CN113348119A

CN113348119A - Vehicle blind area identification method, automatic driving assistance system and intelligent driving vehicle comprising system

Info

Publication number: CN113348119A
Application number: CN202080004420.0A
Authority: CN
Inventors: 陈亮亮; 刘天放; 陈曦; 湛鹤峰
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2020-04-02
Filing date: 2020-04-02
Publication date: 2021-09-03
Also published as: WO2021196145A1

Abstract

A vehicle blind area recognition method (100), an automatic driving assistance system (50), and a smart driving vehicle (21) including the automatic driving assistance system (50), the vehicle blind area recognition method (100) comprising: the method comprises the steps of firstly acquiring surrounding environment information of a vehicle (21), then judging a driving scene of the vehicle (21) according to the surrounding environment information of the vehicle (21), judging whether the vehicle (21) is in a non-obstacle scene or an obstacle scene at present, and determining a dangerous driving blind area at least based on the speed of an obstacle (22) and the speed of the obstacle (22) in the obstacle scene.

Description

Vehicle blind area identification method, automatic driving assistance system and intelligent driving vehicle comprising system

Technical Field

The present application relates to the field of automatic driving, and in particular, to a vehicle blind area recognition method, an automatic driving assistance system, and an intelligent driving vehicle including the system.

Background

With the rapid development of artificial intelligence technology combined with automobile application, the technologies of assistant driving and automatic driving gradually move to the market, the more advanced technologies of assistant driving and automatic driving also require that the vehicle can deal with more complex traffic scenes and dangerous situations, especially in complex urban traffic environments, as dynamic and static traffic vehicles, crossing greenbelts, walls and other obstacles form shelters, the detection area of the sensor is limited, and for traffic participants in a perception blind area to suddenly appear in front of the driving track of the vehicle, collision accidents are easy to occur, especially pedestrians and riders are easy to have behaviors which do not comply with traffic rules, and the track change is uncertain, so that the collision risk is greatly increased.

The following solutions are mainly used to deal with collision risks in the prior art:

1. the method comprises the steps that target tracking and track prediction are carried out on traffic participants based on known information detected by a perception sensor, avoidance control is adopted once collision risks are found, hidden collision risks are not identified aiming at a current driving scene, the problem that sudden risks of blind area sheltering areas are difficult to solve is solved, an automatic emergency braking obstacle avoidance system can be triggered only when the traffic participants enter a perception range, and collision is difficult to avoid when the reaction distance is small.

2. The information of the traffic participants is acquired by using the V2X technology and is sent to the automatic driving system, the automatic driving system can effectively predict the behavior of the traffic participants in the current traffic scene through the information acquired by the sensors of the vehicle and the information acquired by the V2X technology, so that the collision between the vehicle and the traffic participants is avoided, but the realization of the current automatic driving technology is difficult to depend on the V2X technology, and the commercial application of complete road infrastructure and intelligent equipment for vehicles and pedestrians is difficult to realize in a short time.

Based on the above, a scheme is needed, which can accurately identify the blind area of the vehicle in the driving process and make an automatic driving strategy based on the blind area to effectively avoid possible collision risks; also, the solution should be possible on the vehicle itself.

Disclosure of Invention

In order to solve the above problems, various embodiments of the present application provide a vehicle blind area identification method, a driving assistance system, and a vehicle using the system, so as to accurately identify a vehicle driving blind area and make an effective safe driving strategy based on the same.

In a first aspect, various embodiments of the present application provide a vehicle blind area identification method, including: firstly, acquiring surrounding environment information of a vehicle, such as road images, moving/static target information, traffic light information and the like; then judging the driving scene of the vehicle according to the surrounding environment information of the vehicle, such as lane line detection, traffic identification detection, self-vehicle positioning, static/dynamic object detection and the like; and judging whether the vehicle is in a barrier-free scene or a barrier scene at present, and determining a dangerous driving blind area at least based on the barrier and the speed of the barrier in the barrier scene.

