Driving lateral risk detection method and device and electronic equipment

Abstract

The invention discloses a driving lateral risk detection method and device and electronic equipment. According to the specific scheme, in the running process of a target vehicle, at least one first vehicle associated with the target vehicle is obtained, and a to-be-processed vehicle is determined according to the to-be-compared transverse distance between the first vehicle and the target vehicle in the first direction; determining a to-be-fused risk assessment attribute of the to-be-processed vehicle under each risk assessment dimension according to the driving attribute information of the to-be-processed vehicle under at least one risk assessment dimension and a risk assessment function corresponding to each risk assessment dimension; and determining a target lateral risk attribute corresponding to the to-be-processed vehicle according to the to-be-fused risk assessment attribute corresponding to the at least one risk assessment dimension, so as to control the target vehicle to slow down when the target lateral risk attribute meets a first preset condition. According to the invention, accurate evaluation of the driving lateral risk is realized, and the driving safety of the vehicle is ensured.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a driving lateral risk detection method, device and electronic equipment. Background Art

[0002] During the driving process of an autonomous vehicle, the nearest vehicle in the lane directly in front of the autonomous vehicle is usually used as the control target, and basic driving assistance of the vehicle is achieved through a fixed following distance model and lane centering strategy.

[0003] However, when a vehicle in an adjacent lane of the autonomous vehicle invades the lane where the autonomous vehicle is located, the above method is difficult to detect the potential risk of lateral intrusion of the vehicle in the adjacent lane into the autonomous vehicle, and there may be missed detections, making it difficult to effectively control the autonomous vehicle and unable to ensure the safety of the vehicle's driving. Summary of the Invention

[0004] The present invention provides a driving lateral risk detection method, device and electronic equipment, which realize accurate assessment of driving lateral risk and ensure the safety of vehicle driving.

[0005] According to one aspect of the present invention, a method for detecting lateral risk of a vehicle is provided, which is applied to an autonomous driving vehicle. The method comprises:

[0006] During the movement of the target vehicle, at least one first vehicle associated with the target vehicle is obtained, and a vehicle to be processed is determined based on a lateral distance to be compared between the first vehicle and the target vehicle in a first direction; wherein the at least one first vehicle is a vehicle located in front of the target vehicle, the front is related to the movement direction of the target vehicle, and the first direction is a direction perpendicular to the movement direction;

[0007] Determining the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on driving attribute information of the vehicle to be processed in at least one risk assessment dimension and a risk assessment function corresponding to each risk assessment dimension; wherein the at least one risk assessment dimension includes at least one of a lateral deviation risk dimension, a collision risk dimension, a heading angle intrusion risk dimension, an acceleration risk dimension, and a longitudinal distance risk dimension;

[0008] A target lateral risk attribute corresponding to the vehicle to be processed is determined according to the risk assessment attribute to be fused corresponding to at least one risk assessment dimension, so as to control the target vehicle to decelerate when the target lateral risk attribute meets a first preset condition.

[0009] According to another aspect of the present invention, a driving lateral risk detection device is provided, which is applied to an autonomous driving vehicle, and includes:

[0010] a to-be-processed vehicle determination module, configured to, while the target vehicle is traveling, obtain at least one first vehicle associated with the target vehicle and determine the to-be-processed vehicle based on a lateral distance to be compared between the first vehicle and the target vehicle in a first direction; wherein the at least one first vehicle is a vehicle located in front of the target vehicle, the front being related to the traveling direction of the target vehicle, and the first direction being a direction perpendicular to the traveling direction;

[0011] a risk assessment module, configured to determine, based on driving attribute information of the vehicle to be processed in at least one risk assessment dimension and a risk assessment function corresponding to each risk assessment dimension, a risk assessment attribute to be fused for the vehicle to be processed in each risk assessment dimension; wherein the at least one risk assessment dimension includes at least one of a lateral deviation risk dimension, a collision risk dimension, a heading angle intrusion risk dimension, an acceleration risk dimension, and a longitudinal distance risk dimension;

[0012] A vehicle control module is used to determine the target lateral risk attribute corresponding to the vehicle to be processed based on the risk assessment attribute to be fused corresponding to at least one risk assessment dimension, so as to control the target vehicle to decelerate when the target lateral risk attribute meets the first preset condition.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the driving lateral risk detection method of any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the driving lateral risk detection method of any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the driving lateral risk detection method according to any embodiment of the present invention.

[0019] The technical solution of an embodiment of the present invention obtains at least one first vehicle associated with a target vehicle while the target vehicle is traveling, and determines a target vehicle based on a lateral distance to be compared between the first vehicle and the target vehicle in a first direction. Based on this, at least one target vehicle that may pose a lateral intrusion risk to the target vehicle is identified. Based on the driving attribute information of the target vehicle in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension, the target vehicle's risk assessment attributes to be fused in each risk assessment dimension are determined. The target lateral risk attribute corresponding to the target vehicle in the at least one risk assessment dimension is then determined using the fused risk assessment attributes corresponding to the target vehicle in the at least one risk assessment dimension. This enables an accurate assessment of the lateral intrusion risk of the target vehicle. When the target lateral risk attribute is determined to meet a first preset condition, the target vehicle is controlled to decelerate to avoid a collision, thereby ensuring the target vehicle's driving safety. This present invention addresses the prior art issue of difficulty in detecting the potential risk of lateral intrusion posed by vehicles in adjacent lanes. By controlling the target vehicle to decelerate based on the determined target lateral risk attribute of the target vehicle, effective control of the target vehicle is achieved, ensuring driving safety.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flow chart of a driving lateral risk detection method provided by an embodiment of the present invention;

[0023] Figure 2 is an example diagram of a target vehicle driving scene provided by an embodiment of the present invention;

[0024] Figure 3 This is a flow chart of a driving lateral risk detection method provided by an embodiment of the present invention;

[0025] Figure 4 is an example diagram of a hyperbolic tangent function provided by an embodiment of the present invention;

[0026] Figure 5This is a schematic structural diagram of a driving lateral risk detection device provided by an embodiment of the present invention;

[0027] Figure 6 It is a structural diagram of an electronic device for implementing the driving lateral risk detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] Figure 1 This is a flow chart of a driving lateral risk detection method provided by the first embodiment of the present invention. This embodiment can be applied to the situation where the lateral intrusion risk assessment of other vehicles is performed during the driving of the target vehicle to ensure driving safety. The method can be executed by a driving lateral risk detection device, which can be implemented in the form of hardware and / or software. The driving lateral risk detection device can be configured in electronic devices such as mobile phones, computers or servers. Figure 1 As shown, the method includes:

[0032] S110. During the driving process of the target vehicle, obtain at least one first vehicle associated with the target vehicle, and determine a vehicle to be processed based on a lateral distance to be compared between the first vehicle and the target vehicle in a first direction.

