Road condition prediction system

Abstract

The invention discloses a road condition prediction system for a vehicle. First, a computing device receives ambient temperature and relative humidity data from a vehicle, the ambient temperature and relative humidity data collected by a tire sensor mounted external to a tire of the vehicle or external to a wheel of the vehicle. The computing device then applies the machine learning model to the temperature and humidity data from the vehicle to predict a road condition for the vehicle. The computing device then sends the road condition for the vehicle to a control system of the vehicle.

Description

Technical Field

[0001] The invention relates to a road condition prediction system. Background Art

[0002] The vehicle may be equipped with sensors mounted on the tires of each wheel on the vehicle to obtain information about physical parameters of the tires, such as tire pressure, temperature, etc. The information obtained from the sensors may be used to detect potential problems with the tires that may lead to unsafe driving conditions. For example, data obtained from the tire sensors may be used to detect an underinflated tire. Upon detection, the user of the vehicle may be notified of the underinflated tire via an indicator light in the vehicle dashboard. Summary of the invention

[0003] The present invention provides the following technical solutions:

[0004] 1. A method comprising:

[0005] receiving ambient temperature and relative humidity data from the vehicle, the ambient temperature and relative humidity data being collected by a tire sensor mounted to the exterior of a tire of the vehicle or to the exterior of a wheel of the vehicle;

[0006] applying a machine learning model to temperature and humidity data from a vehicle to predict road conditions for the vehicle; and

[0007] Road conditions for the vehicle are sent to the vehicle's control system.

[0008] 2. The method according to Option 1 also includes training a machine learning model to predict road conditions for a vehicle based at least in part on historical weather data including relationships between temperature, relative humidity, and weather conditions.

[0009] 3. The method according to claim 1, wherein the control system is configured to calculate a predicted degree of wear of the vehicle's tires.

[0010] 4. A method according to Option 1, wherein the control system is configured to calculate a current friction coefficient of the road based at least in part on road conditions.

[0011] 5. The method of claim 4, wherein the control system is further configured to adjust operation of an anti-lock braking system (ABS) of the vehicle based at least in part on the current friction coefficient.

[0012] 6. The method of claim 4, wherein the control system is further configured to adjust operation of a traction control system (TCS) of the vehicle based at least in part on the current friction coefficient.

[0013] 7. The method of claim 1, wherein the control system is further configured to activate a brake drying system of the vehicle based at least in part on road conditions for the vehicle.

[0014] 8. A system comprising:

[0015] a computing device comprising a processor and a memory; and

[0016] Machine-readable instructions stored in the memory, which, when executed by the processor, cause the computing device to at least:

[0017] receiving ambient temperature and relative humidity data from the vehicle, the ambient temperature and relative humidity data being collected by a tire sensor mounted to the exterior of a tire of the vehicle or to the exterior of a wheel of the vehicle;

[0018] Applying a machine learning model to temperature and humidity data from a vehicle to predict road conditions for the vehicle; and

[0019] Road conditions for the vehicle are sent to the vehicle's control system.

[0020] 9. The system of claim 8, wherein when the machine-readable instructions are executed by the processor, the computing device is further caused to at least:

[0021] A machine learning model is trained to predict road conditions for a vehicle based at least in part on historical weather data including relationships between temperature, relative humidity, and weather conditions.

[0022] 10. The system of claim 8, wherein the control system is configured to calculate a predicted degree of wear of a vehicle tire.

[0023] 11. A system according to Option 8, wherein the control system is configured to calculate a current friction coefficient of the road based at least in part on road conditions.

[0024] 12. The system of claim 11, wherein the control system is further configured to adjust operation of an anti-lock braking system (ABS) of the vehicle based at least in part on the current friction coefficient.

[0025] 13. The system of claim 11, wherein the control system is further configured to adjust operation of a traction control system (TCS) of the vehicle based at least in part on the current friction coefficient.