The technical scheme of the first aspect can confirm whether the scene where the vehicle is located has an obstacle or has no obstacle, and further comprehensively considers the influence of the obstacle and the speed of the obstacle on the blind area under the condition that the obstacle exists.

In one possible design, when an obstacle exists, whether the speed of the obstacle is zero or not is further judged, and if the speed of the obstacle is zero, an area shielded by the obstacle is determined to be a dangerous driving blind area; if the speed of the obstacle is not zero, the area shielded by the obstacle is a total blind area, the length or the area swept by the obstacle in the total blind area through braking at the maximum deceleration is a safe driving blind area, and the dangerous driving blind area is determined according to the total blind area and the safe driving blind area. By introducing the safe driving blind area, the scheme can confirm the blind area more accurately.

In one possible design, when the vehicle and the obstacle travel in the same direction, the dangerous driving blind area is the total blind area minus the safe driving blind area; when the vehicle and the barrier oppositely run, the dangerous driving blind area is the total blind area plus the safe driving blind area. It is distinguished whether the vehicle is in the same direction as the speed of the obstacle or is opposite to the speed of the obstacle, and a dangerous driving blind area is confirmed accordingly.

In one possible design, determining a risk coefficient of a scene where a vehicle is located according to the driving scene of the vehicle, wherein the risks caused by blind areas of the vehicle in different scenes are different, and distinguishing the risks in the technical scheme; and then determining the vehicle blind area risk level according to the risk coefficients of the dangerous driving blind area and the scene where the vehicle is located, so that the vehicle blind area risk level can be quantitatively evaluated.

In one possible design, various factors are comprehensively considered, and the vehicle blind area risk level is determined according to parameters such as a dangerous driving blind area, the transverse distance between the vehicle and the blind area, the current vehicle speed of the vehicle, the time of the vehicle reaching a collision area, the risk coefficient of the scene where the vehicle is located and the like, so that the evaluation on the vehicle blind area risk level is more accurate.

In one possible design, after the vehicle blind zone risk level is determined, the corresponding control strategy may be validated. When the risk level of the vehicle blind area is higher than a set threshold value, the vehicle is subjected to transverse avoidance preferentially, and the transverse avoidance means that the vehicle enters a lane far away from the blind area in the transverse direction to travel; and if the risk level of the vehicle blind area is lower than the set threshold value, the vehicle continues to run according to the plan of the driving assistance system. If the blind area risk level is high, the technical scheme preferably selects to enable the vehicle to be far away from the blind area in the transverse direction, so that the collision risk is avoided to the greatest extent.

In one possible design, if the risk level of the vehicle blind area is higher than a set threshold value, and the vehicle cannot perform transverse avoidance, the vehicle performs in-lane avoidance, which means that the vehicle moves away from the blind area in the transverse direction of the current lane, so that collision is avoided as much as possible.

In one possible design, if the vehicle blind area risk level is higher than a set threshold, and the vehicle cannot perform lateral avoidance and intra-road avoidance, the vehicle travels at the minimum speed value in the speed planning and the safe travel speed planning of the automatic driving assistance system.

In a second aspect, there is provided an automatic driving assistance system including: a sensor unit including a camera, a GPS, a radar, and the like, for acquiring information on the environment around the vehicle; the sensing part is in communication connection with the sensor part and receives the information acquired by the sensor part and determines a vehicle driving scene according to the acquired information; the decision-making part is in communication connection with the sensing part and determines dangerous driving blind areas and vehicle blind area risk levels according to the vehicle driving scene; and the control part is in communication connection with the decision-making part and determines a driving strategy at least according to the vehicle blind area risk level.

It is understood that the system provided by the second aspect corresponds to the method provided by the first aspect, and therefore, the implementation manners and the achieved technical effects of the second aspect can be referred to the related descriptions of the implementation manners of the first aspect.

In a third aspect, a smart vehicle is provided, which comprises the automatic driving assistance system of the second aspect.