[0033] Among them, at least one first vehicle is a vehicle located in front of the target vehicle, the front is related to the driving direction of the target vehicle, and the first direction is a direction perpendicular to the driving direction. The target vehicle can be the currently traveling vehicle, that is, the vehicle that currently needs to detect whether other vehicles pose a risk of lateral intrusion to it. The first vehicle can be a vehicle located in front of the target vehicle, for example, the first vehicle can be a vehicle located in front of the left of the target vehicle. It can also be a vehicle located in front of the right of the target vehicle, such as Figure 2 As shown, the target vehicle can be Figure 2 The vehicles represented by the black rectangles in the figure, correspondingly, the first vehicles may be vehicles numbered 7, 1, 2, 3, or 9. The lateral distance to be compared may be used to represent the lateral distance between the target vehicle and the first vehicle in a first direction. The vehicle to be processed may be a vehicle that, based on the lateral distance to be processed, may pose a lateral intrusion risk to the target vehicle.

[0034] Specifically, while a target vehicle is traveling using an adaptive cruise control system (ACC) and a lane change assist system (LCA), at least one first vehicle ahead of the target vehicle can be detected through sensing input signals. Based on the lateral distance in a first direction to be compared between each first vehicle and the target vehicle, at least one target vehicle that may laterally intrude into the target vehicle's lane is determined. Because the lateral risk assessment method for each target vehicle is similar, the following description uses a single target vehicle as the basis for this analysis.

[0035] For example, see Figure 2 ,When the target vehicle is driving based on ACC and LCA, the information of the 10 vehicles around the target vehicle can be determined by sensing the input signal and then filtering it through fusion, that is, Figure 2 For ACC and LCA driving scenarios, the two side vehicles in front of the target vehicle may pose a lateral intrusion risk to the target vehicle. In this case, vehicles 1 and 3 are used as pending vehicles to obtain the driving attribute information corresponding to the pending vehicles, facilitating subsequent lateral intrusion risk assessment.

[0036] In an embodiment of the present invention, a method for determining a vehicle to be processed based on the lateral distance to be compared between the first vehicle and the target vehicle in the first direction may be: determining a lateral distance range based on the lane width of the lane to which the target vehicle belongs and a preset lateral distance coefficient; and determining the first vehicle as the vehicle to be processed when it is detected that the lateral distance to be compared between the first vehicle and the target vehicle in the first direction falls within the lateral distance range.

[0037] The preset lateral distance coefficient may be a pre-set proportional coefficient. Optionally, the preset lateral distance coefficient may be 20% and 80%. The lateral distance range may be a distance range determined by multiplying the lane width by the preset lateral distance coefficient. Optionally, the lateral distance range may be from 20% of the lane width to 80% of the lane width.

[0038] Specifically, a lateral distance range is determined based on the lane width of the target vehicle's lane and a preset lateral distance coefficient. If the lateral distance between the target vehicle and a first vehicle to be compared falls within the lateral distance range, it indicates that the first vehicle may pose a lateral intrusion risk to the target vehicle. The first vehicle, whose lateral distance to be compared falls within the lateral distance range, is then selected as a target vehicle to be processed. Based on this, at least one target vehicle to be compared can be determined.

[0039] S120: Determine the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension.

[0040] The at least one risk assessment dimension includes at least one of a lateral offset risk dimension, a collision risk dimension, a heading angle intrusion risk dimension, an acceleration risk dimension, and a longitudinal distance risk dimension. The lateral offset risk dimension can be used to assess the lateral intrusion risk of the vehicle to be processed based on the degree of lateral offset of the vehicle to be processed. For example, Figure 2 The lateral offset risk caused by the pending vehicle numbered 1 and / or the pending vehicle numbered 3 to the target vehicle. The collision risk dimension is used to assess the lateral intrusion risk of the pending vehicle based on the collision time between the pending vehicle and the target vehicle. The heading angle intrusion risk dimension is used to assess the lateral intrusion risk of the pending vehicle based on the degree of deviation of the heading angle of the pending vehicle. The acceleration risk dimension is used to assess the lateral intrusion risk of the pending vehicle based on the changes in the lateral and longitudinal acceleration of the pending vehicle. The longitudinal distance risk dimension is used to assess the lateral intrusion risk of the pending vehicle based on the changes in the longitudinal distance between the pending vehicle and the target vehicle.

[0041] The driving attribute information may include the lateral acceleration, longitudinal acceleration, heading angle of the vehicle to be processed, the lateral distance, longitudinal distance, collision time and longitudinal relative speed between the vehicle to be processed and the target vehicle. It should be noted that the lateral direction mentioned in the embodiment of the present invention is the direction perpendicular to the driving direction of the target vehicle, that is, the first direction, and the longitudinal direction is the driving direction of the target vehicle, that is, the second direction. The risk assessment function can be a function for performing lateral intrusion risk assessment on the vehicle to be processed based on the driving attribute information under the corresponding risk assessment dimension. The risk assessment attributes to be fused can be used to characterize the lateral intrusion risk caused by the vehicle to be processed to the target vehicle under the corresponding risk assessment dimension.

[0042] Specifically, based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension among the lateral offset risk dimension, collision risk dimension, heading angle intrusion risk dimension, acceleration risk dimension and longitudinal distance risk dimension and the risk assessment function corresponding to the corresponding risk assessment dimension, the risk assessment attributes to be fused of the vehicle to be processed in each risk assessment dimension are determined, so as to determine the lateral intrusion risk of the vehicle to be processed to the target vehicle as a whole through the risk assessment attributes to be fused in each risk assessment dimension.

[0043] S130. Determine a target lateral risk attribute corresponding to the vehicle to be processed based on the risk assessment attribute to be fused corresponding to at least one risk assessment dimension, so as to control the target vehicle to decelerate when the target lateral risk attribute meets a first preset condition.

[0044] The target lateral risk attribute may be determined by weighted summation based on the risk assessment attributes to be fused under at least one risk assessment dimension and the corresponding weight coefficient. The target lateral risk attribute may be used to characterize the degree of lateral intrusion risk posed by the current vehicle to be processed to the target vehicle. The first preset condition may be a pre-set condition that the target lateral risk attribute is greater than a preset lateral risk attribute threshold. That is, when the target lateral risk attribute is greater than the preset lateral risk attribute threshold, it is determined that the vehicle to be processed will cause lateral intrusion risk to the target vehicle. The preset lateral risk attribute threshold may be a pre-set standard value of the target lateral risk attribute.

[0045] Specifically, a weighted summation process is performed on the risk assessment attributes to be fused corresponding to at least one risk assessment dimension and the preset weight coefficient of the corresponding risk assessment dimension to determine the target lateral risk attribute corresponding to the vehicle to be processed, so that when the target lateral risk attribute corresponding to the vehicle to be processed meets the first preset condition, that is, exceeds the preset lateral risk attribute threshold, the target vehicle is controlled to decelerate.

