Night slope warning method, device and electronic equipment of autonomous driving vehicle

Abstract

The application relates to a night slope early warning method, device and electronic equipment of an automatic driving vehicle, wherein the night slope early warning method comprises the following steps: acquiring detection data of a vehicle-mounted radar about the road condition in front of the vehicle; judging the road condition and whether an obstacle vehicle in front of the vehicle disappears according to the detection data; determining a current observation distance when the obstacle vehicle disappears; judging the relationship between the current observation distance and a safe following distance; and giving a following vehicle early warning prompt when the current observation distance is smaller than the safe following distance. The application defaults that the obstacle vehicle in front still exists after the obstacle vehicle in front disappears, and continues to calculate the current observation distance between the two. When the current observation distance is smaller than the safe following distance, a following vehicle early warning prompt is given, so that the automatic driving system controls the vehicle speed, and the current observation distance is always greater than or equal to the safe following distance. The application solves the problem that the following vehicle early warning method of the current automatic driving vehicle cannot realize effective following vehicle early warning in a night slope scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic driving, in particular to a night slope warning method, device and electronic equipment of an automatic driving vehicle. BACKGROUND

[0002] In order to improve the active safety of the automatic driving vehicle and reduce the probability of traffic accident, various active safety related technologies begin to be applied in the automatic driving vehicle, and the following vehicle collision warning is concerned.

[0003] The prerequisite for preventing collision is that the automatic driving system can timely find the front vehicle, obtain the distance and speed between the front and rear vehicles, analyze the distance change gradient, design a control algorithm to control the vehicle speed, so as to maintain a safe vehicle distance and realize the safety of following the vehicle. However, in actual situation, when the automatic driving vehicle encounters a slope, the radar is easy to lose the vehicle target after the front vehicle goes uphill or downhill due to the detection angle. Under the influence of light reflection at night, the target features are easy to blur, and the image algorithm is easy to cause false detection and missed detection, which is not conducive to vehicle decision planning. At present, the following vehicle warning and safety protection method is mainly aimed at the horizontal road surface, and there is lack of following vehicle warning method for slope. When encountering night slope, the vehicle-mounted sensor is affected and lost, the automatic driving system considers that there is no obstacle vehicle in front, and controls the vehicle to accelerate to the maximum speed specified by the law. At this time, if the front vehicle starts to decelerate, the distance between the front and rear vehicles will quickly decrease, and when the sensor detects the front vehicle again, the distance between the front and rear vehicles may not meet the driving safety requirement, thereby causing collision accident.

[0004] At present, there is no effective solution to the problem that the following vehicle warning method of the automatic driving vehicle cannot realize effective following vehicle warning in the night slope scene. SUMMARY

[0005] The present application provides a night slope warning method of an automatic driving vehicle to solve the problem that the following vehicle warning method of the automatic driving vehicle cannot realize effective following vehicle warning in the night slope scene.

[0006] The present application provides a night slope warning method of an automatic driving vehicle, comprising:

[0007] Obtaining the detection data of the vehicle-mounted radar about the road condition in front of the vehicle;

[0008] Judging the road condition and whether the obstacle vehicle in front of the vehicle disappears according to the detection data;

[0009] Determining the current observation distance when the obstacle vehicle disappears, judging the relationship between the current observation distance and the safe following distance, and giving a following vehicle warning prompt when the current observation distance is less than the safe following distance.

[0010] The determining step of the current observation distance comprises:

[0011] When the road condition is horizontal to uphill, the current observation distance is determined by a first uphill sight distance model, the first uphill sight distance model being:

[0012]

[0013] When the road condition is uphill to horizontal, the current observation distance is determined by a second uphill sight distance model, the second uphill sight distance model being:

[0014] S v = 2S r | csc

[0015] When the road condition is horizontal to downhill, the current observation distance is determined by a first downhill sight distance model, the first downhill sight distance model being:

[0016] S v = 2S r | csc

[0017] When the road condition is downhill to horizontal, the current observation distance is determined by a second downhill sight distance model, the second downhill sight distance model being:

[0018]

[0019] wherein S v represents the current observation distance, S r represents the maximum road distance detected by the vehicle-mounted radar, and r represents the included angle between the detection center line direction of the vehicle-mounted radar and the detection direction.

[0020] Compared with the related art, the present application defaults that the front obstacle vehicle still exists after the front obstacle vehicle disappears, and continues to calculate the current observation distance between the two. When the current observation distance is less than the safe following distance, a following warning prompt is given, so that the automatic driving system controls the vehicle speed, so that the current observation distance is always greater than or equal to the safe following distance, thereby ensuring driving safety. The present application solves the problem that the following warning method of the current automatic driving vehicle cannot realize effective following warning in the night slope scene.

[0021] The details of one or more embodiments of the present application are presented in the following drawings and description, so that other features, objects and advantages of the present application are more concise and easy to understand. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1FIG. 1 is a flowchart of a night slope warning method of an autonomous vehicle provided in some embodiments of the present application;

[0023] Figure 2 FIG. 2 is a calculation principle diagram of a first uphill sight distance model in the present application;

[0024] Figure 3 FIG. 3 is a calculation principle diagram of a second uphill sight distance model in the present application;

[0025] Figure 4 FIG. 4 is a calculation principle diagram of a first downhill sight distance model in the present application;

[0026] Figure 5 FIG. 5 is a calculation principle diagram of a second downhill sight distance model in the present application;

[0027] Figure 6 FIG. 6 is a calculation principle diagram of a first uphill distance model in the present application;

[0028] Figure 7 FIG. 7 is a calculation principle diagram of a second uphill distance model in the present application;

[0029] Figure 8 FIG. 8 is a calculation principle diagram of a first downhill distance model in the present application;

[0030] Figure 9 FIG. 9 is a calculation principle diagram of a second downhill distance model in the present application. DETAILED DESCRIPTION

[0031] In order to more clearly understand the purpose, technical scheme and advantages of the present application, the present application is described and explained below in combination with the drawings and embodiments.

