Driver assistance system

Abstract

Methods and system are herein provided for a driver assistance system. In one example, a driver assistance system comprises a computing device comprising one or more processors and a memory, wherein the computing device is configured to: receive vehicle state data; receive driving state data, wherein the driving state data comprises environmental data, road data, and map data; determine a recommended vehicle speed based on the vehicle state data and the driving state data; and output the recommended vehicle speed to a driver of the vehicle.

Description

DRIVER ASSISTANCE SYSTEMTECHNICAL FIELD

[0001] Embodiments of the subject matter disclosed herein relate to driver assistance, and more particularly to systems and methods for recommending vehicle speed.BACKGROUND AND SUMMARY

[0002] Driver assistance may include any type of relief that is provided to an individual associated with a vehicle to increase individual protection and enhance driver experience, with the aim of increasing driver safety and road safety. Such reliefs include decreased cognitive load, changes to vehicle parameters such as vehicle speed, for example in the instance of adaptive cruise control, and the like. Driver assistance systems have been developed to assist the individual in controlling the vehicle. For example, advanced driver assistance systems (ADAS), including adaptive cruise control capabilities, lane assist capabilities, and the like are incorporated into vehicle systems that aid the driver in safe driving, including maintaining safe distance from other vehicles by changing vehicle speed and maintaining position within a lane. However, current driver assistance systems may not account for current vehicle state or varying road conditions when altering vehicle operating states or determining recommendations to make to the driver. Vehicle speed is one parameter of vehicle safety that depends on vehicle state, road conditions, and traffic conditions. For example, tire traction, vehicle handling, and the like are affected by vehicle speed, especially in variable environments and with variable vehicle states.

[0003] The inventors herein have recognized the aforementioned issues and developed a driver assistance system that at least partially addresses these issues. The driver assistance system as herein disclosed receives vehicle state data, including parameters such as vehicle load, tire condition, vehicle dynamics, and vehicle health, along with driving state data. Driving state data includes environmental data such as weather, road conditions (e.g., icy, snowy, dry), and traffic information, road data, including gradients and surface quality, and map data. The vehicle state data and the driving state data are analyzed to determine parameters including recommended vehicle speed. The recommended vehicle speed is outputted to the driver and / or outputted to ADAS and / or autonomous driving systems adjustment of vehicle operating state, includingadjustment of vehicle speed. In this way, the driver assistance system may utilize vehicle specific data as well as environmental data to recommend a driving speed for the driver.SUMMARY

[0004] In one example, a driver assistance system for a vehicle comprises a computing device comprising one or more processors and a memory, wherein the computing device is configured to: receive vehicle state data; receive driving state data, wherein the driving state data comprises environmental data, road data, and map data; determine a recommended vehicle speed based on the vehicle state data and the driving state data; and output the recommended vehicle speed to a driver of the vehicle.

[0005] In another example, a method comprises receiving, at a driver assistance system of a vehicle, vehicle state data of the vehicle; receiving, at the driver assistance system of the vehicle, driving state data of the vehicle including environmental conditions and road conditions; determining, based on the vehicle state data and the driving state data, a recommended vehicle speed; and outputting the recommended vehicle speed.

[0006] In another example, a method for a driver assistance system comprising a computing device comprises receiving vehicle state data specific to a vehicle from one or more vehicle systems and one or more sensors of the vehicle; receiving driving state data specific to environmental conditions from the one or more sensors of the vehicle and a server; determining, via application of one or more machine learning (ML) algorithms, a recommended vehicle speed based on the vehicle state data and the driving state data; and outputting the recommended vehicle speed to a user interface of the vehicle.

[0007] It should be understood that the brief description above is provided to introduce in simplified form a selection of concepts that are further described in the detailed description. It is not meant to identify key or essential features of the claimed subject matter, the scope of which is defined uniquely by the claims that follow the detailed description. Furthermore, the claimed subject matter is not limited to implementations that solve any disadvantages noted above or in any part of this disclosure.BRIEF DESCRIPTION OF THE DRAWINGS

[0008] FIG. 1 schematically illustrates a driver assistance system accord to one or more embodiments of the present disclosure;

[0009] FIG. 2 schematically illustrates the driver assistance system of FIG. 1 according to one or more embodiments of the present disclosure;

[0010] FIG. 3 schematically illustrates interactions of the driver assistance system according to one or more embodiments of the present disclosure; and

[0011] FIG. 4 shows a flowchart illustrating a method for a driver assistance system according to one or more embodiments of the present disclosure.

[0012] FIG. 5 is a timing diagram for a use-case scenario for the driver assistance system.DETAILED DESCRIPTION

[0013] The following description relates to systems for a driver assistance system. The driver assistance system herein disclosed ingests various types of data to output a vehicle specific speed recommendation. FIG. 1 shows a block diagram of a driver assistance system. FIGS. 2 and 3 show data transmission patters of the driver assistance system. FIG. 4 shows a method for the driver assistance system.

[0014] Driving safety, among other factors, generally depends on a current driving speed of a vehicle. Vehicles are generally required to comply with speed limits set by governments or communities. The speed limits provide a maximum speed that is allowed on specific streets, roads, or sections of streets. This maximally allowed speed, however, may not be recommended under all circumstances due to vehicle and environmental effects on vehicle traction, handling, braking performance, and the like. For example, in heavy rain or fog, or when a street is covered in snow, a speed well below the maximum speed limit may be recommended to maintain optimal traction, handling, and other parameters. Drivers may not always be able to assess current driving conditions correctly and may drive at the set speed limit rather than at a different (e.g., higher or lower) recommended vehicle speed under the current conditions. This may put the driver and any passengers of the vehicle as well as other road users at risk, as driving at too high speeds under certain driving conditions may result in incidents. The driver assistance system and method thereof disclosed herein are able to determine a recommended speed in real time for a particular vehiclebased on vehicle state data and driving state data, wherein the driving state data includes environmental data, road data, and the like.