[0046] It should be noted that to ensure the safety of the target vehicle, the target lateral risk attribute of at least one of the pending vehicles corresponding to the target vehicle can be simultaneously determined during the target vehicle's driving process. If the target lateral risk attribute corresponding to at least one pending vehicle satisfies a first preset condition, the target vehicle is controlled to decelerate to avoid the pending vehicle, thereby ensuring the target vehicle's driving safety.

[0047] The technical solution of this embodiment obtains at least one first vehicle associated with the target vehicle during its travel, and determines a target vehicle based on a to-be-compared lateral distance in a first direction between the first vehicle and the target vehicle. Based on this, at least one target vehicle that may pose a lateral intrusion risk to the target vehicle is identified. Based on the driving attribute information of the target vehicle in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension, the target vehicle's risk assessment attributes to be fused in each risk assessment dimension are determined. The target lateral risk attribute corresponding to the target vehicle in the at least one risk assessment dimension is then determined using the fused risk assessment attributes corresponding to the target vehicle in the at least one risk assessment dimension. This enables an accurate assessment of the lateral intrusion risk of the target vehicle. When the target lateral risk attribute is determined to meet a first preset condition, the target vehicle is controlled to decelerate to avoid a collision, thereby ensuring the target vehicle's driving safety. This present invention addresses the prior art issue of difficulty in detecting the potential risk of lateral intrusion posed by vehicles in adjacent lanes. By controlling the target vehicle to decelerate based on the determined target lateral risk attribute of the target vehicle, effective control of the target vehicle is achieved, ensuring driving safety.

[0048] Example 2

[0049] Figure 3 This is a flow chart of a method for detecting lateral risk of a vehicle provided by the second embodiment of the present invention. This embodiment is a preferred embodiment of the above embodiment. For its specific implementation, please refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 3 As shown, the method includes:

[0050] S210. During the driving process of the target vehicle, obtain at least one first vehicle associated with the target vehicle, and determine a vehicle to be processed based on a lateral distance to be compared between the first vehicle and the target vehicle in a first direction.

[0051] Among them, at least one first vehicle is a vehicle located in front of the target vehicle, the front is related to the driving direction of the target vehicle, and the first direction is a direction perpendicular to the driving direction.

[0052] S220: Determine the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension.

[0053] The at least one risk assessment dimension includes at least one of a lateral deviation risk dimension, a collision risk dimension, a heading angle intrusion risk dimension, an acceleration risk dimension, and a longitudinal distance risk dimension.

[0054] Optionally, the driving attribute information under the lateral offset risk dimension is a lateral distance to be processed, which is used to represent the lateral distance between the vehicle to be processed and the target vehicle in a first direction. In an embodiment of the present invention, the method for determining the risk assessment attributes to be fused for the vehicle to be processed under the lateral offset risk dimension may be: for the lateral offset risk dimension, the risk assessment attributes to be fused for the vehicle to be processed corresponding to the lateral offset risk dimension are determined based on the lateral distance to be processed, the lane width of the target vehicle's lane, a preset risk sensitivity coefficient, and a risk assessment function corresponding to the lateral offset risk dimension.

[0055] The preset risk sensitivity coefficient may be a pre-set coefficient value for controlling the steepness of risk change. The risk assessment function corresponding to the lateral offset risk dimension may be a function for determining the risk assessment attribute to be fused under the lateral offset risk dimension.

[0056] Specifically, in the lateral deviation risk dimension, the driving attribute information is the lateral distance of the target vehicle. Substituting the lateral distance, the lane width of the target vehicle's lane, and the preset risk sensitivity coefficient into the risk assessment function corresponding to the lateral deviation risk dimension, the corresponding risk assessment attributes for the target vehicle in the lateral deviation risk dimension are obtained.

[0057] Optionally, the risk assessment function corresponding to the lateral offset risk dimension may be a Sigmoid function. Optionally, the Sigmoid function may be expressed as:

[0058]

[0059] Where LR represents the risk assessment attribute to be fused under the lateral offset risk dimension, and x represents the input value, which can be determined as follows: Input value = Preset risk sensitivity coefficient * (Absolute value of the lateral distance to be processed - 1 / 2 lane width - Preset constant). The preset constant is a constant analogous to half the width of the vehicle to be processed.

[0060] For example, if the preset constant is 0.9, the risk assessment function corresponding to the lateral deviation risk dimension can be expressed as:

[0061] LR=1 / 1+exp-k*(abs(Y)-width / 2-0.9

[0062] Wherein, LR represents the risk assessment attribute to be fused under the lateral offset risk dimension, k represents the preset risk sensitivity coefficient, width represents the lane width, Y represents the lateral distance to be processed, and 0.9 represents the preset constant.

[0063] It should be noted that in actual applications, the lateral distance to be processed can be positive or negative. If the target vehicle's travel direction is used as the standard, the lateral distance to be processed between the target vehicle and the target vehicle located to the left of the target vehicle's travel direction is positive. Correspondingly, the lateral distance to be processed between the target vehicle and the target vehicle located to the right of the target vehicle's travel direction is negative. Therefore, if the target vehicle to be processed is located to the left of the target vehicle and the preset constant is 0.7, the risk assessment function corresponding to the lateral offset risk dimension of the target vehicle to be processed can be expressed as:

[0064] LR=1 / (1+exp(-k*(Y-width / 2-0.7)))

[0065] LR represents the risk assessment attribute to be fused under the lateral offset risk dimension, k represents the preset risk sensitivity coefficient, width represents the lane width, Y represents the lateral distance to be processed between the target vehicle and the target vehicle located in front of the target vehicle on the left, and 0.7 represents the preset constant.

[0066] If the vehicle to be processed is located in front of the right side of the target vehicle, and the preset constant is 0.7, the risk assessment function corresponding to the lateral deviation risk dimension of the vehicle to be processed can be expressed as:

[0067] LR=1 / (1+exp(-k*(Y+width / 2+0.7)))

[0068] LR represents the risk assessment attribute to be fused under the lateral offset risk dimension of the vehicle to be processed, k represents the preset risk sensitivity coefficient, width represents the lane width, Y represents the lateral distance to be processed between the vehicle to be processed located in front of the right side of the target vehicle and the target vehicle, and 0.7 represents the preset constant.

[0069] It should be noted that the preset constant is subtracted because the lateral distance to be processed is the lateral distance between the target vehicle and the center point of the rear axle of the vehicle to be processed. Since the preset coefficient of half the vehicle width of the vehicle to be processed is subtracted in the Sigmoid function, the risk assessment attribute to be fused under the lateral offset risk dimension can quickly become greater than the preset value (e.g., 0.5) in the process of the vehicle to be processed approaching the target vehicle, thereby improving the detection accuracy of the lateral intrusion risk.

