阅读说明：本技术 车辆道路摩擦控制 (Vehicle road friction control ) 是由 凯尔·西蒙斯 埃里克·弘泰·曾 迈克尔·哈夫纳 莫森·莱克哈尔-阿亚特 于 2020-02-11 设计创作，主要内容包括：本公开提供了“车辆道路摩擦控制”。基于根据多辆车辆中的每一辆的相应速度确定的交通速度来确定道路位置的道路摩擦。可基于所确定的道路摩擦来操作车辆。(The present disclosure provides "vehicle road friction control". Road friction for a road location is determined based on traffic speeds determined from respective speeds of each of a plurality of vehicles. The vehicle may be operated based on the determined road friction.)

1. A method, comprising:

determining road friction for the road location based on traffic speeds determined from respective speeds of each of the plurality of vehicles; and

operating a vehicle based on the road friction.

2. The method of claim 1, wherein the road friction is determined based on second data in addition to the traffic speed, the second data being one of: whether the location includes a bridge or overpass, sun conditions, rain conditions, snow conditions, fog conditions, construction conditions, the presence or absence of emergency vehicles, the presence or absence of debris, or ambient temperature.

3. The method of claim 2, further comprising: the second data is obtained from a map.

4. The method of claim 1, further comprising: determining whether the traffic speed is below a threshold traffic speed; and providing the traffic speed only when it is determined that the traffic speed is below the threshold traffic speed, thereby determining the road friction based on the traffic speed.

5. The method of claim 1, wherein a zone is included on a planned route of the vehicle.

6. The method of claim 1, wherein operating the vehicle based on the road friction comprises: controlling traction, speed, steering, braking, lane keeping, or lane change.

7. The method of claim 1, wherein determining the road friction comprises: the road friction is obtained as an output from a machine learning program.

8. The method of claim 7, wherein the machine learning program is disposed in an infrastructure node computer.

9. The method of claim 7, wherein the machine learning program is provided in a computer in the vehicle.

10. The method of claim 1, further comprising: providing the traffic speed and the second data for an area comprising the road location, thereby providing the road friction for the area; wherein the area is defined according to a start point and an end point of the road section.

11. A computer programmed to perform the method of any one of claims 1 to 10.

Technical Field

The present disclosure relates generally to vehicle operation, and more particularly to vehicle road friction control.

Background

The friction between two adjacent surfaces (i.e., the contact or sliding against each other) is typically specified in terms of a coefficient of friction (often denoted by the greek letter μ). Friction is an empirical property of adjacent materials, i.e., depending on the composition of the material (e.g., rubber and asphalt), and the presence or absence of other materials (e.g., ice, water, oil, etc.) that may coat or be present between adjacent materials.

Road friction is an important factor in road vehicle operation. Road friction, also known as surface friction or coefficient of friction, is a measure of the traction between a tire on a vehicle and a road surface. As one example, road friction may be measured by determining a tire-road friction coefficient between a tire and a road surface. The tire-road coefficient of friction typically ranges between 0 and 1. The closer the tire-road coefficient of friction is to 1, the greater the friction (e.g., traction). The closer the tire-road friction coefficient is to 0, the smoother the road. The tire-road coefficient of friction generally varies to some extent with the road surface material and/or any substance on the road surface (e.g., water, snow). As one example, a vehicle traveling at a particular speed may maintain traction on a road with a dry asphalt surface and a coefficient of friction of 0.7, while more likely losing traction on a road with an icy surface and a coefficient of friction of 0.25.

The tire-road coefficient of friction may be used to determine a minimum stopping distance (i.e., a minimum distance that the vehicle is able to decelerate from a current speed to a full stop) and a maximum speed at which the vehicle may travel without the tire slipping and/or sliding on the road surface. The surface friction further may at least partially accommodate vehicle speed, turning radius, etc. It is therefore desirable to be able to determine road surface friction as reliably and accurately as possible.

Disclosure of Invention

Improved systems and methods for predicting or estimating road friction are disclosed herein. Advantageously, road friction may be predicted before the vehicle experiences the predicted road friction, for example, a prediction of low friction may be provided to a vehicle approaching an area where the road provides low friction (i.e. is smoother than normal) before the vehicle is located at a location of low friction. That is, a vehicle having a planned route that includes a designated area may obtain information about road friction in the area before the vehicle reaches the area. Vehicle sensors and/or data from the infrastructure system may provide information about the speed of other vehicles in the area, as well as information about other characteristics in the area and/or environment. Such other information may include weather conditions, lighting conditions, lane characteristics (such as the presence of a bridge or overpass), and so forth. Data relating to traffic speed and other information such as just confirmed may be provided as input to a machine learning program, which may then output an estimated road friction for a location or region of the road. The estimated road friction may then be provided as input to a vehicle computer to operate the vehicle.