[0026] 14. The system of claim 8, wherein the control system is further configured to activate a brake drying system of the vehicle based at least in part on road conditions for the vehicle.

[0027] 15. A non-transitory computer-readable medium comprising machine-readable instructions that, when executed by a processor of a computing device, cause the computing device to at least:

[0028] receiving ambient temperature and relative humidity data from the vehicle, the ambient temperature and relative humidity data being collected by a tire sensor mounted to the exterior of a tire of the vehicle or to the exterior of a wheel of the vehicle;

[0029] Applying a machine learning model to temperature and humidity data from a vehicle to predict road conditions for the vehicle; and

[0030] Road conditions for the vehicle are sent to the vehicle's control system.

[0031] 16. The non-transitory computer-readable medium of claim 15, wherein when the machine-readable instructions are executed by the processor, the computing device is further caused to at least:

[0032] A machine learning model is trained to predict road conditions for a vehicle based at least in part on historical weather data including relationships between temperature, relative humidity, and weather conditions.

[0033] 17. The non-transitory computer-readable medium of claim 15, wherein the control system is configured to calculate a predicted degree of wear of a tire of the vehicle.

[0034] 18. A non-transitory computer-readable medium according to embodiment 15, wherein the control system is configured to calculate a current friction coefficient of the road based at least in part on road conditions.

[0035] 19. The non-transitory computer-readable medium of claim 15, wherein the control system is further configured to adjust operation of an anti-lock braking system (ABS) of the vehicle based at least in part on the current coefficient of friction.

[0036] 20. The non-transitory computer-readable medium of claim 15, wherein the control system is further configured to adjust operation of a traction control system (TCS) of the vehicle based at least in part on the current friction coefficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Many aspects of the present disclosure may be better understood with reference to the following drawings. The components in the drawings are not necessarily drawn to scale, but emphasis is placed on clearly illustrating the principles of the present disclosure. In addition, in the drawings, the same reference numerals throughout the several views designate corresponding components.

[0038] Figure 1A is a diagram of a vehicle with one or more tires including tread wear sensor plugs according to various embodiments of the present disclosure.

[0039] Figure 1B Depicted are cross-sectional views of tires according to various embodiments of the present disclosure.

[0040] FIG. 2A to FIG. 2C is a network environment according to various embodiments of the present disclosure.

[0041] Figure 3 The present invention describes various embodiments of the present invention. Figures 2A-2C A flowchart of an example of the operation of one or more components of a network environment.

[0042] definition

[0043] "CAN bus" is the abbreviation for Controller Area Network.

[0044] "Inboard" means the side of the tire closest to the vehicle when the tire is mounted on the wheel and the wheel is mounted on the vehicle. DETAILED DESCRIPTION

[0045] Described herein are various examples related to nondestructive inspection of tires using radar tomography. Reference will now be made in detail to the description of the embodiments illustrated in the accompanying drawings, wherein like reference numerals refer to like components throughout the several views.

[0046] Figure 1A An example of a vehicle 100 is depicted (in this case, a semi-trailer truck with a trailer). Vehicle 100 may have one or more tires 103 (e.g., tires depicted as tires 103a, 103b, 103c, 103d, and 103e). Each tire 103 may have a tire sensor 106 (e.g., tire sensors depicted as tire sensors 106a, 106b, 106c, 106d, and 106e). Tire sensor 106 may include any sensor capable of or configured to continuously or at regular intervals record ambient air temperature and relative humidity near tire sensor 106 and transmit the recorded ambient air temperature and relative humidity to another computing device or system. In some embodiments, tire sensor 106 may be fixed or mounted to the outer wall of tire 103 to improve the accuracy of readings of environmental conditions (e.g., ambient air temperature and relative humidity). In other embodiments, tire sensor 106 may be fixed or mounted to the inside of tire 103 to protect tire sensor 106 from wear. Tire sensor 106 may also include an antenna (not shown) for wirelessly transmitting measured parameters and tire information data to a remote computing device for analysis.

