An automatic emergency braking method, computer device, readable storage medium and motor vehicle

Abstract

The application discloses an automatic emergency braking method, computer equipment, readable storage medium and motor vehicle, and relates to the technical field of motor vehicles, and comprises the following steps: establishing a target set, wherein elements are obstacle vehicles meeting with the ego vehicle; creating a road information set, including lane line information and road edge information; calculating a value of the ego vehicle's collision avoidance according to the ego vehicle's position, the target set and the road information set, wherein the value is the lateral acceleration required for the ego vehicle's collision avoidance; if the value is less than the ego vehicle's limit motion value, warning the driver; and if the value is greater than the ego vehicle's limit motion value, braking the vehicle. The target selection method provided by the application calculates and evaluates the danger degree by extracting road information and information of adjacent lane obstacle vehicles.

Description

Technical Field

[0001] This invention relates to the field of motor vehicle technology, and more specifically to an automatic emergency braking method, a computer device, a readable storage medium, and a motor vehicle. Background Technology

[0002] Automatic Emergency Braking (AEB) is an active safety function that uses environmental perception sensors, such as millimeter-wave radar or vision cameras, to detect potential collision risks with vehicles, pedestrians, or other road users ahead. It then triggers actuators, such as the Electronic Stability Program (ESP), to apply brakes to avoid or mitigate a collision. In a broader sense, AEB includes not only emergency braking but also forward collision warning and emergency braking assistance. The AEB system uses millimeter-wave radar, binocular vision cameras, lidar, and multi-sensor data fusion to detect target information and calculates collision risk in real time based on target speed and relative distance. When the collision risk reaches a pre-set threshold, the system alerts the driver through sound and visual information to avoid a collision. If the driver fails to take any evasive action, the AEB system will proactively intervene to perform emergency collision avoidance.

[0003] Time-to-Traffic (TTC) is the most widely used indicator in hazard estimation, defined as the longitudinal relative distance between the vehicle and the target vehicle divided by their relative speed. However, the TTC algorithm only considers the longitudinal distance between the vehicle and the target vehicle at the TTC time, without considering the target's potential driving behaviors, such as overtaking or lane changing. This simple target selection strategy can easily lead to delayed or missed triggering of the function, thus causing traffic accidents. Therefore, existing target hazard estimation and screening algorithms for AEB (Autonomous Emergency Braking) only consider the target in the vehicle's current lane, i.e., the target in front of the vehicle, and do not perform hazard estimation or screening for targets that may change lanes from adjacent lanes. Summary of the Invention

[0004] To address the aforementioned problems, this invention provides an automatic emergency braking method that calculates and assesses the degree of danger by extracting road information and information on obstructed vehicles in adjacent lanes.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: An automatic emergency braking method includes the following steps: Establish a target set, wherein the elements in the target set are obstacle vehicles that meet the vehicle; Create a road information set, which includes lane line information and curb information; The cost of collision avoidance for the vehicle is calculated based on the vehicle's position, target set, and road information set, wherein the cost is the lateral acceleration required for the vehicle to avoid a collision. Based on the value of the product, the following judgment is made: If the cost is greater than the vehicle's limit motion value, then the vehicle is braked; the vehicle's limit motion value is the maximum lateral acceleration that the vehicle can generate when the steering wheel is turned to its full extent at the current vehicle speed.

[0006] Optionally, calculating the cost of collision avoidance based on the vehicle's location, target set, and road information set includes the following steps: Based on the vehicle's location, target set, and road information set, behaviors are generated and a list of behaviors is created. The behavior is the path that the vehicle takes to avoid collisions with obstacle vehicles without collisions. When generating behaviors, the collision avoidance cost of the vehicle under each behavior is obtained. Based on recursive search, the vehicle position, target set and road information set corresponding to the behavior in the behavior list are regenerated to generate the behavior. When regenerating the behavior, the collision avoidance cost of the vehicle under each regenerated behavior is obtained. For each consecutive action, the larger of the cost values ​​obtained from the two generation actions is selected as the alternative; The minimum value among several alternative costs is selected as the cost of avoiding a collision for the vehicle.

[0007] Optionally, generating behaviors based on the vehicle's location, target set, and road information set, and creating a list of behaviors includes the following steps: Predict the lateral position and velocity of the obstacle vehicle, as well as the lateral velocity of the vehicle at various positions within the prediction time. Perform the following operations for each position of the vehicle within the predicted time: Determine if the location contains an element from the target set and an element from the road information set; if not, assign 0 to the first element in the behavior list; if it exists, calculate the cost of the vehicle's behavior relative to the obstacle vehicle for the target set; calculate the cost of the vehicle's behavior relative to the road for the road information set. The system filters out the cost values ​​and stores the corresponding behaviors, lateral accelerations, the time for applying acceleration, and the sequence number of the obstacle vehicle.

[0008] Optionally, calculating the cost required for the vehicle's behavior relative to obstacle vehicles for the target set includes the following steps: Traverse all obstacle vehicles in the target set, and calculate the cost of the vehicle relative to the four corner points of the obstacle vehicles using the following formula: , , The lateral relative acceleration between the vehicle and the obstacle vehicle is to the left:

[0009] The lateral relative acceleration between the vehicle and the obstacle vehicle is to the right:

[0010] in, P 'This is a process characterization quantity for calculation.' P This refers to the relative distance between the vehicle and the obstacle vehicle. width ego For the width of the vehicle, width obj For the width of the obstructing vehicle, P y The lateral distance between the obstacle vehicle and the vehicle itself. V y The lateral speed of the obstacle vehicle. V yh The lateral speed of the vehicle. A y The lateral acceleration of the obstacle vehicle. A yh_left The value of the corner point of the vehicle relative to the obstacle vehicle to the left; A yh_right The value of the corner point of the vehicle relative to the obstacle vehicle to the right. TTC The time when the vehicle is tangent to or collides with an obstacle vehicle; Of the four corner points whose values ​​are calculated, the right corner points are ALatRqrdRi1 and ALatRqrdRi2, and the TTC value of ALatRqrdRi1 is greater than that of ALatRqrdRi2; the left corner points are ALatRqrdLe1 and ALatRqrdLe2, and the TTC value of ALatRqrdLe1 is greater than that of ALatRqrdLe2. Determine whether the behavior corresponding to the cost of the corner point of the vehicle relative to the obstacle vehicle is valid; Screening the value of the established entities; After filtering, the cost value of the vehicle relative to other obstacle vehicles in the target set is calculated using the following formula:

