GB2522128A

GB2522128A - Automated climate control system and method

Info

Publication number: GB2522128A
Application number: GB1500594.5A
Authority: GB
Inventors: Anna Gaszczak; Thomas Popham
Original assignee: Jaguar Land Rover Ltd
Current assignee: Jaguar Land Rover Ltd
Priority date: 2014-01-14
Filing date: 2015-01-14
Publication date: 2015-07-15
Anticipated expiration: 2035-01-14
Also published as: GB201500594D0; GB2522128B; GB201400574D0

Abstract

An automated climate control system for use in a vehicle, comprising: an input for obtaining a user climate control instruction, a monitor module configured to obtain a value of a condition parameter for the user climate control instruction, and a training module configured to use user climate control instructions and condition parameter values for the respective user climate control instructions, to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter; the monitor module is configured to record the value of the condition parameter for the user climate control instruction at the time of input of the user climate control instruction, and wherein the system is operable to output an automated climate control instruction only following a positive determination that the number of input user climate control instructions recorded for at least one condition parameter exceeds a predetermined threshold. Also disclosed is the method used by the system. The condition parameter may be an environmental parameter, such as a temperature inside or outside the vehicle. The input may be configured to obtain a plurality of types of user climate control instruction, these may be one of: a cabin climate, a seat temperature, and a steering wheel temperature.

Description

AUTOMATED CLIMATE CONTROL SYSTEM AND METHOD

FIELD OF THE INVENTION

This invention is directed to an automated climate control system and method for automating climate control in vehicles. Aspects of the invention relate to a method, to a system and to a vehicle.

BACKGROUND OF THE INVENTION

Climate control systems for vehicles are well known. These can control internal temperature of the cabin, by heating or air conditioning, and switch on and off heated or cooled seats and heated steering wheels and other individual or local heating systems or elements. Previous systems allow a user to set a temperature on a console, in response to which a climate control system sets up a heater temperature, fan speed and air outlets to provide a user with in-cabin conditions corresponding to the set temperature. Seat and steering wheel heaters are typically switched on by the vehicle user, for a desired period of time.

These systems demand user input for most instances where the climate control system is operated, and typically require intensive, frequent and complex user input in order to the get the cabin conditions and local heating systems (such as the seat, steering wheel and the like) right for the user. Many actions are repeated frequently; for example, users typically press the same sequence of buttons in their daily commute.

In addition known systems for climate control can be inefficient. Systems using thermostats will usually always respond at the trigger temperature, with no account taken of variance in the accompanying prevailing conditions, or of variance in user preferences.

Furthermore, attempts made to automate local systems such as heated seats and steering wheels typically require these to work to the same set temperature or duration of heating/cooling as for the cabin temperature setting.

The present invention aims to address these problems and provide improvements upon the known devices and methods.

STATEMENTS OF INVENTION

Aspects and embodiments of the invention are set out in the accompanying claims.

According to an aspect of the present invention there is provided an automated climate control system for use in a vehicle, comprising: an input for obtaining a user climate control instruction; a monitor module configured to obtain a value of a condition parameter for the user climate control instruction; and a training module configured to use user climate control instructions and condition parameter values for the respective user climate control instructions, to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter; wherein the monitor module is configured to record the value of the condition parameter for the user climate control instruction at the time of input of the user climate control instruction, and wherein the system is operable to output an automated climate control instruction only following a IS positive determination that the number of input user climate control instructions recorded for at least one condition parameter exceeds a predetermined threshold.

The system thus provides an improved climate control system for use in a vehicle, reducing the need for a user to manually change climate control settings by automatically outputting climate control instructions for measured environmental conditions. Advantageously, the system only outputs a climate control setting when the number of input user climate control instructions recorded for the measured environmental conditions exceeds a predetermined threshold. Thus, the system only outputs a clinate control setting when routine behaviour has been identified.

The system may be operable to output the automated climate control instruction to a human machine interface of the vehicle for selection by a user.

The system may be operable to output the automated climate control instruction to a climate control device of the vehicle.

The condition parameter may be a climate parameter.

The climate parameter may be a temperature for the vehicle at the time of input of the user climate control instruction.

The monitor module may be configured to obtain values of the condition parameter internal and external to the vehicle, at the time of input of the user climate control instruction The input may be configured to obtain a plurality of types of user climate control instruction.

