FIELD

The present disclosure relates to a system, in particular a system for calibrating sensor data of a sensor. The present disclosure also relates to a vehicle comprising a system, and also to a method.

BACKGROUND

A self-driving vehicle, also known as an autonomous vehicle (AV), is a vehicle that is capable of sensing its environment and moving safely with little or no human input. There are numerous challenges faced by the developers of AV technology.

One challenge is ensuring that sensors located on a vehicle, such as sensors used for navigation or detection of obstacles, are correctly calibrated. The position of sensors relative to the vehicle or the environment may change over time. Following such changes in position of the sensor, it may not be possible to accurately navigate or infer the position of obstacles from the sensor data.

It is an object of the present invention to provide an improved assembly and/or method and/or address one or more of the problems discussed above, or discussed elsewhere, or to at least provide an alternative assembly and/or method.

SUMMARY

According to a first aspect of the present invention, there is provided a system comprising: a sensor adapted to be located on a vehicle; and a processor configured to: receive sensor data from the sensor; process an indication of a change in location of the sensor from a first location to a second location; and calibrate the sensor data at the second location of the sensor.

In one example, the second location is a predetermined location, and the processor is configured to: calibrate the sensor data at the predetermined location of the sensor. In one example, the processor is configured to: calibrate the sensor data at the predetermined location using a pre-set calibration corresponding to the predetermined location.

In one example, the predetermined location is defined by a mount at which the sensor is configured to be mounted.

In one example, the sensor is selectively locatable in a plurality of predetermined locations.

In one example, the processor is configured to: determine the second location of the sensor based on the sensor data.

In one example, the second location is a non-predetermined location.

In one example, the processor is configured to: process an indication of a change in location of the sensor from a first location to a second location due to a change in characteristic of the vehicle.

In one example, the characteristic of the vehicle is vehicle shape, size, weight, pitch, roll and/or temperature.

In one example, the indication of a change in location of the sensor is based on sensor data and vehicle operation data, optionally wherein the vehicle operation data comprises speed, acceleration and/or direction of the vehicle.

In one example, the sensor is a sensor that is capable of emitting a first signal and receiving a second signal related to that first signal, in order to perform a sensing function, optionally a Light Detection and Ranging (LIDAR) sensor.

In one example, the system further comprises a memory. The memory may store one or more pre-set calibrations and/or one or more predetermined sensor positions.

According to a second aspect of the present invention, there is provided a vehicle comprising a system according to the first aspect of the present invention.

In one example, the vehicle is an at least partially autonomous vehicle.

According to a third aspect of the present invention, there is provided a method comprising: providing a sensor at a location relative to a vehicle; receiving sensor data from the sensor; processing an indication of a change in location of the sensor from a first location to a second location; and calibrating the sensor data at the second location of the sensor.

In one example, the second location is a predetermined location, the method comprising: calibrating the sensor data at the predetermined location of the sensor.

In one example, the method comprises: calibrating the sensor data at the predetermined location using a pre-set calibration corresponding to the predetermined location.

According to a fourth aspect of the present invention, there is provided a system configured to perform a method according to the third aspect of the present invention. The system may comprise a sensor and a processor.

It will of course be appreciated that features described in relation to one aspect of the present invention may be incorporated into other aspects of the present invention. For example, the method of any aspect of the invention may incorporate any of the features described with reference to the apparatus of any aspect of the invention and vice versa.

Other preferred and advantageous features of the invention will be apparent from the following description.

BRIEF DESCRIPTION OF THE FIGURES

Embodiments of the invention will now be described by way of example only with reference to the figures, in which:

Figure 1 shows a schematic system;

Figure 2 shows a vehicle comprising the system of Figure 1 ; and

Figure 3 shows general methodology principles.

DETAILED DESCRIPTION

Referring to Figure 1 , a system 100 is shown. The system 100 comprises a sensor 110. The sensor 110 is adapted to be located on a vehicle 200. The system 100 further comprises a processor 120. The processor 120 is configured to receive sensor data from the sensor 110. The processor 120 is configured to process an indication of a change in location of the sensor 110 from a first location (indicated in Figure 1 as location A) to a second location (indicated in Figure 1 as location B). The processor 120 is configured to calibrate the sensor data at the second location B of the sensor 110.