[0011] get:

[0012]

[0013]

[0014]

[0015] in, a h Let t be the acceleration required for lateral positional overlap, and t be the TTC value to be determined. This is the current lateral position of the vehicle in the obstacle. It is the lateral speed of the obstacle vehicle. It is the lateral speed of the vehicle. It is the lateral acceleration of the obstacle vehicle; When the obstacle vehicle is on the right side of the vehicle, if the TTC value to be judged is less than the TTC values ​​of ALatRqrdLe1 and ALatRqrdLe2, the comparison is valid for the following reasons: a h ,if a h If the cost is greater than the value of establishing it, then... a h and t The cost of a valid value substitution and its TTC value; When the obstacle vehicle is to the left of the vehicle, if the TTC value to be judged is less than the TTC values ​​of ALatRqrdRi1 and ALatRqrdRi2, the comparison is valid, and the cost is... a h ,if a h If the cost is greater than the value of establishing it, then... a h and t The value of the substitution and its TTC value.

[0016] Optionally, determining whether the behavior corresponding to the cost of the vehicle's corner relative to the obstacle vehicle is valid includes the following steps: If the relative speed between the vehicle and the obstacle vehicle is to the left, then the action corresponding to the value of the left front corner of the vehicle relative to the nearest right corner of the obstacle vehicle is valid, and the action corresponding to the value of the right front corner of the vehicle relative to the nearest left corner of the obstacle vehicle is valid. If the relative speed between the vehicle and the obstacle vehicle is to the right, then the action corresponding to the value of the right front corner of the vehicle relative to the nearest left corner of the obstacle vehicle is valid, and the action corresponding to the value of the left front corner of the vehicle relative to the nearest right corner of the obstacle vehicle is valid.

[0017] Optionally, the screening of valid cost values ​​may include the following steps: If all the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 are true, determine the magnitudes of ALatRqrdRi1 and ALatRqrdRi2; a behavior being true means that the behavior will not cause the vehicle to collide with the obstacle vehicle. If ALatRqrdRi2 < ALatRqrdRi1, ALatRqrdRi1 is selected; otherwise, the magnitudes of the absolute values of ALatRqrdRi1 and ALatRqrdRi2 are determined; If abs(ALatRqrdRi1) < abs(ALatRqrdRi2), ALatRqrdRi1 is selected; otherwise, ALatRqrdRi2 is selected; If only one of the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 is valid, the cost value corresponding to the valid behavior is selected; If none of the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 are valid, ALatRqrdRi1, ALatRqrdRi2 and their corresponding TTC are each assigned a maximum value; If all of the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 are valid, the magnitudes of ALatRqrdLe1 and ALatRqrdLe2 are determined; If ALatRqrdLe1 < ALatRqrdLe2, ALatRqrdLe1 is selected; otherwise, the magnitudes of the absolute values of ALatRqrdLe1 and ALatRqrdLe2 are determined; If abs(ALatRqrdLe2) < abs(ALatRqrdLe1), ALatRqrdLe1 is selected; otherwise, ALatRqrdLe2 is selected; If only one of the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 is valid, the cost value corresponding to the valid behavior is selected; If none of the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 are valid, ALatRqrdLe1, ALatRqrdLe2 and their corresponding TTC are each assigned a maximum value.

[0018] Optionally, calculating the cost value required for the ego vehicle's behavior relative to the road for the road information set includes the following steps: Comparing the product of the lateral velocity of the ego vehicle and the first-order coefficient of the road polynomial with the product of the longitudinal velocity of the ego vehicle and the first-order coefficient of the road polynomial, to determine whether the ego vehicle is parallel to the lane, wherein the road polynomial is a cubic polynomial for fitting a road curve, if parallel, the TTC load value is set to 0, if not parallel, the TTC is calculated according to the following formula load value:

[0019] wherein, TTC loadVself represents the time when the vehicle is tangent to or collides with the road edge, ConstCoeff is the constant coefficient of the road polynomial, Offset is the vehicle bias, and Vself is the time when the vehicle is tangent to or collides with the road edge. Lat Vself is the lateral velocity of the vehicle. Lgt Let represent the longitudinal velocity of the vehicle, and FirstCoeff be the first-order coefficient of the road polynomial. If the lane line is within half the width of your vehicle, TTC load The value is assigned to 0, and the TTC is also assigned to 0. load The corresponding behavior corresponding to the cost value is invalid behavior, and the cost value is assigned to the maximum value. If the lane line is not within the half width of the vehicle, the corresponding cost value is obtained through the constant acceleration model and used as the cost value tangent to the lane line. Calculate the lateral position of the vehicle relative to the lane line at the time of TTE, where TTE is the time when the vehicle reaches the end of the road. If the lane line is to the left of the vehicle, subtract half the vehicle's width from the lateral position of the vehicle relative to the lane line. If the lane line is to the right of the vehicle, add half the vehicle's width to the lateral position of the vehicle relative to the lane line. If the TTE value corresponding to the lateral position of the vehicle relative to the lane line is greater than 0, obtain the corresponding cost value through the constant acceleration model, and use it as the cost value for the vehicle to reach the end of the road. If the TTE value corresponding to the lateral position of the vehicle relative to the lane line is not greater than 0, assign the maximum value to the cost value. Comparison of TTC load Value and TTE value, if TTC load If the TTE value is greater than the TTE value, the action corresponding to the cost of being tangent to the lane line is valid. If the TTE value is greater than 0 and the distance between the vehicle and the lane line is greater than half the width of the vehicle, the action of the vehicle reaching the end of the road is valid. If both actions are valid, then TTC (Traffic Troubleshooting) is not valid. load The action corresponding to the smaller cost value is valid; if both actions are invalid, then the TTC for each action is sent separately. load The value is assigned to 0.