[0015] FIG. 1 schematically illustrates a driver assistance system 100 in a block diagram. The driver assistance system 100 for a vehicle comprises a computing device 110, the computing device 110 comprising one or more processors 112 and a memory 114. The computing device 110 may be configured to receive data related to current driving conditions. The current driving conditions may include both vehicle state data and driving state data, wherein the driving state data includes current environmental data, current road data, and current map data. The computing device 110 may be configured to analyze the received vehicle state data and driving state data and determine a recommended vehicle speed based thereon. Thus, the driver assistance system may consider data of the environment, including current weather, road condition (e.g., icy, snowy, dry, etc.), and the like, the road the vehicle is traveling on, including gradient, surface quality, and the like, and current map data, including upcoming intersections, traffic status, and the like as well as data specific to the particular vehicle, including parameters such as current vehicle load, tire tread condition, vehicle dynamics, and health of various vehicle systems to determine a recommended speed that is particular to the vehicle and the current driving conditions. The computing device 110 may be further configured to output the determined recommended speed.

[0016] Computing device 110 may be any kind of device that includes one or more processor(s) 112 such as a system-on-a-chip (SoC). In some embodiments, computing device 110 can be a head unit or other component included in a vehicle system. Generally, computing device 110 may be configured to coordinate the overall operation of driver assistance system 100. The embodiments disclosed herein contemplate any technically-feasible system configured to implement the functionality of driver assistance system 100 via computing device 110. In various embodiments, computing device 110 may be located in various environments including, without limitation, road and / or land vehicle environments such as, e.g., consumer vehicles, commercial vehicles, bicycles, motorcycles, wheeled drones, and so forth.

[0017] Processor(s) 112 may be any technically-feasible form of processing device configured to process data and execute program code. Processor(s) 112 could include, for example and without limitation, a system-on-chip (SoC), a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (PFGA), and / or the like. Processor(s) 112 may includeone or more processing cores. In operation, processor(s) 112 may be a primary processor of the computing device 110, controlling and coordinate operations of other system components. For example, processor(s) 112 may be configured to execute instructions (e.g., methods, algorithms, processes, etc.) stored in memory 114.

[0018] Memory 114 may store, for example, a speed recommendation application 116. Memory 114 may include a memory module or a collection of memory modules. Memory 114 may be non-transitory memory or other form of non-volatile memory, random access memory (RAM), or any other feasible type of memory storage system. In various embodiments, processor(s) 112 can execute instructions of the speed recommendation application 116 to implement the overall functionality of the computing device 110 and, thus, to coordinate the operation of the driver assistance system 100 as a whole. For example, data received by the computing device 110 may be processed by the speed recommendation application 116 to determine a recommended speed at which the vehicle can be optimally driven under the current conditions. The computing device 110 may then output the determined recommended speed in various forms. For example, processor(s) 112 may send a command that includes a recommended speed to external devices. In some embodiments, the speed recommendation application 116 may be stored and loaded into the memory 114 for execution.

[0019] The computing device 110, when determining a recommended driving speed via the speed recommendation application 116, may consider any data related to current vehicle state and current driving state. The current vehicle state may include data specific to the vehicle, such as load, tire condition, braking system condition, vehicle dynamics including yaw rate and the like. The current driving state may include environmental data, road data, and map data, as previously described. For example, the computing device 110 may be coupled to and configured to receive data from at least one of one or more vehicle systems 202, a server or cloud 204, and one or more sensors 206 mounted on or in the vehicle. The one or more vehicle systems 202 may include, for example, a navigation unit, a braking system, a tire monitoring system, a load sensing unit, a global positioning system (GPS), a steering input system, and the like. The one or more sensors 206 may include, for example, externally and / or internally facing cameras, rain sensors, thermometers, LiDAR sensors, RADAR sensors, ultrasonic and infrared sensors, and so on. Vehicles are often equipped with these sensors and vehicle systems as part of standard manufacturing. The computingdevice 110 may be configured to receive any data concerning the vehicle itself and its surrounding environment from units mounted on or in the vehicle as well as from a cloud server.

[0020] The speed recommendation application 116 may include any feasible algorithm configured to ingest the various received data types and output the recommended vehicle speed. In one example, the speed recommendation application 116 may utilize machine learning (ML) algorithms 118 that are trained to ingest the various types of data herein discussed and output a recommended speed based thereon. In some examples, the ML algorithms 118 may be trained based on acquired data from real driving scenarios and / or simulated driving scenarios in which various vehicle state (e.g., vehicle weight, tire tread status, etc.) and driving state (e.g., weather condition, road condition, etc.), vehicle speeds, and safety labels are used as training inputs and recommended vehicle speeds are used as training outputs. The ML algorithms 118 may then ingest the received data from the one or more vehicle systems 202, server 204, and one or more sensors 206 and may output a recommended vehicle speed. In some examples, the recommended vehicle speed may be considered a safe driving speed for the given conditions.

[0021] The ML algorithms 118 may continuously learn from the ingested and outputted data. In some examples, the data may be collected locally within the vehicle in order to repeatedly update the ML algorithms 118 for the specific vehicle. The ML algorithms 118 may also ingest data in a central manner, for example from a cloud computing platform or via vehicle-to- everything (V2X) communication to ingest data external to the vehicle. Over time, more and more data may be collected and analyzed by the driver assistance system 100, and optionally by other driver assistance systems of other vehicles. The driver assistance system 100 may thus take into account historic data as well as real time data when determining a recommended vehicle speed. Thus, the driver assistance system 100 may become more adept over time at recommending speeds. This self-improving mechanism may ensure that the driver assistance system 100 remains accurate and relevant even if conditions change and as new data becomes available.

[0022] The ML algorithms 118 may learn from specific driving conditions and patterns associated with individual vehicles, and may further refine the speed recommendations in order to align with the characteristics and driving preferences of the particular vehicle. While not specifically described herein, it should be understood that the use of ML algorithms is one option and other algorithms aside from ML algorithms may also be used to determine the recommended speed.

[0023] The computing device 110 may also be coupled to external sources, such as the server or cloud 204. The computing device 110, via connection to the server 204, may be configured for V2X communication, specifically vehicle-to-vehicle (V2V) communication, vehicle-to-pedestrian (V2P), and / or vehicle-to-infrastructure (V2I) communication. Thus, the computing device 110 may be configured to receive data regarding the environment, including road conditions, road data, and map data from external sources including other vehicles on the road and infrastructure including road side units (RSUs) and the like. Similarly, the computing device 110, via connection to the server 204, may be configured to access the Internet or the like to obtain externally stored data such as weather data, including precipitation data, temperature data, and the like, traffic data, and more. Vehicles are also often equipped with one or more cameras. Information about a surrounding environment, including weather, road surface condition, road type, gradient, and status, traffic status information, and the like may be gathered by means of externally facing cameras. Information about a surrounding environment may additionally or alternatively be gathered by means of other sensors including rain sensors, thermometers, and the like as described above.