The technical scheme firstly confirms whether a scene where the vehicle is located is provided with an obstacle or is not provided with the obstacle, further comprehensively considers the influence of the speed of the obstacle on the blind area under the condition that the obstacle exists, and accurately identifies the vehicle driving blind area by introducing the concept of the safe driving blind area and evaluating the risk level of the vehicle blind area and making an effective safe driving strategy on the basis. On the other hand, the technical scheme of this application can be accomplished based on current driving assistance system, need not expensive road infrastructure, therefore the technical scheme economic nature of this application is high, does benefit to popularization and popularizes to can promote autopilot's security.

Drawings

FIG. 1 is a schematic flow chart of blind zone identification and driving control provided by an embodiment of the present application;

FIG. 2 is a schematic diagram of an embodiment of the present application providing blind spot identification;

FIG. 3 is a schematic diagram of blind zone separation and calculation provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of a safe driving strategy based on blind zone identification provided by an embodiment of the application;

fig. 5 is a schematic diagram of an automatic driving assistance system according to an embodiment of the present application.

Detailed Description

Referring to fig. 1, a schematic flow chart of a vehicle blind area identification method 100 according to an embodiment of the present application is shown, including:

101: starting;

102: the vehicle driving scene is determined, and the step can be realized by vehicle-mounted equipment which can comprise mainstream equipment of the automatic driving vehicle, namely a camera, a GPS (global positioning system) and a radar, wherein the camera can comprise a monocular and/or binocular camera, and the radar can comprise a millimeter wave radar and/or a laser radar (Lidar). Cameras are generally used for acquiring road scene images, laser radars and/or millimeter wave radars are used for acquiring moving and static target data, and GPS is used for positioning vehicle positions. The information acquired by the camera and radar is transmitted to an onboard image processing device or cloud in communication with the vehicle to determine a vehicle driving scenario, which may include, for example: road structure information, vehicle/pedestrian identification, dynamic and static target identification, self-vehicle position, speed, acceleration and course; and state observation information of other vehicles and pedestrians around the own vehicle.

In some embodiments, it may be determined whether the vehicle is currently in an obstacle scene or a non-obstacle scene based on the vehicle driving scene. And judging whether the current vehicle is in a non-obstacle scene within a certain range of the driving direction or not according to the vehicle driving scene information, and if not, determining that the current vehicle is in an obstacle-free scene, otherwise, determining that the current vehicle is in an obstacle-free scene. In some embodiments, the range may be a range of 0-50 meters ahead of the driving direction of the vehicle, and it should be understood that the range may be adjusted according to actual situations, for example, the range may also be a range of 0-75 meters and 10-80 meters ahead of the driving direction of the vehicle, which is not limited in this application.

103: blind area classification and calculation, wherein based on the result of 101, if the vehicle is judged to be in a scene without obstacles, the blind area does not exist for the current vehicle; and if the vehicle is judged to be in the scene with the obstacles, carrying out blind area classification according to the speed of the obstacles. Specifically, if the speed of the obstacle is zero, a blind area caused by shielding of the static obstacle belongs to a dangerous driving blind area; if the speed of the barrier is not zero, the blind area caused by the shielding of the barrier at the current moment is a total blind area, the distance (length and area) swept by the barrier through braking at the maximum deceleration is a safe driving blind area, and the distance obtained by subtracting the safe driving blind area from the total blind area is a dangerous driving blind area. It should be noted that: the velocity of the obstacle is based on a geodetic coordinate system.

Referring to fig. 2 to exemplarily explain the blind spot classification and calculation, in fig. 2, the vehicle 21 is traveling along a lane at a speed V0 with an obstacle 22 in front left of the own vehicle, i.e., the vehicle 21 is currently in an obstacle scene.

