Driving risk identification method, system and device, medium and vehicle

Abstract

The invention provides a driving risk identification method, system and device, a medium and a vehicle. The method comprises the following steps: determining whole vehicle envelope track information according to pose information of a vehicle; determining a driving scene strategy according to the environment information of the vehicle; and determining a driving risk level according to the vehicle envelope track information and the driving scene strategy. According to the method, the vehicle envelope track information and the environment information are determined, and the characteristics of objects possibly interfering with the vehicle or roads possibly causing driving risks on the driving path of the vehicle are covered.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a driving risk identification method, system, device, medium and vehicle. Background Art

[0002] With the prevalence of assisted driving technology, more and more vehicles are equipped with risk warning functions. Risk identification is the foundation of this function. Existing vehicle driving risk identification typically identifies road obstacles, such as pedestrians and non-motorized vehicles, and determines collision risk based on the distance and relative speed between the obstacle and the vehicle, thereby determining whether to issue a warning. This ignores other factors and scenarios that may lead to driving risks, resulting in insufficient accuracy in driving risk identification and a high risk of false or missed alarms. Summary of the Invention

[0003] One of the objectives of the present invention is to provide a driving risk identification method that is applicable to various factors and scenarios that may lead to driving risks and improves the accuracy of driving risk identification.

[0004] To achieve the above-mentioned objectives, the present invention provides a driving risk identification method, comprising: determining the whole vehicle envelope trajectory information based on the vehicle's posture information; determining a driving scenario strategy based on the environmental information in which the vehicle is located; and determining the driving risk level based on the whole vehicle envelope trajectory information and the driving scenario strategy.

[0005] The driving risk identification method provided by the present invention can cover all objects on the vehicle's driving path that may interfere with the vehicle or road features that may cause driving risks, such as ditches, deep pits, height-restricted obstacles, etc., by determining the vehicle's envelope trajectory information and environmental information. This allows driving risk warnings to not only target collisions with physical obstacles on the road surface, but also encompass various driving risks such as accidental falls, bottoming out, and vehicle getting stuck. In addition, the present invention can distinguish the different levels of demand for driving risk identification in various driving scenarios by determining driving scenario strategies, thereby improving the comfort of human-computer interaction during risk warnings.

[0006] Furthermore, in some specific examples, the posture information includes one or more of: wheel angle, wheel speed, brake pedal depth, accelerator pedal depth, suspension state and wheel end adhesion.

[0007] Furthermore, in some specific examples, determining the whole vehicle envelope trajectory information based on the vehicle's posture information includes: determining the center motion trajectory of the vehicle in the geodetic coordinate system based on the posture information; determining the whole vehicle contour information of the vehicle in the geodetic coordinate system; and determining the whole vehicle envelope trajectory information based on the center motion trajectory and the first contour information.

[0008] Furthermore, in some specific examples, determining the entire vehicle contour information of the vehicle in the geodetic coordinate system includes: determining the static contour information of the vehicle in the geodetic coordinate system; determining the dynamic contour envelope information of the vehicle's moving parts in the geodetic coordinate system; and determining the entire vehicle contour information of the vehicle in the geodetic coordinate system based on the static contour information and the dynamic contour envelope information.

[0009] Furthermore, in some specific examples, determining the dynamic contour envelope information of the vehicle moving part in the geodetic coordinate system includes: determining the original dynamic contour envelope information of the vehicle moving part based on the vehicle coordinate system; and converting the original dynamic contour envelope information into the dynamic contour envelope information in the geodetic coordinate system through coordinate transformation.

[0010] Furthermore, in some specific examples, determining the driving scenario strategy based on the environmental information where the vehicle is located includes: determining driving scenario feature information based on the environmental information where the vehicle is located, and determining the driving scenario strategy based on the driving scenario feature information.

[0011] Furthermore, in some specific examples, the environmental information includes one or more of brightness information, temperature information, humidity information, and map location information.

