Active lateral anti-collision behavior decision-making method and device, equipment and storage medium

Abstract

The invention discloses an active lateral anti-collision behavior decision-making method, device and equipment and a storage medium, and relates to the field of auxiliary driving, and the method comprises the steps: based on the driving states of a vehicle and a target vehicle, calculating to obtain avoidance action triggering time corresponding to each avoidance strategy of the vehicle for realizing the avoidance of the vehicle to the target vehicle; according to the calculation result of the avoiding action triggering time, taking the avoiding strategy corresponding to the minimum avoiding action triggering time as the optimal avoiding strategy; wherein the avoidance strategy comprises single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single transverse avoidance and transverse and longitudinal combined avoidance. The most effective avoidance strategy can be calculated in real time according to the actual scene, and the performance of the active safety function is improved.

Description

Technical Field

[0001] The present application relates to the field of assisted driving, and specifically to a method, device, equipment and storage medium for active lateral collision avoidance behavior decision-making. Background Art

[0002] AES (Automatic Emergency Steering) / ESS (Assisted Emergency Steering) systems on vehicles are designed to proactively steer the vehicle laterally when AEB is unable to prevent a collision. However, AES / ESS primarily targets the longitudinal target ahead, not lateral or simply moving targets. Furthermore, AES / ESS is triggered when there is a potential longitudinal collision risk between the vehicle and the preceding vehicle. The responsible party is the vehicle itself, and potential collision scenarios where the responsible party is not the vehicle itself (for example, a nearby vehicle erratically changes lanes or loses lateral control, potentially colliding with the vehicle). Therefore, accurately implementing active lateral collision avoidance has become a pressing issue. Summary of the Invention

[0003] The present application provides a method, device, equipment and storage medium for active lateral collision avoidance behavior decision-making, which can calculate the most effective avoidance strategy in real time according to the actual scenario and improve the performance of active safety functions.

[0004] In a first aspect, an embodiment of the present application provides a method for making a decision on an active lateral collision avoidance behavior, the method comprising: Based on the driving status of the host vehicle and the target vehicle, the trigger time of each avoidance action corresponding to the host vehicle's avoidance strategy is calculated to achieve the host vehicle's avoidance of the target vehicle; According to the calculation results of the avoidance action trigger time, the avoidance strategy corresponding to the minimum avoidance action trigger time is taken as the optimal avoidance strategy; The avoidance strategies include single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance.

[0005] In conjunction with the first aspect, in one embodiment, the avoidance action triggering time corresponding to the single longitudinal acceleration avoidance is specifically: Determine the implementation phases of single longitudinal acceleration avoidance, which include normal driving phase, uniform acceleration phase, and uniform acceleration phase in sequence; Calculate the speed and acceleration of the vehicle after the normal driving phase, as well as the distance traveled by the vehicle during the normal driving phase; Calculate the vehicle's speed after the uniform acceleration phase, as well as the distance and time traveled during the uniform acceleration phase. Calculate the speed of the vehicle after the uniform acceleration phase ends, as well as the distance traveled by the vehicle during the uniform acceleration phase; Based on the calculation results of the implementation phase of single longitudinal acceleration avoidance, the collision avoidance distance is determined, and the avoidance action triggering time corresponding to the single longitudinal acceleration avoidance is obtained.

[0006] In conjunction with the first aspect, in one embodiment, the avoidance action triggering time corresponding to the single longitudinal deceleration avoidance is specifically: Based on the avoidance action trigger time corresponding to single longitudinal acceleration avoidance, compensate obj_length × sin(theta) / v_vel_lat as the avoidance action trigger time corresponding to single longitudinal deceleration avoidance; Where obj_length represents the length of the target vehicle, theta represents the heading angle of the target vehicle relative to the host vehicle, and v_vel_lat represents the current relative lateral velocity between the host vehicle and the target vehicle.