If the velocity V1 of the obstacle 22 is 0, i.e., the obstacle 22 is stationary relative to the geodetic coordinate system, the obstacle 22 is a stationary obstacle, in which case the blind spot caused by the obstruction by the obstacle 22 is a dangerous driving blind spot for the vehicle 22. Referring to fig. 2, the blind area in which the line of sight of the vehicle 21 is blocked by the obstacle 22 in this case is an area ABC in two dimensions and a section AB in one dimension (length S1). In some embodiments, area ABC may be defined as a dangerous driving blind area; in other embodiments, section AB may be positioned as a dangerous driving blind spot. It should be understood that there is no essential difference in selecting a one-dimensional zone or a two-dimensional area as the blind zone, and it is only necessary to keep the same in one scheme.

It should also be understood that the above-described line of sight of the vehicle 21 refers to the line of sight of the onboard camera. The above-mentioned area ABC or zone AB is "invisible" to the vehicle 21 when the speed of the obstacle 22 is zero, and if an object 23 (which may be a person or a vehicle, for example) with a lateral speed V3 is present within the area ABC or zone AB, the object 23 is now invisible to the vehicle 21 and has a potential collision risk, and thus the area ABC or zone AB is a dangerous driving blind area for the vehicle 21.

The value of S1 may be calculated using a variety of methods, for example, S1 may be determined by lidar measurements of the distance between vehicle 21 and obstacle 22 and the road edge (L1 and L0) and the angle α between the vehicle' S line of sight and the road edge, in which case S1 ═ L0-L1) × tan α.

It should be noted that if the vehicle 21 is stationary at the obstacle 22, the extent of the dangerous driving blind spot for the vehicle 21 is time-varying because the vehicle 21 is moving and its line of sight is also changing, so the area ABC or the section AB is also time-varying.

If the speed V1 of the obstacle 22 is not zero, see fig. 2, if the obstacle 22 is also a vehicle and its speed is V1, the angle between V1 and the speed V0 of the vehicle 21 is θ. In this case, the distance (area) over which the obstacle 22 is swept to brake at the maximum deceleration is considered. Assuming that the deceleration of the obstacle 22 is a and the direction of a coincides with the velocity V1, a in the direction V0 is a cos θ, and the distance the obstacle 22 travels from moving to stopping in the direction V0 is (V1 cos θ) based on the kinematics principle²/(2 a. cos. theta.). This distance is identified in fig. 2 by S3 and, if expressed in area, by the region DECB.

The present application distinguishes between a safe driving blind area and a dangerous driving blind area in this case, and defines section AB (S1) or area DECB as a total blind area, and section DB (S3) or area DECB as a safe driving blind area. The meaning is as follows: if there is an object 24 (vehicle or pedestrian) within DB (S3) or region DECB having a lateral velocity V4, the object 24 is likely to collide with the obstacle (vehicle) 22 first, and the distance/area swept by the vehicle 22 braking at maximum deceleration is therefore a "safe zone" for the vehicle 21, since it should be the first object 24 to collide with the vehicle 22 within this distance/area. Further, the section S4 or the area ADE is a dangerous driving blind area for the vehicle 21.

In some embodiments, the maximum deceleration of the vehicle may take 8-12m/S²A value of (1).

In some embodiments, the system delay time T may also need to be considered in calculating the time from when the obstacle 22 moves to rest_delayIn this case, the distance (S3) that the obstacle passes from moving to stopping in the V0 direction is:

V1*cosθ*T_delay+(V1*cosθ)²/(2a*cosθ)。

in some embodiments, isSystem delay time T_delayValues in the range of 0.1-1 second may be taken.

When the vehicle 21 and the vehicle 22 travel in the same direction, the dangerous driving blind area in the one-dimensional case can be expressed by the following formula:

the dangerous driving blind area is S1-S3;

while when the vehicle 21 and the vehicle 22 are running in opposite directions, the dangerous driving blind area in the one-dimensional case can be expressed by the following equation:

and (4) a dangerous driving blind area is S1+ S3.