[0020] Optionally, screening for value may include the following steps: Determine whether a lateral acceleration of 0 is a usable behavior. A usable behavior is one in which the vehicle does not collide with other vehicles calculated from other positions at any location. For paths where there is no collision with obstacle vehicles, if a lateral acceleration of 0 is not a usable behavior, then the behaviors of moving left, moving right, and tangent to the road line are determined as follows: If the absolute value of the cost is less than a preset threshold, then the behavior corresponding to the cost value is a useless behavior. If it is less than the threshold, then it is determined whether the behavior corresponding to the cost value collides with the behavior calculated from other locations. If there is no collision, then the cost value is used as the selected cost value. If no value is found among the selected values, then the first element in the list of behaviors is assigned a maximum value.

[0021] Optionally, creating a road information set includes the following steps: The curve of the road is fitted with a cubic polynomial; Divide the line segment into at least three segments, and determine whether each segment is within the road boundary using the following formula:

[0022] in, Boundaries For the width of the road, x Let c0 be the position of the line segment on the road, c1 be the constant term in the cubic polynomial, c2 be the coefficient of the quadratic term in the cubic polynomial, and c3 be the coefficient of the cubic term in the cubic polynomial. Obtain road enabling information. If the road is continuous and the vehicle's acceleration within the road is less than a threshold, then the road is a valid road; otherwise, it is an invalid road. Calculate the time elapsed (TTE) required for the vehicle to reach the end of the road:

[0023] Among them, V rel a is the negative of the vehicle's speed. rel P is the negative of the vehicle's acceleration, and P is the road length minus the length from the center of the vehicle's rear axle to the front of the vehicle. Stores the road's enabling information, TTE value, constant term and linear term in the cubic polynomial; The road information set is stored separately for left and right. The TTE value of invalid roads is assigned as -2, the TTE value of valid roads but the constant term in the cubic polynomial does not meet the limit value is assigned as -1, and the TTE value of valid roads and the constant term in the cubic polynomial meets the limit value is the calculated value. The roads are sorted in descending order, and the index values ​​of the sorted left and right roads are stored separately. The valid roads and their index values ​​are stored in the road information set, with a maximum of 4 valid roads stored. The index value is the sequence number of the road information in the road information set.

[0024] Optionally, establishing the target set includes the following steps: Apart from the vehicle's position, the remaining positions are filled into the initial target set by InPath targets in order of distance from nearest to farthest. InPath targets are obstacle vehicles whose projection on the y-axis in the vehicle's coordinate system coincides with the vehicle's position; wherein, the y-axis is the direction perpendicular to the vehicle's driving direction. The initial target set obtained by traversal is considered if the elements in the initial target set satisfy the preset validity conditions and the corresponding... If the element meets the preset range, then store it in the target set. The longitudinal relative distance between the vehicle and the target vehicle is divided by the relative speed; the preset validity conditions include: the element is the first preset number of elements in the initial target set, and the element is an obstacle vehicle that overlaps with the vehicle in the lateral direction.

[0025] The automatic emergency braking method provided by this invention generates a series of collision-free obstacle avoidance behaviors or collision avoidance paths based on a recursive search tree. The behavior generation algorithm uses the assumption that if the optimal path is not straight ahead, it will always be tangent to at least one object. By using this assumption, the computational cost of finding the optimal path is significantly reduced, saving a considerable amount of computing power. Furthermore, through two searches, the current time is used to predict the future time, and then the future time is used for prediction. Combining road information and vehicle information from adjacent lanes, the overall risk level is calculated and assessed. This includes situations such as vehicles crossing lane lines, colliding with curbs, and merging from adjacent lanes, overcoming the limitation of existing technologies that only consider the vehicle's own lane. The calculated hazardous targets have a higher confidence level.

[0026] Furthermore, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the automatic emergency braking method described in any of the preceding claims.

[0027] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the automatic emergency braking method described in any of the above claims.

[0028] Furthermore, the present invention also provides a motor vehicle having an AEB system, the AEB system performing the automatic emergency braking method described in any one of the preceding claims; Or the motor vehicle has the aforementioned computer equipment; Alternatively, the motor vehicle may have the aforementioned computer-readable storage medium, and the computer program, when executed by a processor, implements the automatic emergency braking method described in any of the preceding claims.

[0029] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and accompanying drawings. The preferred embodiments or means of the present invention will be shown in detail in conjunction with the accompanying drawings, but are not intended to limit the technical solutions of the present invention. In addition, each of these features, elements and components appearing in the following text and drawings is a plurality of, and different symbols or numbers are used for convenience of representation, but all represent parts with the same or similar construction or function. Attached Figure Description

[0030] The present invention will be further described below with reference to the accompanying drawings: Figure 1This is a flowchart from an embodiment of the present invention; Figure 2 This is a flowchart illustrating the process of filtering the established cost values ​​in an embodiment of the present invention. Figure 3 This is a schematic diagram illustrating continuous behavior in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be explained and described below with reference to the accompanying drawings. However, the following embodiments are only preferred embodiments of the present invention and not all of them. Other embodiments obtained by those skilled in the art based on the embodiments in the implementation methods without creative effort are all within the protection scope of the present invention.

[0032] The terms "an embodiment," "example," or "trademark" used in this specification refer to a particular feature, structure, or characteristic described in connection with the embodiment itself that may be included in at least one embodiment disclosed in this patent. The phrase "in an embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0033] Example: like Figure 1 As shown, this embodiment provides an automatic emergency braking method for a vehicle's AEB system, including the following steps: A target set is established, where each element represents an obstacle vehicle that will encounter the vehicle. In this embodiment, "encountering" refers not only to oncoming vehicles, but also to calculating the distances between the rear axle center of the vehicle and the front of the target vehicle, and between the front of the vehicle and the rear of the target vehicle, in the vehicle's coordinate system. These distances are the farthest and closest sides of the two vehicles, and have a direction. If both distances have the same sign, the target is considered an oncoming vehicle, and its lateral distance is assigned the true lateral distance; otherwise, the value is assigned 100000.