One method comprises the following steps: determining road friction for the road location based on traffic speeds determined from respective speeds of each of the plurality of vehicles; and

operating a vehicle based on the road friction. In addition to traffic speed, the road friction may be determined based on second data, the second data being one of: whether the location includes a bridge or overpass, sun conditions, rain conditions, snow conditions, fog conditions, construction conditions, the presence or absence of emergency vehicles, the presence or absence of debris, or ambient temperature. The second data may be obtained from a map. The method may further comprise: determining whether the traffic speed is below a threshold traffic speed; and providing the traffic speed only when it is determined that the traffic speed is below the threshold traffic speed, thereby determining the road friction based on the traffic speed. The area may be included on a planned route of the vehicle. Operating the vehicle based on the road friction may include: controlling traction, speed, steering, braking, lane keeping, or lane change. Determining the road friction may include: the road friction is obtained as an output from a machine learning program. The machine learning program may be provided in an infrastructure node computer. The machine learning program may be provided in a computer in the vehicle. The method may further comprise: providing the traffic speed and the second data for an area comprising the road location, thereby providing the road friction for the area; wherein the area is defined according to a start point and an end point of the road section.

A computer comprising a processor and a memory, the memory storing instructions executable by the processor such that the computer is programmed to: determining road friction for the road location based on traffic speeds determined from respective speeds of each of the plurality of vehicles; and operating the vehicle based on the road friction. The computer may be further programmed to determine the road friction based on second data in addition to the traffic speed, the second data being one of: whether the location includes a bridge or an overpass, a state of sunshine, a rain condition, a snow condition, a fog condition, a construction condition, presence or absence of an emergency vehicle, presence or absence of debris, or ambient temperature. The computer may be further programmed to obtain the second data from a map. The computer may be further programmed to: determining whether the traffic speed is below a threshold traffic speed, and providing the traffic speed only when it is determined that the traffic speed is below the threshold traffic speed, thereby determining the road friction based on the traffic speed. The area may be included on a planned route of the vehicle. Operating the vehicle based on the road friction may include: controlling traction, speed, steering, actuation, lane keeping, or lane change. Determining the road friction may include: the road friction is obtained as an output from a machine learning program. The machine learning program may be provided in an infrastructure node computer. The method may also include programming for executing the machine learning program. The computer may be further programmed to provide the traffic speed for an area including the road location, thereby providing the road friction for the area; wherein the area is defined according to a start point and an end point of the road section.

Drawings

FIG. 1 is a diagram illustrating an exemplary vehicle navigation and control system.

Fig. 2 is an illustration of an exemplary deep neural network.

FIG. 3 is a flow chart of an exemplary process for estimating or predicting road friction and operating a vehicle according to the predicted road friction.

FIG. 4 illustrates an exemplary process 400 for operating the vehicle 105 according to estimated or predicted road friction.

Detailed Description

FIG. 1 is a block diagram of an exemplary vehicle control system 100. The system 100 includes a vehicle 105, the vehicle 105 being a land vehicle, such as an automobile, truck, or the like. The vehicle 105 includes a vehicle computer 110, vehicle sensors 115, actuators 120 to actuate various vehicle components 125, and a vehicle communication module 130. Via the network 135, the communication module 130 allows the vehicle computer 110 to communicate with one or more data collection or infrastructure nodes 140, a central server 145, and/or one or more second vehicles 106.

The vehicle computer 110 includes a processor and memory. The memory includes one or more forms of computer-readable media and stores instructions executable by the vehicle computer 110 for performing various operations, including as disclosed herein.

The vehicle computer 110 may operate the vehicle 105 in an autonomous mode, a semi-autonomous mode, or a non-autonomous (manual) mode. For purposes of this disclosure, an autonomous mode is defined as a mode in which each of propulsion, braking, and steering of the vehicle 105 is controlled by the vehicle computer 110; in semi-autonomous mode, the vehicle computer 110 controls one or both of propulsion, braking, and steering of the vehicle 105; in the non-autonomous mode, the human operator controls each of propulsion, braking, and steering of the vehicle 105.

The vehicle computer 110 may include programming for operating one or more of brakes, propulsion of the vehicle 105 (e.g., controlling acceleration of the vehicle by controlling one or more of an internal combustion engine, an electric motor, a hybrid engine, etc.), steering, climate control, interior and/or exterior lights, etc., and determining whether and when the vehicle computer 110 (rather than a human operator) is controlling such operations. Additionally, the vehicle computer 110 may be programmed to determine if and when a human driver controls such operations.