A type of user climate control instruction may address one of: a cabin climate; a seat temperature; and a steering wheel temperature.

The training module may be configured to train respective algorithms for each of the IS types of user climate control instruction.

The training module may be configured to record a frequency of occurrence of a user climate control instruction for each of a set of values of the condition parameter.

The user climate control instruction may be a climate value. The training module may be configured to record climate values instructed for each of a set of values of the condition parameter.

The training module may be configured to use the recorded data for a set of values of the condition parameter to estimate a probability for a user climate control instruction given a particular measured condition parameter.

The system may comprise: a current condition module configured to measure a condition parameter for the vehicle; and a processor configured to use the current condition parameter and the algorithm to provide a climate control instruction to a climate control device.

The condition parameter may be a location for the vehicle.

The condition parameter may be an ambient light condition for the vehicle.

According to another aspect of the present invention there is provided a method of automating climate control for a vehicle, comprising the steps of: obtaining a user climate control instruction; obtaining a value of a condition parameter for the user climate control instruction; and using user climate control instructions and condition parameter values for the respective user climate control instructions to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter; recording the value of the condition parameter for the user climate control instruction at the time of input of the user climate control instruction, and outputting an automated climate control instruction only following a positive determination that the number of input user climate control instructions recorded for at least one condition parameter exceeds a predetermined threshold.

IS According to another aspect of the present invention there is provided a media device storing computer program code adapted, when loaded into or run on a computer or processor, to cause the computer or processor to become a system, or to carry out a method as previously described.

According to another aspect of the present invention there is provided a vehicle comprising a system as previously described.

According to another aspect of the invention there is provided an automated climate control system for use in a vehicle, comprising: an input for obtaining a user climate control instruction; a monitor module configured to obtain a value of a condition parameter for the user climate control instruction; and a training module configured to use user climate control instructions and condition parameter values for the respective user climate control instructions, to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter.

This allows a climate control system to be automated for a user's preferences, in the varying conditions experienced in the vehicle. It removes the need for repeated instructions from the user in circumstances where a pattern can be learned by the algorithm, and removes much of the frequent user interaction required in previous climate control systems.

The monitor module may be configured to record the value of the condition parameter for the user climate control instruction at the time of input of the user climate control instruction The condition parameter may be a basic parameter such as a time of entry of the user instruction, or may be an environmental parameter.

Optionally, the condition parameter is a climate parameter. Optionally! the climate parameter is a temperature for the vehicle at the time of input of the user climate control instruction. The climate parameter may be an internal or external temperature for the vehicle, or alternatively a humidity.

This provides a more accurate representation of the user's preferences at different IS conditions, which allows a more user-attuned automated climate control system, and allows for greater energy efficiency.

The monitor module may be configured to obtain values of the condition parameter internal and external to the vehicle, at the time of input of the user climate control instruction.

In an embodiment, the input is configured to obtain a plurality of types of user climate control instruction. Preferably, a type of user climate control instruction addresses one of: a cabin climate; a seat temperature; and a steering wheel temperature. More preferably, the training module is configured to train respective algorithms for each of the types of user climate control instruction.

This allows algorithms to be generated for each of different types of vehicle climate control devices, which in turn provides for more accuracy as such devices work in different ways. In the case of a seat or steering wheel temperature, the input may be configured to obtain a duration of use of a heater and/or cooler, such as a seat or steering wheel heater/cooler.

In an embodiment, the training module is configured to record a frequency of occurrence of a user climate control instruction for each of a set of values of the condition parameter.

In another embodiment, the user climate control instruction is a climate value, and the training module is configured to record climate values instructed for each of a set of values of the condition parameter.

The training module may be configured to use the recorded data for the sets of values of the condition parameter to estimate a probability for a user climate control instruction given a particular measured condition parameter.

For example, the recorded data may be used to construct a probability distribution for the condition parameters and user climate control instructions. The probability distribution may be used to predict automated climate control instruction in response to a measured condition parameter.

The system may further comprise: a current condition module configured to measure a condition parameter for the vehicle; and a processor configured to use the current condition parameter and the algorithm to provide a climate control instruction to a climate control device.

In an embodiment, the condition parameter is a location for the vehicle. The location for the vehicle may be recorded at the time of input of the user climate control instruction.