Such a system is advantageous as it addresses the problem that the location of the sensor 110 may not remain constant during operation of the vehicle 200 and may change due to a characteristic of the vehicle and/or a property of the environment. Furthermore, it may be desired to move the sensor 110 to accommodate additional vehicle components which would otherwise obstruct the sensor 110 or that the sensor 110 would inhibit the installation of. By the present system, following a change in location of the sensor 110, the sensor 110 is calibrated (which may mean recalibrated) at the second location B. In this way, the sensor data can be correctly interpreted and used by the system 100, for example in navigation and/or detection of obstacles.

In an example, the indication of a change in location of the sensor 110 may be a notification from a remote device 130 that the sensor 110 is moved to the second location B, or a notification from a remote device 130 that the sensor 110 is no longer in the first location A. The system 100 may comprise the remote device 130.

Alternatively, or additionally, the indication of a change in location of the sensor 110 may be generated by the processor 120 if or when the processor 120 determines that the sensor 110 is not in the first location A or is in the second location B. The processor 120 may determine that the sensor 110 is not in the first location A or is in the second location B based on a determination that the sensor 110 is no longer correctly calibrated. That is, the processor 120 may be configured to process sensor data based on a calibration of the sensor at the first location A, and upon determining from the sensor data that the sensor 110 is not in the first location A, generate an indication of a change in location of the sensor 110.

The location of the sensor 110 may be deliberately or purposefully changed. As mentioned above, the sensor 110 may be purposefully moved from the first location A to the second location B to accommodate additional vehicle components, such as a storage module. Alternatively, or additionally, the location of the sensor 110 may be accidentally changed or changed due to a change characteristic of the vehicle 200, a change in property of the environment and/or due to operation of the vehicle 200.

As an example, the first location A may be a central location on the vehicle 200, for example on the roof of the vehicle, and the second location B may be a forward location on the vehicle 200, for example at the bonnet or front bumper of the vehicle 200. When the sensor 110 is located at the first location A, it may prevent the installation of additional vehicle components, such as a storage module, whereas relocating the sensor 110 at the forward location may facilitate the installation of the additional vehicle component in a central location on the vehicle 200.

In the description provided herein, the system 100 comprises the sensor 110 adapted to be located on the vehicle 200. It will be appreciated that the sensor 110 may form part of an existing vehicle 200 to which the system 100 is retrofitted. That is, the system 100 may be retrofitted to an existing vehicle 200, the existing vehicle 200 comprising the sensor 110.

The vehicle 200 may be an autonomous vehicle (AV) 200. The AV 200 may otherwise be known as a self-driving vehicle. The AV 200 may be operable in an autonomous driving condition. In the autonomous driving condition, the AV 200 may be operational without a user input, e.g., from a driver, occupant of the vehicle, or remote operator. That is, in the autonomy condition, the AV 200 may be driving autonomously. The present system 100 is highly advantageous when implemented or employed in an AV 200 due to the prevalence and dependence on sensors and sensor data for safe and reliable operation of the AV 200. In this vein, the system 100 may be for use on, in, or with, an AV 200. In one highly advantageous example, the system 100 is for calibrating sensor data provided by a sensor 100 located on an AV 200. This is highly advantageous due to the prevalence and dependence on sensors and sensor data for safe and reliable operation of AVs, in particular, during navigation and detection/avoidance of obstacles.

In an advantageous embodiment, the second location B is a predetermined location, and the processor 120 is configured to calibrate the sensor data at the predetermined location of the sensor 110. Advantageously, use of a predetermined location facilitates the use of a pre-set calibration, where the calibration for the predetermined location is stored in the system 100. The sensor data can thus be readily recalibrated following an indication of a change to a predetermined location. Predetermined locations may be those particularly suited to placement of the sensor 110. Predetermined locations may be determined or defined during vehicle manufacture and/or predeployment vehicle testing. Predetermined locations may be known locations, or intended locations for placement of the sensor 110.

A plurality of predetermined locations may be provided about the vehicle 200. The first location A may also be a predetermined location.

The indication of a change in location of the sensor 110 may indicate that the sensor 110 has been moved to a predetermined location.