The vehicle computer 110 may include or be communicatively coupled to more than one processor, such as via a vehicle 105 communication module 130 as described further below, for example, included in an Electronic Controller Unit (ECU) or the like (e.g., a powertrain controller, a brake controller, a steering controller, etc.) included in the vehicle 105 for monitoring and/or controlling various vehicle components 125. Further, the vehicle computer 110 may communicate with a navigation system using a Global Positioning System (GPS) via the vehicle 105 communication module 130. As one example, the vehicle computer 110 may request and receive location data for the vehicle 105. The location data may be in a known form, for example, geographic coordinates (latitude and longitude coordinates).

The vehicle computer 110 is generally arranged to communicate by means of the vehicle 105 communication module 130 and also utilizing wired and/or wireless networks (e.g., buses or the like in the vehicle 105, such as a Controller Area Network (CAN) or the like) and/or other wired and/or wireless mechanisms internal to the vehicle 105.

Via the vehicle 105 communication network, the vehicle computer 110 may transmit and/or receive messages to and/or from various devices in the vehicle 105, such as vehicle sensors 115, actuators 120, vehicle components 125, Human Machine Interfaces (HMIs), and the like. Alternatively or additionally, where the vehicle computer 110 actually includes multiple devices, the vehicle 105 communication network may be used for communication between the devices, represented in this disclosure as the vehicle computer 110. Further, as mentioned below, various controllers and/or vehicle sensors 115 may provide data to the vehicle computer 110.

The vehicle sensors 115 may include various devices such as are known for providing data to the vehicle computer 110. For example, the vehicle sensors 115 may include light detection and ranging (lidar) sensors 115 or the like disposed on the roof of the vehicle 105, behind a front windshield of the vehicle 105, around the vehicle 105, or the like, the light detection and ranging sensors 115 providing relative positions, sizes, and shapes of objects and/or conditions around the vehicle 105, including objects and/or conditions on the roadway 155. As another example, one or more radar sensors 115 fixed to a bumper of vehicle 105 may provide data to provide a range and rate of position of an object (possibly including second vehicle 106) or the like relative to vehicle 105. Alternatively or additionally, the vehicle sensors 115 may also include, for example, one or more camera sensors 115 (e.g., front view, side view, etc.) that provide images from views internal and/or external to the vehicle 105.

The vehicle 105 actuators 120 are implemented via circuitry, chips, motors, or other electronic and or mechanical components that can actuate various vehicle subsystems in accordance with appropriate control signals, as is known. The actuators 120 may be used to control components 125, including braking, acceleration, and steering of the vehicle 105.

In the context of the present disclosure, the vehicle component 125 is one or more hardware components adapted to perform a mechanical or electromechanical function or operation, such as moving the vehicle 105, decelerating or stopping the vehicle 105, steering the vehicle 105, or the like. Non-limiting examples of components 125 include propulsion components (including, for example, an internal combustion engine and/or an electric motor, etc.), transmission components, steering components (e.g., which may include one or more of a steering wheel, a steering rack, etc.), braking components (as described below), parking assist components, adaptive cruise control components, adaptive steering components, movable seats, etc.

Additionally, the vehicle computer 110 may be configured to communicate with devices external to the vehicle 105 via a vehicle-to-vehicle communication module or interface 130, for example, by vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2X) wireless communication with another vehicle, an infrastructure node 140 (typically via direct radio frequency communication), and/or a remote server 145 (typically via a network 135). The module 130 may include one or more mechanisms by which the vehicle computer 110 may communicate, including any desired combination of wireless (e.g., cellular, wireless, satellite, microwave, and radio frequency) communication mechanisms, and any desired network topology (or topologies when multiple communication mechanisms are utilized). Exemplary communications provided via module 130 include cellular, and data communications services,IEEE 802.11, Dedicated Short Range Communication (DSRC), and/or Wide Area Networks (WANs), including the internet.

The network 135 includes one or more mechanisms by which the vehicle computer 110 can communicate with the infrastructure node 140, the central server 145, and/or the second vehicle 150 a. Thus, the network 135 can be one or more of a variety of wired or wireless communication mechanisms, including any desired combination of wired (e.g., cable and fiber) and/or wireless (e.g., cellular, wireless, satellite, microwave, and radio frequency) communication mechanisms, as well as any desired network topology (or topologies when multiple communication mechanisms are utilized). Exemplary communication networks include wireless communication networks (e.g., using bluetooth, Bluetooth Low Energy (BLE), IEEE 802.11, vehicle-to-vehicle (V2V) such as Dedicated Short Range Communication (DSRC), etc.), Local Area Networks (LANs), and/or Wide Area Networks (WANs), including the internet, that provide data communication services.