[0007] In conjunction with the first aspect, in one embodiment, the avoidance action triggering time corresponding to a single lateral avoidance is specifically: Determine the expected lateral movement distance of the vehicle; Based on the determined expected lateral movement distance of the vehicle, the avoidance action triggering time corresponding to a single lateral avoidance is calculated.

[0008] In conjunction with the first aspect, in one embodiment, When the relative speed between the vehicle and the target vehicle is less than the set speed, the maximum allowed lateral movement distance is used as the expected lateral movement distance of the vehicle; When the host vehicle's speed is greater than the target vehicle's, the expected lateral movement distance of the host vehicle is (ttc_AD - ttc_lat_collision) × v_vel_lat, where ttc_AD represents the time it takes for the rear corner of the host vehicle to meet the front corner of the target vehicle in the longitudinal direction on the opposite sides of the host vehicle. ttc_AD = s_AD / v_rel_long, where s_AD represents the distance in the axial direction between the rear corner of the host vehicle and the front corner of the target vehicle on the opposite sides of the host vehicle. v_rel_long represents the longitudinal relative phase velocity between the host vehicle and the target vehicle. When the host vehicle's speed is less than that of the target vehicle, the expected lateral movement distance of the host vehicle is (ttc_CB - ttc_lat_collision) × v_vel_lat – obj_length × sin(theta), where ttc_CB represents the time when the front angle of the host vehicle and the rear angle of the target vehicle meet in the longitudinal direction on the opposite sides of the host vehicle and the target vehicle, v_vel_lat represents the current relative lateral speed of the host vehicle and the target vehicle, theta represents the heading angle of the target vehicle relative to the host vehicle, ttc_lat_collision represents the lateral collision time between the host vehicle and the target vehicle, and ttc_lat_collision = d_lat / v_vel_lat, where d_lat represents the current lateral distance between the host vehicle and the target vehicle, and obj_length represents the length of the target vehicle.

[0009] In conjunction with the first aspect, in one embodiment, the avoidance action triggering time corresponding to the combined lateral and longitudinal avoidance is specifically: Under the set current expected lateral movement distance, the avoidance action trigger time corresponding to a single lateral avoidance is calculated, the longitudinal collision avoidance distance is corrected, and the avoidance action trigger time corresponding to a single longitudinal acceleration / deceleration avoidance is calculated; Determining the maximum time among the avoidance action triggering times calculated based on the current expected lateral movement distance as the final avoidance action triggering time corresponding to the current expected lateral movement distance; Determine whether the final avoidance action trigger time corresponding to the current expected lateral movement distance is greater than the final avoidance action trigger time corresponding to the previous expected lateral movement distance: If so, the final avoidance action triggering time corresponding to the previous expected lateral movement distance is used as the avoidance action triggering time corresponding to the lateral and longitudinal combined avoidance; If not, the expected lateral movement distance is set again by increasing the current expected lateral movement distance according to the set step size, and then the avoidance action trigger time is calculated again, the final avoidance action trigger time is determined, and the final avoidance action trigger time is judged, and the cycle continues.

[0010] In conjunction with the first aspect, in one embodiment, the method of using the avoidance strategy corresponding to the minimum avoidance strategy trigger time as the optimal avoidance strategy based on the avoidance action trigger time calculation result specifically includes: Get the corresponding avoidance action trigger time for single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance; Based on the judgment of the triggering time of each avoidance action, the avoidance strategy corresponding to the minimum avoidance action triggering time is taken as the optimal avoidance strategy.

[0011] In a second aspect, an embodiment of the present application provides an active lateral collision avoidance behavior decision-making device, the active lateral collision avoidance behavior decision-making device comprising: A calculation module, which is used to calculate the avoidance action trigger time corresponding to each avoidance strategy of the vehicle to achieve the avoidance of the target vehicle based on the driving status of the vehicle and the target vehicle; A confirmation module is used to determine the avoidance strategy corresponding to the minimum avoidance action trigger time as the optimal avoidance strategy based on the avoidance action trigger time calculation result; The avoidance strategies include single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance.