[0032] Unless otherwise defined, technical terms or scientific terms used in the present application shall have the same meaning as those commonly understood by a person skilled in the art to which the present application belongs. The terms "one", "a", "an", "the", "these", and similar terms in the present application do not indicate quantity, and they can be singular or plural. The terms "include", "contain", "have", and any variants thereof in the present application are intended to cover non-exclusive inclusion; for example, a process, method, and system, product or device containing a series of steps or modules (units) are not limited to the listed steps or modules (units), but can include steps or modules (units) not listed, or can include other steps or modules (units) inherent to the process, method, product or device. The terms "connect", "connected", "coupled" and the like in the present application are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The term "multiple" in the present application refers to two or more. The term "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. Generally, the character " / " means that the objects before and after are in an "or" relationship. The terms "first", "second", "third" and the like in the present application are only used to distinguish similar objects, and do not represent a specific order of the objects.

[0033] In an embodiment of the present application, a night slope warning method for an autonomous vehicle is provided, Figure 1 is a flowchart of the night slope warning method for an autonomous vehicle provided in some embodiments of the present application, as Figure 1 shown, the flow includes the following steps:

[0034] Step S110, acquiring detection data of a vehicle-mounted radar about the road conditions in front of the vehicle.

[0035] Since the light condition is poor at night, the use of an image sensor to acquire the road conditions in front of the vehicle at this time is prone to image target missing and false detection, thereby making it difficult to accurately determine the road conditions in front of the vehicle. The present application aims to solve the problem of poor light at night by acquiring the road conditions in front of the vehicle through a vehicle-mounted radar. The vehicle-mounted radar realizes distance detection between the vehicle and various objects in front of the vehicle through the transmission and reception of radio waves. For example, within the detection range of the vehicle-mounted radar, the distances between the vehicle and the road surface, the preceding vehicle and the pedestrian can be detected, and the above information can be acquired from the detection data of the vehicle-mounted radar.

[0036] Step S120, determining whether the road conditions and the obstacle vehicle in front of the vehicle disappear according to the detection data.

[0037] When the obstacle vehicle disappears, step S130 is performed, the current observation distance is determined, the relationship between the current observation distance and the safe following distance is judged, and when the current observation distance is less than the safe following distance, a following warning prompt is given.

[0038] Wherein, the obstacle vehicle disappearing in front of the ego vehicle means that the obstacle vehicle disappears from the detection range of the vehicle-mounted radar. This case can be judged by the detection data of the vehicle-mounted radar. Generally, at the moment when the obstacle vehicle disappears, the distance value detected by the vehicle-mounted radar will change suddenly. For example, at the last moment, the distance data between the ego vehicle and the front obstacle vehicle still exists in the detection data of the vehicle-mounted radar (indicating that there is an obstacle vehicle in front), and at the next moment, the distance data between the ego vehicle and the front obstacle vehicle disappears or the value tends to infinity (which are two cases of sudden change of distance value, at this time it is indicated that there is no obstacle vehicle in front), and the change of value can be used to judge whether the obstacle vehicle in front disappears. The specific principle is that if the front vehicle is always within the radar detection range of the rear vehicle, the distance between the front and rear vehicles changes continuously, and the distance change range should comply with the kinematics law. Assuming that the speed of the front vehicle is V f , the deceleration is a f , the speed of the rear vehicle is V e , the deceleration is a e , and the distance gradient change value Δd at the next moment should satisfy:

[0039]

[0040] If the distance gradient change value Δd at a certain moment does not satisfy the above relationship, it means that the front vehicle disappears in the detection field of view of the rear vehicle at that moment.

[0041] When the front obstacle vehicle disappears, the observation distance between the ego vehicle and the front vehicle is calculated, and the observation distances of the two are used as the warning judgment standard, so that the most safe automatic driving can be realized.

[0042] The determination step of the current observation distance includes:

[0043] Referring to Figure 2 When the road condition is a horizontal turn to an uphill, the current observation distance is determined by a first uphill sight distance model, and the first uphill sight distance model is:

[0044]

[0045] Referring to Figure 3 When the road condition is an uphill turn to a horizontal, the current observation distance is determined by a second uphill sight distance model, and the second uphill sight distance model is:

[0046] S v = 2S r |θ1|csc|θ1|

[0047] Referring toFigure 4 When the road condition is horizontal turning down slope, the current observation distance is determined by a first down slope sight distance model, which is:

[0048] S v = 2S r |θ1|csc|θ1|

[0049] Referring to Figure 5 When the road condition is down slope turning horizontal, the current observation distance is determined by a second down slope sight distance model, which is:

[0050]

[0051] wherein S v represents the current observation distance, S r represents the maximum road surface distance detected by the vehicle-mounted radar, θ1represents the included angle between the detection center line direction of the vehicle-mounted radar and the S r detection direction, and S r detection direction refers to the farthest road surface position detected by the vehicle-mounted radar in the direction.