The infrastructure node 140 includes a physical structure, such as a tower or other support structure (e.g., pole, box mountable to a bridge support, cell phone tower, road sign support, etc.), on which the infrastructure sensors 165, as well as the infrastructure communication module 170 and computer 175 may be mounted, stored and/or housed and powered, etc. For ease of illustration, one infrastructure node 140 is shown in fig. 1, but system 100 may, and likely does, include tens, hundreds, or thousands of nodes 140. The infrastructure nodes 140 are typically stationary, i.e., fixed to a particular geographic location and cannot be moved from that location. The infrastructure sensors 165 may include one or more sensors such as described above for the vehicle 105 sensors 115, e.g., lidar, radar, cameras, ultrasonic sensors, and the like. The infrastructure sensors 165 are fixed or stationary. That is, each sensor 165 is mounted to an infrastructure node so as to have a field of view that does not substantially move and change.

The area included on the road surface map provided by the infrastructure nodes 140, i.e., the area referred to as the area "near" the nodes 140, is typically bounded by an area within the field of view of one or more node sensors 165. The word "region" as used herein should be understood to have its plain and ordinary geometric meaning, i.e., a region bounded by a boundary bounded by three or more points. For example, the triangular region is defined by a boundary line connecting three vertices of the triangle. The circular area is defined by a boundary circle defined by the endpoints of a radius extending from the center of the circle. Irregular areas, i.e. areas defined as partly or completely without regular geometric shapes, can likewise be specified. Returning to the present example, the area proximate to the infrastructure node 140 area may be substantially circular, i.e., bounded by a radius, the length of which is determined by the range of the node 140 sensor 165. Likewise, the area proximate to the vehicle 105 may be a rectangular area defined by the side boundaries of the road 155 and the front-to-back sensing range of the vehicle 105 sensors 115. Further, the area on the route of the vehicle 105 may be a designated section of the road 155. Such a route area may be defined in terms of the start and end points of the segments and the lateral boundaries of the roads 155 between the start and end points, i.e. with boundaries specified accordingly.

The communication module 170 and the computer 175 generally have features in common with the vehicle communication module 130 and the vehicle computer 110, and therefore will not be described further to avoid redundancy. Although not shown for ease of illustration, infrastructure node 140 also includes a power source, such as a battery, a solar cell, and/or a connection to a power grid.

The infrastructure node 140 computer 175 and/or the vehicle 105 computer 110 may receive data from the sensors 115, 165 to monitor one or more objects. In the context of the present disclosure, an "object" is a physical structure, i.e., a material structure, that is detected by the vehicle sensors 115 and/or the infrastructure sensors 165. The object may be a "mobile" object, an infrastructure object, or a physical feature. The physical features are physical attributes or conditions of the location or area, including attributes or conditions of infrastructure objects, such as surface conditions of the roadway 155 (e.g., the roadway 155 is an infrastructure object, and the physical features may be surface coatings (such as water or ice), deformations (such as potholes, etc.)).

A "moving" object is an object that is capable of moving, even if the moving object is movable or not actually moving at any given time. The vehicles 105, 106 are examples of moving objects. Other examples may include animals, bicycles, pedestrians, etc. The "mobile" objects are so designated for convenience to distinguish from infrastructure objects and physical features (each discussed below). Infrastructure objects are objects that are typically intentionally fixed and/or held stationary. For example, infrastructure objects may include roads 155, bridges or overpasses, road signs, exit ramps, guard rails, traffic lights, and the like.

The server 145 may be a conventional computing device programmed to provide operations such as those disclosed herein, i.e., including one or more processors and one or more memories. Further, the server 145 may be accessible via a network 135, such as the Internet or some other wide area network.

Infrastructure node 140 computer 175 may include a memory or other storage having map data describing an area around node 140 (e.g., within a predetermined radius such as 100 meters, 300 meters, etc.). For example, such map data may be received from the central server 145 by a technician of the service node 140 and/or periodically updated, and so forth. The map data typically includes geographic coordinates that define fixed or stationary objects 155 (e.g., roads 155, crosswalks, road markings such as center stripes, etc.) and physical features such as wet locations, locations with designated embankments, locations with potholes, etc.