The location for the vehicle may for example be recorded by a location device in the vehicle, or in a user device. The location device may be a GPS device.

In another embodiment, the condition parameter is an ambient light condition for the vehicle. The ambient light condition may be a light condition internal or external to the vehicle, and may be recorded by a light sensor device of the vehicle.

According to another aspect of the invention there is provided a method of automating climate control for a vehicle, comprising the steps of: obtaining a user climate control instruction; obtaining a value of a condition parameter for the user climate control instruction; and using user climate control instructions and condition parameter values for the respective user climate control instructions, to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter.

According to yet another aspect of the invention there is provided a media device storing computer program code adapted, when loaded into or run on a computer or processor, to cause the computer or processor to become a system, or to carry out a method, according to any of the above described embodiments.

According to a further aspect of the invention there is provided a vehicle comprising a system according to any of the above described embodiments.

Within the scope of this application it is expressly envisaged that the various aspects, embodiments, examples and alternatives set out in the preceding paragraphs, in the IS claims and/or in the following description and drawings, and in particular the individual features thereof, may be taken independently or in any combination. For example, features disclosed in connection with one embodiment are applicable to all embodiments, except where such features are incompatible.

BRIEF DESCRIPTION OF THE DRAWINGS

The invention will now be described, by way of example only, with reference to the accompanying drawings, in which: Figure 1 is a diagram illustrating an automated climate control system according to an embodiment of the invention; Figure 2 is a diagram illustrating steps associated with an automated climate control system according to an embodiment of the invention; and Figure 3 is a diagram illustrating a typical screenshot from a human-machine interface according to an embodiment of the invention.

DETAILED DESCRIPTION

Embodiments of the invention improve the automatic settings on a vehicle's climate control system, by learning user climate control instructions for given conditions. For example, the system may learn how the user sets up heated seats, steering wheel and cabin temperature over time (e.g. if user always turns off the heated seats after five minutes) over a range of environmental conditions, such as varying internal and external temperatures and humidities.

These embodiments make users' habitual use of climate control features easier by, for

example:

reducing the number of times a user changes climate settings; * removing the need for the user to press the same sequence of buttons in a common routine, such as a daily commute; * proposing to automate certain habitual and repetitive user actions (e.g. cabin temperature setting 20 degrees Celsius in the morning, 18 degrees Celsius in the IS evening).

In embodiments, the user routine is learnt by monitoring the user's climate settings, and usage of devices such as heated/cooled seats and heated steering wheel. If the pattern is consistent enough, then the system proposes that the vehicle can be heated automatically to the routine temperatures in given climatic conditions inside and outside the vehicle, devices can be automatically turned on for a period of time in the given conditions, and also that the cabin and/or devices can be preheated at routine times.

Once a regular pattern has been identified, the system asks the user to confirm if they wish the proposed settings to be applied automatically. This means that once the user has confirmed a "self-learning climate" mode, the car will execute the sequence of events according to the user's habits, whenever that user uses the vehicle. For example, at the beginning of a journey the system will set preferred cabin temperature, and enable heated/cooled seats and/or a heated steering wheel. After a period of time corresponding to usual user behaviour the heated/cooled seats and heated steering wheel will be disabled and a temperature setting may change.

The measurement of temperature (and other) conditions at the time of the user instruction differs from a typical thermostat-type application -in that case, the temperature is set at a certain time of day, whatever the prevailing conditions, whether it is already hot or cold, inside or out, or not. Embodiments of the invention have the advantage that they can more closely model the preferences of the user, who is likely to prefer different starting temperatures at different times of year (with different ambient temperatures), will prefer cooling at the same ambient temperature in one season as would produce a preference for heating in a colder season, or will accept a temperature of 17.5 degrees Celsius rather than turn the heater on just to achieve a (thermostat's required) temperature of 18 degrees Celsius.

Figure 1 illustrates an automated climate control system according to an embodiment of the invention. The system in this embodiment is wholly contained within a vehicle 100, however in other embodiments parts of the system (particularly those indicated inside system 112) may be embodied in peripheral devices, on server systems providing cloud data and processing, or a mobile device. I5

The system includes an input or human-machine interface (HMI) device 104, with which the user interacts. Here the user can enter a climate control instruction, such as setting a cabin temperature, or turning on a heated seat. When this instruction is made, a sensor 102 measures an environmental condition, such as a temperature. In this embodiment, the temperature inside and outside the car is measured, at the time the user makes the instruction. The monitor module 106 receives measurements from the sensor. Alternatively or additionally, the monitor module may record the time of instruction, or in the case of the turning on and off of a device, such as a heated seat, the duration of the use of the device.