[0070] Through the risk assessment function under the lateral offset risk dimension, the larger the lateral distance to be processed, the smaller the corresponding risk assessment attribute to be fused. Correspondingly, the smaller the lateral distance to be processed, the larger the corresponding risk assessment attribute to be fused.

[0071] Optionally, the driving attribute information under the collision risk dimension is a pending collision time, which is used to represent the duration required for a collision between the target vehicle and the pending vehicle at the current moment. In an embodiment of the present invention, the method for determining the pending risk assessment attributes of the pending vehicle under the collision risk dimension may be: for the collision risk dimension, if it is determined that the pending collision time is not a preset value, the pending risk assessment attributes of the pending vehicle under the collision risk dimension are determined based on the ratio of a first preset coefficient to the pending collision time.

[0072] The preset value can be used to indicate that the collision time between the pending vehicle and the target vehicle is unavailable. For example, if the pending collision time is set to 99, it means that there is no collision risk or sufficient safety between the pending vehicle and the target vehicle. If the pending collision time is set to -1, it means that the current pending collision time is invalid.

[0073] Specifically, for the collision risk dimension, when it is determined that the time of collision to be processed is not a preset value, the ratio of the first preset coefficient to the time of collision to be processed is used as the risk assessment attribute to be fused for the vehicle to be processed under the collision risk dimension.

[0074] Optionally, the corresponding risk assessment function under the collision risk dimension can be expressed as:

[0075] ttc_term=w2 / ttc

[0076] Among them, ttc_term represents the risk assessment attribute to be fused under the collision risk dimension of the vehicle to be processed, w2 represents the first preset coefficient, and ttc represents the collision time to be processed.

[0077] Optionally, the driving attribute information under the heading angle intrusion risk dimension includes: the current heading angle corresponding to the vehicle to be processed at the current collection moment and the historical heading angle corresponding to at least one historical collection moment before the current collection moment. In an embodiment of the present invention, a method for determining the risk assessment attributes to be fused under the heading angle intrusion risk dimension of the vehicle to be processed may be: for the heading angle intrusion risk dimension, based on the current heading angle and at least one historical heading angle, and a second preset coefficient corresponding to each heading angle, determine the risk assessment attributes to be fused under the heading angle intrusion risk dimension of the vehicle to be processed.

[0078] The historical heading angle may be a heading angle collected at at least one historical collection time before the current collection time. The heading angle of the vehicle to be processed is used to represent the driving direction of the vehicle to be processed. The second preset coefficient may be a pre-set coefficient value.

[0079] Specifically, the current heading angle of the vehicle to be processed at the current acquisition moment is multiplied by the second preset coefficient corresponding to the current heading angle to determine the first result. The historical heading angles of the vehicle to be processed at at least one historical acquisition moment are multiplied by the second preset coefficient corresponding to each historical heading angle to determine the second result. The first result and the second result are summed to determine the third result. The third result is substituted into the hyperbolic tangent function to determine the risk assessment attribute to be fused of the vehicle to be processed under the heading angle intrusion risk dimension. The hyperbolic tangent function can be as follows: Figure 4 shown.

[0080] Optionally, the risk assessment function corresponding to the heading angle intrusion risk dimension can be expressed as:

[0081] RF_theta=tanh(0.5*θ+0.3*θ k1 +0.2*θ k2 )

[0082] Among them, RF_theta represents the risk assessment attribute to be fused under the heading angle intrusion risk dimension of the vehicle to be processed, θ represents the current heading angle, 0.5 represents the second preset coefficient corresponding to the current heading angle, and θ k1 Indicates the historical heading angle corresponding to the previous historical collection time of the current collection time, 0.3 indicates the second preset coefficient corresponding to the historical heading angle, θ k2 It represents the historical heading angle corresponding to the previous historical collection moment, and 0.2 represents the second preset coefficient corresponding to the historical heading angle.

[0083] It should be noted that in actual application, the heading angle has positive and negative values, which is used to characterize whether the direction of the vehicle to be processed is to the left or to the right based on the current direction of travel. Normally, the heading angle corresponding to driving to the left is positive, and the heading angle corresponding to driving to the right is negative. Therefore, if the vehicle to be processed located in front of the left of the target vehicle is detected to be driving to the right, the heading angle is negative. In order to accurately calculate the risk assessment attribute to be fused corresponding to the heading angle intrusion risk dimension of the vehicle to be processed, the absolute value of the negative heading angle can be taken, or a coefficient of -1 can be added.

[0084] Optionally, the driving attribute information under the acceleration risk dimension includes: the lateral acceleration to be processed and the longitudinal acceleration to be processed of the vehicle to be processed, the longitudinal acceleration to be processed is used to characterize the longitudinal acceleration of the vehicle to be processed in the second direction, and the second direction is consistent with the driving direction of the vehicle to be processed. In an embodiment of the present invention, the method of determining the risk assessment attribute to be fused of the vehicle to be processed under the acceleration risk dimension may be: for the acceleration risk dimension, the lateral acceleration to be processed is normalized according to a preset lateral acceleration threshold, and the longitudinal acceleration to be processed is normalized according to a preset longitudinal acceleration threshold to obtain a normalized lateral acceleration and a normalized longitudinal acceleration; determining a first multiplication result between the normalized lateral acceleration and a third preset coefficient, and determining a second multiplication result between the normalized longitudinal acceleration and a fourth preset coefficient; and determining the risk assessment attribute to be fused of the vehicle to be processed under the acceleration risk dimension based on the difference between the first multiplication result and the second multiplication result.

[0085] The lateral acceleration to be processed is used to characterize the lateral acceleration of the vehicle to be processed in a first direction. The first direction is a direction perpendicular to the driving direction of the vehicle to be processed. The preset lateral acceleration threshold may be a preset standard value of the lateral acceleration to be processed. The preset longitudinal acceleration threshold may be a preset standard value of the longitudinal acceleration to be processed. The normalized lateral acceleration may be the normalized lateral acceleration to be processed. The normalized longitudinal acceleration may be the normalized longitudinal acceleration to be processed. The third preset coefficient may be a preset coefficient value corresponding to the normalized lateral acceleration. The fourth preset coefficient may be a preset coefficient value corresponding to the normalized longitudinal acceleration. The first multiplication result may be a result determined by multiplying the normalized lateral acceleration by the third preset coefficient. The second multiplication result may be a result determined by multiplying the normalized longitudinal acceleration by the fourth preset coefficient.

[0086] Specifically, the lateral acceleration to be processed is normalized according to a preset lateral acceleration threshold to determine the normalized lateral acceleration. Optionally, the lateral acceleration to be processed can be normalized using the following function.