[0024] The current vehicle stat data received by the computing device 110, for example from the one or more vehicle systems 202, may include a current load of the vehicle, a current mark, type, and condition of tires of the vehicle, a type of the vehicle, vehicle dynamics, age, wear, and operation of one or more vehicle components, and current vehicle equipment information. The one or more vehicle components may include systems such as braking systems, suspensions, powertrains, engine and / or motor. Vehicle dynamics may include yaw rate, lateral acceleration, and steering input that affect vehicle handling. If, for example, the vehicle is comparably old, and its brakes have not been replaced, a braking distance may be longer as compared to the same vehicle having brakes that in a good or as good as new condition. Similarly, the condition of many other vehicle components may influence the recommended speed for the specific vehicle. The current mark, type, and condition (e.g., wear, pressure, and temperature) of tires of the vehicle may also have an influence as to a recommended speed. For example, more worn tries may have less tread and therefore lower speed for greater braking distance or traction on turns may be recommended. Further, a vehicle may generally drive at a higher speed if no vehicle equipment such as, e.g., a trailer, a roof box, one or more bikes, etc., is attached to the vehicle. However, relatively lighter vehicles without attached equipment may have generally higher recommendedspeeds compared to heavier vehicles (e.g., vehicles with higher loads), but, in certain circumstances, such as during periods of high wind speeds, recommended speed may be lower for the lighter vehicles than heavier vehicles. Thus, the driver assistance system 100 may take both current driving state as well as current vehicle state into account in order to determine the recommended vehicle speed.

[0025] The current environmental data received by the computing device 110 may comprise at least one of current weather conditions in a surrounding environment of the vehicle, a visibility of the surrounding environment of the vehicle, a current road condition, and a current traffic volume. The current weather conditions may include parameters such as temperature, precipitation status, wind speed, and the like. As an example, the recommended vehicle speed may generally be higher for vehicles in dry conditions. When it is raining or snowing, for example, a lower speed may be recommended for the same vehicle due to effect of precipitation on traction, vehicle handling, visibility, and the like. However other factors, such as wind speeds, may alter the recommended vehicle speeds for different vehicles in different ways based on current vehicle state data. Other factors, as will be explained further with respect to FIGS. 3 and 4 may be considered when determining the recommended speed.

[0026] The current road data received by the computing device 110 may comprise current road course of the road the vehicle is being driven on (e.g., straight, curvy, winding, etc.), a current gradient of the road, a surface quality of the road (e.g., smooth, loose gravel, paved with potholes, paved without potholes, etc.), and a current speed limit set by government or communities. The current map data received by the computing device 110 may comprise type of road the vehicle is being driven on (e.g., multi-lane highway, single-lane street, residential street, forest road, etc.), a speed limit, a current road course, and information about intersections that are upcoming within a defined timeframe.

[0027] The computing device 110 may be configured to output the determined recommended vehicle speed in one or more ways. For example, the computing device 110 may output the recommended vehicle speed to a user interface 302. The user interface 302 may be configured as part of the vehicle dashboard, a vehicle infotainment unit, or the like. The computing device 110, in outputting the recommended vehicle speed to the user interface 302, may instruct the user interface 302 to present a visual or audible reproduction of the recommended speed to the driver of the vehicle. The user interface 302 may comprise a display, for example, and the recommendedspeed may be presented on the display as a guidance to the driver of the vehicle. Additionally or alternatively, the user interface 302 may comprise one or more loudspeakers (e.g., loudspeakers of the infotainment unit), and an audible reproduction (e.g., a spoken reproduction) of the recommended speed may be output via the one or more loudspeakers. In this respect, the recommended vehicle speed may be directly conveyed to the driver. Further, if the driver exceeds the recommended speed, as determined by a speedometer, the computing device 110 may output via the user interface an alert indicating the current speed exceeds the recommended speed.

[0028] In other examples, the computing device 110 may be configured to output the recommended speed to an autonomous driving system 304 and / or to an advanced driver assistance system (ADAS) 306. The computing device 110 may instruct the autonomous driving system 304 or ADAS 306 to set a current speed of the vehicle to the recommended speed.

[0029] For example, the ADAS 306 may comprise an adaptive cruise control system or standard cruise control system that is manually set by the driver to a certain traveling speed. An adaptive cruise control system may modulate the set speed based on proximity to another vehicle that is in front of the vehicle. For example, if the set speed is 75 mph and the other vehicle that is in front of the vehicle is traveling at 70 mph, the adaptive cruise control system may adaptively reduce the speed of the vehicle to 70 mph once within a predefined distance of the other vehicle. Standard cruise control systems may maintain the set speed of the vehicle without regard for other vehicles on the road. In some examples, for example in electric vehicles, the system may oscillate the vehicle speed around the set vehicle speed to optimize electric motor efficiency. When the computing device 110 instructs the ADAS 306 to set the current speed to the recommended speed, the set cruise control speed may be changed to the recommended speed, which may be lower or higher than the set cruise control speed.

[0030] In examples in which an oscillating cruise control is employed in order to optimize electric motor efficiency, the recommended vehicle speed may also include an oscillation pattern. For example, the recommended vehicle speed may include one of a narrower oscillation pattern at a first speed (e.g., a more stagnant speed) and wider oscillation pattern (e.g., a more variable speed) at a second speed. In some examples, the wider oscillation pattern may provide for more efficient motor output, but the second speed may be lower than the first speed and thus the first speed may be more desirable to the driver in certain circumstances. Based on predefined settings or user preferences, the computing device 110 may select one of the two to output.

[0031] For autonomous driving vehicles, similar to adaptive cruise control, the speed of the vehicle may be automatically adapted based on driving conditions such as government or community issued speed limits and distances to other vehicles on the road. When the computing device 110 instructs the autonomous driving system 304 to set the current speed to the recommended speed, the autonomous driving system 304 may use the recommended speed instead of the speed limit to determine vehicle speed.