[0012] Furthermore, in some specific examples, determining the driving scene strategy based on the environmental information of the vehicle also includes: extracting target features based on the visual information of the vehicle; determining the scene category based on the target feature extraction result; and determining the driving scene strategy based on the scene category and the driving scene feature information.

[0013] Furthermore, in some specific examples, the scene categories include: one or more of: parking lots, congested roads, markets, jungles, snow, grasslands, mountains, sand, and mudflats.

[0014] Furthermore, before determining the driving risk level based on the vehicle envelope trajectory information and the driving scenario strategy, the method also includes: identifying obstacles based on the vehicle's visual information; determining obstacle motion trajectory information based on the obstacle identification result and the scenario category; and determining a collision probability based on the obstacle motion trajectory information and the vehicle envelope trajectory information.

[0015] Furthermore, in some specific examples, the method further includes: determining an expected driving path based on the driving scene feature information, the scene category, and the collision probability.

[0016] Furthermore, in some specific examples, the method further includes: determining a warning strategy based on the scenario category.

[0017] The present invention also provides a driving risk identification system, which includes: a perception unit, a decision unit and an execution unit; wherein the perception unit is suitable for obtaining the vehicle's posture information and the environmental information of the vehicle, and inputting the posture information and the environmental information into the decision unit; the decision unit is suitable for determining the driving risk level based on the posture information and the environmental information.

[0018] Furthermore, in some specific examples, the perception unit includes: one or more of: radar, visual sensor, temperature sensor, humidity sensor, inertial sensor, odometer and vehicle motion control sensor.

[0019] The present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-mentioned driving risk identification method.

[0020] The present invention also provides a computer-readable storage medium, in which instructions are stored. When a computer executes the instructions, the computer executes the above-mentioned driving risk identification method.

[0021] The present invention also provides a vehicle, comprising the aforementioned driving risk identification system or the aforementioned electronic device.

[0022] The beneficial effects of the vehicle provided by the present invention are that, compared with the existing technology, the vehicle provided by the present invention can judge driving risks in various environmental scenarios, improve the accuracy of driving risk identification, and provide driving risk warnings that are consistent with the driver's psychological expectations based on the driving scenario, thereby improving the comfort of human-computer interaction in the entire vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 is a flow chart of a driving risk identification method according to a specific embodiment of the present invention;

[0025] Figure 2 is a flow chart of a driving risk identification method according to a specific embodiment of the present invention;

[0026] Figure 3 is an architectural diagram of a driving risk identification system according to another specific embodiment of the present invention;

[0027] Figure 4 3 is a schematic diagram of a strategy of a driving risk identification method according to a specific embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0029] It should be noted that when an element is referred to as being “fixed on” or “disposed on” another element, it may be directly on the other element or indirectly on the other element. When an element is referred to as being “connected to” another element, it may be directly connected to the other element or indirectly connected to the other element.

[0030] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0031] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0032] A driving risk identification method according to a specific embodiment of the present invention is now described.

[0033] refer to Figure 1 As shown, the present invention provides a driving risk identification method, including: determining the whole vehicle envelope trajectory information according to the vehicle posture information; determining the driving scenario strategy according to the environment information where the vehicle is located; and determining the driving risk level according to the whole vehicle envelope trajectory information and the driving scenario strategy.

[0034] The driving risk identification method provided by the present invention can cover all objects on the vehicle's driving path that may interfere with the vehicle or road features that may cause driving risks, such as ditches, deep pits, height-restricted obstacles, etc., by determining the vehicle's envelope trajectory information and environmental information. This allows driving risk warnings to not only target collisions with physical obstacles on the road surface, but also encompass various driving risks such as accidental falls, bottoming out, and vehicle getting stuck. In addition, the present invention can distinguish the different levels of demand for driving risk identification in various driving scenarios by determining driving scenario strategies, thereby improving the comfort of human-computer interaction during risk warnings.