[0047] Although Figure 1AThe vehicle 100 is depicted as a commercial truck, but the vehicle 100 may include any type of vehicle using tires, with a commercial truck being presented as an example. To this end, the vehicle 100 may include a passenger car, an off-road vehicle, etc., wherein these vehicles 100 include more than Figure 1A A greater or lesser number of tires 103 may be shown.

[0048] Figure 1B A cross-sectional view of a tire 103 is shown, showing a tire sensor 106 mounted to the outer wall of the tire 103. The tire sensor 106 may be mounted or attached to the outer wall or outer surface of the tire 103, such as by an adhesive. Although the tire sensor 106 is depicted as being attached to the outer wall of the tire 103, it should be understood that in various embodiments of the present disclosure, the tire sensor 106 may be mounted to other portions of the tire 103, such as the inside of the tire 103, on the wheel 113, etc. For convenience, reference will be made herein to mounting the tire sensor 106 to the tire 103, but it should be understood that such mounting includes all such attachments.

[0049] In various examples, the tire sensor 106 includes a processor and a memory to store vehicle tire information for each specific tire 103. For example, the tire vehicle tire information may include a tire identifier (ID), manufacturing information of the tire 103 (e.g., model, manufacturer name, etc.), size information (e.g., rim size, width, and outer diameter), manufacturing location, manufacturing date, tread cap code including or associated with compound identification, mold code including or associated with tread structure identification, and / or other information. The vehicle tire information may also include a maintenance history or other information to identify specific characteristics and parameters of each tire 103. Alternatively or additionally, the vehicle tire information may be included in another sensor 106, or in a separate vehicle storage medium, such as a tire ID tag, which is preferably in electronic communication with the tire sensor 106.

[0050] Figures 2A-2C is a schematic block diagram of a network environment 200 (eg, network environment 200a, network environment 200b, or network environment 200c) according to various embodiments of the present disclosure. Figure 2A A network environment 200 a is depicted in which various components (eg, tire sensors 106 , control system 203 , and / or road condition prediction system 206 ) are independent within vehicle 100 . Figure 2B A network environment 200 b is depicted in which components within the vehicle 100 are in data communication with a computing environment 209 via a telematics unit 213 . Figure 2CA network environment 200c is depicted that is similar to network environment 200b. However, with respect to network environment 200c, components within the vehicle are in data communication with computing environment 203 via control system 206.

[0051] The control system 203 may represent any hardware or software system that directly or indirectly controls the operation of the various components and / or systems of the vehicle 100. The control system 203 may be connected to a CAN bus of the vehicle 100 to allow the control system 203 to send and receive messages to and from various other components or systems of the vehicle 100.

[0052] The road condition prediction system 206 may represent any software application or service executed locally on the vehicle 100 or remotely in the computing environment 209 that can use the road condition model 216 to predict the current road condition of the vehicle 100 in response to the ambient air temperature and relative humidity readings provided by one or more tire sensors 106 of the vehicle. The current road condition can then be used as an input to other systems or services of the vehicle 100, such as an anti-lock braking system (ABS), a traction control system (TCS), a brake drying system, a tire wear level predictor, etc.

[0053] The road condition model 216 can represent any machine learning model (e.g., a neural network, such as a convolutional neural network, a recurrent neural network; a linear regression model; a decision learning tree, etc.) that is trained to predict the current weather conditions near the vehicle 100, thereby predicting the current road conditions. For example, the road condition model 216 can be trained on a data set that includes historical or collected mappings of ambient air temperature and relative humidity to historical or collected weather conditions. Table 1 below lists an example of a training data set for illustrative purposes. A larger training data set can be used in various embodiments.