[0034] Apart from the vehicle's position, the remaining positions are filled into the initial target set by InPath targets in order of distance from nearest to farthest. InPath targets are obstacle vehicles whose projection on the y-axis in the vehicle's coordinate system coincides with the vehicle's position; wherein, the y-axis is the direction perpendicular to the vehicle's driving direction. The initial target set obtained by traversal is considered if the elements in the initial target set satisfy the preset validity conditions and the corresponding... If the element meets the preset range, it will be stored in the target set (TTC). F The longitudinal relative distance between the vehicle and the target vehicle is divided by the relative speed. The preset validity conditions include: the element is one of the first preset elements in the initial target set, and the element is an obstacle vehicle that overlaps with the vehicle in the lateral direction. Specifically, in this embodiment, TTC... F The preset range is 0 <TTCF <10, and the validity of the target is determined by the first 8 elements in the initial target set being valid. Furthermore, in this embodiment, the target set can hold a maximum of 6 targets. In other embodiments, TTC... F The preset range and the validity of the elements can be flexibly set by those skilled in the art according to the vehicle model and calibration requirements, and are not limited here.

[0035] Creating a road information set, including lane line information and curb information, involves the following steps: The curve of the road is fitted with a cubic polynomial; Divide the line segment into at least three segments, and determine whether each segment is within the road boundary using the following formula:

[0036] in, Boundaries For the width of the road, x Let x represent the position of the line segment on the road, c0 be the constant term in the cubic polynomial, c1 be the coefficient of the linear term in the cubic polynomial, c2 be the coefficient of the quadratic term in the cubic polynomial, and c3 be the coefficient of the cubic term in the cubic polynomial. If the value of x obtained by solving this formula satisfies the inequality requirements, then the line segment is considered to be within the road boundary in the corresponding interval.

[0037] The system obtains road enabling information. If the road is continuous and the vehicle's acceleration within the road is less than a threshold, then the road is considered valid; otherwise, it is considered invalid. The acceleration threshold is set by those skilled in the art based on the vehicle type and performance; in this embodiment, 5 m / s² is selected. 2 .

[0038] Calculate the time elapsed (TTE) required for the vehicle to reach the end of the road:

[0039] Among them, V rel a is the negative of the vehicle's speed. rel P is the negative of the vehicle's acceleration, and P is the road length minus the length from the center of the vehicle's rear axle to the front of the vehicle. Stores the road's enabling information, TTE value, constant term and linear term in the cubic polynomial; The road information set is stored separately for left and right sides. Invalid roads are assigned a TTE value of -2, valid roads where the constant term in the cubic polynomial does not meet the specified value are assigned a TTE value of -1, and valid roads where the constant term in the cubic polynomial meets the specified value have a calculated TTE value. In this embodiment, the specified value for the constant term is an absolute value greater than or equal to 3.

[0040] The roads are sorted in descending order, and the index values ​​of the sorted left and right roads are stored separately. The valid roads and their index values ​​are stored in the road information set, with a maximum of 4 valid roads stored. The index value is the sequence number of the road information in the road information set.

[0041] It should be noted that there is no specific order in which the target set and the road information set are established. The order described in this embodiment is not a limitation on the order of the two steps. In implementation, the target set and the road information set can be established simultaneously or sequentially; no limitation is made here.

[0042] After establishing the target set and road information set, the cost of collision avoidance for the vehicle is calculated based on the vehicle's position, the target set, and the road information set. The cost is the lateral acceleration required for collision avoidance. The cost calculation includes the following steps: Following these sub-steps, generate behaviors based on the vehicle's position, target set, and road information set, and create a list of behaviors. A behavior is a path where the vehicle is tangent to an obstacle vehicle without collision. When generating behaviors, obtain the collision avoidance cost for each behavior: Predict the lateral position and velocity of obstacle vehicles, as well as the lateral velocity of the vehicle at various positions within the prediction time. The prediction order is from the last one in the storage order forward. Based on the relationship formula between distance, velocity, and acceleration in conventional physics formulas, calculate the positions within the time range to be predicted.

[0043] Perform the following operations for each position of the vehicle within the predicted time: Determine if a corresponding element exists in both the target set and the road information set at the given location. If not, assign 0 to the first element in the behavior list. If it exists, calculate the cost of the vehicle's behavior relative to the obstacle vehicles for the target set; calculate the cost of the vehicle's behavior relative to the road for the road information set. In the step of calculating the cost of the vehicle's behavior relative to the obstacle vehicles for the target set, iterate through all obstacle vehicles in the target set and calculate the cost of the vehicle's four corner points relative to the obstacle vehicles using the following formula: , , The lateral relative acceleration between the vehicle and the obstacle vehicle is to the left:

[0044] The lateral relative acceleration between the vehicle and the obstacle vehicle is to the right:

[0045] in, P 'This is a process characterization quantity for calculation.' PThis refers to the relative distance between the vehicle and the obstacle vehicle. width ego For the width of the vehicle, width obj Given the width of the obstacle vehicle, those skilled in the art know how the vehicle and the obstacle vehicle should be tangent to avoid a collision. Therefore, depending on the relative position of the obstacle vehicle and the vehicle, the relative distance P between the vehicle and the obstacle vehicle will also change accordingly. Consequently, when the lateral relative acceleration between the vehicle and the obstacle vehicle is to the left and to the right, different values ​​are taken, and two cost values ​​are calculated respectively. P y The lateral distance between the obstacle vehicle and the vehicle itself. V y The lateral speed of the obstacle vehicle. V yh The lateral speed of the vehicle. A y The lateral acceleration of the obstacle vehicle. A yh_left The value of the corner point of the vehicle relative to the obstacle vehicle to the left; A yh_right The value of the corner point of the vehicle relative to the obstacle vehicle to the right. TTC The time when the vehicle becomes tangent to or collides with an obstacle vehicle. A yh_left and A yh_right It is the cost value that needs to be solved.

[0046] The cost values ​​of the four corner points are calculated, and each corner point corresponds to a TTC value. The corner points on the right are ALatRqrdRi1 and ALatRqrdRi2, and the TTC value of ALatRqrdRi1 is greater than that of ALatRqrdRi2. The corner points on the left are ALatRqrdLe1 and ALatRqrdLe2, and the TTC value of ALatRqrdLe1 is greater than that of ALatRqrdLe2.