[0012] In the third aspect, an embodiment of the present application provides an active lateral collision avoidance behavior decision-making device, which includes a processor, a memory, and an active lateral collision avoidance behavior decision-making program stored on the memory and executable by the processor, wherein when the active lateral collision avoidance behavior decision-making program is executed by the processor, the steps of the active lateral collision avoidance behavior decision-making method described above are implemented.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which an active lateral collision avoidance behavior decision-making program is stored, wherein when the active lateral collision avoidance behavior decision-making program is executed by a processor, the steps of the active lateral collision avoidance behavior decision-making method described above are implemented.

[0014] The beneficial effects of the technical solutions provided in the embodiments of the present application include: Based on the driving status of the own vehicle and the target vehicle, the avoidance action trigger time corresponding to each avoidance action trigger time of the own vehicle is calculated to achieve the avoidance of the target vehicle. Then, according to the calculation result of the avoidance action trigger time, the avoidance strategy corresponding to the minimum avoidance action trigger time is used as the optimal avoidance strategy, which improves the applicable scenarios of the active safety function, including side collision scenarios (situations where the responsible party is the target vehicle). At the same time, single longitudinal, single lateral and combined lateral and longitudinal avoidance strategies are provided. The most effective avoidance strategy can be calculated in real time according to the actual scenario, thereby improving the performance of the active safety function. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flowchart of the active lateral collision avoidance behavior decision-making method of this application; Figure 2 This is the schematic diagram corresponding to single longitudinal acceleration avoidance; Figure 3 This is the schematic diagram corresponding to single longitudinal deceleration avoidance; Figure 4 This is the schematic diagram corresponding to single lateral avoidance; Figure 5 This is a schematic diagram of the functional modules of the active lateral collision avoidance behavior decision-making device of this application; Figure 6 This is a schematic diagram of the hardware structure of the active lateral collision avoidance behavior decision-making device in this application. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments 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 creative work are within the scope of protection of this application.

[0017] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0018] First, an embodiment of the present application provides an active lateral collision avoidance behavior decision-making method by calculating the avoidance action triggering time under three behaviors: single longitudinal avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance. Among them, the longitudinal avoidance adopts a uniform acceleration model, and the lateral avoidance adopts a fifth-order polynomial for trajectory planning, and then selects the avoidance behavior with the shortest avoidance action triggering time as the optimal avoidance strategy.

[0019] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the active lateral collision avoidance behavior decision-making method of this application. Figure 1 As shown in FIG, the active side collision avoidance behavior decision-making method includes: S1: Based on the driving states of the host vehicle and the target vehicle, the triggering time of each avoidance action corresponding to the host vehicle's avoidance strategy is calculated to achieve the host vehicle's avoidance of the target vehicle; S2: Based on the calculation result of the avoidance action trigger time, the avoidance strategy corresponding to the minimum avoidance action trigger time is used as the optimal avoidance strategy; The avoidance strategies include single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance.