[0052] The above four cases are respectively for four road conditions. The horizontal turning up slope refers to that the ego vehicle is on the horizontal road and the front is the up slope road, the up slope turning horizontal refers to that the ego vehicle is on the up slope road and the front is the horizontal road, the horizontal turning down slope refers to that the ego vehicle is on the horizontal road and the front is the down slope road, and the down slope turning horizontal refers to that the ego vehicle is on the down slope road and the front is the horizontal road. It should be noted that the front referred to in the above is the range that can be detected by the vehicle-mounted radar, not the infinitely extended front. Therefore, in the following, it will also be explained that the judgment of various road conditions is also based on the detection data of the vehicle-mounted radar.

[0053] It should be noted that in the first up slope sight distance model and the second down slope sight distance model, the road surface distance between the farthest road surface position and the ego vehicle is taken as the observation distance of the ego vehicle and the front vehicle. In the second up slope sight distance model and the first down slope sight distance model, the symmetry of the road surface is considered, and the twice of the road surface distance between the farthest road surface position and the ego vehicle is taken as the observation distance of the ego vehicle and the front vehicle. At this time, the actual distance between the ego vehicle and the front vehicle must be greater than or equal to the observation distance.

[0054] In the prior art, after the front obstacle vehicle disappears, it is usually judged that there is no obstacle vehicle in front, and no warning information is given again, and the automatic driving system will speed up the vehicle. In fact, the obstacle vehicle disappears in the detection field of view, and it is very likely that it encounters a slope road condition, and it still exists in front of the ego vehicle. The present application defaults that the front obstacle vehicle still exists after it disappears, and continues to calculate the current observation distance between the two. When the current observation distance is less than the safe following distance, a following warning prompt is given, so that the automatic driving system controls the vehicle speed, so that the current observation distance is always greater than or equal to the safe following distance, thereby ensuring driving safety. The present application solves the problem that the current automatic driving vehicle following warning method cannot realize effective following warning in the night slope scene.

[0055] In some embodiments thereof, when the obstacle vehicle disappears, the road condition judgment step comprises:

[0056] When the ego vehicle is horizontal and the azimuth angle of the maximum road surface distance detected by the vehicle-mounted radar is greater than 0, it is determined that the road condition is horizontal turning uphill.

[0057] When the ego vehicle is horizontal and the azimuth angle of the maximum road surface distance detected by the vehicle-mounted radar is less than 0, it is determined that the road condition is horizontal turning downhill.

[0058] When the ego vehicle is upward, it is determined that the road condition is uphill turning horizontal.

[0059] When the ego vehicle is downward, it is determined that the road condition is downhill turning horizontal.

[0060] Firstly, the state of the ego vehicle can be determined according to the vehicle-mounted pose sensor (such as a gyroscope). When the ego vehicle is on a horizontal road and the front vehicle disappears, there are two cases, one is that the front is uphill, and the other is that the front is downhill, both of which will make the front obstacle vehicle suddenly disappear in the radar field of view. If the front is uphill, the road surface can be detected in the vehicle-mounted radar field of view, and the road surface distance detected by the upper boundary of the field of view is the maximum, that is, the azimuth angle of the maximum road surface distance (the angle of the sound wave conducted to detect the distance) is greater than 0. If the front is downhill, the road surface can be detected only in the lower part of the vehicle-mounted radar field of view, and then the azimuth angle of the maximum road surface distance is less than 0. When the ego vehicle is on an uphill and the front vehicle disappears, it usually means that the front is a horizontal road (it can also be possible that the front is downhill, but it can be regarded as horizontal, and the two have the same visual distance model). When the ego vehicle is on a downhill and the front vehicle disappears, it usually means that the front is a horizontal road (it can also be possible that the front is uphill, but it can be regarded as horizontal, and the two have the same visual distance model).

[0061] As above, the main is the warning processing step when the front obstacle vehicle suddenly disappears.

[0062] On the other hand, the prior art usually takes the detected vehicle distance (usually a straight-line distance) as the actual vehicle distance when the front obstacle vehicle is in the detection field of view, which is relatively accurate on a horizontal road, but is inaccurate on a slope road. For example, when the road surface changes from horizontal to uphill, the road surface is curved, and the vehicle distance is not equal to the straight-line distance between the two vehicles.

[0063] In some embodiments, step S140 is performed when the obstacle vehicle exists, the current actual vehicle distance is determined, and the relationship between the current actual vehicle distance and the safe following distance is determined. When the current actual vehicle distance is less than the safe following distance, a following warning prompt is given.

[0064] The step of determining the current actual vehicle distance includes:

[0065] Referring to Figure 6 When the road condition changes from horizontal to uphill, the current actual vehicle distance is determined by a first uphill distance model, and the first uphill distance model is:

[0066]

[0067] Referring to Figure 7 When the road condition changes from uphill to horizontal, the current actual vehicle distance is determined by a second uphill distance model, and the second uphill distance model is:

[0068] S d = 2S c · |θ2| csc |θ2|

[0069] Referring to Figure 8 When the road condition changes from horizontal to downhill, the current actual vehicle distance is determined by a first downhill distance model, and the first downhill distance model is:

[0070] S d = 2S c · |θ2| csc |θ2|

[0071] Referring to Figure 9 When the road condition changes from downhill to horizontal, the current actual vehicle distance is determined by a second downhill distance model, and the second downhill distance model is:

[0072]

[0073] wherein S d represents the current actual vehicle distance, S c represents the straight-line distance between the vehicle and the obstacle vehicle detected by the vehicle-mounted radar, θ2 represents the included angle between the detection center line direction of the vehicle-mounted radar and the S c detection direction, and S c detection direction refers to the direction in which the vehicle-mounted radar detects the obstacle vehicle.