The user instruction and the recorded condition are passed to the training module 110.

The training module gathers data during use of the vehicle, entry of various climate control instructions and associated conditions at the time. These are used to train an algorithm which is later used to predict the desired climate conditions of a user when given climatic conditions arise during use of the vehicle.

The monitor module, training module and processor in this embodiment are contained in a computer or logic system 112.

Once trained, and the algorithm has been activated by a user agreeing to its use, the system checks current conditions, using the sensor and the monitoring module. It then instructs the climate control devices 114 (cabin heater/air conditioning, seat and steering wheel healers) to replicate the conditions predicted by the algorithm that the user would wish to have according to the measured current conditions.

For example, given an early morning journey in winter, where a user usually uses the heated seats and heated steering wheel, and where the inside and outside temperatures are both low, the system will have been trained to instruct the heaters to switch on (for a predicted lenglh of time) and the cabin heater to heat the cabin to a predicted temperature relative to the conditions.

Figure 2 illustrates steps associated with an aulomated climate control system according to an embodimenl of the invention. Initially in training mode, the user first inputs a IS climate conlrol instruction (202), such as turning the cabin temperature up to 20 degrees Celsius, and the monitoring module and sensor (204) note the conditions, for example 8am, internal temperature 15 degrees Celsius, external temperature 11 degrees Celsius.

The instruction and noted conditions are all passed to the training module to further train the algorithm (206). If not enough data has yet been collected (208), training continues with more user inputs. If enough data has been collected (208), the model is now ready for implementation, typically on next use of the vehicle (although on a journey long enough for conditions to vary, the model could be used as soon as the conditions change). The sensor and monitoring module measure the current conditions (210); an example might be another morning where the temperatures are again 15 degrees Celsius inside and 11 degrees Celsius outside. The algorithm then determines a climate control inslruction for the conditions (212), to instruct the climate control device(s) (214).

For example, Ihe algorithm may have determined that the user is likely to want the cabin temperature at 20 degrees Celsius, and so instructs the cabin heater.

A particular embodiment of the invention is described in more detail hereafter. The system consists of three independent learning algorithms, one for each of the components: temperature setting, heated/cooled seats, and heated steering. The algorithms in this embodiment are separate, as the devices are used in different ways, and therefore may require different training to satisfactorily predict the user's preferences. For example, the heated seats and steering wheel are turned on or off, for periods of time, whereas the cabin temperature is set at a value (rather than toggled on/off), and usually maintained at that value.

The algorithms use the following steps to determine the automatic settings for each of the components.

1) The algorithm begins by logging the ambient temperature, in car temperature, time, user temperature settings, heated/cooled seat and heated steering wheel settings and the duration of usage for every journey of the vehicle.

2) After around two weeks of data has been collected, a histogram of usage for each system element is constructed which represents the user set settings against ambient temperature and in-car temperature. I5

Once the histogram is constructed, the probability of applying particular settings is calculated (referred to as the built probability distribution) and used as a basis for a decision function when applying automatic settings. If observed histograms contain enough data points (n>n_min) and there have been enough manual changes applied by the user (m>m_min) then the routine corresponding to this component (temperature, seats or steering) is proposed to the driver.

3) Once the driver accepts the proposed routine then this routine is automated.

4) In the next drive cycle the conditions (ambient temperature, in-car temperature) at the beginning of the journey are compared to the built probability distribution and if observed probabilities are above a certain threshold (p>p mm) the automatic settings are applied.

5) Once in operation, the model is constantly updated based on user interactions, in particular those in previously unobserved conditions.

6) If a user interaction contradicts the learnt model consistently over a number of consecutive journeys, the model is updated faster to avoid user discomfort.

7) The usage patterns can be linked with personalization, linking separate models to different users -for example, unique users can be identified by their unique key-fobs which transmit a signal to the vehicle, instructing it to use that user's climate control profile.

The histograms for the different types of device can be constructed as follows.