[0032] In this way, the driver assistance system 100 as herein presented, based on the available information concerning the vehicle and its surrounding environment, is able to provide real-time recommendations to the driver concerning a recommended driving speed under various circumstances. The driver assistance system 100 may analyze any available data and information which may include vehicle-specific parameters as well as environmental parameters and road parameters. As the driver assistance system 100 is arranged in the respective vehicle and comprises the computing device 110, the computing is performed locally within the vehicle, e.g., via edge computing. Performing the analysis and determinations locally may ensure a swift response and adaptation to changing conditions, especially as environmental conditions and road conditions may change rapidly in some circumstances. The driver assistance system 100 thus provides a centralized system that aggregates data from various inputs for further processing and analysis. The recommended speed output by the driver assistance system 100 may be refined with a holistic understanding of prevailing conditions.

[0033] Referring now to FIG. 2, exemplary interactions of the computing device 110 according to embodiments of the disclosure are schematically illustrated in a sequence diagram. The computing device 110 may first receive a request for a recommended speed. This request may be received via a user interface. For example, the driver may indicate via the infotainment unit that speed recommendations are to be determined at a specified interval. The request, alternatively, may be received from an autonomous driving system 304 or ADAS 306. Alternatively, the driver assistance system 100 may be equipped to generate recommended speeds without any request from the driver or other vehicle system. In yet further examples, various driving parameters may trigger the driver assistance system 100 to determine a recommended vehicle speed, such as the driver exceeding the speed limit, a change in weather pattern, a change in road surface, and the like. In this way, the recommended vehicle speed may be determined in real-time.

[0034] Upon receipt of a request for a safe driving speed, the computing device 110 may collect available data. For example, the computing device 110 may request vehicle state data and driving state data, including environmental data, road data, and / or map data from available sources. In some examples, certain types of data may be collected first and other types of data subsequently. In other examples the data may be retrieved at substantially the same time. One the computing device 110 receives the data that is currently available, the computing device 110 may analyze and further process the data in order to determine the recommended vehicle speed as described above.

[0035] As is explained above, the speed recommendation application 116 of the computing device 110 may utilize one or more algorithms, such as ML algorithms, to generate the recommended vehicle speed.

[0036] Referring the FIG. 3, exemplary interactions of the driver assistance system according to embodiments of the disclosure are schematically illustrated. FIG. 3 provides an overview of different kinds of data that may be received and analyzed by the computing device 110. As mentioned above, ML models and algorithms may optionally be utilized.

[0037] As is described with respect to FIG. 1 , the computing device may receive vehicle state data and driving state data. The driving state data may include environmental data, road data, and map data. The vehicle state data may include vehicle load, tire condition, vehicle type, age, wear, and operation data of vehicle components including braking systems, powertrains, and engines / electric motors, vehicle equipment data, and vehicle dynamics data. The vehicle state data may be retrieved from one or more vehicle systems and / or one or more sensors. The environmental data may include weather data, visibility data, and road condition data as retrieved from one or more sensors. The road data may comprise road course, gradient, road surface quality, road type, and speed limit as retrieved from one or more sensors, including GPS and cameras, and externally retrieved data. The map data may include road type, speed limit, road course, and intersection data as retrieved from GPS, cameras, and external data.

[0038] The various retrieved data may be ingested by the speed recommendation application to determine the recommended speed. As an example, a ML model may ingest the retrieved data and output the recommended speed. The recommended speed may be outputted for display to the driver in an audio and / or visual manner and / or may be outputted to an ADAS or autonomous driving system. The recommended vehicle speed may comply with the preset speed limits of the roads and thus the recommended vehicle speed may be equal to or less than a current speed limit.However, the recommended vehicle speed may be greater to or less than a current traveling speed of the vehicle.

[0039] As described above, the driver assistance system 100 may instruct a user interface 302 to present the speed at which the vehicle may be securely driven to a driver of the vehicle. According to some examples, only the recommended speed is then presented to a driver of the vehicle. The driver assistance system 100, according to further embodiments, may instruct the user interface 302 to present further information to the driver, in addition to the recommended speed. For example, the driver assistance system 100 may provide information to the user interface 302 concerning the reasons why a specific speed is being recommended in a specific situation and instruct the user interface 302 to also present such reasons to a driver of the vehicle. In this way, the driver may gain a better understanding why a specific speed is recommended by the driver assistance system 100.

[0040] The driver assistance system according to the various embodiments disclosed herein may be seamlessly integrated with already existing vehicle systems such as, e.g., adaptive cruise control or autonomous driving systems, and may enhance effectiveness and safety of such systems. The driver assistance system may be implemented with only few additional components. The driver assistance system may receive data from other systems already present in the vehicle, or from external servers. The computing device may analyze any such currently available data and determine a recommended speed based on such data. The kind of data that is available to a driver assistance system generally depends on the vehicle. Small and medium-sized cars may have less vehicle systems as compared to premium cars. For examples, some vehicles do not comprise any sensors monitoring a state of the tires, brakes, or other vehicle systems. Other sensors such as, e.g., rain sensors, are usually also optional. Some vehicles do not have built-in navigation systems. The amount of data that is available, therefore, highly depends on the available sources. It is also possible that the driver assistance system communicates with mobile devices such as smartphones, tablets, laptops, and so forth. The driver assistance system may receive environmental data, road data or map data via such connection, for example.

[0041] Turning now to FIG. 4, a flowchart illustrating a method 400 for a driver assistance system of a vehicle, such as driver assistance system 100 of FIG. 1, is shown. The method 400 may be executed by one or more processors of the driver assistance system, such as processor(s) 112, based on instructions stored in memory, such as memory 114. The vehicle as herein describedmay be a gasoline or diesel powered vehicle, a batery electric vehicle, a hybrid electric vehicle, a plug-in hybrid electric vehicle, a hydrogen powered vehicle, or the like. The vehicle may be equipped with one or more sensors, including cameras, RADAR, GPS, and more, as described with respect to FIG. 1. The vehicle may include a plurality of vehicle systems, including braking systems, suspension, powertrains, an engine and / or electric motor, vehicle dynamics systems, and the like that are monitored at regular intervals. The vehicle may also be equipped with a V2X communication system configured for V2X communication with other vehicles, infrastructure, and a cloud, in some examples.