[0035] In some specific embodiments, the posture information includes one or more of: wheel angle, wheel speed, brake pedal depth, accelerator pedal depth, suspension state and wheel end adhesion.

[0036] The present invention comprehensively introduces vehicle gear position, vehicle speed, wheel-end adhesion, front and rear wheel angles, and vehicle body posture, and calculates the collision probability between the vehicle's spatial envelope motion trajectory and the obstacle motion trajectory as a driving risk identification criterion, thereby improving identification accuracy.

[0037] In some specific embodiments, determining the whole vehicle envelope trajectory information based on the vehicle's posture information includes: determining the center motion trajectory of the vehicle in the geodetic coordinate system based on the posture information; determining the whole vehicle contour information of the vehicle in the geodetic coordinate system; and determining the whole vehicle envelope trajectory information based on the center motion trajectory and the first contour information.

[0038] In some specific embodiments, determining the entire vehicle contour information of the vehicle in the geodetic coordinate system includes: determining the static contour information of the vehicle in the geodetic coordinate system; determining the dynamic contour envelope information of the vehicle's moving parts in the geodetic coordinate system; and determining the entire vehicle contour information of the vehicle in the geodetic coordinate system based on the static contour information and the dynamic contour envelope information.

[0039] In some specific embodiments, determining the dynamic contour envelope information of the vehicle moving part in the geodetic coordinate system includes: determining the original dynamic contour envelope information of the vehicle moving part based on the vehicle coordinate system; and converting the original dynamic contour envelope information into the dynamic contour envelope information in the geodetic coordinate system through coordinate transformation.

[0040] In some specific embodiments, determining the driving scenario strategy based on the environmental information of the vehicle includes: determining driving scenario feature information based on the environmental information of the vehicle and determining the driving scenario strategy based on the driving scenario feature information.

[0041] In some specific embodiments, the environmental information includes one or more of brightness information, temperature information, humidity information, and map location information.

[0042] In some specific embodiments, determining the driving scene strategy based on the environmental information of the vehicle further includes: extracting target features based on the visual information of the vehicle; determining the scene category based on the target feature extraction result; and determining the driving scene strategy based on the scene category and the driving scene feature information.

[0043] In some specific embodiments, the scene categories include: one or more of: parking lot, congested road section, market, jungle, snow, grassland, mountain, sand, and mudflat.

[0044] Furthermore, before determining the driving risk level based on the vehicle envelope trajectory information and the driving scenario strategy, the method also includes: identifying obstacles based on the vehicle's visual information; determining obstacle motion trajectory information based on the obstacle identification result and the scenario category; and determining a collision probability based on the obstacle motion trajectory information and the vehicle envelope trajectory information.

[0045] In some specific embodiments, the method further includes: determining an expected driving path based on the driving scene feature information, the scene category and the collision probability.

[0046] In some specific embodiments, the method further includes: determining a warning strategy based on the scenario category.

[0047] This invention integrates environmental sensor signals, visual signals, millimeter-wave radar signals, and map positioning to create scenario-based collision warning mode categories. Different collision warning strategies and driving guidance strategies are then applied to different scenario mode categories. The invention also expands the risk identification scope from general road obstacles to ditches, deep pits, height-restricted obstacles, and their corresponding distance recognition methods.

[0048] refer to Figure 2 and Figure 4 As shown, in another embodiment of the present invention, the logical architecture of the driving risk identification method includes: spatial motion trajectory prediction of vehicle envelope, obstacle motion trajectory prediction, scene recognition, collision probability prediction, driving guidance planning and interactive reminder strategy.

[0049] The spatial trajectory prediction of the vehicle envelope primarily involves predicting the vehicle envelope and its trajectory. A simplified spatial contour representation of the vehicle is established based on the geodetic coordinate system. The external contour moving parts are then mapped to a coordinate system on the vehicle to establish equations. A spatial coordinate transformation is then used to obtain a contour representation consistent with the vehicle coordinate system, thereby establishing a set of equations for the vehicle's spatial contour representation. Vehicle trajectory prediction is also divided into short-term kinematic trajectory prediction and driving intention prediction. Driving intention prediction is achieved through a deep learning algorithm, which establishes the vehicle's spatial kinematic control equations and combines them with driving intention prediction to calculate the vehicle trajectory and probability set.