It should be understood that, taking fig. 2 as an example, the above-mentioned co-directional or counter-directional driving does not mean that the speed directions of the vehicle 21 and the obstacle 22 are exactly the same and parallel, or exactly opposite and parallel; in general, if the cosine value cos θ of the angle θ of the vehicle speeds of the vehicle 21 and the obstacle is greater than zero, the vehicle 21 and the obstacle 22 are considered to travel in the same direction, and if the cosine value cos θ is less than zero, the vehicle 21 and the obstacle 22 are considered to travel in the opposite direction.

In some special cases, referring to fig. 2, if the distance S5 that is traveled when the obstacle (vehicle) 22 is braked at the maximum acceleration is greater than S1, the total blind area is smaller than the safe-driving blind area for the vehicle 21 in this case, i.e., the total blind area is considered to be a safe-driving blind area for the vehicle 21 at this time.

Referring to fig. 3, a flow of blind zone classification and calculation is shown, including:

31: confirming that the scene is an obstacle scene currently;

32: judging whether the barrier is static or not, if so, entering step 34, and directly determining that a blind area caused by the barrier of the barrier is a dangerous driving blind area; if the obstacle is judged to be in the moving state, the step 33 is carried out;

33: calculating blind areas caused by barrier of the obstacles, recording the blind areas as total blind areas, and then entering step 35;

35: calculating a safe driving blind area, namely the length (area) swept by the obstacle through braking at the maximum deceleration, and then entering step 36;

36: judging whether the safe driving blind area is larger than the total blind area; if the safe driving blind area is greater than the total blind area, the safe driving blind area is directly determined in step 38; if the safe driving blind area is smaller than the total blind area, the step 37 is carried out;

37: and (4) subtracting the safe driving blind area from the total blind area to obtain a dangerous driving blind area, and if the vehicle and the barrier oppositely run, adding the safe driving blind area to the total blind area to obtain the dangerous driving blind area.

104: determining a vehicle blind area risk level; the current scene where the vehicle is located can be determined according to the driving scene of the vehicle, and the risk grade r of the scene can be given based on big data analysis according to the scene where the vehicle is located.

In some embodiments, the current scene of the vehicle may be divided into: urban roads, expressways, parking lots. For the three scenarios described above, different risk factors r may be given, for example:

the risk coefficient r of the urban road is 0.4-0.6;

the risk coefficient r of the expressway is 0.2-0.8;

the parking lot road risk coefficient r is 0.1-0.6;

for the three scenarios described above, it is also possible to continue subdividing the scenarios, with different subdivided scenarios corresponding to different risk coefficients r, for example: for urban roads, intersection scenes can be included, and as the vehicles in the intersection scenes are intersected and accidents are easy to happen, the risk coefficient r in the scenes can be defined as 0.6; and if the scene of the urban road is urban overhead, the probability of accidents is low, and the risk coefficient r in the scene can be defined as 0.4. In an expressway, because an event that pedestrians pass through the expressway transversely does not occur generally, the risk coefficient can be defined as 0.2 in a normal expressway scene, and if the expressway is subjected to confluence and intersection, more lane-changing actions can occur due to vehicle intersection, and the vehicle speed is higher on the expressway, the risk coefficient r can be defined as 0.8 in the scene.

It should be understood that the above-mentioned scenarios and risk coefficients r are only exemplary and not limiting, and those skilled in the art can determine the scenarios and risk coefficients r corresponding to the scenarios based on actual situations.

After determining the risk level of the scene, a vehicle blind zone risk level may be determined, and specifically, the vehicle blind zone risk level may be determined according to the following parameters:

a dangerous driving blind area B; b may be the dangerous driving blind area determined in step 103, and may be a one-dimensional value or a two-dimensional value;

the vehicle is away from the blind area by a transverse distance D; d may take the value of vehicle center to obstacle edge, in the example of fig. 2, D may take L1;

the current running speed V of the vehicle;

time to collision ttc (time to collision) when the vehicle reaches the area where collision may occur; in the example of fig. 2, the TTC may take the time at which the vehicle 21 reaches the lower edge of the dangerous-driving blind area, that is, the time required for the vehicle to travel to DF at the current travel vehicle speed V.