[0042] At 402, method 400 includes determining whether a speed determination is indicated. A speed determination may be indicated after a predefined amount of time. For example, the driver assistance system may determine a new recommended vehicle speed at regular, predefined intervals. A speed determination may also be indicated in response to detection of a change in vehicle or driving state. For example, a change in weather (e.g., rain begins), visibility, road condition, or the like, may be detected via one or more sensors. The sensors may then send data to the driver assistance system, indicating to the system that speed determination is indicated. Other indications for speed determination may include a rapid change in driver indicated speed (e.g., as the vehicle enters a higher speed road, like a freeway), the vehicle approaching an intersection, and the like. If a speed determination is indicated, method 400 proceeds to 404. If a speed determination is not indicated, method 400 ends.

[0043] At 404, method 400 includes receiving vehicle state data from one or more vehicle systems. As is described above, the vehicle state data may include vehicle load, tire condition, vehicle type, age, wear, and operation data of vehicle components including braking systems, powertrains, and engines / electric motors, vehicle equipment data, and vehicle dynamics data. The one or more vehicle systems may include braking systems, suspensions, powertrains, engine and / or motor that store data of age, wear, and operation of components including brakes, suspensions, and powertrains (e.g., including batteries and engines / motors), as well as vehicle dynamics data including yaw rate, steering input, and lateral acceleration, and constant vehicle data including make, model, year, length, base weight, and the like. Operation data of the powertrain may include batery state of charge, output torque, set cruise control speeds, including oscillating speed parameters for motor input / output speeds and efficiency data thereof. As an example, tire condition may be determined based on sensor data that provides tire pressure (e.g., from a tire pressuremonitoring system), temperature, and tread depth. Tire condition may also be determined based on camera data of the tires to determine tread status, physical wear and tear (e.g., cracks, uneven tread, presence of sidewall bubbles, and the like). Tire condition may further be extrapolated from other data types, such as vehicle dynamics, in which certain parameter values may be associated with various tire conditions.

[0044] At 406, method 400 includes receiving driving state data. The driving state data, as previously described, may include environmental data, road data, and map data. The driving state data may be received via V2X communication, as noted at 408, from one or more sensors, as noted at 410, and / or from the one or more vehicle systems, as noted at 412. As an example, road data including traffic statuses, intersection information, and the like may be obtained via V2I communication from RSUs or other entities. Weather and visibility data may be obtained via a server connected to internet and / or from camera and temperature sensors mounted on the vehicle. Similarly, road condition, including whether the road is dry, wet, icy, snowy, etc. may be obtained via one or more camera sensors and / or RADAR sensors or the like. Map data may be obtained from a GPS and / or in-vehicle navigation system, similar to as obtained for display on a maps application of an infotainment unit of the vehicle.

[0045] At 414, method 400 includes processing the vehicle state data and the driving state data. As an example, a speed recommendation application of the computing device of the vehicle may process the received data. In some examples, processing and analyzing the vehicle state data and the driving state data may include feeding the received data through one or more ML algorithms. In other examples, other types of algorithms may be applied to the data. For example, heuristics algorithms, decision tree type algorithms, statistical and optimization algorithms, and / or time series analysis algorithms may be employed by the speed recommendation application.

[0046] At 416, method 400 includes determining a vehicle speed recommendation based on the vehicle state data and the driving state data. As explained above, the recommended vehicle speed may be determined based on the processing and analysis of the vehicle state data and the driving state data. As the vehicle state data is specific to the particular vehicle being considered, the determined vehicle speed recommendation may be specific to the vehicle. In some examples, the vehicle speed recommendation may also include engine / motor operation parameters, including oscillation patterns as well as a maximum recommended speed. As noted previously, therecommended vehicle speed may comply with an issued speed limit of the road the vehicle is traveling on.

[0047] In this way, the recommended vehicle speed may depend on environmental and roadbased factors as well as vehicle specific factors. Thus, the determined vehicle speed may be specific to the current conditions of the surroundings as well as the current conditions of the vehicle. One or more implementation scenarios are described below to illustrate how different driving state conditions and vehicle state conditions may result in different recommended vehicle speeds for different vehicles.

[0048] At 418, method 400 includes determining whether the recommended vehicle speed is different from the current speed. As described above, in some examples, the recommended vehicle speed may include both an average traveling speed as well as an oscillation pattern, for example in instances in which the vehicle is an electric vehicle operating in cruise control. If the recommended vehicle speed is different from the current speed, method 400 proceeds to 420. IF the recommended vehicle speed is not different from the current speed, method 400 ends as the current travel speed and powertrain parameters (e.g., oscillation pattern) are being maintained without change.

[0049] At 420, method 400 includes outputting the recommended vehicle speed to the driver of the vehicle. As is described with respect to FIG. 1 , the vehicle may be equipped with a user interface, such as user interface 302, which may be a component of a dash or an infotainment unit in some examples. The recommended vehicle speed may be outputted via the user interface in an audio and / or visual manner.

[0050] At 422, method 400 optionally includes adjusting vehicle operating state based on the recommended vehicle speed. In examples in which the vehicle includes an ADAS system with adaptive cruise control or an autonomous driving system, the recommended vehicle speed may adjust the parameters of the ADAS system or autonomous driving system to set the maximum speed to the recommended vehicle speed. In some examples, the recommended vehicle speed may be lower or higher than a previously set travel speed, in which case the ADAS or autonomous driving system may adjust the travel speed to the recommended vehicle speed. As noted above, in some electric vehicles, a set travel speed (e.g., a cruise control speed) may be an oscillated speed intended to optimize efficiency of the electric motor. In such vehicles, the recommended vehicle speed may also include oscillation parameters, as will be further explained below.

[0051] The method 400 may be performed at regular intervals, such as every 1 second, every 5 seconds, every 60 seconds, every 5 minutes, etc., or in response to a change such as a change in environmental condition or a change in vehicle state, such as a change in driver chosen speed. Thus, the recommended vehicle speed may be updated in real-time at each interval and in response to various state changes. In this way, the method herein described may repeatedly determine a recommended vehicle speed that compensates for rapidly changing vehicle states and surrounding conditions.