[0087]

[0088] Among them, AY norm represents the normalized lateral acceleration, AY target Indicates the lateral acceleration to be processed, AY max Indicates the preset lateral acceleration threshold.

[0089] The longitudinal acceleration to be processed is normalized according to a preset longitudinal acceleration threshold to determine a normalized longitudinal acceleration. Optionally, the lateral acceleration to be processed can be normalized using the following function.

[0090]

[0091] Among them, AX norm represents the normalized longitudinal acceleration, AX target Indicates the longitudinal acceleration to be processed, AX max Represents the preset longitudinal acceleration threshold. For example, the preset longitudinal acceleration threshold could be 5, and the preset lateral acceleration threshold could be 2. Through this process, both the normalized lateral acceleration and the normalized longitudinal acceleration can be limited to the range [-1, 1]. It should be noted that the negative sign for the longitudinal acceleration is to account for deceleration scenarios. If the vehicle ahead is accelerating, the risk value is lower.

[0092] The normalized lateral acceleration is multiplied by the third preset coefficient to obtain a first multiplication result. The normalized longitudinal acceleration is multiplied by the fourth preset coefficient to obtain a second multiplication result. The difference between the first and second multiplication results is used as the risk assessment attribute to be fused for the vehicle under consideration under the acceleration risk dimension. For example, the third preset coefficient may be 0.6, and the fourth preset coefficient may be 0.4. The following function can then be used to determine the risk assessment attribute to be fused for the vehicle under consideration under the acceleration risk dimension.

[0093] a combined =0.6*AY norm -0.4*AX norm

[0094] Among them, a combined Indicates the risk assessment attributes of the vehicle to be processed under the acceleration risk dimension to be integrated, AX norm represents the normalized longitudinal acceleration, AY norm represents the normalized lateral acceleration.

[0095] It should be noted that the embodiment of the present invention is aimed at the assessment of lateral intrusion risk, and the third preset coefficient is set to 0.6. At the same time, if it is a decelerating vehicle, for example, the vehicle located in front of the left of the target vehicle slows down, it is necessary to consider whether there is a possibility of changing lanes. The target vehicle can be controlled to decelerate or perform an operation similar to releasing the accelerator based on the target lateral risk attribute determined subsequently.

[0096] Optionally, the driving attribute information under the longitudinal distance risk dimension includes: a longitudinal relative speed to be processed and a longitudinal distance to be processed between the target vehicle and the vehicle to be processed, the longitudinal relative speed to be processed being used to represent the relative speed of the target vehicle and the vehicle to be processed in a first direction. In an embodiment of the present invention, a method for determining the risk assessment attribute to be fused for the vehicle to be processed under the longitudinal distance risk dimension may include: determining a first distance for the longitudinal distance risk dimension based on the product of the target vehicle's speed and a preset reaction time and a preset distance threshold; wherein the first distance is the maximum value between the product and the preset distance threshold; if the longitudinal distance to be processed does not exceed the first distance, normalizing the longitudinal distance to be processed based on the first distance to obtain a normalized distance; determining a function based on the longitudinal relative speed to be processed and a preset dynamic attenuation coefficient to determine a dynamic attenuation coefficient; and determining the risk assessment attribute to be fused for the vehicle to be processed based on the normalized distance and the dynamic attenuation coefficient; and determining the risk assessment attribute to be fused for the vehicle to be processed under the longitudinal distance risk dimension based on the risk assessment attribute to be processed, the first distance, the longitudinal distance to be processed, and the longitudinal distance risk determination function when the first distance and the longitudinal distance to be processed meet a second preset condition.

[0097] The longitudinal distance to be processed represents the longitudinal distance in the first direction between the target vehicle and the vehicle to be processed. The preset reaction time may be a pre-set standard value for the driver's reaction time. For example, the preset reaction time may be 2.5. The preset distance threshold may be a pre-set standard value for the longitudinal distance between the vehicle to be processed and the target vehicle. For example, the preset distance threshold may be 50 meters.

[0098] The first distance can be used to represent the dynamic longitudinal distance between the vehicle to be processed and the target vehicle. The normalized distance can be the normalized longitudinal distance to be processed. The preset dynamic attenuation coefficient determination function can be a pre-set function for determining the dynamic attenuation coefficient. Optionally, the greater the longitudinal relative speed to be processed, the steeper the attenuation represented by the dynamic attenuation coefficient. The risk assessment attribute to be processed can be used to represent the basic risk assessment attribute of the vehicle to be processed under the longitudinal distance risk dimension. If the first distance and the longitudinal distance to be processed meet a second preset condition, the risk assessment attribute to be fused can be determined based on the risk assessment attribute to be processed. If the first distance and the longitudinal distance to be processed do not meet the second preset condition, the risk assessment attribute to be fused can be determined as the risk assessment attribute to be fused. The second preset condition can be a pre-set condition that the first distance and the longitudinal distance to be processed must meet. Optionally, if the longitudinal distance to be processed is less than a preset multiple of the first distance, the first distance and the longitudinal distance to be processed are determined to meet the second preset condition. For example, the preset multiple can be 0.3. The longitudinal distance risk determination function can be a function for determining the risk assessment attribute to be fused for the vehicle to be processed under the longitudinal distance risk dimension.

[0099] Specifically, for the longitudinal distance risk dimension, determine the multiplication result between the speed of the target vehicle and the preset reaction time. And take the maximum value between the multiplication result and the preset distance threshold as the first distance. When the longitudinal distance to be processed between the vehicle to be processed and the target vehicle does not exceed the first distance, the longitudinal distance to be processed is normalized to determine the normalized distance. Optionally, the normalization method can be: taking the ratio of the longitudinal distance to be processed to the first distance as the normalized distance. Substitute the longitudinal relative speed to be processed into the preset dynamic attenuation coefficient determination function to obtain the dynamic attenuation coefficient. Optionally, the preset dynamic attenuation coefficient determination function can be expressed as:

[0100] alpha=0.5+0.5*tanh(-V rel / 5)

[0101] Among them, alpha represents the dynamic attenuation coefficient, V rel Indicates the longitudinal relative velocity to be processed.

[0102] Based on the normalized distance and the dynamic attenuation coefficient, the risk assessment attribute corresponding to the vehicle to be processed is determined. Optionally, the risk assessment attribute to be processed can be determined using the following function.

[0103] X risk =exp(-alpha*10*X norm )

[0104] Among them, X risk represents the risk assessment attributes to be processed, X norm represents the normalized distance.

[0105] When the longitudinal distance to be processed is less than the first distance of the preset multiple, the risk assessment attribute to be fused of the vehicle to be processed under the longitudinal distance risk dimension is determined according to the risk assessment attribute to be processed, the first distance, the longitudinal distance to be processed and the longitudinal distance risk determination function. clamped <(0.3*dynamic threshold ), the risk assessment function to be fused can be determined by the following longitudinal distance risk determination function.