[0074] Through the above distance model, the actual vehicle distance between the front and rear vehicles can be accurately obtained.

[0075] When the obstacle vehicle exists, the road condition determining step comprises:

[0076] When the ego vehicle is horizontal and the straight-line distance azimuth between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is greater than 0, it is determined that the road condition is horizontal turning up a slope.

[0077] When the ego vehicle is horizontal and the straight-line distance azimuth between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is less than 0, it is determined that the road condition is horizontal turning down a slope.

[0078] When the ego vehicle is upward and the straight-line distance azimuth between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is less than the detection center line azimuth, the road condition is up a slope turning horizontal.

[0079] When the ego vehicle is downward and the straight-line distance azimuth between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is greater than the detection center line azimuth, the road condition is down a slope turning horizontal.

[0080] Specifically, if the front obstacle vehicle and the ego vehicle are in the same straight line and have the same direction of travel (such as being on a horizontal road surface or an uphill road surface, etc.), the front obstacle vehicle will be detected by the detection center line of the vehicle-mounted radar. With this as a reference, the relationship between the front obstacle vehicle and the ego vehicle can be determined through the above steps.

[0081] Correspondingly, when the obstacle vehicle exists, the road condition determining step further comprises:

[0082] When the ego vehicle is horizontal and the straight-line distance azimuth between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is equal to 0, it is determined that the road condition is continuously horizontal.

[0083] When the ego vehicle is upward and the straight-line distance azimuth between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is equal to the detection center line azimuth, it is determined that the road condition is continuously uphill.

[0084] When the ego vehicle is downward and the straight-line distance azimuth between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is equal to the detection center line azimuth, it is determined that the road condition is continuously downhill.

[0085] The determination step of the current actual vehicle distance further comprises:

[0086] When the road condition is continuously horizontal, continuously uphill, or continuously downhill, the straight-line distance between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is determined as the current actual vehicle distance.

[0087] In the above road conditions, since the road surface is basically flat and not curved, the straight-line distance between the ego vehicle and the obstacle vehicle detected by the vehicle-mounted radar is the current actual vehicle distance.

[0088] In some embodiments, the safe following distance comprises a first safe following distance and a second safe following distance, the first safe following distance is greater than the second safe following distance, the following warning prompt comprises a general following warning prompt and an emergency following warning prompt.

[0089] When the current observation distance is less than the safe following distance, giving the following warning prompt comprises:

[0090] When the current observation distance is less than the first safe following distance and greater than the second safe following distance, a general following warning prompt is given; when the current observation distance is less than the second safe following distance, an emergency following warning prompt is given.

[0091] And / or, when the current actual vehicle distance is less than the safe following distance, giving the following warning prompt comprises:

[0092] When the current actual vehicle distance is less than the first safe following distance and greater than the second safe following distance, a general following warning prompt is given; when the current actual vehicle distance is less than the second safe following distance, an emergency following warning prompt is given.

[0093] Wherein, the calculation formula of the first safe following distance is:

[0094] S warning = V e *TTC warning

[0095] Wherein, S warning represents the first safe following distance, V e represents the vehicle speed, TTC warning represents the preset safe time, and the preset safe time is usually between 2.5-3.5 seconds;

[0096] The calculation formula of the second safe following distance is:

[0097] S min =S e -S f +S p

[0098] Wherein, S min represents the second safe following distance, S e represents the vehicle braking distance, S f represents the obstacle vehicle braking distance, and S p represents the preset safe distance.

[0099] As above, the night slope warning method of the automatic driving vehicle has been described more completely.

[0100] It also needs to be explained that when the obstacle vehicle in front of the ego vehicle disappears in the detection field of view, it is also possible that it is caused by the obstacle vehicle turning. However, this situation can be excluded by the detection data. The most important feature is that when the obstacle vehicle disappears by turning, its last moment position in the detection field of view must be on the left or right side of the detection field of view, and when the obstacle vehicle disappears by going up and down the slope, its last moment position in the detection field of view must be on the upper side or the upper side.

[0101] Therefore, in some embodiments thereof, judging whether the obstacle vehicle in front of the ego vehicle disappears means judging whether the obstacle vehicle in front of the ego vehicle disappears by non-turning, and the disappearance of the obstacle vehicle means the disappearance of the obstacle vehicle by non-turning. However, it needs to be emphasized that even if the disappearance mode is not distinguished, that is, it is defaulted that the disappearance of the obstacle vehicle is the occurrence of the slope road condition, it will not affect the implementation of the method and the solution of the technical problem. At this time, the method only has certain use defects, that is, in some cases, the turning of the obstacle vehicle is misjudged as the obstacle vehicle going up and down the slope. Compared with the prior art that defaults the disappearance of the obstacle vehicle as the absence of the obstacle vehicle in front of the ego vehicle, there is still obvious progress.

[0102] The automatic driving vehicle night slope early warning method provided by the present application is further described below through a specific embodiment.

[0103] In a specific embodiment, the automatic driving vehicle night slope early warning method comprises a scene perception module, a risk assessment module, a distance detection module, an early warning module, and a safety guarantee module.

[0104] The scene perception module analyzes the collected radar time series data, analyzes the distance parameter change gradient in the following process, and judges whether the preceding vehicle is in a detected state at all times by comparing the preset gradient value.