[0047] Determine whether the action corresponding to the cost of the vehicle's corner relative to the obstacle vehicle is valid by following these steps. Whether the action is valid refers to whether the action will cause a collision between the vehicle and the obstacle vehicle. If the action will not cause a collision, then the action is valid. Figure 2 As shown: If the relative speed between the vehicle and the obstacle vehicle is to the left, then the action corresponding to the value of the left front corner of the vehicle relative to the nearest right corner of the obstacle vehicle is valid, and the action corresponding to the value of the right front corner of the vehicle relative to the nearest left corner of the obstacle vehicle is valid. If the relative speed of the ego vehicle and the obstacle vehicle is directed to the right, the behavior corresponding to the cost value of the right front corner point of the ego vehicle relative to the closest left corner point of the obstacle vehicle is valid, and the behavior corresponding to the cost value of the left front corner point of the ego vehicle relative to the closest right corner point of the obstacle vehicle is valid.

[0048] The valid cost values are screened according to the following steps, and the screened behavior is the most reasonable behavior at this position: If the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 are both valid, determine the magnitudes of ALatRqrdRi1 and ALatRqrdRi2; a valid behavior means that the behavior will not cause collision between the ego vehicle and the obstacle vehicle; If ALatRqrdRi2<ALatRqrdRi1, select ALatRqrdRi1; otherwise determine the magnitudes of the absolute values of ALatRqrdRi1 and ALatRqrdRi2; If abs(ALatRqrdRi1)<abs(ALatRqrdRi2), select ALatRqrdRi1, otherwise select ALatRqrdRi2; If only one of the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 is valid, select the cost value corresponding to the valid behavior; If none of the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 is valid, assign maximum values to ALatRqrdRi1, ALatRqrdRi2 and their corresponding TTC respectively; If the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 are both valid, determine the magnitudes of ALatRqrdLe1 and ALatRqrdLe2; If ALatRqrdLe1<ALatRqrdLe2, select ALatRqrdLe1, otherwise determine the magnitudes of the absolute values of ALatRqrdLe1 and ALatRqrdLe2; If abs(ALatRqrdLe2)<abs(ALatRqrdLe1), select ALatRqrdLe1, otherwise select ALatRqrdLe2; If only one of the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 is valid, select the cost value corresponding to the valid behavior; If none of the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 is valid, assign maximum values to ALatRqrdLe1, ALatRqrdLe2 and their corresponding TTC respectively.

[0049] After identifying the valid cost values, the behavior tangent to the paths of other obstacle vehicles is calculated. The difference from the previous calculation is the presence of longitudinal TTC (Traffic Traverse Cost). F Within a given timeframe, it's possible that both vehicles have reached the same position laterally. In other words, after identifying the valid cost, it's necessary to calculate whether a lateral collision will occur before the longitudinal collision with the obstacle vehicle. Furthermore, this calculation step is only required when the lateral relative velocity between the vehicle and the obstacle vehicle is 0.

[0050] The cost value of the vehicle relative to other obstacle vehicles in the target set is calculated using the following formula:

[0051] get:

[0052]

[0053]

[0054]

[0055] in, a h Let t be the acceleration required for lateral positional overlap, and t be the TTC value to be determined. This is the current lateral position of the vehicle in the obstacle. It is the lateral speed of the obstacle vehicle. It is the lateral speed of the vehicle. It is the lateral acceleration of the obstacle vehicle; When the obstacle vehicle is on the right side of the vehicle, if the TTC value to be judged is less than the TTC values ​​of ALatRqrdLe1 and ALatRqrdLe2, the comparison is valid for the following reasons: a h ,if a h If the cost is greater than the value of establishing it, then... a h and t The cost of a valid value substitution and its TTC value; When the obstacle vehicle is to the left of the vehicle, if the TTC value to be judged is less than the TTC values ​​of ALatRqrdRi1 and ALatRqrdRi2, the comparison is valid, and the cost is... a h ,if a h If the cost is greater than the value of establishing it, then... a h and t The value of the substitution and its TTC value.

[0056] Calculating the cost required for a vehicle's behavior relative to the road based on a road information set includes the following steps: The system compares the product of the vehicle's lateral velocity and the first coefficient of the road polynomial with the product of the vehicle's longitudinal velocity and the first coefficient of the road polynomial to determine if the vehicle is parallel to the lane. If the product of the vehicle's lateral velocity and the first coefficient of the road polynomial is greater than the product of the vehicle's longitudinal velocity and the first coefficient of the road polynomial, then the vehicle is parallel to the road, and there is no lane crossing. Therefore, TTC (Traffic Traffic Control) is applied. load The value is assigned to 0. The road polynomial is a cubic polynomial fitted to the road curve. If the curves are not parallel, the TTC is calculated according to the following formula. load value:

[0057] Among them, TTC load The time when the vehicle is tangent to or collides with the road edge, ConstCoeff is the constant coefficient of the road polynomial, Offset is the vehicle offset, VselfLat is the lateral velocity of the vehicle, VselfLgt is the longitudinal velocity of the vehicle, and FirstCoeff is the first-order coefficient of the road polynomial. Then determine if your vehicle has crossed the lane line: if the lane line is within half the width of your vehicle, TTC load The value is assigned to 0, and the TTC is also assigned to 0. load The corresponding action corresponding to the cost value is considered invalid, and the cost value is assigned to the maximum value. If the lane line is not within the vehicle's half-width, the corresponding cost value is obtained through the constant acceleration model and used as the cost value for tangency to the lane line. The constant acceleration model is the formula relating distance, velocity, and acceleration in conventional physics, i.e. v = at , s =(1 / 2) at 2 .

[0058] Calculate the lateral position of the vehicle relative to the lane line at the Time of Exit (TTE), where TTE represents the moment the vehicle reaches the end of the road. If the lane line is to the left of the vehicle, subtract half the vehicle's width from the lateral position of the vehicle relative to the lane line. If the lane line is to the right of the vehicle, add half the vehicle's width to the lateral position of the vehicle relative to the lane line. If the TTE value corresponding to the lateral position of the vehicle relative to the lane line is greater than 0, the corresponding cost is obtained through the constant acceleration model and used as the cost of the vehicle reaching the end of the road. If the TTE value corresponding to the lateral position of the vehicle relative to the lane line is not greater than 0, it means that the vehicle has already reached the end of the road, so the cost is assigned a maximum value, and the corresponding action is invalid.

