an acceptable range then a signal may be transmitted (for instance from the robot) to a fixed air purifying or ventilation device instructing the air purifying or ventilation device to operate.

[00258] It will be appreciated that examples of the present invention can be realized in the form of hardware, software or a combination of hardware and software. Any such software may be stored in the form of volatile or non-volatile storage, for example a storage device like a ROM, whether erasable or rewritable or not, or in the form of memory, for example RAM, memory chips, device, or integrated circuits or on an optically or magnetically readable medium, for example a CD, DVD, magnetic disk, or magnetic tape or the like. It will be appreciated that the storage devices and storage media are examples of machine-readable storage that are suitable for storing a program or programs comprising instructions that, when executed, implement examples of the present invention.

[00259] Accordingly, examples provide a program comprising code for implementing apparatus or a method as claimed in any one of the claims of this specification and a machine-readable storage storing such a program. Still further, such programs may be conveyed electronically via any medium, for example a communication signal carried over a wired or wireless connection and examples suitably encompass the same.

[00260] Throughout this specification, the words “comprise” and “contain” and variations of them mean “including but not limited to”, and they are not intended to (and do not) exclude other components, integers, or steps. Throughout this specification, the singular encompasses the plural unless the context otherwise requires. In particular, where the indefinite article is used, the specification is to be understood as contemplating plurality as well as singularity, unless the context requires otherwise. Throughout this specification, the term “about” is used to provide flexibility to a range endpoint by providing that a given value may be “a little above” or “a little below” the endpoint. The degree of flexibility of this term can be dictated by the particular variable and can be determined based on experience and the associated description herein.

[00261] Features, integers, or characteristics described in conjunction with a particular aspect or example of the invention are to be understood to be applicable to any other aspect or example described herein unless incompatible therewith. All of the features disclosed in this specification, and / or all of the steps of any method or process so disclosed, may be combined in any combination, except combinations where at least some of such features and / or steps are mutually exclusive. The invention is not restricted to the details of any foregoing examples. The invention extends to any novel feature or combination of features disclosed in this specification. It will be also be appreciated that, throughout this specification, language in the general form of “X for Y” (where Y is some action, activity or step and X is some means for carrying out that action, activity or step) encompasses means X adapted or arranged specifically, but not exclusively, to do Y.

[00262] Each feature disclosed in this specification may be replaced by alternative features serving the same, equivalent, or similar purpose, unless expressly stated otherwise. Thus, unless expressly stated otherwise, each feature disclosed is one example only of a generic series of equivalent or similar features.

[00263] The reader's attention is directed to all papers and documents which are filed concurrently with or previous to this specification in connection with this application and 5 which are open to public inspection with this specification, and the contents of all such papers and documents are incorporated herein by reference.

Claims

1. A method of controlling a robot, the method comprising:obtaining air quality data measured at a fixed air quality sensor within a building; anddetermining, based on the received air quality data, whether to operate the robot within the building;wherein operating the robot within the building comprises:navigating the robot within the building; andoperating an air purifying device mounted on the robot to improve the air quality; oroperating an air quality sensor mounted upon the robot to measure air quality.

2. A method according to claim 1, wherein determining whether to operate the robot further comprises:inferring, based on the received air quality data, a first location within the building where air quality is outside of an air quality range indicating acceptable air quality; orinferring, based on the received air quality data, a second location within the building where the air quality is unknown.

3. A method according to claim 2, wherein navigating the robot within the building further comprises:navigating the robot such that it traverses the first location or the second location.

4. A method according to claim 2 or claim 3, wherein navigating the robot further comprises:inferring, based on the received air quality data, a third location within the building where air quality is within the air quality range; andnavigating the robot to avoid the third location.

5. A method according to any one of claims 2 to 4, wherein determining whether to operate the robot comprises:forming a map of air quality within the building based on the received air quality data and corresponding measurement locations for the fixed air quality sensors; andusing the map to infer the first location, second location or third location.

6. A method according to claim 5, further comprising:supplementing the map with air quality data measured by the air quality sensor mounted on the robot and corresponding measurement locations.

7. A method according to claim 5 or claim 6, further comprising using the map to infer the second location by calculating a location remote from air quality measurement locations.