[0106] X risk '=X risk +0.5*(1-X clamped / (0.3*dynamic threshold ))

[0107] Among them, X risk ' represents the risk assessment attribute to be fused under the vertical distance risk dimension, X riskrepresents the risk assessment attributes to be processed, X clamped Indicates the vertical distance to be processed, dynamic threshold Indicates the first distance, and 0.3 indicates the preset multiple.

[0108] It should be noted that in order to ensure the uniformity of data for subsequent processing, the risk assessment attributes to be fused of the vehicle to be processed under each risk assessment dimension can be normalized to determine the target lateral risk attribute through the normalized risk assessment attributes to be fused.

[0109] S230. Determine the target lateral risk attribute corresponding to the vehicle to be processed based on the risk assessment attribute to be fused corresponding to at least one risk assessment dimension, so that when the target lateral risk attribute of the vehicle to be processed exceeds a preset lateral risk attribute threshold, generate warning prompt information based on the target lateral risk attribute, so as to control the target vehicle to decelerate based on the warning prompt information.

[0110] Among them, the warning prompt information can be displayed on the instrument panel and / or central control display screen of the target vehicle or in the form of an audio broadcast to remind the corresponding vehicle to be processed that there is a risk of lateral intrusion into the target vehicle.

[0111] Specifically, after determining the target lateral risk attribute corresponding to the vehicle to be processed based on the risk assessment attribute to be fused corresponding to at least one risk assessment dimension, if it is detected that the target lateral risk attribute of the vehicle to be processed exceeds the preset lateral risk attribute threshold, a warning prompt information can be generated based on the target lateral risk attribute, and the warning prompt information can be displayed on the instrument panel and / or central control display screen of the target vehicle or in the form of an audio broadcast to warn the driver. At the same time, the warning prompt information can also be sent to the control system of the target vehicle to control the target vehicle to slow down through the operation of the control system or the driver.

[0112] Optionally, the target lateral risk attribute can be determined by the following function.

[0113] RiskScore=w1*LR+ttc_term+w3*RF_theta+w4*a combined +w5*X risk '

[0114] Among them, RiskScore represents the target lateral risk attribute corresponding to the vehicle to be processed. LR represents the risk assessment attribute to be fused under the lateral offset risk dimension of the vehicle to be processed, ttc_term represents the risk assessment attribute to be fused under the collision risk dimension of the vehicle to be processed, RF_theta represents the risk assessment attribute to be fused under the heading angle intrusion risk dimension of the vehicle to be processed, and a combinedrepresents the risk assessment attributes to be fused under the acceleration risk dimension of the vehicle to be processed, X risk ' represents the risk assessment attribute to be fused, X risk ' represents the risk assessment attributes to be fused under the longitudinal distance risk dimension of the vehicle to be processed. w1, w3, w4, w5 represent the corresponding weight coefficients. For example, w1 = 0.3, w3 = 0.2, w4 = 0.1, w5 = 0.2. Since the first preset coefficient w2 is set when determining the risk assessment attributes to be fused under the collision risk dimension of the vehicle to be processed, the weight coefficient corresponding to the risk assessment attributes to be fused under the collision risk dimension is not set here. It should be noted that when w1 = 0.3, w3 = 0.2, w4 = 0.1, w5 = 0.2, w2 = 0.2.

[0115] The technical solution of this embodiment is to obtain at least one first vehicle associated with the target vehicle during the driving process of the target vehicle, and determine the vehicle to be processed based on the lateral distance to be compared between the first vehicle and the target vehicle in the first direction. Based on this, at least one vehicle to be processed that may cause lateral intrusion risk to the target vehicle can be determined. Based on the driving attribute information of the vehicle to be processed under at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension, the risk assessment attribute to be fused of the vehicle to be processed under each risk assessment dimension is determined, so that the target lateral risk attribute corresponding to the vehicle to be processed is determined through the risk assessment attribute to be fused corresponding to the vehicle to be processed in at least one risk assessment dimension. Based on this, an accurate assessment of the lateral intrusion risk of the vehicle to be processed is achieved, so that when the target lateral risk attribute of the vehicle to be processed exceeds the preset lateral risk attribute threshold, a warning prompt information is generated based on the target lateral risk attribute, so that the target vehicle is controlled to slow down based on the warning prompt information to avoid vehicle collision, thereby ensuring the driving safety of the target vehicle. The present invention solves the problem in the prior art that it is difficult to detect the potential risk of lateral intrusion into a target vehicle caused by vehicles in adjacent lanes. By controlling the target vehicle to slow down according to the target lateral risk attributes of the vehicle to be processed, effective control of the target vehicle is achieved, ensuring the comfort and safety of the vehicle's driving.

[0116] Example 3

[0117] Figure 5 This is a schematic diagram of the structure of a driving lateral risk detection device provided by the third embodiment of the present invention. Figure 5 As shown, the device includes: a to-be-processed vehicle determination module 310 , a risk assessment module 320 and a vehicle control module 330 .

[0118] The vehicle determination module 310 to be processed is used to obtain at least one first vehicle associated with the target vehicle during the driving process of the target vehicle, and determine the vehicle to be processed based on the lateral distance to be compared between the first vehicle and the target vehicle in the first direction; wherein, the at least one first vehicle is a vehicle located in front of the target vehicle, the front is related to the driving direction of the target vehicle, and the first direction is a direction perpendicular to the driving direction; the risk assessment module 320 is used to determine the risk assessment attributes to be fused of the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension; wherein, the at least one risk assessment dimension includes: at least one of: lateral offset risk dimension, collision risk dimension, heading angle intrusion risk dimension, acceleration risk dimension and longitudinal distance risk dimension; the vehicle control module 330 is used to determine the target lateral risk attribute corresponding to the vehicle to be processed based on the risk assessment attribute to be fused corresponding to the at least one risk assessment dimension, so as to control the target vehicle to decelerate when the target lateral risk attribute meets the first preset condition

[0119] The technical solution of this embodiment obtains at least one first vehicle associated with the target vehicle during its travel, and determines a target vehicle based on a to-be-compared lateral distance in a first direction between the first vehicle and the target vehicle. Based on this, at least one target vehicle that may pose a lateral intrusion risk to the target vehicle is identified. Based on the driving attribute information of the target vehicle in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension, the target vehicle's risk assessment attributes to be fused in each risk assessment dimension are determined. The target lateral risk attribute corresponding to the target vehicle in the at least one risk assessment dimension is then determined using the fused risk assessment attributes corresponding to the target vehicle in the at least one risk assessment dimension. This enables an accurate assessment of the lateral intrusion risk of the target vehicle. When the target lateral risk attribute is determined to meet a first preset condition, the target vehicle is controlled to decelerate to avoid a collision, thereby ensuring the target vehicle's driving safety. This present invention addresses the prior art issue of difficulty in detecting the potential risk of lateral intrusion posed by vehicles in adjacent lanes. By controlling the target vehicle to decelerate based on the determined target lateral risk attribute of the target vehicle, effective control of the target vehicle is achieved, ensuring driving safety.