[0050] Obstacle trajectory prediction primarily involves predicting the trajectory of moving obstacles. Short-term predictions are based on the object's kinematic model, while long-term predictions utilize deep learning algorithms to understand obstacle types and scenarios and predict intent.

[0051] The scene recognition function primarily implements scene recognition based on multiple information, combined with map location information, and scene characteristics. Scenes are categorized into simple scene recognition based on signals and complex scene recognition based on scene understanding. The former directly invokes the corresponding scene strategy through logical calculations based on brightness, humidity, map location information, etc.; the latter uses deep learning and scene understanding to identify the vehicle's surroundings, such as markets, jungles, mudflats, unmanaged parking lots at night, and unpaved snowy areas, among other complex scenarios.

[0052] The collision probability prediction mainly realizes the calculation of collision probability based on different obstacles. Combining the kinematic model and deep learning intention prediction will generate multiple trajectories. The vehicle kinematic trajectory and driver operation prediction will also generate multiple trajectories. The set of trajectories of obstacles and vehicles will generate multiple intersections. The intersection density of spatial positions is combined with the trajectory line probability function to calculate the spatial distribution of collision risks. Combined with the identification of scenes and feature categories after environmental modeling, some high-risk collision objects such as shrubs in dense forests and pedestrians close to vehicles in market environments will not generate collision warning prompts. Instead, vehicle driving suggestions will be provided to the driver. When the collision probability is lower than the probability threshold, no warning will be generated when the vehicle moves safely close to the obstacle.

[0053] Driving guidance planning primarily implements driving guidance strategies for different scenarios. It combines environmental modeling based on the BEV algorithm, simplified vehicle spatial contour modeling, and scenario pre-set conditions to calculate the desired vehicle trajectory. This is then converted into vehicle operational actions through the solution module.

[0054] The interactive reminder strategy primarily implements different human-machine interaction strategies based on scenario definitions. For example, the program will use different interaction strategies in environments with good visibility and extremely low visibility. When driving on a curve, different reminder strategies will be used for obstacles on the side of the vehicle. The system also provides guidance on vehicle operation and provides positive feedback when the driver operates the vehicle according to the reminders.

[0055] The present invention also provides a driving risk identification system, which includes: a perception unit, a decision unit and an execution unit; wherein the perception unit is suitable for obtaining the vehicle's posture information and the environmental information of the vehicle, and inputting the posture information and the environmental information into the decision unit; the decision unit is suitable for determining the driving risk level based on the posture information and the environmental information.

[0056] refer to Figure 3 As shown, in some specific embodiments, the perception unit includes: one or more of: radar, visual sensor, temperature sensor, humidity sensor, inertial sensor, odometer and vehicle motion control sensor.

[0057] The present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-mentioned driving risk identification method.

[0058] The present invention also provides a computer-readable storage medium, in which instructions are stored. When a computer executes the instructions, the computer executes the above-mentioned driving risk identification method.

[0059] The present invention also provides a vehicle, comprising the aforementioned driving risk identification system or the aforementioned electronic device.

[0060] The beneficial effect of the vehicle provided by the present invention is that, compared with the prior art, the vehicle provided by the present invention can judge driving risks in various environmental scenarios and issue driving risk warnings based on the driving scenarios.

[0061] Although one or more specific embodiments of the present disclosure have been shown and described, equivalent variations and modifications will occur to those skilled in the art after reading and understanding this specification and the accompanying drawings. The present disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terms used to describe such components are intended to correspond to any component (functionally equivalent) that performs the specific functions of the described components, even if structurally not equivalent to the disclosed structures. In addition, although specific features of the present disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations as may be desired and beneficial for any given or specific application. In addition, with respect to the terms "including," "having," "having," "having," or variations thereof used in the specific embodiments or claims, such terms are intended to be inclusive in a manner similar to the term "comprising."