[0054] Table 1:

[0055] Ambient air temperature Relative humidity Weather conditions Road conditions 50°F 28％ clear dry 32°F 75％ rain wet 28°F 12％ clear dry 41°F 45％ rain wet 68°F 22％ clear dry 85°F 44％ clear dry 15°F 79％ Snow Snow 12°F 44％ clear dry 76°F 69％ rain wet 82°F 70％ rain wet

[0056] Telematics unit 213 may represent any unit capable of receiving data from various components of vehicle 100 (e.g., tire sensors 106) and relaying the data to another device or component (e.g., computing environment 209 or control system 203). Telematics unit 213 may be installed on vehicle 100, for example, to provide a connection between tire sensors 106 and control system 203 or computing environment 209. Telematics unit 213 may also be installed when tire sensors 106 do not have access to the vehicle's CAN bus, for example, because they are aftermarket tires rather than original equipment manufacturer (OEM) tires.

[0057] The computing environment 209 may include one or more computing devices including processors, memory, and / or network interfaces. For example, a computing device may be configured to perform computations on behalf of other computing devices or applications. As another example, such a computing device may host and / or provide content to other computing devices in response to a request for content.

[0058] In addition, computing environment 209 can employ multiple computing devices, which can be arranged in one or more server groups or computer groups or other arrangements. Such computing devices can be located in a single installation or distributed in many different geographical locations. For example, computing environment 209 can include multiple computing devices, which together can include managed computing resources, grid computing resources, or any other distributed computing arrangements. In some cases, computing environment 209 can correspond to elastic computing resources, in which the capacity of allocated processing, network, storage, or other computing-related resources can change over time.

[0059] exist Figure 2A In the network environment 200a of FIG. 1 , one or more tire sensors 106 and a control system 203 are shown as components of the vehicle 100. The tire sensors 106 can communicate data with the control system 203, for example, via a CAN bus of the vehicle 100. In these embodiments, the tire sensors 106 can include a wireless transmitter (e.g., a low-power Bluetooth (BLE) transmitter, an ultra-wideband (UWB) transmitter, etc.) that allows the tire sensors 106 to transmit information to a receiver connected to the CAN bus. The receiver can in turn relay the ambient air temperature and relative humidity readings provided by the tire sensors 106 to the control system 203 via the CAN bus.

[0060] The road condition prediction system 206 of the control system 203 can then use the road condition model 216 to predict the current road condition of the vehicle 100. The resulting road condition can then be used as an input to other systems of the vehicle 100 (e.g., an anti-lock braking system (ABS), a traction control system (TCS), a brake drying system, etc.). For example, the ABS or TCS can use the predicted current road condition as a basis for estimating the coefficient between the tires 103 of the vehicle 100 and the road in order to adjust its performance accordingly. The brake drying system can use the predicted road condition to determine or adjust the frequency with which it attempts to remove water from the brakes of the vehicle 100. Similarly, since tire wear and tread wear vary depending on road conditions, a tire or tread wear predictor can use the predicted road condition to more accurately estimate the wear on the tire 103 and / or the tread of the tire 103.

[0061] exist Figure 2BIn network environment 200 b , one or more tire sensors 106 and control system 203 are shown as components of vehicle 100 , as is telematics unit 213 . Figure 2B The embodiments depicted in can be used in situations where the manufacturer of the tire 106 does not have direct access to the CAN bus of the vehicle 100 (e.g., because the tire is an aftermarket tire for the vehicle 100, rather than an original equipment manufacturer (OEM) tire). The telematics unit 213 allows the vehicle 100 to maintain data communication with the computing environment 209 via the network 219. The tire sensors 106 may include a wireless transmitter (e.g., a Bluetooth Low Energy (BLE) transmitter, an ultra-wideband (UWB) transmitter, etc.) that allows the tire sensors 106 to communicate information to the telematics unit 213. The telematics unit 213, in turn, can relay the ambient air temperature and relative humidity readings provided by the tire sensors 106 to the computing environment 209 via the network 219.