[0052] Further, the driver assistance system may present information, such as reasonings, to the driver via the user interface describing how the recommended vehicle speed is determined. Additionally, the driver assistance system may present alerts to the driver, for example blinking lights, beeping sounds, verbal audio, words, etc., when the vehicle is driven at a speed that exceeds the recommended vehicle speed.

[0053] Further, the method 400 as described herein may be performed by different vehicles with respective driver assistance systems thereof. When the vehicles are traveling along the same road at the same time, the driving state data may be the same, as the driving state data is specific to the environment, including the speed limit, the road condition, upcoming intersections at the like. The vehicles may have specific vehicle state data, however. Thus, the respective driver assistance systems may output different recommended speeds and / or oscillation patterns given that the recommended speeds are in part determined based on vehicle specific data, including load, vehicle type, age, wear, and operating state of vehicle components including the powertrain, and more. Thus, the driver assistance system as herein disclosed may provide for an individualized speed recommendation for a vehicle.

[0054] Turning now to FIG. 5, a timing diagram 500 illustrating an exemplary use-case scenario for the driver assistance system as herein disclosed. It should be understood that the usecase scenario described herein is exemplary in nature and is not intended to limit the acquired data types and outputs of the system. The vertical lines at times tl -t6 represent times of interest during the sequence, including time points relating to data acquisitions, outputted recommended vehicle speeds, and the like for a vehicle. The vehicle may be a battery electric vehicle or plug-in hybrid electric vehicle, in some examples operating with an adaptive cruise control system on. Times t4 and t5 of the sequence may be separated visually in each graph by slashed lines. As an example, times tl-t4 may correspond to a first day and times t5-t6 may correspond to a second, subsequentday. For example, times tl-t4 may be during a daily commute on the first day and times t5-t6 may be during the daily commute on the second day. Thus, the first and second sections of time may represent the vehicle driving on the same road, at the same time of day, with similar traffic patterns.

[0055] A first graph from the top of FIG. 5 includes a first plot 502 of a state of road slipperiness, as affected by precipitation, objects such as wet leaves, and the like. A second graph from the top includes a second plot 504 of a battery state of charge of the vehicle. For simplicity sake, the road slipperiness and battery state of charge are either high or low, though it should be understood that in practicality, the variations may be more specific and minute. A third graph from the top includes a third plot 506 of a recommended vehicle speed as outputted by the driver assistance system, the recommended vehicle speed may increase from bottom to top along the y- axis of the third plot. A fourth graph from the top includes a fourth plot 508 of a recommended oscillation pattern. Similarly for simplicity sake, the oscillation pattern may be wide or narrow, though it should be understood that more variable types of oscillation patterns may be available in practicality.

[0056] Time tl may represent a first data acquisition. During the first data acquisition, the driver assistance system may acquire first vehicle state data and first driving state data. Thus, at tl, a road slipperiness may be low and a battery state of charge may be high. The road slipperiness may be an example of one of multiple driving state parameters acquired from sensors and external sources, as herein described. The battery state of charge may be an example of one of multiple vehicle state parameters acquired from sensors and vehicle systems, in this case from a battery and associated battery sensors.

[0057] Time t2 may represent a first recommendation output, including a recommended vehicle speed and a recommended oscillation pattern, in this particular example. The recommendations may be determined based on the first vehicle state data and the first driving state data, as previously described. At t2, the road slipperiness may remain low and the battery state of charge may remain high. The recommended vehicle speed at t2 may be a first speed. Relative to the third graph as presented, the first speed may be higher than a second speed. Further, the recommended oscillation pattern for the powertrain of the vehicle at t2 may be narrow, given the high battery state of charge at tl -t2. With high state of charge of the battery, energy preservation and efficiency may be prioritized lower than when the state of charge is low. Thus, the oscillationpatern about the recommended vehicle speed may be narrow, which may be a less efficient patern of speed output for the powertrain.

[0058] Time t3 may represent a second data acquisition. The second data acquisition may occur at a regular interval after the first data acquisition or in response to a perceived change in environmental condition. As an example, during the second data acquisition, the driver assistance system may acquire second vehicle state data and second driving state data. The vehicle state data may be relatively unchanged compared to the first vehicle state data, with a similar batery state of charge, similar powertrain operating states, and similar load, tire condition, and the like. The second driving state data, however, may be different than the first driving state data. As an example, it may have begun to rain between time tl and time t3. For example, between times t2 and t3, the road slipperiness may increase from low to high as the road gets wet from the rain. Thus, due to the rainy weather conditions, a second recommended speed output at time t4 may be different than the first recommended speed output.

[0059] Time t4 may represent a second recommendation output of vehicle speed and oscillation pattern. Due to the unchanged vehicle state data (including a similar state of charge of the battery), the oscillation pattern may be unchanged (e.g., may remain narrow at t4). The recommended vehicle speed however, at t4, may decrease from the first speed to the second speed. Given the increased road slipperiness at t3 compared to tl, the outputted vehicle speed at t4 may be lower than the outputted vehicle speed at t2 in order to account for the decreased traction / grip of the tires on a slipperier surface. Based on the second recommended vehicle speed output, the vehicle’s adaptive cruise control may responsively adjust the driving speed and powertrain oscillation patterns. Thus, the vehicle may be traveling at a slower average speed, however the vehicle’s powertrain may continue to oscillate the speed the same as at time t2.

[0060] Time t5 of the timeline 500 may represent a third data acquisition. As noted, time t5 may occur at a time later than times tl -t4 greater than the regular interval of data acquisition. For example, time t5 may be the next day, at a similar time of day as time tl , for example during the driver’s daily commute to or from work. During the third data acquisition, third vehicle state data and third driving state data may be acquired. The third vehicle state data may be different from the first and second vehicle state data due to the separation of time. For example, at t5, the battery state of charge may be low. As an example, the battery may not have been charged overnight and thus the battery state of charge may be lower at t5 than compared to the previous day when it wasfully charged. At t5, the road slipperiness may be high. For example, it may still or again be raining at t5.