For the heated seats algorithm, for every activation of the heated seats by a user, the pair of temperatures inside and outside the vehicle is recorded. This data can be used to construct a three-dimensional histogram, the dimensions being: cabin temperature; ambient temperature; and activation of the heated seats. The latter can be handled in a number of ways. For example, the number of instances of the heated seats being turned on, for a particular pair of temperatures can be recorded (and instances of the seats not being turned on, if required). This can be used to provide an estimate of the IS probability that the user will want the heated seats turned on, when that temperature pair occurs. For instance, during training the user may have always had the seats on at temperature pair (4, 4) i.e. 4 degrees Celsius both inside and out, implying a probability 100%, and never for temperature pair (25, 25) implying probability 0%. For pair (14, 16) the seats may have been used some of the time, perhaps 50%. The model will use these probabilities. The probabilities may not of course relate to frequency directly -there may only have been one or two instances of (4, 4), but since all were on" the probability may be set at 100%. Many more instances of "on" may have occurred at (14, 16) as this pair is more likely to occur, but there may equally have been many more instances of "not on" for this pair, to produce the qualified probability of 50%.

The duration of use of the heated seats is also recorded, and this can be used as part of the histogram (i.e. a fourth dimension to it) or recorded separately to run a moving average, to provide a typical duration of heated seat use for all uses, or for each temperature pair.

The algorithm for the heated steering wheel is largely the same, although the values will be different as the steering wheel is usually heated for different lengths of time compared to the seats.

However, the histogram for the cabin temperature is slightly different, as the choice of the user via the HMI is for a value (temperature) rather than for on/off. The histogram can be constructed similarly, but in four dimensions: inside temperature, outside temperature, user temperature setting, and frequency. For example, at (10, 10), the user may choose a variety of cabin settings, perhaps 18, 19 and 20 degrees Celsius on different occasions, perhaps to do with the season or location (see below) The frequency of these different settings is also counted, to give an overall probability for the temperature desired by the users at each temperature condition pair. Alternatively, an average of the temperatures can be taken, with a frequency of the average used.

In embodiments, further conditions can be measured and added to the training schedule, and thus applied later to permitted predictions for the user. For example, a OPS device in the vehicle (not shown) can be used to record the location of the vehicle at the time of the user's input of a climate control instruction during training. This location information can be used in the algorithm, for example if conditions requested usually differ at certain locations. For example, a user may wish when driving home from the gym to have a relatively cool cabin, in spite of a cool ambient temperature, in contrast to an early morning drive to work where, although the ambient temperature may be exactly the same, the user may prefer a warmer cabin temperature. Similarly, journeys usually sheltered or shaded will usually require more heating in the cabin than journeys completely exposed to external temperatures and sun conditions.

A light sensor may be used to record light conditions as part of the training and later prediction. For example, a user may prefer to heat the cabin less if the sun is out, and more if it is not, although the ambient and in-cabin temperature may be the same.

Figure 3 illustrates a typical screenshot 300 from a human-machine interface according to an embodiment of the invention. Each ot the three devices which in this system are capable of automation are shown: heating seats (302), steering wheel (304) and cabin temperature (306). The automation of the climate control for these devices can be initiated by toggling the on/off buttons (310) for each device. A status (308) for each device is shown: here the heated seat system is shown as "learning", indicating that the user has agreed to allow the system to learn the user's preferences for heated seats, but that not enough data has yet been gathered to allow the algorithm to be used for prediction. The steering wheel status is "available", meaning that the user has not activated the learning algorithm for it yet. The cabin temperature system is active", meaning that both the user has allowed the system to learn preferences, and that it has sufficient data to predict and so has now activated the system to work from the algorithm to choose cabin temperature for the user, according to measured conditions.

The initialisation of the learning system will typically be prompted either by an HMI message suggesting that it be used, or that a pattern has been detected, or by the user activating the system manually. As noted above, the system will take notice of consistent (frequent and self-conforming) and contradictory (not in agreement with system predictions) settings made by the user, and re-train the algorithms accordingly.

Alternatively the user can re-set the entire training data set to start from scratch.

It will be appreciated by those skilled in the art that the invention has been described by IS way of example only, and that a variety of alternative approaches may be adopted without departing from the scope of the invention, as defined by the appended claims.

For example, instead of starting from scratch when the learning algorithm is first activated, the system may use a default predictive setting, programmed into the system.