[0062] The network 219 may include a wide area network (WAN), a local area network (LAN), a personal area network (PAN), or a combination thereof. These networks may include wired or wireless components or a combination thereof. Wired networks may include Ethernet, cable networks, fiber optic networks, and telephone networks, such as dial-up, digital subscriber line (DSL), and integrated services digital network (ISDN) networks. Wireless networks may include cellular networks, satellite networks, Institute of Electrical and Electronics Engineers (IEEE) 802.11 wireless networks (i.e., wireless networks). ), Networks, microwave transmission networks, and other networks that rely on radio broadcasting. Network 219 may also include a combination of two or more networks 219. Examples of network 219 may include the Internet, an intranet, an extranet, a virtual private network (VPN), and similar networks.

[0063] When the road condition prediction system 206 receives the ambient air temperature and relative humidity readings of the tire sensors 106 from the telematics unit 213, the road condition prediction system 206 can use the road condition model 216 to predict the current road condition of the vehicle 100. The road condition prediction system 206 can then return the predicted current road condition to the telematics unit 213, which can relay it to the control system 203 (e.g., via the CAN bus of the vehicle 100).

[0064] The control system 203 can then use the resulting road conditions as input to other systems of the vehicle 100 (e.g., an anti-lock braking system (ABS), a traction control system (TCS), a brake drying system, etc.). For example, the ABS or TCS can use the predicted current road conditions as a basis for estimating the coefficient between the tires 103 of the vehicle 100 and the road in order to adjust its performance accordingly. The brake drying system can use the predicted road conditions to determine or adjust the frequency with which it attempts to remove water from the brakes of the vehicle 100. Similarly, since tire wear and tread wear vary depending on road conditions, a tire or tread wear predictor can use the predicted road conditions to more accurately estimate the wear on the tire 103 and / or the tread of the tire 103.

[0065] Figure 2C The network environment 200c and Figure 2B However, in network environment 200c, there is no telematics unit 213. Instead, Figure 2A Like the network environment 200a of the vehicle 100, the tire sensor 106 communicates data with the control system 203 via the CAN bus of the vehicle 100. Figure 2A Unlike the network environment 200a of the vehicle 100, the road condition prediction system 206 is hosted by the computing environment 209. The ambient air temperature and relative humidity detected by the tire sensor 106 and provided to the control system 203 may be sent by the control system 203 to the computing environment 209 for processing by the road condition prediction system 206. The road condition prediction system 206 may apply the road condition model 216 to the ambient air temperature and relative humidity to predict the current road condition of the vehicle 100. The road condition prediction system 206 may then return the predicted current road condition to the control system 203, which may use the current road condition as input to other systems of the vehicle 100 (e.g., an anti-lock braking system (ABS), a traction control system (TCS), a brake drying system, etc.).

[0066] Figure 3 is a flow chart showing a flowchart providing one example of the operation of a portion of the road condition prediction system 206 . Figure 3 The flowchart of FIG. 200 merely provides an example of many different types of functional arrangements that may be used to implement the operation of the illustrated portion of the road condition prediction system 206. As an alternative, Figure 3 The flowcharts of FIG. 200a - c may be viewed as examples depicting elements of a method implemented within network environments 200a - c .

[0067] Beginning at block 303, the road condition prediction system 206 may receive temperature and humidity data collected from one or more tire sensors 106 of the vehicle 100. In some embodiments, only one tire 103 may have a tire sensor 106 installed on the vehicle, while in other embodiments, multiple tires 103 may have installed tire sensors 106. The temperature and humidity data may represent the ambient temperature and relative humidity near the tire sensor 106.

[0068] Turning to block 306, the road condition prediction system 206 can apply the road condition model 216 to each set or pair of ambient temperature and relative humidity collected by the tire sensor 106. If a single set or pair of ambient temperature and relative humidity readings are received, the prediction based on the road condition model 216 can be used as a prediction of the current road condition for the vehicle 100. However, if multiple sets or pairs of readings are received, such as separate ambient temperature and relative humidity readings for separate tires 103 of the vehicle 100, the road condition prediction system 206 can apply the road condition model 216 to each set or pair to make separate predictions of the road condition for the vehicle 100. The separate predictions can then be coordinated or compared with each other to improve the accuracy of the predictions. For example, if there is an inconsistency between the predictions based on the readings provided by the separate tire sensors 106, the most common or majority prediction can be used (e.g., in order to ignore erroneous or error readings from defective or damaged tire sensors 106).