[0105] Since the vehicle-mounted visual sensor is prone to failure under night working conditions, the front vehicle is mainly detected by the vehicle-mounted radar. The visual sensor is affected by night lighting and can only rely on the radar to detect the front vehicle; the radar returns 32 target parameters, and according to the number of detected targets, it outputs stable target parameters with speed and distance, and the rest are noise points; in order to extract accurate target parameters, first, the noise points are filtered, the high-frequency noise is filtered out by using a low-pass filter according to the high-frequency characteristics of the noise points, and the low-frequency effective target parameters are retained; then, according to the following requirements, the target in front is detected, and the horizontal direction sensor detection range is constrained to ± 10°; the vertical direction detection angle is constrained to ≥ 0°. Among them, if there is a vehicle in front, the relative speed value in the target parameter tends to 0 after stable following; if a slope is encountered, the obstacle vehicle disappears, and the relative speed value of the detected target is approximately the opposite value of the ego vehicle speed.

[0106] The radar detection working conditions mainly include:

[0107] The detection working conditions are divided into horizontal working condition, horizontal-slope working condition, slope working condition and slope-horizontal working condition, the once climbing process of the following vehicle will experience the horizontal working condition, the horizontal-slope working condition, the slope working condition and the slope-horizontal working condition in turn, and the main purpose of the stage analysis of the climbing process is to obtain the accurate distance between the front and rear vehicles through accurate modeling.

[0108] The horizontal working condition is that the front and rear vehicles are on the horizontal road surface, at this moment, the distance change between the front and rear vehicles is continuous, and the distance change range should meet the kinematics law, assuming that the speed of the front vehicle is V f , the deceleration is a f , the speed of the rear vehicle is V e , the deceleration is a e , and the distance gradient change value Δd at the next moment should meet:

[0109]

[0110] The horizontal-slope working condition is that the front vehicle drives on the slope, and the rear vehicle is still on the horizontal road surface; if the slope is too large, and the radar detection vehicle has no left and right movement trend at the previous moment, the front vehicle is climbing, and the basis for judging the working condition is that the front vehicle leaves the radar detection angle, and the detection distance value suddenly becomes larger and far exceeds Δd.

[0111] The slope working condition is that the front and rear vehicles drive on the slope, under this condition, the slope angle of the front vehicle relative to the rear vehicle is 0, the distance value detected by the radar is the actual distance between the front and rear vehicles, and the distance change meets the Δd change law. The basis for judging the working condition is that the horizontal-slope working condition appears first, and then the front vehicle is detected again and meets the Δd change law.

[0112] The slope-horizontal working condition is that the front vehicle leaves the slope and reaches the horizontal road surface at the top of the slope, and the rear vehicle is still on the slope, and the basis for judging the working condition is that under the condition that the horizontal-slope working condition has appeared, the slope angle of the front vehicle relative to the rear vehicle turns to negative, until the slope angle turns to 0, and the front and rear vehicles return to the horizontal road surface.

[0113] The accurate modeling extracts the road surface in the radar angle of view for different detection working conditions, and uses mathematical expressions to represent the distance size obtained by the radar through analyzing the geometric relationship.

[0114] The front vehicle is in a detected state, that is, the front vehicle is in the sensor detection angle of view, and the distance value detected by the radar changes relatively stably, after the front vehicle disappears, the radar detection distance will suddenly increase due to the influence of the slope, and the increase value is significantly greater than Δd; in addition, due to the lost dynamic target, the relative speed detected by the radar will suddenly change, and the relative speed value of the detected static target is approximately equal to the opposite of the speed of the ego vehicle.

[0115] According to the relative position of the front and rear vehicles, the downhill process is opposite to the uphill process, and the four stages of horizontal-horizontal condition (indicating that the front and rear vehicles are on the horizontal ground), horizontal-ramp condition (indicating that the rear vehicle is on the horizontal ground and the front vehicle is on the ramp), ramp condition (indicating that the front and rear vehicles are on the downhill ramp), and ramp-horizontal condition (indicating that the rear vehicle is on the ramp and the front vehicle returns to the horizontal ground) are experienced in sequence.

[0116] The judgment of whether the front vehicle is uphill or downhill is mainly determined by analyzing the radar sensor return data. If the front vehicle is uphill, the radar first detects the vehicle, then obtains the farthest ground distance within the visual range after the front vehicle disappears, the azimuth angle is upward and greater than 0, and then the stages in the uphill process appear in sequence. In the ramp condition, the front and rear vehicle heads have the same angle, which is relative to the horizontal, and the radar can always detect the front vehicle. After the front vehicle reaches the top of the ramp, the vehicle suddenly disappears, and the farthest distance of the radar visual range has an azimuth angle downward and less than 0. After the front vehicle reaches the top of the ramp, the front vehicle appears in the radar visual angle again, and the position condition of the front and rear vehicles is horizontal-horizontal, and the uphill process is completed.

[0117] Before downhill, the front and rear vehicles are on the same horizontal ground, and the front vehicle is always within the detection visual angle of the radar. When downhill, the front vehicle disappears after the relative speed, the azimuth angle of the farthest distance of the radar visual range is downward and less than 0. Then, the ramp condition and the ramp-horizontal condition are experienced in sequence, and finally the horizontal-horizontal condition is experienced, in which the front and rear vehicles leave the ramp and the downhill process is completed.

[0118] The risk assessment module analyzes the motion behavior that may appear after the front vehicle disappears and poses a threat to the safety of the rear vehicle according to the change of the detected state of the front vehicle, and assesses the maximum risk faced by the vehicle.