[0062] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the appended claims.

[0063] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A driving risk identification method, characterized in that: The method comprises: Determine the vehicle envelope trajectory information based on the vehicle's posture information; Determining a driving scenario strategy based on environmental information of the vehicle; The driving risk level is determined according to the vehicle envelope trajectory information and the driving scenario strategy.

2. The driving risk identification method according to claim 1, characterized in that: The posture information includes one or more of: wheel angle, wheel speed, brake pedal depth, accelerator pedal depth, suspension state and wheel end adhesion.

3. The driving risk identification method according to claim 2, characterized in that: Determining the vehicle envelope trajectory information based on the vehicle posture information includes: Determine the center motion trajectory of the vehicle in the geodetic coordinate system based on the posture information; Determining vehicle profile information of the vehicle in the geodetic coordinate system; The entire vehicle envelope trajectory information is determined according to the central motion trajectory and the first contour information.

4. The driving risk identification method according to claim 3, characterized in that: Determining the entire vehicle profile information of the vehicle in the geodetic coordinate system includes: Determining static profile information of the vehicle in the geodetic coordinate system; Determining dynamic contour envelope information of the vehicle moving part in the earth coordinate system; The entire vehicle contour information of the vehicle in the geodetic coordinate system is determined according to the static contour information and the dynamic contour envelope information.

5. The driving risk identification method according to claim 4, characterized in that: Determining the dynamic contour envelope information of the vehicle moving part in the earth coordinate system includes: Determining original dynamic profile envelope information of the vehicle moving part based on a vehicle coordinate system; The original dynamic contour envelope information is converted into the dynamic contour envelope information in the geodetic coordinate system through coordinate transformation.

6. The driving risk identification method according to claim 1, characterized in that: The determining of the driving scenario strategy according to the environment information of the vehicle includes: Determining driving scene feature information based on environmental information of the vehicle; The driving scenario strategy is determined according to the driving scenario characteristic information.

7. The driving risk identification method according to claim 6, characterized in that: The determining of the driving scenario strategy according to the environmental information of the vehicle further includes: Extracting target features based on visual information of the vehicle; Determine the scene category based on the target feature extraction results; The driving scenario strategy is determined based on the scenario category and the driving scenario feature information.

8. The driving risk identification method according to claim 7, characterized in that: Before determining the driving risk level according to the vehicle envelope trajectory information and the driving scenario strategy, the method further includes: performing obstacle recognition based on visual information of the vehicle; Determining obstacle motion trajectory information based on the obstacle recognition result and the scene category; The collision probability is determined based on the obstacle motion trajectory information and the vehicle envelope trajectory information.

9. The driving risk identification method according to claim 8, characterized in that: The method further comprises: An expected driving path is determined based on the driving scene feature information, the scene category, and the collision probability.

10. The driving risk identification method according to claim 7, characterized in that: The method further comprises: An early warning strategy is determined based on the scenario category.

11. A driving risk identification system, characterized in that: include: A perception unit, a decision unit and an execution unit; wherein the perception unit is adapted to obtain the position information of the vehicle and the environment information where the vehicle is located, and input the position information and the environment information into the decision unit; The decision unit is adapted to determine a driving risk level according to the posture information and the environment information.

12. The driving risk identification system according to claim 11, characterized in that: The perception unit includes: one or more of a radar, a visual sensor, a temperature sensor, a humidity sensor, an inertial sensor, an odometer, and a vehicle motion control sensor.

13. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method according to any one of claims 1 to 10.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions. When a computer executes the instructions, the computer executes the method according to any one of claims 1 to 10.

15. A vehicle, characterized in that: The vehicle includes the driving risk identification system according to any one of claims 11-12, or the electronic device according to claim 13.

Images