[0020] Furthermore, in one embodiment, the avoidance action triggering time corresponding to the single longitudinal acceleration avoidance is specifically: a1: Determine the implementation phase of single longitudinal acceleration avoidance, which includes the normal driving phase, the uniform acceleration phase, and the uniform acceleration phase in sequence; Specifically, for single longitudinal acceleration avoidance, it is completed in three stages. The first stage is normal driving of the vehicle, which lasts for t1. After the completion of this stage, the vehicle travels a distance of s1, with a final speed of v1 and a final acceleration of a1. The second stage is the start of uniform acceleration motion with a jerk until the acceleration reaches max_a. The duration of this stage is t2. During this stage, the vehicle travels a distance of s2, with a final speed of v2 and a final acceleration of a2. The third stage is uniform acceleration motion according to the acceleration max_a. The duration of this stage is t3. During this stage, the vehicle travels a distance of t3, with a final speed of v3 and a final acceleration of a3. a2: Calculate the vehicle's speed, acceleration, and distance traveled during the normal driving phase after the normal driving phase ends; After the normal driving phase ends, the vehicle's speed, acceleration, and distance traveled during the normal driving phase are as follows: s1=v0×t1+a0×t1^2 / 2 v1=v0+a0×t1 a1=a0 Where s1 represents the distance traveled by the vehicle during the normal driving phase, v0 represents the initial speed of the vehicle during the normal driving phase, t1 represents the duration of the normal driving phase, a0 represents the acceleration of the vehicle during the normal driving phase, v1 represents the speed of the vehicle after the normal driving phase ends, and a1 represents the acceleration of the vehicle after the normal driving phase ends. a3: Calculate the vehicle's speed after the uniform acceleration phase, as well as the distance and time traveled during the uniform acceleration phase. The calculation of the vehicle's speed after the uniform acceleration phase, as well as the vehicle's travel distance and travel time during the uniform acceleration phase, is as follows: t2=(max_a-a0) / jerk s2=v1×t2+a1×t2^2 / 2+jerk×t2^3 / 6 v2=v1+a1×t2+a1×t2 / 2 a2=a1+jerk×t2=max_a Where t2 represents the driving time of the vehicle in the uniform acceleration phase, max_a represents the acceleration of the vehicle after the uniform acceleration phase, jerk represents the jerk of the vehicle in the uniform acceleration phase, s2 represents the driving distance of the vehicle in the uniform acceleration phase, v2 represents the speed of the vehicle after the uniform acceleration phase, and a2 represents the acceleration of the vehicle after the uniform acceleration phase. a4: Calculate the speed of the vehicle after the uniform acceleration phase ends, as well as the distance traveled by the vehicle during the uniform acceleration phase; The calculation of the vehicle's speed after the uniform acceleration phase and the distance traveled during the uniform acceleration phase are as follows: s3=v2×t3+a2×t3^2 / 2 v3=v2+a2×t3 Among them, s3 represents the distance traveled by the vehicle in the uniform acceleration phase, t3 represents the travel time of the vehicle in the uniform acceleration phase, and v3 represents the speed of the vehicle after the uniform acceleration phase ends; a5: Based on the calculation results of the implementation phase of the single longitudinal acceleration avoidance, the collision avoidance distance is determined, and the avoidance action triggering time corresponding to the single longitudinal acceleration avoidance is obtained.

[0021] For the collision avoidance distance d (i.e. the longitudinal overlap distance in a lateral collision without taking any action), see Figure 2 The following conditions must be met: d=s1+s2+s3-(v0×T+a0×T^2 / 2) =(a2-a1)×t3^2 / 2+jerk×t2^2×t3 / 2+jerk×t2^3 / 6; by Figure 2 For example, the above collision avoidance distance d satisfies the condition to ensure that the left rear corner of the vehicle can pass the right front corner of the target vehicle after the avoidance is completed; Where T represents the lateral collision time between the host vehicle and the target vehicle, T = t1 + t2 + t3, which is used to ensure that within the lateral collision time T, the host vehicle moves away from the target vehicle in the longitudinal direction through the above three stages to ensure that there is no collision. Therefore, the final avoidance action triggering time corresponding to the single longitudinal acceleration avoidance is: active_ttc_long= t2+t3 Among them, active_ttc_long represents the avoidance action trigger time corresponding to single longitudinal acceleration avoidance.

[0022] Furthermore, it should be noted that after the uniform acceleration phase, if the longitudinal relative speed between the host vehicle and the target vehicle is less than 0, active_ttc_long is compensated by v_rel_long_final / (max_a-a0) to ensure that the final longitudinal speed of the host vehicle is higher than the longitudinal speed of the target vehicle, where v_rel_long_final represents the longitudinal relative speed between the host vehicle and the target vehicle after the uniform acceleration phase.