[0061] Time t6 may represent a third recommendation output of vehicle speed and oscillation pattern, wherein the third recommendation output is determined based on the third vehicle state data and the third driving state data.. At t6, the recommended vehicle speed may be the second speed given that the road slipperiness is high at t5. Further, at t6, the recommended oscillation pattern may be wide. The wide oscillation pattern may be outputted due to the lower state of charge of the battery, in which efficiency of the battery and motor is prioritized in order to reduce charge losses while driving to maximize remaining range. In some examples, the outputted speed at t6 may be even lower than the second speed, in examples in which a lower speed may optimize efficiency of the battery and motor.

[0062] The timing diagram 500 thus exemplifies how the driver assistance system uses multiple types of parameters to output vehicle speeds that are safe considering conditions as well as efficient for the vehicle systems.

[0063] The following scenarios are provided to further exemplify the driver assistance system and methods as herein described, specifically to exemplify how the system acquires vehicle specific information and driving condition specific information to generate a recommended vehicle speed that is specific to the vehicle and the circumstance.

[0064] As a first non-limiting example, a first vehicle may be traveling along a road. The first vehicle be configured as a truck or other heavy-weight vehicle. Weather conditions may be received by a first driver assistance system of the first vehicle for the road, wherein the weather conditions include relatively high wind speeds. The first driver assistance system may receive the vehicle load information of the first vehicle as well as the high wind speed condition. A second vehicle may also be traveling along the road. The second vehicle may be configured as a relatively light vehicle, compared to the first vehicle. The same weather conditions may be received by a second driver assistance system of the second vehicle for the road (e.g., at substantially the same time as the first vehicle). The second driver assistance system may receive the vehicle load information of the second, lighter weight vehicle, as well as the high wind speed condition. The first vehicle may usually have a lower recommended vehicle speed than the second vehicle due to the higher vehicle load and the resulting effect on handling. However, given the condition of high wind speed, which may adversely affect handling of the second, lighter weight vehicle more thanthe first, heaver weight vehicle, a first recommended vehicle speed of the first vehicle may be higher than a second recommended vehicle speed of the second vehicle.

[0065] As another example, a vehicle may be traveling along a road under cruise control parameters. The vehicle may be an electric vehicle and the cruise control parameters may include an oscillating speed that optimizes the electric motor’s efficiency. The driver assistance system may receive vehicle state data and driving state data as previously described. A first recommended vehicle speed option may be determined that includes a narrow oscillation pattern. A second recommended vehicle speed option may be determined that includes a wide oscillation pattern. The wide oscillation pattern may be more efficient for the electric motor than the narrow oscillation pattern but the second recommended vehicle speed may be lower than the first recommended vehicle speed. The driver assistance system may choose one of the first and second recommended vehicle speeds depending on predefined settings and operating states. For example, the vehicle may be set in “eco mode” which is configured to prioritize motor and / or engine efficiency for efficient motor, battery, and / or engine performance, in which case the second recommended vehicle speed may be selected and recommended by the driver assistance system for output to the driver and / or vehicle systems. Alternatively, the vehicle may be set in “sport mode” which is configured to prioritize acceleration and / or speed over efficiency, in which case the first recommended vehicle speed may be selected. The operating states of the vehicle’s motor may be received by the driver assistance system as one of the vehicle state data, and as such the recommended vehicle speed that is determined by the speed recommendation application may be based on the operating states as is herein described.

[0066] In this way, the driver assistance system as herein presented considers both the driving conditions, including road data and environment data, as well as vehicle specific data to generate a recommended vehicle speed that is catered specifically to the given vehicle.

[0067] Further, the following are presented as exemplary driving state conditions (e.g., weather, road condition, etc.) which may affect the recommended vehicle speed. As a first nonlimiting example, it may start snowing while a vehicle is driving. Due to the beginning snowfall, the recommended vehicle speed determined by the driver assistance system at or after the beginning of the snowfall may be lower than a previously recommended vehicle speed or previously set vehicle speed. The beginning snowfall may reduce visibility and traction of tires on the road and therefore a lower speed may be recommended.

[0068] As a second non-limiting example, a traffic volume may increase as the vehicle is driving. Due to the increased traffic volume, the recommended vehicle speed determined by the driver assistance system may be lower than a previously recommended vehicle speed or previously set vehicle speed as increased traffic volume may increase cognitive load on the driver. Therefore a reduced speed may be recommended to ensure adequate following distance of the vehicle with respect to a directly preceding vehicle.

[0069] As a third non-limiting example, a vehicle may be driven on a road in mountainous terrain. On sections of the road with a low gradient and / or on comparably straight sections of the road, a recommended vehicle speed may be higher as compared to a recommended vehicle speed on sections with an increased slope and / or on curvy and winding sections of road. The handling parameters of the vehicle, as obtained from a steering system of the vehicle, may also affect the recommended vehicle speeds.

[0070] As a fourth non-limiting example, a vehicle may be traveling on a road adjacent to or passing through a forest. That is, a probability of leaves falling on the road is significantly increased. Leaves, especially when wet, may decrease a grip of the vehicle on the road. Even further, in the vicinity of forests there is an increased risk of animals crossing the road. The driver assistance system, therefore, may output a lower recommended vehicle speed than a set speed limit of the road. As the vehicle is approaching a forest, the recommended speed output by the driver assistance system may be gradually decreased, as the distance between the vehicle and the forest decreases. Similarly, once the vehicle moves away from the forest, the recommended speed that is output by the driver assistance system may gradually increase, as the distance between the vehicle and the forest increases.

[0071] In a fifth, non-limiting example, a vehicle may be driven in an urban environment. Especially in urban environments, visibility at crossings may not always be optimal. For example, buildings, vehicles or other objects or obstacles may significantly impair visibility. As the vehicle approaches a crossing, the driver assistance system therefore may analyze the visibility conditions. If it is detected that visibility is impaired for any reason, a reduced recommended vehicle speed may be output by the driver assistance system. When driving at a reduced speed, the vehicle may be brought to a stop significantly faster if, for example, another vehicle or a pedestrian suddenly appears from behind the obstacle. It is also possible, for example, that the driver assistance system receives information about approaching vehicles or pedestrians by means of V2V and / or V2Icommunication. Receipt of such information may also result in a reduced recommended vehicle speed being output by the driver assistance system.