Further, the computer 175 may receive various data from the node 140 sensors 165 and from the vehicle 105 sensors 115, for example, via V2X communication. The image data is digital image data (e.g., including pixels having density and color values) and may be acquired by the camera sensors 115, 165. The lidar data typically comprises conventional lidar point cloud data acquired by the lidar sensors 115, 165, i.e. comprises data describing points in three dimensions, i.e. each point represents a position of a surface of the object 150, 155, 160.

The vehicle computer 110 and/or the node computer 175 may receive and analyze data from the sensors 115, 165 substantially continuously, periodically, and/or when instructed by the server 145, etc. Further, conventional object classification or recognition techniques may be used, for example, in the computer 110, 175 to identify the type of object (e.g., vehicle, person, rock, pot hole, bicycle, motorcycle, etc.) and the physical characteristics of the object based on the data of the lidar sensors 115, 165, camera sensors 115, 165, etc.

Various techniques such as are known may be used to interpret the data of the sensors 115, 165. For example, the camera and/or lidar image data may be provided to a classifier that includes programming for utilizing one or more conventional image classification techniques. For example, the classifier may use machine learning techniques in which data known to represent various objects is provided to a machine learning program for training the classifier. Once trained, the classifier can accept the image as input and then provide, for each of one or more respective regions of interest in the image, an indication of one or more objects or an indication that no objects are present in the respective region of interest as output. Further, a coordinate system (e.g., a polar coordinate system or a cartesian coordinate system) applied to an area proximate to the vehicle 105 and/or the node 140 may be applied to specify a location and/or area of the object identified from the data of the sensors 115, 165 (e.g., converted to global latitude and longitude geographic coordinates, etc., according to the coordinate system of the vehicle 105 or the node 140). Still further, the computer 110, 175 may employ various techniques to fuse data from different sensors 115, 165 and/or different types of sensors 115, 165, such as data of lidar, radar, and/or optical cameras.

The computer 110, 175 may predict or estimate road friction according to a machine learning program. Fig. 2 is an illustration of an exemplary Deep Neural Network (DNN) 200. DNN 200 may be a software program that may be loaded in memory and executed by a processor included in, for example, computer 110, 175. DNN 200 may include n input nodes 205, each input node 205 accepting a set of inputs i (i.e., each set of inputs i may include one or more inputs x). DNN 200 may include m output nodes (where m and n may, but typically are not, the same number) that provide multiple sets of outputs o₁...o_m. DNN 200 includes a plurality of layers (including a number k of hidden layers), each layer including one or more nodes 205. Because the nodes 205 are designed to mimic biological (e.g., human) neurons, they are sometimes referred to as artificial neurons 205. Neuron block 210 shows inputs to and processing performed in an exemplary artificial neuron 205 i. A set of inputs x to each neuron 205₁...x_rEach multiplied by a respective weight w_i1...w_irThe weighted inputs are then summed in input function ∑ to provide the difference b, possibly_iAdjusted net input a_iThen inputting said net input a_iProviding to an activation function f which in turn provides a godOutput y via element 205i_i. The activation function f may be any suitable function typically selected based on empirical analysis. As indicated by the arrows in fig. 2, the output of the neuron 205 may then be provided for inclusion in a set of inputs to one or more neurons 205 in the next layer.

DNN 200 may be trained to accept sensor 115 and/or sensor 165 data as input, for example, from a vehicle 101CAN bus or other network, from node 140 sensor 165, etc., and output an estimated road friction. The DNN 200 may be trained with ground truth data, i.e., data about real world conditions or states. The weight w may be initialized by using, for example, a gaussian distribution, and the deviation b of each node 205 may be set to zero. Training the DNN 200 may include: the weights and biases are updated via optimization via conventional techniques, such as back propagation. In one example, exemplary initial and final (i.e., post-training) parameters (in this context, the parameters are weights w and biases b) for the node 205 are as follows:

parameter(s)	Initial value	Final value
			w1	0.902	-0149428
w2	-0.446	-0.0102792
			w2	1.152	0.00850074
wr	0.649	0.00249599
			bi	0	0.00241266

TABLE 1

The set of weights w for node 205 together act as a weight vector for node 205. The weight vectors of the respective nodes 205 in the same layer of the DNN 200 may be combined to form a weight matrix for that layer. The offset values b for respective nodes 205 in the same layer of DNN 200 may be combined to form an offset vector for that layer. The weight matrix for each layer and the deviation vector for each layer may then be used in the trained DNN 200.