[0059] Comparison of TTC loadValue and TTE value, if TTC load If the TTE value is greater than the lane tether value, the action corresponding to the cost of being tangent to the lane line is valid. If the TTE value is greater than 0 and the distance between the vehicle and the lane line is greater than half the width of the vehicle, the action of the vehicle reaching the end of the road is valid. This is because if the vehicle has already reached the end of the road, it can be considered that there is no risk of crossing the line. If both actions are valid, then TTC (Traffic Tether) is applied. load The action corresponding to the smaller cost value is valid; if both actions are invalid, then the TTC for each action is sent separately. load The value is assigned to 0.

[0060] It should also be noted that there is no specific order in which the cost required to calculate the vehicle's behavior relative to obstacle vehicles for the target set and the cost required to calculate the vehicle's behavior relative to the road for the road information set are performed. The order of description in this embodiment is not a limitation on the order of the two steps. In the implementation of this embodiment, the cost required for the vehicle's behavior relative to obstacle vehicles and the cost required for the vehicle's behavior relative to the road can be calculated simultaneously or sequentially, without any limitation here.

[0061] The above steps only calculate the cost value for a single location. Therefore, after calculating the cost value required for the vehicle's behavior relative to obstacle vehicles and the vehicle's behavior relative to the road for a single location, it is necessary to concatenate all locations. Therefore, the calculated cost values ​​are filtered according to the following steps: the behaviors corresponding to the cost values ​​between each location that will not result in a collision are selected, and the behaviors corresponding to the selected cost values, along with the resulting lateral acceleration, the time at which the acceleration should be applied, and the sequence number of the obstacle vehicle are stored. Determine whether a lateral acceleration of 0 is a usable behavior. A usable behavior is one in which the vehicle does not collide with other vehicles calculated from other positions at any location. For paths where there is no collision with obstacle vehicles, if a lateral acceleration of 0 is not a usable behavior, then the behaviors of moving left, moving right, and tangent to the road line are determined as follows: The system checks if the absolute value of the cost is less than a preset threshold. If it is not less, the corresponding behavior is considered useless. If it is less, it checks if the behavior collides with behaviors calculated from other positions. If there is no collision, the cost is selected and the corresponding behavior is added to the behavior list. The threshold here refers to the maximum lateral acceleration calculated in the extreme motion state, which is the motion state when the steering wheel is fully turned. "No collision" means that the behavior corresponding to the cost at the current position does not collide with behaviors corresponding to the cost at other positions. If no selected cost exists, the first element in the behavior list is assigned a maximum value, indicating that no effective collision avoidance behavior is generated.

[0062] At this point, the behavior list is complete. Then, based on recursive search, behaviors are regenerated for the vehicle's location, target set, and road information set corresponding to the behaviors in the behavior list. During behavior regeneration, the collision avoidance cost for each regenerated behavior is obtained. The process of regenerating behaviors and obtaining their costs is consistent with the aforementioned cost and behavior calculation process, and will not be repeated here.

[0063] like Figure 3 As shown, the solid gray rectangle represents the vehicle's current position, and the dashed gray rectangle represents the vehicle's position after the generated action; the black rectangle represents obstacle vehicles. The solid line represents one of the actions generated during the first search, and the dashed lines represent four actions generated during the second search based on that action. For each consecutive action, the larger of the cost values ​​obtained from the two generated actions is used as an alternative. The minimum value among several alternative costs is selected as the cost of avoiding a collision for the vehicle.

[0064] Based on the value of the product, the following judgment is made: If the cost is less than the vehicle's limit of motion, the driver can avoid the collision on their own, and no action is required. If the cost is greater than the vehicle's limit of motion, the vehicle is braked. The vehicle's limit of motion is the maximum lateral acceleration that the vehicle can generate when the steering wheel is turned to its full extent at the current speed.

[0065] The automatic emergency braking method provided in this embodiment generates a series of collision-free obstacle avoidance behaviors or collision avoidance paths based on a recursive search tree. The behavior generation algorithm uses the assumption that if the optimal path is not straight ahead, it will always be tangent to at least one object. By using this assumption, the computational cost of finding the optimal path is significantly reduced, saving a considerable amount of computing power. Furthermore, through two searches—predicting future times from the current time and then using future times for prediction—combining road information and vehicle information from adjacent lanes, the overall risk level is calculated and assessed. This includes situations such as vehicles crossing lane lines, colliding with curbs, and merging from adjacent lanes, overcoming the limitation of existing technologies that only consider the vehicle's own lane. The calculated hazardous targets have a higher confidence level.

[0066] Meanwhile, this embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the above-described target selection method.

[0067] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. Accordingly, the computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can implement the methods of any of the above embodiments. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0068] Furthermore, this embodiment also provides a motor vehicle equipped with an AEB system, wherein the AEB system of the motor vehicle provided in this embodiment performs the aforementioned automatic emergency braking method.

[0069] Or the motor vehicle has the aforementioned computer equipment; The vehicle may have the aforementioned computer-readable storage medium, and when the computer program is executed by the processor, it implements the aforementioned automatic emergency braking method.

[0070] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Those skilled in the art should understand that the present invention includes, but is not limited to, the contents described in the accompanying drawings and the specific embodiments above. Any modifications that do not depart from the functional and structural principles of the present invention will be included within the scope of the claims.

Claims

1. An automatic emergency braking method, characterized in that, Includes the following steps: Establish a target set, wherein the elements in the target set are obstacle vehicles that meet the vehicle; Create a road information set, which includes lane line information and curb information; The cost of collision avoidance for the vehicle is calculated based on the vehicle's position, target set, and road information set, wherein the cost is the lateral acceleration required for the vehicle to avoid a collision. Based on the value of the product, the following judgment is made: If the cost is greater than the vehicle's limit motion value, then the vehicle is braked; the vehicle's limit motion value is the maximum lateral acceleration that the vehicle can generate when the steering wheel is turned to its full extent at the current vehicle speed. The calculation of the collision avoidance cost based on the vehicle's position, target set, and road information set includes the following steps: Based on the vehicle's location, target set, and road information set, behaviors are generated and a list of behaviors is created. The behavior is the path that the vehicle takes to avoid collisions with obstacle vehicles without collisions. When generating behaviors, the collision avoidance cost of the vehicle under each behavior is obtained. Based on recursive search, the vehicle position, target set and road information set corresponding to the behavior in the behavior list are regenerated to generate the behavior. When regenerating the behavior, the collision avoidance cost of the vehicle under each regenerated behavior is obtained. For each consecutive action, the larger of the cost values ​​obtained from the two generation actions is selected as the alternative; The minimum value among several alternative costs is selected as the cost of avoiding a collision for the vehicle.