A risk coefficient r of a current scene of the vehicle;

the function with parameters can be expressed as:

vehicle blind zone risk rating R ═ f (B, D, TTC, V, R)

In some embodiments, the expression for the vehicle blind zone risk level may be:

in some embodiments, the vehicle blind zone risk level may be calculated in a relatively simple manner, i.e. the vehicle blind zone risk level is determined using only risk coefficients of the dangerous driving blind zone and the scene in which the vehicle is located, when the vehicle blind zone risk level is B r.

It should be understood that the functional expression of the vehicle blind zone risk level described above is merely exemplary, and those skilled in the art may adopt any suitable functional expression according to actual needs without departing from the spirit of the present application, for example, e may be used^BR to calculate a vehicle blind spot risk rating, where e is the base of the natural logarithm.

105: determining a driving strategy; after the vehicle blind zone risk level is determined 104, the driving strategy may be determined based on the vehicle blind zone risk R level.

Firstly, judging whether the current vehicle blind area risk level R is smaller than a safety threshold value, if so, only needing to plan to run according to an Automatic Driving Assistance System (ADAS), namely step 47; if not, firstly, performing transverse planning avoidance, judging whether the current vehicle can perform lane change avoidance or not, and continuing returning to the risk coefficient calculation step after the lane change avoidance is successful; if the lane change avoidance cannot be carried out, judging whether the vehicle can carry out intra-lane avoidance or not, and if the intra-lane avoidance is successful, continuing returning to the risk coefficient calculation step; and if the obstacle avoidance in the road can not be carried out, continuing to carry out safe driving speed planning to enable the risk coefficient to reach the safety threshold value, and combining the safe driving speed planning and the speed planning of the automatic driving auxiliary system to obtain the minimum speed as the planning speed to be sent to the execution system for execution.

Specifically, referring to fig. 4, a flow for determining a driving strategy based on a vehicle blind spot risk level is shown, including:

41: acquiring a current vehicle blind area risk level R;

42: judging whether the vehicle blind area risk level R is smaller than a set threshold value, if so, indicating that the current vehicle blind area risk level is smaller, so that the vehicle can run according to the plan of an automatic Driving assistance System (ADAS for short); in some embodiments, the set threshold may be set to 0.5, it being understood that the threshold may be adjusted up or down depending on actual demand; if R is greater than the set threshold, go to step 43;

43: judging whether the vehicle can carry out lane change avoidance, wherein the lane change avoidance refers to that the vehicle is far away from the blind area in the transverse direction to avoid possible collision risks, and taking fig. 2 as an example, if the vehicle 21 carries out lane change avoidance, the vehicle cuts into a lane on the right side of the vehicle to realize the purpose of being far away from the blind area in the transverse direction; continuously returning to the step 41 after the lane changing avoidance is successful so as to obtain the vehicle blind area risk level R at the next moment; if the lane change avoidance is not allowed, the method goes to step 44; it should be understood that the disallowance of lane change avoidance is determined by the ADAS based on the actual situation of the vehicle, for example, when there are more vehicles on the lane beside the current vehicle and the lane change cannot be performed, the ADAS may make a determination that the lane change avoidance is disallowed;

44: judging whether to allow in-lane avoidance, namely considering whether to avoid possible collision under the condition of not performing lane change avoidance, referring to fig. 2, if the range of a dangerous driving blind area (for example, ADE or S4) is small, the probability representing that vehicles or pedestrians are in the blind area is also small, in this case, the vehicle 21 can perform avoidance only in the current lane without performing lane change avoidance, and the vehicle 21 can transversely move away from the blind area in the current lane to realize in-lane avoidance; continuing returning to the step 41 after the in-road avoidance is successful to obtain the vehicle blind area risk level R at the next moment; if the in-lane avoidance cannot be performed, the step 46 is carried out;

46: the safe driving speed planning is performed such that the risk factor is within a threshold value, generally speaking, the vehicle speed is reduced below a certain value, and the step 45 of introducing the automatic driving assistance system speed planning is also considered, and the minimum safe speed (step 48) is taken as the planning speed to be sent to the execution system for execution.