In the present context, ground truth data for training the DNN 200 typically includes data specifying the speed or average speed of the vehicles 106 in an area on the road 155 (e.g., within a specified distance of the vehicles 105, such as within 500 meters), as well as data regarding the environment in the area. Table 2 below identifies other possible inputs to DNN 200:

TABLE 2

Thus, the DNN 200 may be trained by obtaining data specifying inputs such as those above, as well as corresponding road rubs associated with various combinations of inputs. Advantageously, the following problems may be avoided, which are caused not only by an inability to estimate the friction of a location or area before the vehicle 105 is at that location or area, and/or by estimating the friction from only one or more speeds of the vehicle 106 at that location or area. For example, even when road friction is not reduced, the vehicle 106 may be slowed down by an emergency vehicle, by construction, based on weather conditions, or ambient light conditions. Thus, processing such additional inputs by a machine learning program such as DNN 200 may provide a more accurate and reliable determination of road friction.

FIG. 3 is a flow chart of an exemplary process 300 for estimating or predicting road friction and operating a vehicle according to the predicted road friction. The blocks of process 300 may be performed by vehicle computer 110 or node computer 175.

The process 300 begins at block 305, where the computer 110, 175 obtains speed data for each of a plurality of vehicles 106 in an area, which is then aggregated to determine traffic speed in block 305. This aggregated speed data may be referred to as traffic speed because it represents an average or other representation (e.g., some statistical measure different from the average) of the speeds of two or more vehicles 106 in the area. For example, computer 110 may obtain speed data for an upcoming area of the vehicle 105 route, e.g., an average speed of vehicle 106, from server 145, e.g., according to a currently existing application that collects and reports vehicle speed data for an area of road 155. In another example, the node computer 175 may obtain data from the sensor 165 indicating the respective speed of the vehicle 106 proximate to the node 140. Computer 175 may then provide an average vehicle 106 speed for the area over a time period of monitoring speed (e.g., one minute, two minutes, etc.). It should be noted that determining traffic speed based on the average speed of the vehicle 106, etc., does not require or generally does not include determining a derivative of the speed of the vehicle 106, i.e., positive or negative acceleration. However, determining the traffic speed based on the respective speeds of the plurality of vehicles 106 is a prerequisite to predicting a single value of road friction for a location as discussed below in block 320, i.e., the predicted coefficient of friction is for the location or area of the road, rather than for one or more particular vehicles 106.

Next, in block 310, the computer 110, 175 may determine whether the traffic speed determined in block 305 is below a specified threshold speed. For example, the specified threshold speed may be based on a speed limit of the area, e.g., the threshold may be a speed limit, or may be a specified amount above or below the speed limit, e.g., five percent or ten percent. If the traffic speed is not below the threshold speed, the process 300 proceeds to block 330, discussed below. Otherwise, process 300 proceeds to block 315.

Block 310 may be omitted, for example, block 305 discussed above and block 315 discussed below may be combined. It is even possible that blocks 305 and 310 may be omitted, i.e. road friction may be predicted by a machine learning procedure as described herein, without having traffic speed as an input. However, if the traffic speed is at a normal or expected speed, then road friction is likely not to be reduced or abnormal, and the computers 110, 175 need not expend processing cycles to predict road friction, as described with respect to the remainder of the process 300.

In block 315, the computer 110, 175 obtains second data, i.e., input for the machine learning procedure that is different from the traffic speed described with respect to block 305. Such inputs may include data as described above with respect to table 2. Further, the computer 110, 175 may obtain data from the sensors 115, 165 regarding, for example, ambient temperature, the presence or absence of precipitation, ambient light, and the like. Likewise, data regarding road 155 characteristics (i.e., physical characteristics of road 155, such as whether an area of road 155 includes a bridge) may be obtained from, for example, map data and/or data of camera sensors 115, 165: a sign indicating the presence of a bridge or other physical feature, such as a speed bump, etc., or an image of such physical feature that may be identified using image recognition techniques. Still alternatively or additionally, second data may be obtained from the server 145, for example reporting weather conditions, the location or area of a construction zone, a planned or current route of an emergency vehicle, or the like.

Next, in block 320, the computer 110, 175 provides the second data and typically also traffic speed as input to a trained machine learning program (e.g., DNN 200) which then predicts road friction μ and then provides road friction μ as output in block 325. The output road friction may then be used to operate the vehicle 105, for example, as described with respect to fig. 4.

In block 330, which may follow either of blocks 310, 325, the computer 110, 175 determines whether the process 300 should continue. For example, where the vehicle 105 continues to operate, i.e., continues to travel on the road 155, the vehicle computer 110 may continue and may return to block 305 to determine an estimated or predicted road friction for a second or subsequent area of the vehicle 105 route. Further, the computer 110, 175 may estimate or predict road friction for an area over a second or subsequent time period. If the process 300 is to continue, the process 300 returns to block 305. Otherwise, process 300 ends after block 330.