[0069] Continuing to block 309, the road condition prediction system 206 may return a prediction of the current road condition of the vehicle 100 to the control system 203 of the vehicle 100. The control system 203 of the vehicle 100 may then use the current road condition in a variety of ways, such as those described above.

[0070] In this disclosure, unless expressly stated otherwise, disjunctive language, such as the phrase "at least one of X, Y, or Z," should be understood along with the context and is generally used to indicate that an item, term, etc. can be X, Y, or Z, or any combination thereof (e.g., X, Y, and / or Z). Thus, such disjunctive language is generally not intended to, and should not, imply that certain embodiments require that at least one of X, at least one of Y, or at least one of Z each be present.

[0071] It should be emphasized that the above-mentioned embodiments of the present disclosure are merely examples of possible implementations proposed for a clear understanding of the principles of the present disclosure. Many changes and modifications may be made to the above-mentioned embodiments without substantially departing from the spirit and principles of the present disclosure. All such modifications and changes are intended to be included herein within the scope of the present disclosure and are protected by the following claims.

Claims

1. A method comprising: receiving ambient temperature and relative humidity data from the vehicle, the ambient temperature and relative humidity data being collected by a tire sensor mounted to the exterior of a tire of the vehicle or to the exterior of a wheel of the vehicle; Applying machine learning models to temperature and humidity data from vehicles to predict road conditions for vehicles; and Road conditions for the vehicle are sent to the vehicle's control system.

2. The method of claim 1 further comprising training a machine learning model to predict road conditions for a vehicle based at least in part on historical weather data including relationships between temperature, relative humidity, and weather conditions.

3. The method according to claim 1, wherein: The control system is configured to calculate a predicted degree of wear of tires of the vehicle.

4. The method according to claim 1, wherein: The control system is configured to calculate a current coefficient of friction of the road based at least in part on road conditions.

5. The method according to claim 4, wherein: The control system is also configured to adjust operation of an anti-lock braking system (ABS) of the vehicle based at least in part on the current friction coefficient.

6. The method according to claim 4, wherein: The control system is also configured to adjust operation of a traction control system (TCS) of the vehicle based at least in part on the current friction coefficient.

7. The method according to claim 1, wherein: The control system is also configured to activate a brake drying system of the vehicle based at least in part on road conditions for the vehicle.

8. A system comprising: A computing device including a processor and a memory; as well as Machine-readable instructions stored in the memory, which, when executed by the processor, cause the computing device to at least: receiving ambient temperature and relative humidity data from the vehicle, the ambient temperature and relative humidity data being collected by a tire sensor mounted to the exterior of a tire of the vehicle or to the exterior of a wheel of the vehicle; Applying machine learning models to temperature and humidity data from vehicles to predict road conditions for vehicles; and Road conditions for the vehicle are sent to the vehicle's control system.

9. The system according to claim 8, wherein: When the machine-readable instructions are executed by the processor, the computing device is further caused to at least: A machine learning model is trained to predict road conditions for a vehicle based at least in part on historical weather data including relationships between temperature, relative humidity, and weather conditions.

10. A non-transitory computer-readable medium comprising machine-readable instructions that, when executed by a processor of a computing device, cause the computing device to at least: receiving ambient temperature and relative humidity data from the vehicle, the ambient temperature and relative humidity data being collected by a tire sensor mounted to the exterior of a tire of the vehicle or to the exterior of a wheel of the vehicle; Applying machine learning models to temperature and humidity data from vehicles to predict road conditions for vehicles; and Road conditions for the vehicle are sent to the vehicle's control system.

Images