8. A method according to any one of claims 5 to 7, further comprising: updating the map to remove air quality data older than a first time threshold.

9. A method according to any one of claim 4 to 8, further comprising: interpolating air quality at locations between measurement locations.

10. A method according to any one of claims 2 to 9, wherein determining whether to operate the robot further comprises:determining an estimated time to improve air quality at the first location such that the air quality is within the air quality range using a fixed air purifying or ventilation device within the building;comparing the estimated time to a second time threshold; anddetermining whether to navigate the robot and operate the robot’s air purifying device or whether to operate the fixed air purifying or ventilation device based on the result of the comparison.

11. A method according to claim 10, wherein determining an estimated time comprises: processing received air quality data or air quality data measured by the robot using a trained predictive machine learning algorithm to determine an estimated time.

12. A method according to claim 11, further comprising:processing received air quality data or air quality data measured by the robot using the trained predictive machine learning algorithm to infer a location within the building where future air quality will be outside of the air quality range.

13. A method according to claim 11 or claim 12, further comprising:receiving the trained predictive machine learning algorithm from a fog computing device; andforwarding air quality data measured by the robot or data indicating operation of the robot air purifying device to the fog computing device fortraining or updating the training of the predictive machine learning algorithm.

14. A method according to any one of claims 10 to 13, further comprising:processing received air quality data, air quality data measured by the robot, or data obtained from the fixed air purifying or ventilation device using a trained reinforcement machine learning algorithm to determine a preferred remedy to an inference of air quality outside of the air quality range;wherein determining whether to navigate the robot and operate the robot’s air purifying device or whether to operate the fixed air purifying or ventilation device is further based on the determined preferred remedy.

15. A method according to any one of the preceding claims, wherein navigating the robot within the building comprises prioritising visiting:known regions of the building where air quality measurements have previously differed from measurements recorded at a fixed air quality sensor, those known regions being preprogramed or determined from previous operation of the robot;regions of the building where it is predicted that air quality measurements may differ from measurements recorded at a fixed air quality sensor, the prediction being based on operation of a camera mounted on the robot to determine a layout of the building or a room within the building or furniture or other obstacles located within the building indicative of low air circulation; orregions within the building that are a priority for maintaining air quality within the air quality range, including regions where people congregate, either preprogramed or determined using a camera mounted on the robot.

16. A method according to any one of the preceding claims, wherein navigating the robot within the building comprises one or more of:providing the robot with a map indicating the layout of the building;using a camera mounted on the robot to determine a layout of the building or a room within the building; orusing the camera mounted on the robot to detect furniture or other obstacles located within the building.

17. A method according to claim 16, wherein the map indicates the locations of a fixed air quality sensor or fixed air purifying or ventilation devices; orwherein the method further comprises using the camera mounted on the robot to detect the locations of fixed air quality sensors or fixed air purifying or ventilation devices.

18. A method according to any one of the preceding claims, wherein different air quality ranges are applied in different regions of a building; orwherein an air quality range applied in a region of the building where it is known or detected that people congregate is indicative of cleaner air than an air quality range applied in a region of the building that is unoccupied.

19. A method according to any one of the preceding claims, the method further comprises:determining sources of pollution through fixed or robot air quality measurements or through a camera mounted upon the robot and navigating the robot towards determined sources of pollution to perform air quality measurements or to perform air purification; or receiving a signal from a building occupancy sensor indicative of occupancy levels and adjusting the frequency of navigating the robot through the building according to detected occupancy levels.

20. A computer-readable storage medium having computer-readable program code stored therein that, in response to execution by a processor, causes the processor to control a robot perform the method of any one of the preceding claims.

21. A robot comprising:propulsion means for navigating through a building;an air purifying device or an air quality sensor;a processor; anda memory storing executable instructions that, in response to execution by the processor, cause the processor to control the robot to perform the method of any one of claims 1 to 19.

22. An air purifying or air quality measurement system for a building, the system comprising:a robot according to claim 21; anda fixed air quality sensor configured to be located within the building and configured to measure air quality.

23. A system according to claim 22 when dependent upon claim 13, further comprising:a fog computing device configured to train or to update the training of the predictive machine learning algorithm for execution by the robot.

Images