This default predictive setting is designed to predict a typical user's settings based on conditions encountered. The system then learns the user's preferences from adjustments to these predictions, rather than spending a period of days or weeks collecting only raw data, before the prediction system can be used. The default predictive setting may be compiled as an average or typical profile from user data sourced with permission from other vehicles, transmitting user data to a central processing hub from each vehicle.

The data collected by the system in the vehicle may be stored locally, or alternatively may be transmitted to and stored in a remote location, for example on a remote server via a cloud computing interface. The data can then easily be ported from vehicle to vehicle, for example multiple owned vehicles, or old and new ones. Similar porting can be done if the profile is stored on a user device, such as a mobile device or tablet.

The HMI in one embodiment is provided by a software application on a user's personal or mobile device, rather than or in addition to the HMI inside the vehicle. The user's preferences may also be edited on the application on the device.

In one embodiment, data points (i.e. climate control settings) are recorded at each drive start (i.e. at the beginning of a journey or key on') and this can be either a setting from a previous drive cycle or a setting actively changed by the user at the beginning of the journey. When new data points (observations) are added to the probability distribution, they can be assigned a different weighting in dependence on whether the new data point is a carry over from a previous drive cycle, or an active (user requested) change. A greater weighting can be given to an active change of the settings made by the user.

In addition, once the automatic system is active, the number of times a user is manually changing the setting for each temperature the automatic system chooses can be IS monitored, so that the probability setting can be adjusted accordingly. This manual interaction of the user with the automatic system is recorded, so that it can be determined if the user changes the settings manually in a consistent manner, e.g. if three times in a row the user has changed the setting of the automatic system, indicating that they are not happy with the prediction. In this case, the probability distributions can be updated with even higher weighting for the user input settings.

Additionally, embodiments of the invention may require that the probability distribution for at least one point in the histogram has to exceed a threshold. This means that the automatic system will propose to the user a routine, only if it is verified that at least one routine exists. This allows a situation to be avoided where, although sufficient observations have been made, a user does not have an observable routine, i.e. their behaviour is random'.

When a data point is added to the probability distribution for a measured condition parameter, an inference may be made for similar conditions. A discretised 2D Gaussian distribution may be added to the probability distribution such that the centre of the distribution is the data point relating to the observed condition parameter. In this way, probabilities for condition parameters proximal to the observed condition parameter (but for which no data points may have been recorded) are also updated.

Further aspects of the invention are set out in the following set of numbered clauses: Clause 1. An automated climate control system for use in a vehicle, comprising an input configured to obtain a user climate control instruction; a monitor module configured to obtain a value of a condition parameter for the user climate control instruction; and a training module configured to use user climate control instructions and condition parameter values for the respective user climate control instructions, to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter.

Clause 2. A system according to Clause 1, wherein the monitor module is configured to record the value of the condition parameter for the user climate control instruction at the time of input of the user climate control instruction.

Clause 3. A system according to Clause 1, wherein the condition parameter is a climate parameter.

Clause 4. A system according to Clause 3, wherein the climate parameter is a temperature for the vehicle at the time of input of the user climate control instruction.

Clause 5. A system according to Clause 3, wherein the monitor module is configured to obtain values of the condition parameter internal and external to the vehicle, at the time of input of the user climate control instruction.

Clause 6. A system according to Clause 1, wherein the input is configured to obtain a plurality of types of user climate control instruction.

Clause 7. A system according to Clause 6, wherein a type of user climate control instruction addresses one of: a cabin climate; a seat temperature; and a steering wheel temperature.

Clause 8. A system according to Clause 6, wherein the training module is configured to train respective algorithms for each of the types of user climate control instruction.

Clause 9. A system according to Clause 6, wherein the training module is configured to record a frequency of occurrence of a user climate control instruction for each of a set of values of the condition parameter.

Clause 10. A system according to Clause 6, wherein the user climate control instruction is a climate value, and wherein the training module is configured to record climate values instructed for each of a set of values of the condition parameter.

Clause 11. A system according to Clause 9, wherein the training module is configured to use the recorded data for the sets of values of the condition parameter to IS estimate a probability for a user climate control instruction given a particular measured condition parameter.

Clause 12. A system according to Clause 1, further comprising a current condition module configured to measure a condition parameter for the vehicle; and a processor configured to use the current condition parameter and the algorithm to provide a climate control instruction to a climate control device.