[0120] Based on the above embodiment, optionally, a module for determining a vehicle to be processed is used to determine a lateral distance range based on the lane width of the lane to which the target vehicle belongs and a preset lateral distance coefficient; when it is detected that the lateral distance to be compared between the first vehicle and the target vehicle in the first direction falls within the lateral distance range, the first vehicle is determined as the vehicle to be processed.

[0121] Optionally, the driving attribute information under the lateral offset risk dimension is the lateral distance to be processed, which is used to characterize the lateral distance between the vehicle to be processed and the target vehicle in the first direction. The risk assessment module includes: a first risk assessment attribute determination unit to be fused, which is used to determine the risk assessment attribute to be fused corresponding to the lateral offset risk dimension of the vehicle to be processed according to the lateral distance to be processed, the lane width of the lane to which the target vehicle belongs, the preset risk sensitivity coefficient and the risk assessment function corresponding to the lateral offset risk dimension.

[0122] Optionally, the driving attribute information under the collision risk dimension is the pending collision time, which is used to characterize the time required for the target vehicle to collide with the pending vehicle at the current moment. The risk assessment module includes: a second unit for determining the risk assessment attribute to be fused, which is used to determine the risk assessment attribute to be fused of the pending vehicle under the collision risk dimension based on the ratio of the first preset coefficient to the pending collision time when it is determined that the pending collision time is not a preset value.

[0123] Optionally, the driving attribute information under the heading angle intrusion risk dimension includes: the current heading angle corresponding to the vehicle to be processed at the current collection moment and the historical heading angle corresponding to at least one historical collection moment before the current collection moment. The risk assessment module includes: a third risk assessment attribute determination unit to be fused, which is used to determine the risk assessment attribute to be fused of the vehicle to be processed under the heading angle intrusion risk dimension based on the current heading angle and at least one historical heading angle, and a second preset coefficient corresponding to each heading angle.

[0124] Optionally, the driving attribute information under the acceleration risk dimension includes: the lateral acceleration to be processed and the longitudinal acceleration to be processed of the vehicle to be processed, the longitudinal acceleration to be processed is used to characterize the longitudinal acceleration of the vehicle to be processed in a second direction, and the second direction is consistent with the driving direction of the vehicle to be processed. The risk assessment module includes: a fourth risk assessment attribute determination unit to be fused, which is used to normalize the lateral acceleration to be processed according to a preset lateral acceleration threshold value for the acceleration risk dimension, and to normalize the longitudinal acceleration to be processed according to a preset longitudinal acceleration threshold value to obtain a normalized lateral acceleration and a normalized longitudinal acceleration; determine a first multiplication result between the normalized lateral acceleration and a third preset coefficient, and determine a second multiplication result between the normalized longitudinal acceleration and a fourth preset coefficient; determine the risk assessment attribute to be fused of the vehicle to be processed under the acceleration risk dimension based on the difference between the first multiplication result and the second multiplication result.

[0125] Optionally, the driving attribute information under the longitudinal distance risk dimension includes: the longitudinal relative speed to be processed and the longitudinal distance to be processed between the target vehicle and the vehicle to be processed, the longitudinal relative speed to be processed is used to characterize the relative speed of the target vehicle and the vehicle to be processed in the first direction, and the risk assessment module includes: a fifth risk assessment attribute to be fused determination unit, used to determine the first distance for the longitudinal distance risk dimension according to the multiplication result between the speed of the target vehicle and the preset reaction time and the preset distance threshold; wherein the first distance is the maximum value between the multiplication result and the preset distance threshold; when the longitudinal distance to be processed does not exceed the first distance, the longitudinal distance to be processed is normalized based on the first distance to obtain a normalized distance; a function is determined based on the longitudinal relative speed to be processed and the preset dynamic attenuation coefficient to determine the dynamic attenuation coefficient; and the risk assessment attribute to be processed corresponding to the vehicle to be processed is determined based on the normalized distance and the dynamic attenuation coefficient; when the first distance and the longitudinal distance to be processed meet the second preset condition, the risk assessment attribute to be fused of the vehicle to be processed under the longitudinal distance risk dimension is determined based on the risk assessment attribute to be processed, the first distance, the longitudinal distance to be processed and the longitudinal distance risk determination function.

[0126] Optionally, the vehicle control module includes: a target vehicle deceleration unit, which is used to generate early warning information based on the target lateral risk attribute when the target lateral risk attribute of the vehicle to be processed exceeds a preset lateral risk attribute threshold, so as to control the target vehicle to decelerate based on the early warning information.

[0127] The driving lateral risk detection device provided in the embodiment of the present invention can execute the driving lateral risk detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0128] Example 4

[0129] Figure 6 1 is a structural diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0130] like Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0132] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, or microcontroller. The processor 11 executes the various methods and processes described above, such as the lateral risk detection method.

[0133] In some embodiments, the lateral driving risk detection method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the lateral driving risk detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the lateral driving risk detection method via any other suitable means (e.g., via firmware).

[0134] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs for implementing the lateral risk detection method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-mentioned functions defined in the method of the embodiment of the present invention are performed.

[0137] Example 5

[0138] The fifth embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a processor to execute a driving lateral risk detection method, the method comprising:

[0139] During the driving process of the target vehicle, at least one first vehicle associated with the target vehicle is obtained, and a vehicle to be processed is determined based on the lateral distance to be compared between the first vehicle and the target vehicle in a first direction; wherein, the at least one first vehicle is a vehicle located in front of the target vehicle, the front is related to the driving direction of the target vehicle, and the first direction is a direction perpendicular to the driving direction; according to the driving attribute information of the vehicle to be processed under at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension, the risk assessment attributes to be fused of the vehicle to be processed under each risk assessment dimension are determined; wherein, at least one risk assessment dimension includes: at least one of a lateral offset risk dimension, a collision risk dimension, a heading angle intrusion risk dimension, an acceleration risk dimension and a longitudinal distance risk dimension; according to the risk assessment attributes to be fused corresponding to the at least one risk assessment dimension, the target lateral risk attribute corresponding to the vehicle to be processed is determined, so as to control the target vehicle to decelerate when the target lateral risk attribute meets a first preset condition.