[0119] Considering the failure of the night ramp camera detection function and the limited radar detection visual angle, the front vehicle enters the detection blind area, and the motion change of the front vehicle after entering the blind area can be divided into three conditions. The three conditions are:

[0120] Condition one: the front vehicle accelerates after entering the blind area; in the condition one, the rear vehicle maintains the original speed after the front vehicle accelerates into the blind area, and the distance between the front and rear vehicles continues to increase. Based on the minimum safety theory, the increased distance between the vehicles does not pose a threat to the safety of the vehicle. If the rear vehicle also accelerates after the front vehicle disappears, the specific change of the distance between the front and rear vehicles needs to be analyzed to assess whether the distance between the vehicles meets the safety requirements of the vehicle.

[0121] Condition two: the front vehicle uniformly drives after entering the blind area; in the condition two, the front vehicle uniformly enters the blind area, and the rear vehicle maintains the speed, and the distance between the front and rear vehicles remains unchanged. The distance between the vehicles meets the safety requirements of the following vehicle, and the safety of the vehicle is not threatened. If the rear vehicle accelerates due to the lack of vehicles in front, the distance between the front and rear vehicles decreases rapidly, and based on the minimum safety theory, the safety of the vehicle will be seriously threatened.

[0122] Case three: the front vehicle enters the detection blind area and drives at a reduced speed; in case three, the front vehicle enters the detection blind area and drives at a reduced speed, and the rear vehicle keeps the speed unchanged, so the distance between the front and rear vehicles will gradually decrease; if the rear vehicle drives at an accelerated speed, the distance between the vehicles will continue to decrease; in both cases, when the front vehicle is detected again, the distance between the front and rear vehicles cannot meet the following safety at all, and the probability of rear-end collision is extremely high.

[0123] The risk assessment is based on three cases, and the minimum safety distance theory is used to calculate the minimum safety distance in real time. The actual distance between the vehicles is compared to assess the safety of following, and if the distance between the vehicles is found to be less than the minimum safety distance, it is judged that the risk of following at this moment is extremely high; the following warning distance is converted by the warning collision time, and the actual following distance is compared, if the actual distance between the vehicles is found to be less than the warning distance, it means that there is a risk of following, and the system needs to adjust the speed in time to restore the distance between the vehicles to a safe value.

[0124] The distance detection module first analyzes the following distance after the front vehicle disappears based on the risk assessment result, establishes a following model according to the vehicle motion state and parameters, and calculates the distance between the vehicles; at the same time, a sight distance model is established according to the radar viewing angle to calculate the maximum distance value that can be detected within the radar viewing angle range;

[0125] The distance detection module is aimed at four cases of horizontal, horizontal-slope, slope, and slope-horizontal, and the position relationship between the front and rear vehicles is different, and the distance detection acquisition approach is different; the horizontal case, the radar can detect the front vehicle, and the radar output distance is the actual distance between the front and rear vehicles; the horizontal-slope case, the distance between the front and rear vehicles needs to be calculated according to the position relationship between the front and rear vehicles; the slope case, the front and rear vehicles are on the slope, and the vehicles are in the same plane, and the radar output distance is the actual distance between the front and rear vehicles; the slope-horizontal case, the distance between the front and rear vehicles needs to be calculated according to the position relationship between the front and rear vehicles; the distance detection module, after the front vehicle enters the detection blind area, establishes a geometric model based on the sensor viewing angle to calculate the sight distance.

[0126] The warning module classifies the warning information, and outputs different degrees of warning information at different levels.

[0127] The warning module classifies the warning information, including general warning and emergency warning; the general warning is calculated by the warning collision time TTC warning multiplied by the current vehicle speed V e to calculate the warning following distance S warning , which is calculated as follows:

[0128] S warning = V e *TTC warning

[0129] Wherein, TTCwarning As an experience value, it is usually 2.5-3.5. When the pre-warning following distance is greater than the actual following distance S, it indicates that the distance between the front and rear vehicles is too small, and the vehicle starts to issue a periodic sound warning to remind the driver to control the deceleration and increase the distance between the vehicles.

[0130] The emergency pre-warning is based on the minimum safety distance theory to calculate the minimum following distance S in real-time working conditions min , which is calculated as follows:

[0131] S min = S e -S f +S p

[0132] Wherein, S e is the rear vehicle braking distance, and S f is the front vehicle braking distance, which is calculated as follows:

[0133]

[0134] When the minimum safety distance is greater than the actual following distance, the vehicle is in a dangerous state, and a collision is extremely likely to occur during the following process, and the system continuously issues a sound warning.

[0135] The safety guarantee module plans the driving speed by comparing the actual distance and the pre-warning distance when the vehicle is following, adjusts the driving speed, and maintains a safe and reasonable following distance.

[0136] When the system issues a general pre-warning, the safety guarantee module does not take effective measures to increase the distance between the vehicles within 2 seconds, and the system adopts active safety measures to decelerate by braking. Among them, the active safety measures after the general pre-warning consider the comfort of riding, and control the braking deceleration value to ≤4m / s 2

[0137] When the system finds that the following process is about to issue an emergency pre-warning, the safety guarantee module gives priority to driving safety, and increases the distance between the vehicles quickly by using emergency braking to prevent the vehicle from adjusting the speed due to the small distance between the vehicles, resulting in a collision accident. Among them, the emergency braking is the braking of the vehicle with the maximum deceleration, and the brake hydraulic pressure reaches the maximum value.