Fig. 4 illustrates an exemplary process 400 of operating the vehicle 105 according to road friction as estimated or predicted, for example, above with respect to process 300. The process 400 may be performed according to instructions stored in a memory of the vehicle computer 110.

The process 400 begins at block 405, where the vehicle 105 is operating in an area or location that has provided road friction as described with respect to the process 300.

Next, in block 410, the computer 110 provides the road friction from the process 300 to the one or more components 125. For example, traction control systems, lane keeping systems, lane change systems, speed management, etc. may all operate based at least in part on road friction. For example, certain driver assistance systems (such as lane change or brake assistance) may be disabled altogether when the road friction estimate is below a threshold, or different calibrations may be used to allow the features to operate more properly. In another example, a vehicle 105 having a selectably managed function may automatically switch to "snow mode" in low road friction conditions. Further, for example, when the road friction estimate is below a threshold, vehicle 105 features that allow a semi-automatic "hands-off" mode in which the operator's hands may be off the steering wheel may be disabled.

Next, in block 415, the computer 110 operates the vehicle 105 by actuating the components 125 according to the road friction from the process 300.

Next, in block 420, the computer 110 determines whether to continue the process 400, e.g., whether the vehicle 105 continues to operate, is heading toward a subsequent zone where its new road friction should be determined, etc. If process 400 is to continue, process 400 returns to block 405. Otherwise, process 400 ends after block 420.

As used herein, the adverb "substantially" means that shapes, structures, measurements, quantities, times, etc. may deviate from the precisely described geometries, distances, measurements, quantities, times, etc. due to imperfections in materials, machining, manufacturing, data transmission, computational speed, etc. The word "substantially" should be understood similarly.

In general, the described computing systems and/or devices may employ any of a number of computer operating systems, including, but in no way limited to, the following versions and/or variations of the operating system: fordApplication program, AppLink/SmartDevice Link middleware, Microsoft WindowsOperating System, Microsoft WindowsOperating System, Unix operating System (e.g., distributed by Oracle corporation of the coast of sequoia, Calif.)Operating system), the AIX UNIX operating system, the Linux operating system, the Mac OSX and iOS operating systems, the Mac OS operating system, the BlackBerry OS, the BlackBerry, Inc. of Tokyo, Calif., the Android operating system developed by Google and the open cell phone alliance, or the QNX software system supplied by International Business machines corporation, Armonk, N.Y.CAR infotainment platform. Examples of computing devices include, but are not limited to: an on-board computer, a computer workstation, a server, a desktop, a notebook, a laptop, or a handheld computer, or some other computing system and/or device.

Computers and computing devices generally include computer-executable instructions that may be executed by one or more computing devices, such as those listed above. The computer-executable instructions may be compiled or interpreted by a computer program created using a variety of programming languages and/or techniques, including but not limited to Java alone or in combination^TMC, C + +, Matlab, Simulink, Stateflow, Visual Basic, Java Script, Perl, HTML, and the like. Some of these applications may be compiled and executed on a virtual machine (such as a Java virtual machine, a Dalvik virtual machine, etc.). In general, a processor (e.g., a microprocessor) receives instructions, e.g., from a memory, a computer-readable medium, etc., and executes the instructions, thereby performing one or more processes, including one or more of the processes described herein. Such instructions and other data may be stored and transmitted using a variety of computer-readable media. A file in a computing device is generally a collection of data stored on a computer-readable medium, such as a storage medium, random access memory, or the like.

The memory may include a computer-readable medium (also referred to as a processor-readable medium) including any non-transitory (e.g., tangible) medium that participates in providing data (e.g., instructions) that may be read by a computer (e.g., by a processor of a computer). Such a medium may take many forms, including but not limited to, non-volatile media and volatile media. Non-volatile media may include, for example, optical or magnetic disks and other persistent memory. Volatile media may include, for example, Dynamic Random Access Memory (DRAM), which typically constitutes a main memory. Such instructions may be transmitted by one or more transmission media, including coaxial cables, copper wire and fiber optics, including the wires that comprise a system bus coupled to the processor of the ECU. Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, a RAM, a PROM, an EPROM, a FLASH-EEPROM, any other memory chip or cartridge, or any other medium from which a computer can read.