[0072] The technical effect of the methods and systems herein provided is that, as the driver assistance system described herein analyzes and considers vehicle specific data (e.g., vehicle load, tire mark, type and condition, vehicle type, age and wear of vehicle components, vehicle equipment information, etc.) in addition to environmental data, it is able to provide a more accurate recommended speed for a particular vehicle in any possible situation. Different vehicles may react differently in identical situations. Considering vehicle specific data in addition to environmental data, therefore, significantly increases accuracy of the system. By further applying ML algorithms, the driver assistance system may be continuously improved and refined over time such that it is able to provide suitable safe speeds for any kind of situation. The driver assistance system significantly improves road safety, as a suitable speed is output in real-time for any kind of situation.

[0073] The following claims particularly point out certain combinations and subcombinations regarded as novel and non-obvious. These claims may refer to “an” element or “a first” element or the equivalent thereof. Such claims should be understood to include incorporation of one or more such elements, neither requiring nor excluding two or more such elements. Other combinations and sub-combinations of the disclosed features, functions, elements, and / or properties may be claimed through amendment of the present claims or through presentation of new claims in this or a related application. Such claims, whether broader, narrower, equal, or different in scope to the original claims, also are regarded as included within the subject matter of the present disclosure.

Claims

CLAIMS1. A driver assistance system for a vehicle, comprising: a computing device comprising one or more processors and a memory, wherein the computing device is configured to: receive vehicle state data; receive driving state data, wherein the driving state data comprises environmental data, road data, and map data; determine a recommended vehicle speed based on the vehicle state data and the driving state data; and output the recommended vehicle speed to a driver of the vehicle.

2. The driver assistance system of claim 1 , wherein the vehicle state data comprises one or more of a current vehicle load, a current tire condition, a vehicle type, age and wear of one or more vehicle components, vehicle dynamics, and operating state of one or more vehicle components, including one or more of vehicle engine and / or motor, powertrain, braking system, and suspension.

3. The driver assistance system of claim 1, wherein the environmental data comprises one or more of weather data, visibility data, and road condition data.

4. The driver assistance system of claim 1 , wherein the road data comprises one or more of road course, gradient of road, road surface quality, road type, and speed limit.

5. The driver assistance system of claim 1, wherein the map data comprises one or more of road type, speed limit, road course, and intersection data.

6. The driver assistance system of claim 1, wherein the recommended vehicle speed is determined by a speed recommendation application configured to apply one or more machine learning (ML) algorithms to the vehicle state data and the driving state data.

7. The driver assistance system of claim 1 , wherein the vehicle state data and the driving state data are obtained from one or more of one or more vehicle systems, one or more sensors, and a server.

8. The driver assistance system of claim 1, wherein the computing device is configured to output the recommended vehicle speed to the driver of the vehicle via a user interface of the vehicle and to instruct the user interface to present one or more of a visual and audio reproduction of the recommended vehicle speed.

9. The driver assistance system of claim 1, wherein the computing device is further configured to adjust vehicle operating state based on the recommended vehicle speed, wherein adjusting vehicle operating state comprises adjusting parameters of one or more of an adaptive cruise control system and an autonomous driving system.

10. A method, comprising: receiving, at a driver assistance system of a vehicle, vehicle state data of the vehicle, wherein the vehicle state data includes a battery state of charge, a tire condition, and vehicle load; receiving, at the driver assistance system of the vehicle, driving state data of the vehicle including weather data, road condition data, speed limit, and intersection data; determining, based on the vehicle state data and the driving state data, a recommended vehicle speed and a recommended oscillation pattern; outputting the recommended vehicle speed and the recommended oscillation pattern to a driver of the vehicle; and adjusting one or more vehicle operating states of the vehicle based on the recommended vehicle speed.

11. The method of claim 10, wherein outputting the recommended vehicle speed comprises outputting the recommended vehicle speed to a user interface of the vehicle and instructing the user interface to present one or more of a visual and audible reproduction of the recommended vehicle speed to a driver of the vehicle.

12. The method of claim 10, wherein adjusting the one or more vehicle operating states comprises adjusting a cruise control setting based on the recommended vehicle speed.

13. The method of claim 10, wherein adjusting the one or more vehicle operating states comprises adjusting autonomous driving system parameters based on the recommended vehicle speed.

14. The method of claim 10, wherein the recommended oscillation pattern is determined based on powertrain efficiency prioritization parameters.

15. A method, comprising: receiving first vehicle state data specific to a first vehicle by a first driver assistance system from one or more first vehicle systems and one or more first sensors of the first vehicle; receiving second vehicle state data specific to a second vehicle by a second driver assistance system from one or more second vehicle systems and one or more second sensors of the second vehicle, wherein the second vehicle state data is different from the first vehicle state data; receiving driving state data specific to environmental conditions from a server and the one or more first sensors of the first vehicle at the first driver assistance system; receiving the driving state data specific to environmental conditions from the server and the one or more second sensors of the second vehicle at the second driver assistance system; determining, via application of one or more first machine learning (ML) algorithms, a first recommended vehicle speed based on the first vehicle state data and the driving state data; determining, via application of one or more second ML algorithms, a second recommended vehicle speed based on the second vehicle state data and the driving state data, wherein the second recommended vehicle speed is different from the first recommended vehicle speed; outputting the first recommended vehicle speed to a first user interface of the first vehicle; and outputting the second recommended vehicle speed to a second user interface of the second vehicle, wherein the first and second vehicles are traveling along the same road at the same time.

16. The method of claim 16, wherein the one or more first ML algorithms are configured to learn driving patterns of the first vehicle and the one or more second ML algorithms are configured to learn driving patterns of the second vehicle.

17. The method of claim 16, wherein the first and second user interfaces of the first and second vehicles are each one of a dashboard and infotainment unit of the vehicle.

18. The method of claim 16, wherein the first and second vehicle state data each comprises one or more of vehicle load, tire condition, vehicle type, operating state, age, and wear of one or more of a braking system, suspension system, engine, motor, and powertrain of the vehicle, battery state of charge, vehicle equipment information, and vehicle dynamics.

19. The method of claim 16, wherein the driving state data specific to environmental conditions comprises weather conditions, visibility, road condition, road surface quality, road gradient, map data, road course, traffic volume, and road speed limit.

20. The method of claim 16, wherein the first and second vehicle state data and the driving state data are received by the respective first and second driver assistance systems at regular intervals.

Images