The processor 120 is configured to calibrate the sensor data at the predetermined location using a pre-set calibration corresponding to the predetermined location.

In this way, the sensor data can be calibrated without an appropriate calibration being determined by the system 100 following the indication of a change in location of the sensor 110. Rather, a pre-set calibration for the predetermined location may be determined during vehicle manufacture or predeployment vehicle testing and employed when it is indicated, or established by the processor 120, that the sensor 110 is in the predetermined location. It will be appreciated that a pre-set calibration may be determined for each of the plurality of predetermined sensor locations, and the appropriate pre-set calibration selected for the location of the sensor 110.

The system 100 may further comprise a memory 130. The pre-set calibration, or plurality of pre-set calibrations, may be stored in the memory 130. Furthermore, the predetermined location(s) may be stored in the memory 130. The processor 120 may access the memory 130 to retrieve the pre-set calibrations. When the indication of a change in location indicates that the sensor 110 is moved to a particular predetermined location, the appropriate pre-set calibration for that predetermined location may be selected from the memory 130 by the processor 120 and used to calibrate the sensor data at the predetermined location.

The predetermined location may be defined by a mount at which the sensor 110 is configured to be mounted.

Advantageously, pre-deployment AV testing may determine the appropriate calibration for the mount and store the calibration as a pre-set calibration for the mount location. The pre-set calibration may then be employed when it is determined that the sensor 110 is mounted at the mount. The mount may be provided on, or integrated in, the outer panels of the body of the vehicle 200. A plurality of mounts may be provided, and a pre-set calibration may be stored in the memory 130 for each mount location.

The sensor 110 may be selectively locatable in a plurality of predetermined locations.

In this way, the sensor 110 may be moved between the plurality of predetermined locations. This may facilitate the addition of vehicle components and installations on the vehicle 200, such as a storage module. That is, the sensor 110 can be moved to a different predetermined locations based on a configuration of the vehicle 200. Nevertheless, as a pre-set calibration corresponding to the predetermined location may be stored in the memory 130 and employed by the processor 120, recalibrating the sensor data is quick and does not require an extensive recalibration process.

The processor 120 is configured to determine the second location B of the sensor 110 based on the sensor data.

In this way, the sensor data may be used in the calibration to supplement, or replace, the pre-set calibration. That is, by determining the second location of the sensor 110 based on sensor data, pre-set calibrations need not be required, or the pre-set calibrations may be improved by determining the second location B based on the sensor data which will correspond to the actual location of the sensor. Uncertainty in the sensor location (e.g., uncertainty of a predetermined location) can thus be accounted for.

In an example, where pre-determined locations are used there may be some uncertainty in the actual sensor location. That is, it may not be possible or desired to locate the sensor 110 precisely at the pre-determined location. By determining the second location B of the sensor 110 based on the sensor data, the predetermined location can be used as an initial location and the pre-set calibration could be used as an initial calibration from which to determine a calibration having improved accuracy using the actual sensor location determined based on the sensor data.

In an example, the sensor 110 may be freely moveable and mountable on the vehicle 200. That is, predetermined locations are not used, and the second location may be a non-predetermined location. The second location B may be any position on the vehicle 200. Thus, the second location of the sensor 110 can be determined based on the sensor data for determining an appropriate calibration. In such cases, pre-set calibrations may not be useable, and so determining the second location B of the sensor 110 based on the sensor data is highly advantageous.

The processor 120 may be configured to process an indication of a change in location of the sensor 110 from a first location to a second location due to a change in characteristic of the vehicle 200.

Advantageously, the effect of change in a characteristic of the vehicle 200 can be mitigated, and the sensor 110 recalibrated to provide accurate sensor data despite the change in characteristic. The system 100 may determine a change in characteristic of the vehicle 200 from one or more additional sensors (e.g., stress sensors, distance sensors, accelerometers, gyroscopes, and the like). Additionally, or alternatively, the system 100 may determine a change in characteristic of the vehicle 200 from the sensor data. That is, the processor 120 may establish that the sensor data is incorrectly calibrated (which may be as a result of the change in characteristic) and process an indication of a change in location of the sensor 110. The second location B is thus a location that the sensor 110 has moved to due to the change in characteristic of the vehicle 200.