Referring to fig. 5, an automatic driving assistance system 50 is schematically illustrated, including:

a sensor part 51, which may include a commonly used vehicle-mounted sensor such as a camera, a GPS, a radar, etc., the camera may include a monocular and/or binocular camera, and the radar may include a Lidar (Lidar) or a millimeter wave radar; the camera is responsible for collecting road scene images, the laser radar and the millimeter wave radar are responsible for collecting dynamic and static target data, and the GPS is used for acquiring the current position of the vehicle;

a sensing portion 52 that receives the information collected by the sensor portion and determines a vehicle driving scenario from the information, which may include, for example (but not limited to), lane line detection, traffic sign detection, self-vehicle positioning, static/dynamic object detection, etc.;

a decision part 53, which receives the vehicle driving scene information of the sensing part and makes corresponding decisions, such as (but not limited to) confirming the dangerous driving blind area and the vehicle blind area risk level, for a specific confirmation method, see the description of the above embodiments, and the vehicle blind area risk level is used for making a corresponding control strategy;

the control unit 54 controls the vehicle according to the control strategy of the decision unit 53, including (but not limited to) the various lateral control and longitudinal control described in the above embodiments.

Some embodiments also provide a smart driving vehicle that includes the above-described automated driving assistance system 50, thereby enabling the smart driving vehicle to implement various aspects of the above-described embodiments.

Various embodiments of the application provide a vehicle blind area identification method, a driving assistance system and a vehicle comprising the system, the technical scheme of the application firstly confirms whether a scene where the vehicle is located is an obstacle or no obstacle, under the condition of the obstacle, the influence of the speed of the obstacle on the blind area is further comprehensively considered, and by introducing the concept of a safe driving blind area and evaluating the risk level of the vehicle blind area, the technical scheme can accurately identify the vehicle driving blind area and make an effective safe driving strategy on the basis. On the other hand, the technical scheme of this application can be accomplished based on current driving assistance system, unordered expensive road infrastructure, therefore the technical scheme economic nature of this application is high, does benefit to popularization and popularizes to can promote autopilot's security.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, a division of a unit is only a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each service unit in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a hardware form, and can also be realized in a software service unit form.

The integrated unit, if implemented in the form of a software business unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Those skilled in the art will recognize that, in one or more of the examples described above, the services described herein may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the services may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

The above embodiments are intended to explain the objects, aspects and advantages of the present invention in further detail, and it should be understood that the above embodiments are merely illustrative of the present invention.

The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle blind zone identification method, comprising:

acquiring vehicle surrounding environment information;

judging a vehicle driving scene at least according to the information of the environment around the vehicle, wherein the vehicle driving scene comprises a non-obstacle scene and an obstacle scene;

in the obstacle scene, a dangerous driving blind area is determined at least based on the obstacle and the speed of the obstacle.

2. The method of claim 1, wherein determining a dangerous driving blind area based on at least an obstacle and a speed of the obstacle in an obstacle scene comprises:

when the speed of the obstacle is zero, determining that an area shielded by the obstacle is a dangerous driving blind area;

when the speed of the obstacle is not zero, determining the area shielded by the obstacle as a total blind area, determining the length or the area swept by the obstacle in the total blind area by the maximum deceleration as a safe driving blind area, and determining the dangerous driving blind area according to the total blind area and the safe driving blind area.

3. The method of claim 2, wherein determining the dangerous driving blind area according to the total blind area and the safe driving blind area comprises:

when the vehicle and the barrier run in the same direction, the dangerous driving blind area is the total blind area minus the safe driving blind area;

when the vehicle and the barrier oppositely run, the dangerous driving blind area is the total blind area plus the safe driving blind area.