Clause 13. A system according to Clause 1, wherein the condition parameter is a location for the vehicle.

Clause 14. A system according to Clause 1, wherein the condition parameter is an ambient light condition for the vehicle.

Clause 15. A method of automating climate control for a vehicle, comprising the steps of obtaining a user climate control instruction; obtaining a value of a condition parameter for the user climate control instruction; and using user climate control instructions and condition parameter values for the respective user climate control instructions, to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter.

Clause 16. A media device storing computer program code adapted, when loaded into or run on a computer or processor, to cause the computer or processor to carry out a method according to Clause 15.

Clause 17. A vehicle comprising a system according to Clause 1.

Claims

CLAIMS1. An automated climate control system for use in a vehicle, comprising: an input for obtaining a user climate control instruction; a monitor module configured to obtain a value of a condition parameter for the user climate control instruction; and a training module configured to use user climate control instructions and condition parameter values for the respective user climate control instructions, to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter; wherein the monitor module is configured to record the value of the condition parameter for the user climate control instruction at the time of input of the user climate control instruction, and wherein the system is operable to output an automated climate control instruction only following a positive determination IS that the number of input user climate control instructions recorded for at least one condition parameter exceeds a predetermined threshold.
2. A system as claimed in claim 1, wherein the system is operable to measure a condition parameter, estimating a probability for a user climate control instruction associated with the measured condition parameter and, in response to a determination that said probability exceeds a predetermined threshold, to automatically output said climate control instruction.
3. A system according to claim 1 or claim 2, wherein the system is operable to output the automated climate control instruction to a human machine interface of the vehicle for selection by a user.
4. A system according to claim 1 or claim 2, wherein the system is operable to output the automated climate control instruction to a climate control device of the vehicle.
5. A system according to any one of the preceding claims, wherein the condition parameter is a climate parameter.

-20 -
6. A system according to claim 5, wherein the climate parameter is a temperature for the vehicle at the time of input of the user climate control instruction.
7. A system according to claim 5 or claim 6, wherein the monitor module is configured to obtain values of the condition parameter internal and external to the vehicle, at the time of input of the user climate control instruction.
8. A system according to any preceding claim, wherein the input is configured to obtain a plurality of types of user climate control instruction.
9. A system according to claim 8, wherein a type of user climate control instruction addresses one of: a cabin climate; a seat temperature; and a steering wheel temperature.

IS
10.A system according to claim 8 or claim 9, wherein the training module is configured to train respective algorithms for each of the types of user climate control instruction.
11. A system according to any one of the preceding claims, wherein the training module is configured to record a frequency of occurrence of a user climate control instruction for each of a set of values of the condition parameter.
12. A system according to any one of the preceding claims, wherein the user climate control instruction is a climate value, and wherein the training module is configured to record climate values instructed for each of a set of values of the condition parameter.
13. A system according to claim 11 or claim 12, wherein the training module is configured to use the recorded data for a set of values of the condition parameter to estimate a probability for a user climate control instruction given a particular measured condition parameter.
14. A system according to any preceding claim, further comprising: -21 -a current condition module configured to measure a condition parameter for the vehicle; and a processor configured to use the current condition parameter and the algorithm to provide a climate control instruction to a climate control device.
15. A system according to any preceding claim, wherein the condition parameter is a location for the vehicle.
16. A system according to any preceding claim, wherein the condition parameter is an ambient light condition for the vehicle.
17. A method of automating climate control for a vehicle, comprising the steps of: obtaining a user climate control instruction; obtaining a value of a condition parameter for the user climate control IS instruction; using user climate control instructions and condition parameter values for the respective user climate control instructions to train an algorithm for providing an automated climate control instruction in response to a measured condition parameter; recording the value of the condition parameter for the user climate control instruction at the time of input of the user climate control instruction; and outputting an automated climate control instruction only following a positive determination that the number of input user climate control instructions recorded for at least one condition parameter exceeds a predetermined threshold.
18. A media device storing computer program code adapted, when loaded into or run on a computer or processor, to cause the computer or processor to become a system, or to carry out a method, according to any preceding claim.
19. A vehicle comprising a system as claimed in any of Claims ito 14.
20. A system, method or vehicle substantially as herein described with reference to the accompanying figures.