A database, data store, or other data storage described herein may include various mechanisms for storing, accessing, and retrieving various data, including a hierarchical database, a set of files in a file system, an application database in a proprietary format, a relational database management system (RDBMS), and so forth. Each such data storage device is generally included within a computing device employing a computer operating system (such as one of those mentioned above) and is accessed via a network in any one or more of a variety of ways. The file system may be accessible from a computer operating system and may include files stored in various formats. RDBMS generally employ the Structured Query Language (SQL) in addition to the languages used to create, store, edit, and execute stored programs, such as the PL/SQL language mentioned above.

In some examples, system elements may be implemented as computer readable instructions (e.g., software) on one or more computing devices (e.g., servers, personal computers, etc.) stored on computer readable media (e.g., disks, memory, etc.) associated therewith. A computer program product may comprise such instructions stored on a computer-readable medium for performing the functions described herein.

With respect to the media, processes, systems, methods, heuristics, etc. described herein, it should be understood that, although the steps of such processes, etc. have been described as occurring according to a certain ordered sequence, such processes could be practiced with the described steps performed in an order different than the order described herein. It should also be understood that certain steps may be performed simultaneously, that other steps may be added, or that certain steps described herein may be omitted. In other words, the description of processes herein is provided for the purpose of illustrating certain embodiments and should in no way be construed as limiting the claims.

Accordingly, it is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of the invention should be determined, not with reference to the above description, but instead should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. It is anticipated and intended that the technology discussed herein will not be developed in the future and that the disclosed systems and methods will be incorporated into such future embodiments. In sum, it should be understood that the invention is capable of modification and variation and is limited only by the following claims.

Unless expressly indicated to the contrary herein, all terms used in the claims are intended to be given their plain and ordinary meaning as understood by those skilled in the art. In particular, unless a claim recites an explicit limitation to the contrary, the use of singular articles such as "a," "the," "said," or the like should be read to recite one or more of the indicated elements.

According to the invention, a method comprises: determining road friction for the road location based on traffic speeds determined from respective speeds of each of the plurality of vehicles; and operating the vehicle based on the road friction.

According to one embodiment, the road friction is determined based on second data in addition to the traffic speed, the second data being one of: whether the location includes a bridge or overpass, sun conditions, rain conditions, snow conditions, fog conditions, construction conditions, the presence or absence of emergency vehicles, the presence or absence of debris, or ambient temperature.

According to one embodiment, the invention is further characterized in that: the second data is obtained from a map.

According to one embodiment, the invention is further characterized in that: determining whether the traffic speed is below a threshold traffic speed; and providing the traffic speed only when it is determined that the traffic speed is below the threshold traffic speed, thereby determining the road friction based on the traffic speed.

According to one embodiment, the area is comprised on a planned route of the vehicle.

According to one embodiment, operating the vehicle based on the road friction comprises: controlling traction, speed, steering, braking, lane keeping, or lane change.

According to one embodiment, determining the road friction comprises: the road friction is obtained as an output from a machine learning program.

According to one embodiment, the machine learning program is provided in an infrastructure node computer.

According to one embodiment, the machine learning program is provided in a computer in the vehicle.

According to one embodiment, the invention is further characterized in that: providing the traffic speed and the second data for an area comprising the road location, thereby providing the road friction for the area; wherein the area is defined according to a start point and an end point of the road section.

According to the invention, there is provided a computer having a processor and a memory, the memory storing instructions executable by the processor such that the computer is programmed to: determining road friction for the road location based on traffic speeds determined from respective speeds of each of the plurality of vehicles; and operating the vehicle based on the road friction.

According to one embodiment, the computer is further programmed to determine the road friction based on second data in addition to the traffic speed, the second data being one of: whether the location includes a bridge or overpass, sun conditions, rain conditions, snow conditions, fog conditions, construction conditions, the presence or absence of emergency vehicles, the presence or absence of debris, or ambient temperature.

According to one embodiment, the computer is further programmed to obtain the second data from a map.

According to one embodiment, the computer is further programmed to determine whether the traffic speed is below a threshold traffic speed, and provide the traffic speed only when it is determined that the traffic speed is below the threshold traffic speed, thereby determining the road friction based on the traffic speed.

According to one embodiment, the area is comprised on a planned route of the vehicle.

According to one embodiment, operating the vehicle based on the road friction comprises: controlling traction, speed, steering, braking, lane keeping, or lane change.

According to one embodiment, determining the road friction comprises: the road friction is obtained as an output from a machine learning program.

According to one embodiment, the machine learning program is provided in an infrastructure node computer.

According to one embodiment, the invention is further characterized in that: programming for executing a machine learning program.

According to one embodiment, the computer is further programmed to provide a traffic speed for an area including a road location, thereby providing a road friction for the area; wherein the area is defined according to a start point and an end point of the road section.