2. The automatic emergency braking method according to claim 1, characterized in that, Generating behaviors and creating a list of behaviors based on the vehicle's location, target set, and road information set includes the following steps: Predict the lateral position and velocity of the obstacle vehicle, as well as the lateral velocity of the vehicle at various positions within the prediction time. Perform the following operations for each position of the vehicle within the predicted time: Determine if the location contains an element from the target set and an element from the road information set; if not, assign 0 to the first element in the behavior list; if it does, calculate the cost required for the vehicle's behavior relative to the obstacle vehicle for the target set. The cost required to calculate the vehicle's behavior relative to the road given the road information set; The system filters out the cost values ​​and stores the corresponding behaviors, lateral accelerations, the time for applying acceleration, and the sequence number of the obstacle vehicle.

3. The automatic emergency braking method according to claim 2, characterized in that, Calculating the cost required for the behavior of a vehicle relative to obstacle vehicles on a target set includes the following steps: Traverse all obstacle vehicles in the target set, and calculate the cost of the vehicle relative to the four corner points of the obstacle vehicles using the following formula: ， ， The lateral relative acceleration between the vehicle and the obstacle vehicle is to the left: The lateral relative acceleration between the vehicle and the obstacle vehicle is to the right: in, P 'This is a process characterization quantity for calculation.' P This refers to the relative distance between the vehicle and the obstacle vehicle. width ego For the width of the vehicle, width obj For the width of the obstructing vehicle, P y The lateral distance between the obstacle vehicle and the vehicle itself. V y The lateral speed of the obstacle vehicle. V yh The lateral speed of the vehicle. A y The lateral acceleration of the obstacle vehicle. A yh_left The value of the corner point of the vehicle relative to the obstacle vehicle to the left; A yh_right The value of the corner point of the vehicle relative to the obstacle vehicle to the right. TTC The time when the vehicle is tangent to or collides with an obstacle vehicle; Of the four corner points whose values ​​are calculated, the right corner points are ALatRqrdRi1 and ALatRqrdRi2, and the TTC value of ALatRqrdRi1 is greater than that of ALatRqrdRi2; the left corner points are ALatRqrdLe1 and ALatRqrdLe2, and the TTC value of ALatRqrdLe1 is greater than that of ALatRqrdLe2. Determine whether the behavior corresponding to the cost of the corner point of the vehicle relative to the obstacle vehicle is valid; Screening the value of the established entities; After filtering, the cost value of the vehicle relative to other obstacle vehicles in the target set is calculated using the following formula: get: in, a h Let t be the acceleration required for lateral positional overlap, and t be the TTC value to be determined. This is the current lateral position of the vehicle in the obstacle. It is the lateral speed of the obstacle vehicle. It is the lateral speed of the vehicle. It is the lateral acceleration of the obstacle vehicle; When the obstacle vehicle is on the right side of the vehicle, if the TTC value to be judged is less than the TTC values ​​of ALatRqrdLe1 and ALatRqrdLe2, the comparison is valid for the following reasons: a h ,if a h If the cost is greater than the value of establishing it, then... a h and t The cost of a valid value substitution and its TTC value; When the obstacle vehicle is to the left of the vehicle, if the TTC value to be judged is less than the TTC values ​​of ALatRqrdRi1 and ALatRqrdRi2, the comparison is valid, and the cost is... a h ,if a h If the cost is greater than the value of establishing it, then... a h and t The cost of a valid value substitution and its TTC value; Wherein, determining whether the behavior corresponding to the cost value of the ego vehicle relative to the corner points of the obstacle vehicle is valid includes the following steps: if the relative velocity of the ego vehicle and the obstacle vehicle is towards the left, the behavior corresponding to the cost value of the left front corner point of the ego vehicle relative to the closest right corner point of the obstacle vehicle is valid, and the behavior corresponding to the cost value of the right front corner point of the ego vehicle relative to the closest left corner point of the obstacle vehicle is valid; if the relative velocity of the ego vehicle and the obstacle vehicle is towards the right, the behavior corresponding to the cost value of the right front corner point of the ego vehicle relative to the closest left corner point of the obstacle vehicle is valid, and the behavior corresponding to the cost value of the left front corner point of the ego vehicle relative to the closest right corner point of the obstacle vehicle is valid.

4. The automatic emergency braking method according to claim 3, characterized in that, screening the valid cost values includes the following steps: if all the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 are valid, determining the magnitudes of ALatRqrdRi1 and ALatRqrdRi2; a valid behavior means that the behavior will not cause a collision between the ego vehicle and the obstacle vehicle; if ALatRqrdRi2<ALatRqrdRi1, selecting ALatRqrdRi1; otherwise, determining the magnitudes of the absolute values of ALatRqrdRi1 and ALatRqrdRi2; if abs(ALatRqrdRi1) < abs(ALatRqrdRi2), selecting ALatRqrdRi1, otherwise selecting ALatRqrdRi2; if only one of the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 is valid, selecting the cost value corresponding to the valid behavior; if none of the behaviors corresponding to ALatRqrdRi1 and ALatRqrdRi2 is valid, assigning a maximum value to ALatRqrdRi1, ALatRqrdRi2 and their corresponding TTC respectively; if all the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 are valid, determining the magnitudes of ALatRqrdLe1 and ALatRqrdLe2; if ALatRqrdLe1<ALatRqrdLe2, selecting ALatRqrdLe1, otherwise determining the magnitudes of the absolute values of ALatRqrdLe1 and ALatRqrdLe2; if abs(ALatRqrdLe2)<abs(ALatRqrdLe1), selecting ALatRqrdLe1, otherwise selecting ALatRqrdLe2; if only one of the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 is valid, selecting the cost value corresponding to the valid behavior; if none of the behaviors corresponding to ALatRqrdLe1 and ALatRqrdLe2 is valid, assigning a maximum value to ALatRqrdLe1, ALatRqrdLe2 and their corresponding TTC respectively.