[0023] Furthermore, in one embodiment, for single longitudinal deceleration avoidance, the process is similar to single longitudinal acceleration avoidance. Figure 3As shown in the figure, it is necessary to ensure that the left front corner of the vehicle avoids the right rear corner of the target vehicle after the collision avoidance action is completed. Therefore, the triggering time of the avoidance action corresponding to the single longitudinal deceleration avoidance is as follows: Based on the avoidance action trigger time corresponding to single longitudinal acceleration avoidance, compensate obj_length × sin(theta) / v_vel_lat as the avoidance action trigger time corresponding to single longitudinal deceleration avoidance; Where obj_length represents the length of the target vehicle, theta represents the heading angle of the target vehicle relative to the host vehicle, and v_vel_lat represents the current relative lateral velocity between the host vehicle and the target vehicle.

[0024] Furthermore, in one embodiment, for single lateral avoidance, the lateral collision time is prolonged by turning action, and then the collision avoidance is achieved by relying on the existing longitudinal speed difference.

[0025] Therefore, for the avoidance action triggering time corresponding to single lateral avoidance, specifically: c1: Determine the expected lateral movement distance of the vehicle; Among them, when the relative speed between the host vehicle and the target vehicle is less than the set speed, the maximum allowed lateral movement distance is used as the expected lateral movement distance of the host vehicle (that is, when the relative speed between the host vehicle and the target vehicle is very small, the maximum allowed lateral movement distance of the host vehicle is used as the expected lateral movement distance of the host vehicle). When the speed of the host vehicle is greater than that of the target vehicle, the expected lateral movement distance of the host vehicle is (ttc_AD-ttc_lat_collision)×v_vel_lat, where ttc_AD represents the time when the rear corner of the host vehicle meets the front corner of the target vehicle in the longitudinal direction on the two opposite sides of the host vehicle (that is, Figure 4 As shown in the figure, the time when two points AD meet in the longitudinal direction), ttc_AD = s_AD / v_rel_long, s_AD represents the distance between the rear corner of the vehicle and the front corner of the target vehicle on the opposite sides of the vehicle (i.e. Figure 4 As shown in the figure, the distance between points AD in the axial direction of the vehicle), v_rel_long represents the longitudinal relative phase velocity between the vehicle and the target vehicle. When the speed of the vehicle is less than that of the target vehicle, the expected lateral movement distance of the vehicle is (ttc_CB-ttc_lat_collision)×v_vel_lat–obj_length×sin(theta). ttc_CB represents the time when the front corner of the vehicle and the rear corner of the target vehicle meet in the longitudinal direction on the opposite sides of the vehicle and the target vehicle (i.e., Figure 4As shown in the figure, CB is the time when the two points meet in the longitudinal direction), v_vel_lat represents the current relative lateral velocity of the host vehicle and the target vehicle, theta represents the heading angle of the target vehicle relative to the host vehicle, ttc_lat_collision represents the lateral collision time between the host vehicle and the target vehicle, ttc_lat_collision=d_lat / v_vel_lat, d_lat represents the current lateral distance between the host vehicle and the target vehicle, and obj_length represents the length of the target vehicle; c2: Calculate the triggering time for a single lateral avoidance maneuver based on the vehicle's expected lateral movement distance: active_lat_ttc=0.667×sqrt(5.773×abs(lat_bias) / max_a_lat) Among them, active_lat_ttc represents the avoidance action trigger time corresponding to a single lateral avoidance, lat_bias represents the desired lateral movement distance of the vehicle, and max_a_lat represents the maximum lateral acceleration allowed during the lateral movement of the vehicle.

[0026] Furthermore, in one embodiment, for combined lateral and longitudinal avoidance, the lateral offset distance is traversed according to the above-mentioned single longitudinal and single lateral calculation methods to find a trigger point, and acceleration / deceleration and steering are activated simultaneously to achieve collision avoidance.