The characteristic of the vehicle 200 may be vehicle shape, size, weight, pitch, roll and/or temperature. In this way, a characteristic that may cause a change in location of the sensor 110, and thus have an effect on the accuracy of the calibration, can be accounted for.

As examples, the vehicle shape may change due to forces on the vehicle 200 or due to temperature or other environmental/weather conditions. The size of the vehicle 200 may change due to the addition of components, modules, units, or the like. The weight of the vehicle 200 may change due to the addition of component, modules (e.g., a storage module), units, passengers and/or cargo. The vehicle pitch and roll may change due to forces on the vehicle 200, or due to the addition of components, modules, units, passengers and/or cargo. The vehicle temperature may change due to operation of the vehicle and/or due to environmental temperature changes.

The above are each an example of a change in characteristic of the vehicle which may result in a change in location of the sensor from a first location A to a second location B. The displacement caused by such changes in characteristic may be small but can negatively impact the operation of the sensor 110 and the data obtained thereon. As a result, it is highly advantageous to process an indication of a change in location of the sensor from a first location A (i.e., the location prior to the change) to a second location B (i.e., the location after the change in characteristic, and calibrate the sensor data at the second location B of the sensor 110 (i.e., the new sensor location).

The indication of a change in location of the sensor 110 may be based on sensor data and vehicle operation data. The vehicle operation data may comprise speed, acceleration and/or direction of the vehicle 200.

Advantageously, in this way, the change in location of the sensor 110 may established from vehicle operation data which in combination with sensor data can increase certainty of the determination that the location of the sensor 110 is changed.

The sensor 110 may be a sensor that is capable of emitting a first signal and receiving a second signal related to that first signal, in order to perform a sensing function. A sensor of this kind may be known as an “active sensor” or “ranging sensor”. An example of such a sensor is a Light Detection and Ranging (LIDAR) sensor. Advantageously, the LIDAR sensor may be located on the AV for navigation and/or detection of obstacles.

Referring to Figure 2, a vehicle 200 comprising a system 100 as described above is shown. In an advantageous example, the vehicle 200 is an at least partially autonomous vehicle (AV). In a highly advantageous example, the vehicle 200 is an autonomous vehicle (AV).

Referring to Figure 3, a method is shown. The method is a method of calibrating sensor data. Step 302 comprises providing a sensor 110 at a location relative to a vehicle 200. Step 304 comprises receiving sensor data from the sensor 110. Step 306 comprises processing an indication of a change in location of the sensor 110 from a first location A to a second location B. Step 308 comprises calibrating the sensor data at the second location B of the sensor 110. The second location B may be a predetermined location, and optional Step 310 comprises calibrating the sensor data at the predetermined location of the sensor 110. Optional Step 312 comprises calibrating the sensor data at the predetermined location using a pre-set calibration corresponding to the predetermined location.

Such a method is advantageous as it addresses the problem that the location of the sensor 110 may not remain constant during operation of the vehicle 200 and may change due to a characteristic of the vehicle and/or a property of the environment. Furthermore, it may be desired to move the sensor 110 to accommodate additional vehicle components which would otherwise obstruct the sensor 110 or that the sensor 110 would inhibit the installation of. By the present method, following a change in location of the sensor 110, the sensor 110 is calibrated (which may mean recalibrated) at the second location B. In this way, the sensor data can be correctly interpreted and used by the system 100, for example in navigation and/or detection of obstacles.

Although a few preferred embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes and modifications might be made without departing from the scope of the invention, as defined in the appended claims. Although the examples have been described with reference to the components, modules and units discussed herein, such functional elements may be combined into fewer elements or separated into additional elements. Various combinations of optional features have been described herein, and it will be appreciated that described features may be combined in any suitable combination. In particular, the features of any one example may be combined with features of any other embodiment, as appropriate, except where such combinations are mutually exclusive. Throughout this specification, the term “comprising” or “comprises” means including the component(s) specified but not to the exclusion of the presence of others.

All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), 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.

Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) 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.

The invention is not restricted to the details of the foregoing embodiment(s). The invention extends to any novel one, or any novel combination, of the features disclosed in this specification (including any accompanying claims, abstract and drawings), or to any novel one, or any novel combination, of the steps of any method or process so disclosed.