[0138] Figure 2 ​A distance detection logic process chart for a night slope pre-warning and active safety implementation method for automatic driving assistance is provided in the present application. First, it is determined whether the road ahead is a slope or a straight road through radar detection data. If the preceding vehicle is going uphill and disappears, the farthest distance and azimuth angle detected by the radar is greater than 0. Then, horizontal-slope, slope, slope-horizontal and horizontal-horizontal conditions appear one by one, and the radar detection azimuth angle changes according to greater than 0, equal to 0, less than 0 and equal to 0 respectively, and the current condition is determined according to the angle change. The distance value detected by the sensor in the straight road condition is equal to the actual vehicle-to-vehicle distance. In the slope condition, the radar detection distance cannot be directly used, and the actual vehicle-to-vehicle distance or the sight distance needs to be calculated based on the radar detection distance according to the uphill and downhill processes and the relative position between the front and rear vehicles.

[0139] The downhill process is opposite to the uphill process. In the downhill process, the radar detection angle will be less than 0, equal to 0, greater than 0 and equal to 0 in turn, corresponding to the horizontal-slope, slope, slope-horizontal and horizontal-horizontal conditions.

[0140] In the embodiments of the present application, a night slope pre-warning device for an autonomous vehicle is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. The terms "module", "unit", "sub-unit" and the like used below can be a combination of software and / or hardware that can implement a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and is conceived.

[0141] The night slope pre-warning device for an autonomous vehicle comprises:

[0142] A data acquisition module for acquiring detection data of a vehicle-mounted radar about the road conditions in front of the vehicle;

[0143] A state judgment module for judging the road conditions and whether the obstacle vehicle in front of the vehicle disappears according to the detection data;

[0144] A pre-warning prompt module for determining the current observation distance when the obstacle vehicle disappears, judging the relationship between the current observation distance and the safe following distance, and giving a following pre-warning prompt when the current observation distance is less than the safe following distance;

[0145] The determination of the current observation distance comprises:

[0146] When the road conditions are horizontal to uphill, the current observation distance is determined by a first uphill sight distance model, and the first uphill sight distance model is:

[0147]

[0148] When the road condition changes from uphill to level, the current observation distance is determined using a second uphill sight distance model, which is:

[0149] S v =2S r |θ1|csc|θ1|

[0150] When the road condition is a horizontal to downhill transition, the current observation distance is determined using a first downhill sight distance model, which is as follows:

[0151] S v =2S r |θ1|csc|θ1|

[0152] When the road condition changes from downhill to level, the current observation distance is determined using a second downhill sight distance model, which is as follows:

[0153]

[0154] Among them, S v S represents the current observation distance. r θ1 represents the maximum road distance detected by the vehicle-mounted radar, and θ2 represents the detection centerline direction of the vehicle-mounted radar and S. r The angle between the detected directions.

[0155] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0156] An embodiment of the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to execute the nighttime slope warning method for autonomous vehicles provided by the present invention.

[0157] In an embodiment of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the nighttime slope warning method for autonomous vehicles provided by the present invention are implemented.

[0158] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0159] It is apparent that the drawings depict only some of the embodiments or examples of the application and are therefore not to be considered limiting of the scope of the application, for the application can be applied to other similar situations. Moreover, it is to be understood that unless otherwise specifically stated herein, the application can be practiced with other systems, components, materials and the like without resorting to creativity.