4. The method of any of claims 1-3, further comprising:

determining a risk coefficient of a scene where the vehicle is located according to the driving scene of the vehicle;

and determining the vehicle blind area risk level at least according to the risk coefficients of the dangerous driving blind area and the scene where the vehicle is located.

5. The method according to any one of claims 1-4, wherein determining the vehicle blind zone risk level based on at least the risk factors of the dangerous driving blind zone and the scene in which the vehicle is located comprises:

and determining the risk level of the vehicle blind area according to the dangerous driving blind area, the transverse distance between the vehicle and the blind area, the current speed of the vehicle, the time of the vehicle reaching the collision area and the risk coefficient of the scene where the vehicle is located.

6. The method of claim 5, further comprising:

when the risk level of the vehicle blind area is higher than a set threshold value, indicating the vehicle to perform transverse avoidance preferentially, wherein the transverse avoidance indicates that the vehicle enters a lane far away from the blind area in the transverse direction to travel;

and when the vehicle blind area risk level is lower than a set threshold value, indicating the vehicle to continue to run according to the plan of the driving assistance system.

7. The method of claim 6, further comprising:

when the risk level of the vehicle blind area is higher than a set threshold value and the vehicle cannot carry out transverse avoidance, the vehicle is indicated to carry out in-lane avoidance, and the in-lane avoidance means that the vehicle moves away from the blind area in the transverse direction of the current lane.

8. The method of claim 7, further comprising:

and when the risk level of the vehicle blind area is higher than a set threshold value and the vehicle cannot carry out transverse avoidance and in-road avoidance, the vehicle runs at the minimum speed value in the speed planning and the safe running speed planning of the automatic driving auxiliary system.

9. An automatic driving assistance system comprising:

a sensor portion, the sensor portion comprising: the sensor part is used for acquiring the surrounding environment information of the vehicle;

the sensing part is in communication connection with the sensor part and receives the information acquired by the sensor part and determines a vehicle running scene according to the acquired information;

the decision-making part is in communication connection with the sensing part and determines dangerous driving blind areas and vehicle blind area risk levels according to the vehicle driving scene;

and the vehicle control part is in communication connection with the decision-making part, and determines a driving strategy at least according to the vehicle blind area risk level.

10. The system of claim 9, wherein determining a dangerous driving blind area based on at least the obstacle and the speed of the obstacle in the obstacle scene comprises: :

the vehicle driving scene comprises a non-obstacle scene and an obstacle scene; in the obstacle scene, a dangerous driving blind area is determined at least based on the speed of the vehicle and the obstacle.

11. The system of claim 10, wherein:

the scene with the obstacle comprises an obstacle with a speed of zero and non-zero;

when the speed of the obstacle is not zero, the area shielded by the obstacle is a total blind area, the length or the area swept by the obstacle in the total blind area in a braking mode with the maximum deceleration is a safe driving blind area, and the dangerous driving blind area is determined according to the total blind area and the safe driving blind area.

12. The system of claim 11, wherein determining the dangerous driving blind area according to the total blind area and the safe driving blind area comprises:

13. The system of any of claims 9-12, wherein:

14. The system of claim 13, wherein:

15. The system of claim 14, wherein:

when the risk level of the vehicle blind area is higher than a set threshold value, the vehicle is subjected to transverse avoidance preferentially, and the transverse avoidance refers to the fact that the vehicle enters a lane far away from the blind area in the transverse direction to travel;

and when the risk level of the vehicle blind area is lower than a set threshold value, the vehicle continues to run according to the plan of the driving assistance system.

16. The system of claim 15, wherein:

when the risk level of the vehicle blind area is higher than a set threshold value and the vehicle cannot carry out transverse avoidance, the vehicle carries out in-lane avoidance, wherein the in-lane avoidance means that the vehicle moves away from the blind area in the transverse direction of the current lane.

17. The system of claim 16, wherein:

18. A smart driving vehicle comprising an automatic driving assistance system according to any one of claims 9-17.