[0140] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0141] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0142] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0143] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0144] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0145] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting lateral risk of a vehicle, characterized in that: Applied to an autonomous driving vehicle, the method includes: During the movement of a target vehicle, at least one first vehicle associated with the target vehicle is acquired, and a vehicle to be processed is determined based on a lateral distance to be compared between the first vehicle and the target vehicle in a first direction; wherein the at least one first vehicle is a vehicle located in front of the target vehicle, the front is related to the movement direction of the target vehicle, and the first direction is a direction perpendicular to the movement direction; Determining the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and a risk assessment function corresponding to each risk assessment dimension; wherein the at least one risk assessment dimension includes at least one of a lateral deviation risk dimension, a collision risk dimension, a heading angle intrusion risk dimension, an acceleration risk dimension, and a longitudinal distance risk dimension; According to the risk assessment attribute to be fused corresponding to the at least one risk assessment dimension, a target lateral risk attribute corresponding to the vehicle to be processed is determined, so as to control the target vehicle to decelerate when the target lateral risk attribute meets a first preset condition.

2. The method according to claim 1, characterized in that The determining of the vehicle to be processed according to the lateral distance to be compared between the first vehicle and the target vehicle in the first direction includes: Determining a lateral distance range based on the lane width of the target vehicle and a preset lateral distance coefficient; When it is detected that the lateral distance to be compared between the first vehicle and the target vehicle in the first direction belongs to the lateral distance range, the first vehicle is determined as the vehicle to be processed.

3. The method according to claim 1, characterized in that The driving attribute information under the lateral deviation risk dimension is a lateral distance to be processed, and the lateral distance to be processed is used to represent the lateral distance between the vehicle to be processed and the target vehicle in the first direction. The step of determining the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension includes: For the lateral offset risk dimension, the risk assessment attribute to be fused corresponding to the lateral offset risk dimension of the vehicle to be processed is determined based on the lateral distance to be processed, the lane width of the lane to which the target vehicle belongs, the preset risk sensitivity coefficient, and the risk assessment function corresponding to the lateral offset risk dimension.

4. The method according to claim 1, wherein The driving attribute information under the collision risk dimension is the pending collision time, which is used to represent the time required for the target vehicle to collide with the pending vehicle at the current moment. The step of determining the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension includes: For the collision risk dimension, when it is determined that the time of collision to be processed is not a preset value, the risk assessment attribute to be fused of the vehicle to be processed under the collision risk dimension is determined based on the ratio of the first preset coefficient to the time of collision to be processed.

5. The method according to claim 1, wherein The driving attribute information under the heading angle intrusion risk dimension includes: the current heading angle of the vehicle to be processed corresponding to the current collection time and the historical heading angle corresponding to at least one historical collection time before the current collection time, The step of determining the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension includes: For the heading angle intrusion risk dimension, the risk assessment attribute to be fused of the vehicle to be processed under the heading angle intrusion risk dimension is determined based on the current heading angle and at least one of the historical heading angles, and a second preset coefficient corresponding to each heading angle.

6. The method according to claim 1, characterized in that The driving attribute information under the acceleration risk dimension includes: the lateral acceleration to be processed and the longitudinal acceleration to be processed of the vehicle to be processed, wherein the longitudinal acceleration to be processed is used to represent the longitudinal acceleration of the vehicle to be processed in a second direction, and the second direction is consistent with the driving direction of the vehicle to be processed. The step of determining the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension includes: For the acceleration risk dimension, normalizing the lateral acceleration to be processed according to a preset lateral acceleration threshold, and normalizing the longitudinal acceleration to be processed according to a preset longitudinal acceleration threshold, to obtain a normalized lateral acceleration and a normalized longitudinal acceleration; determining a first multiplication result between the normalized lateral acceleration and a third preset coefficient, and determining a second multiplication result between the normalized longitudinal acceleration and a fourth preset coefficient; According to the difference between the first multiplication result and the second multiplication result, a risk assessment attribute to be fused of the vehicle to be processed in the acceleration risk dimension is determined.

7. The method according to claim 1, characterized in that The driving attribute information under the longitudinal distance risk dimension includes: the longitudinal relative speed to be processed and the longitudinal distance to be processed between the target vehicle and the vehicle to be processed, wherein the longitudinal relative speed to be processed is used to represent the relative speed between the target vehicle and the vehicle to be processed in the first direction; The step of determining the risk assessment attributes to be fused for the vehicle to be processed in each risk assessment dimension based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and the risk assessment function corresponding to each risk assessment dimension includes: For the longitudinal distance risk dimension, a first distance is determined based on a product of the target vehicle's speed and a preset reaction time and a preset distance threshold; wherein the first distance is the maximum value between the product and the preset distance threshold; When the longitudinal distance to be processed does not exceed the first distance, normalizing the longitudinal distance to be processed based on the first distance to obtain a normalized distance; Determining a function based on the longitudinal relative speed to be processed and a preset dynamic attenuation coefficient to determine the dynamic attenuation coefficient; and determining a risk assessment attribute to be processed corresponding to the vehicle to be processed based on the normalized distance and the dynamic attenuation coefficient; When the first distance and the longitudinal distance to be processed meet a second preset condition, the risk assessment attribute to be fused of the vehicle to be processed under the longitudinal distance risk dimension is determined according to the risk assessment attribute to be processed, the first distance, the longitudinal distance to be processed, and the longitudinal distance risk determination function.

8. The method according to claim 1, characterized in that When the target lateral risk attribute satisfies a first preset condition, controlling the target vehicle to decelerate includes: When the target lateral risk attribute of the vehicle to be processed exceeds a preset lateral risk attribute threshold, early warning prompt information is generated based on the target lateral risk attribute, so as to control the target vehicle to decelerate based on the early warning prompt information.

9. A driving lateral risk detection device, characterized in that: Applied to an autonomous driving vehicle, the device comprises: a to-be-processed vehicle determination module, configured to, while a target vehicle is traveling, obtain at least one first vehicle associated with the target vehicle and determine the to-be-processed vehicle based on a lateral distance to be compared between the first vehicle and the target vehicle in a first direction; wherein the at least one first vehicle is a vehicle located in front of the target vehicle, the front being related to a traveling direction of the target vehicle, and the first direction being a direction perpendicular to the traveling direction; a risk assessment module, configured to determine, based on the driving attribute information of the vehicle to be processed in at least one risk assessment dimension and a risk assessment function corresponding to each risk assessment dimension, a risk assessment attribute to be fused for the vehicle to be processed in each risk assessment dimension; wherein the at least one risk assessment dimension includes at least one of a lateral deviation risk dimension, a collision risk dimension, a heading angle intrusion risk dimension, an acceleration risk dimension, and a longitudinal distance risk dimension; The vehicle control module is used to determine the target lateral risk attribute corresponding to the vehicle to be processed based on the risk assessment attribute to be fused corresponding to the at least one risk assessment dimension, so as to control the target vehicle to decelerate when the target lateral risk attribute meets a first preset condition.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the driving lateral risk detection method according to any one of claims 1 to 8.

Images