Claims

1. A method for night slope warning of an autonomous vehicle, the method comprising: The method comprises: acquiring detection data of a vehicle-mounted radar about road conditions in front of the vehicle; judging the road conditions and whether an obstacle vehicle in front of the vehicle disappears according to the detection data; determining a current observation distance after the obstacle vehicle disappears, and judging the relationship between the current observation distance and a safe following distance, and giving a following vehicle warning prompt when the current observation distance is less than the safe following distance; the determination of the current observation distance comprises: when the road conditions are horizontal turning to an upward slope, determining the current observation distance by a first upward slope sight distance model, the first upward slope sight distance model being: when the road conditions are upward slope turning to horizontal, determining the current observation distance by a second upward slope sight distance model, the second upward slope sight distance model being: S v = 2S r θ1|cscθ1| when the road conditions are horizontal turning to a downward slope, determining the current observation distance by a first downward slope sight distance model, the first downward slope sight distance model being: S v = 2S r |θ1| csc |θ1| when the road conditions are downward slope turning to horizontal, determining the current observation distance by a second downward slope sight distance model, the second downward slope sight distance model being: Among them, S v S represents the current observation distance. r θ1 represents the maximum road distance detected by the vehicle-mounted radar, and θ2 represents the detection centerline direction of the vehicle-mounted radar and S. r The angle between the detected directions. 2.The automatic driving vehicle night slope warning method of claim 1, wherein, determining a current actual vehicle distance when the obstacle vehicle exists, and judging the relationship between the current actual vehicle distance and the safe following distance, and giving a following vehicle warning prompt when the current actual vehicle distance is less than the safe following distance; the determination of the current actual vehicle distance comprises: when the road conditions are horizontal turning to an upward slope, determining the current actual vehicle distance by a first upward slope distance model, the first upward slope distance model being: when the road conditions are upward slope turning to horizontal, determining the current actual vehicle distance by a second upward slope distance model, the second upward slope distance model being: S d = 2S c · |θ2| csc |θ2| when the road conditions are horizontal turning to a downward slope, determining the current actual vehicle distance by a first downward slope distance model, the first downward slope distance model being: S d = 2S c · |θ2| csc |θ2| when the road conditions are downward slope turning to horizontal, determining the current actual vehicle distance by a second downward slope distance model, the second downward slope distance model being: where S d represents the current actual vehicle distance, S c represents the straight-line distance between the host vehicle and the obstacle vehicle detected by the vehicle-mounted radar, and θ2 represents the included angle between the detection center line direction of the vehicle-mounted radar and the detection direction. c of the vehicle-mounted radar. 3.The automatic driving vehicle night slope warning method of claim 1, wherein, when the obstacle vehicle disappears, the road condition judging step comprises: when the vehicle is horizontal and the azimuth angle of the maximum road surface distance detected by the vehicle-mounted radar is greater than 0, determining that the road conditions are horizontal turning to an upward slope; when the vehicle is horizontal and the azimuth angle of the maximum road surface distance detected by the vehicle-mounted radar is less than 0, determining that the road conditions are horizontal turning to a downward slope; when the vehicle is upward, determining that the road conditions are upward slope turning to horizontal; when the vehicle is downward, determining that the road conditions are downward slope turning to horizontal. 4.The automatic driving vehicle night slope warning method of claim 2, wherein, when the obstacle vehicle exists, the road condition judging step comprises: when the vehicle is horizontal and the azimuth angle of the straight-line distance between the vehicle and the obstacle vehicle detected by the vehicle-mounted radar is greater than 0, determining that the road conditions are horizontal turning to an upward slope; when the vehicle is horizontal and the azimuth angle of the straight-line distance between the vehicle and the obstacle vehicle detected by the vehicle-mounted radar is less than 0, determining that the road conditions are horizontal turning to a downward slope; when the vehicle is upward and the azimuth angle of the straight-line distance between the vehicle and the obstacle vehicle detected by the vehicle-mounted radar is less than the azimuth angle of the detection center line, the road conditions are upward slope turning to horizontal; when the vehicle is downward and the azimuth angle of the straight-line distance between the vehicle and the obstacle vehicle detected by the vehicle-mounted radar is greater than the azimuth angle of the detection center line, the road conditions are downward slope turning to horizontal. 5.The automatic driving vehicle night slope warning method of claim 4, wherein, when the obstacle vehicle exists, the road condition judging step further comprises: When the vehicle is level and the azimuth angle of the straight distance between the vehicle and the obstacle vehicle detected by the vehicle radar is equal to 0, the road condition is determined to be continuously level. When the vehicle is facing upwards and the azimuth angle of the straight distance between the vehicle and the obstacle vehicle detected by the vehicle radar is equal to the azimuth angle of the detection centerline, the road condition is determined to be a continuous uphill slope. When the vehicle is facing downhill and the azimuth angle of the straight distance between the vehicle and the obstacle vehicle detected by the vehicle radar is equal to the azimuth angle of the detection centerline, the road condition is determined to be a continuous downhill slope. The steps for determining the current actual vehicle distance also include: When the road conditions are continuously horizontal, continuously uphill, or continuously downhill, the straight-line distance between the vehicle and the obstacle vehicle detected by the vehicle-mounted radar is determined as the current actual vehicle distance. 6.The automatic driving vehicle night slope warning method of claim 2, wherein, The safe following distance includes a first safe following distance and a second safe following distance, wherein the first safe following distance is greater than the second safe following distance, and the following warning prompts include general following warning prompts and emergency following warning prompts; When the current observation distance is less than the safe following distance, a following warning prompt is given, including: When the current observation distance is less than the first safe following distance and greater than the second safe following distance, the general following warning prompt is given; When the current observation distance is less than the second safe following distance, the emergency following warning prompt is given; And / or, when the current actual following distance is less than the safe following distance, a following warning prompt is given, including: When the current actual following distance is less than the first safe following distance and greater than the second safe following distance, the general following warning prompt is given. When the current actual following distance is less than the second safe following distance, an emergency following warning is given. 7.The automatic driving vehicle night slope warning method of claim 6, wherein, The formula for calculating the first safe following distance is: S warning =V e *TTC warning wherein S warning represents the first safe following distance, V e represents the host vehicle speed, TTC warning represents the preset safety time; The formula for calculating the second safe following distance is: S min = S e - S f + S p wherein S min represents the second safe following distance, S e represents the self-vehicle braking distance, S f represents the obstacle-vehicle braking distance, S p represents the preset safe distance.

8. A nighttime slope warning device for an autonomous vehicle, characterized in that, include: The data acquisition module is used to acquire detection data from the vehicle radar regarding the road conditions ahead of the vehicle; The status judgment module is used to determine the road conditions and whether the obstacle vehicle in front of the vehicle has disappeared based on the detection data. The early warning module is used to determine the current observation distance when the obstacle vehicle disappears, judge the relationship between the current observation distance and the safe following distance, and give a following warning when the current observation distance is less than the safe following distance; The steps for determining the current observation distance include: When the road condition is a horizontal road turning uphill, the current observation distance is determined by a first uphill sight distance model, which is: When the road condition changes from uphill to level, the current observation distance is determined using a second uphill sight distance model, which is: S v = 2S r θ1|cscθ1| When the road condition is a horizontal to downhill transition, the current observation distance is determined using a first downhill sight distance model, which is as follows: S v = 2S r θ1|cscθ1| When the road condition changes from downhill to level, the current observation distance is determined using a second downhill sight distance model, which is as follows: Among them, S v S represents the current observation distance. r θ1 represents the maximum road distance detected by the vehicle-mounted radar, and θ2 represents the detection centerline direction of the vehicle-mounted radar and S. r The angle between the detected directions.

9. An electronic device comprising a memory and a processor, characterized in that The memory stores a computer program, and the processor is configured to run the computer program to perform the nighttime slope warning method for an autonomous vehicle according to any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the nighttime slope warning method for an autonomous vehicle as described in any one of claims 1 to 7.

Images