5. The automatic emergency braking method according to claim 2, characterized in that, calculating the cost value required for the behavior of the ego vehicle relative to the road according to the road information set includes the following steps: The product of the vehicle's lateral velocity and the first coefficient of the road polynomial is compared with the product of the vehicle's longitudinal velocity and the first coefficient of the road polynomial to determine whether the vehicle is parallel to the lane. The road polynomial is a cubic polynomial fitted to the road curve. If parallel, TTC (Traffic Traffic Control) is applied. load If the value is set to 0, and the lines are not parallel, calculate TTC according to the following formula. load value: Among them, TTC load Vself represents the time when the vehicle is tangent to or collides with the road edge, ConstCoeff is the constant coefficient of the road polynomial, Offset is the vehicle bias, and Vself is the time when the vehicle is tangent to or collides with the road edge. Lat Vself is the lateral velocity of the vehicle. Lgt Let represent the longitudinal velocity of the vehicle, and FirstCoeff be the first-order coefficient of the road polynomial. If the lane line is within half the width of your vehicle, TTC load The value is assigned to 0, and the TTC is also assigned to 0. load The corresponding behavior corresponding to the cost value is invalid behavior, and the cost value is assigned to the maximum value. If the lane line is not within the half width of the vehicle, the corresponding cost value is obtained through the constant acceleration model and used as the cost value tangent to the lane line. Calculate the lateral position of the vehicle relative to the lane line at the time of TTE, where TTE is the time when the vehicle reaches the end of the road. If the lane line is to the left of the vehicle, subtract half the vehicle's width from the lateral position of the vehicle relative to the lane line. If the lane line is to the right of the vehicle, add half the vehicle's width to the lateral position of the vehicle relative to the lane line. If the TTE value corresponding to the lateral position of the vehicle relative to the lane line is greater than 0, obtain the corresponding cost value through the constant acceleration model, and use it as the cost value for the vehicle to reach the end of the road. If the TTE value corresponding to the lateral position of the vehicle relative to the lane line is not greater than 0, assign the maximum value to the cost value. Comparison of TTC load Value and TTE value, if TTC load If the TTE value is greater than the TTE value, the action corresponding to the cost of being tangent to the lane line is valid. If the TTE value is greater than 0 and the distance between the vehicle and the lane line is greater than half the width of the vehicle, the action of the vehicle reaching the end of the road is valid. If both actions are valid, then TTC (Traffic Troubleshooting) is not valid. load The action corresponding to the smaller cost value is valid; if both actions are invalid, then the TTC for each action is sent separately. load The value is assigned to 0.

6. The automatic emergency braking method according to claim 2, characterized in that, The screening of value includes the following steps: Determine whether a lateral acceleration of 0 is a usable behavior. A usable behavior is one in which the vehicle does not collide with other vehicles calculated from its positions. For paths where the vehicle does not collide with obstacle vehicles, if a lateral acceleration of 0 is not a usable behavior, then the behaviors of moving left, moving right, and tangent to the road line are determined as follows: If the absolute value of the cost is less than a preset threshold, the behavior corresponding to the cost value is a useless behavior. If it is less than the threshold, it is determined whether the behavior corresponding to the cost value collides with the behavior calculated from other locations. If there is no collision, the cost value is used as the selected cost value. If no value is found among the selected values, then assign a maximum value to the first element in the list of behaviors.

7. The automatic emergency braking method according to any one of claims 1 to 6, characterized in that, Creating a road information set involves the following steps: The curve of the road is fitted with a cubic polynomial; Divide the line segment into at least three segments, and determine whether each segment is within the road boundary using the following formula: in, Boundaries For the width of the road, x Let c0 be the position of the line segment on the road, c1 be the constant term in the cubic polynomial, c2 be the coefficient of the quadratic term in the cubic polynomial, and c3 be the coefficient of the cubic term in the cubic polynomial. Obtain road enabling information. If the road is continuous and the vehicle's acceleration within the road is less than a threshold, then the road is a valid road; otherwise, it is an invalid road. Calculate the time elapsed (TTE) required for the vehicle to reach the end of the road: Among them, V rel a is the negative of the vehicle's speed. rel P is the negative of the vehicle's acceleration, and P is the road length minus the length from the center of the vehicle's rear axle to the front of the vehicle. Stores the road's enabling information, TTE value, constant term and linear term in the cubic polynomial; The road information set is stored separately for left and right. The TTE value of invalid roads is assigned as -2, the TTE value of valid roads but the constant term in the cubic polynomial does not meet the limit value is assigned as -1, and the TTE value of valid roads and the constant term in the cubic polynomial meets the limit value is the calculated value. The roads are sorted in descending order, and the index values ​​of the sorted left and right roads are stored separately. The valid roads and their index values ​​are stored in the road information set, with a maximum of 4 valid roads stored. The index value is the sequence number of the road information in the road information set.

8. The automatic emergency braking method according to any one of claims 1 to 6, characterized in that, Establishing the target set includes the following steps: Apart from the vehicle's position, the remaining positions are filled into the initial target set by InPath targets in order of distance from nearest to farthest. InPath targets are obstacle vehicles whose projection on the y-axis in the vehicle's coordinate system coincides with the vehicle's position; wherein, the y-axis is the direction perpendicular to the vehicle's driving direction. The initial target set obtained by traversal is considered if the elements in the initial target set satisfy the preset validity conditions and the corresponding... If the element meets the preset range, then store it in the target set. The longitudinal relative distance between the vehicle and the target vehicle is divided by the relative speed; the preset validity conditions include: the element is the first preset number of elements in the initial target set, and the element is an obstacle vehicle that overlaps with the vehicle in the lateral direction.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the automatic emergency braking method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the automatic emergency braking method according to any one of claims 1 to 8.

11. A motor vehicle, characterized in that, The motor vehicle is equipped with an AEB system, which performs the automatic emergency braking method according to any one of claims 1 to 8; Or the motor vehicle may have the computer equipment as described in claim 9; Alternatively, the motor vehicle may have a computer-readable storage medium as described in claim 10, wherein the computer program, when executed by a processor, implements the automatic emergency braking method as described in any one of claims 1 to 8.

Images