[0027] The triggering time of the avoidance action corresponding to the combined horizontal and vertical avoidance is as follows: d1: Calculates the avoidance action trigger time for a single lateral avoidance maneuver based on the current expected lateral movement distance. Corrects the longitudinal collision avoidance distance and calculates the avoidance action trigger time for a single longitudinal acceleration / deceleration maneuver. Specifically, for a given expected lateral movement distance, the avoidance action triggering time for a single lateral avoidance maneuver is calculated using the same method as for a single turn. The longitudinal avoidance distance is then corrected (because lateral movement changes the collision time, if the two vehicles have a relative speed or acceleration in the longitudinal direction, the longitudinal avoidance distance required at the new collision point must be recalculated). The avoidance action triggering time for a single longitudinal acceleration / deceleration maneuver is then calculated based on the corrected longitudinal avoidance distance and lateral collision time. d2: The maximum avoidance action trigger time calculated based on the current expected lateral movement distance is determined as the final avoidance action trigger time corresponding to the current expected lateral movement distance. Specifically, among the calculated avoidance action trigger times corresponding to single lateral avoidance, single longitudinal acceleration avoidance, and single longitudinal deceleration avoidance, the largest time is selected as the final avoidance action trigger time corresponding to the current expected lateral movement distance. d3: Determine whether the final avoidance action trigger time corresponding to the current expected lateral movement distance is greater than the final avoidance action trigger time corresponding to the previous expected lateral movement distance: If so, the final avoidance action triggering time corresponding to the previous expected lateral movement distance is used as the avoidance action triggering time corresponding to the lateral and longitudinal combined avoidance; If not, the current expected lateral movement distance is increased according to the set step size (the value can be 0.1m) and the expected lateral movement distance is set again. Then, the avoidance action trigger time is calculated again, the final avoidance action trigger time is determined, and the final avoidance action trigger time is judged, and this cycle is repeated.

[0028] Specifically, the expected lateral movement distance (initially 0) is set in sequence, and the final avoidance action trigger time is calculated under the set expected lateral movement distance. If the final avoidance action trigger time calculated under the current set expected lateral movement distance is greater than the final avoidance action trigger time calculated under the last set expected lateral movement distance, the final avoidance action trigger time calculated under the last set expected lateral movement distance is used as the avoidance action trigger time corresponding to the joint lateral and longitudinal avoidance; if the final avoidance action trigger time calculated under the current set expected lateral movement distance is not greater than the final avoidance action trigger time calculated under the last set expected lateral movement distance, 0.1m is added to the current set expected lateral movement distance to obtain the next set expected lateral movement distance, and the corresponding final avoidance action trigger time is calculated. Then, the final avoidance action trigger time calculated under the next set expected lateral movement distance is compared with the final avoidance action trigger time calculated under the current set expected lateral movement distance, and the cycle continues.

[0029] Furthermore, in one embodiment, based on the calculation result of the avoidance action trigger time, the avoidance strategy corresponding to the minimum avoidance action trigger time is used as the optimal avoidance strategy, which specifically includes: S201: Obtaining avoidance action trigger times corresponding to single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance; S202: Based on the determination of the avoidance maneuver trigger times, the avoidance strategy corresponding to the minimum avoidance maneuver trigger time is determined as the optimal avoidance strategy. For example, if the avoidance maneuver trigger time corresponding to the longitudinal acceleration avoidance strategy is greater than the avoidance maneuver trigger times corresponding to the other avoidance strategies, the longitudinal acceleration avoidance strategy is selected as the optimal avoidance strategy and controls the vehicle's avoidance maneuver.

[0030] The active lateral collision avoidance behavior decision-making method of the embodiment of the present application calculates the avoidance action trigger time corresponding to each avoidance strategy of the vehicle in order to achieve the avoidance of the vehicle to the target vehicle based on the driving status of the vehicle and the target vehicle, and then uses the avoidance action trigger time calculation result as the avoidance strategy corresponding to the minimum avoidance action trigger time as the optimal avoidance strategy, thereby improving the applicable scenarios of the active safety function, including lateral collision scenarios (situations where the responsible party is the target vehicle). At the same time, it provides single longitudinal, single lateral, and combined lateral and longitudinal avoidance strategies, which can calculate the most effective avoidance strategy in real time according to the actual scenario, thereby improving the performance of the active safety function.

[0031] In a second aspect, an embodiment of the present application also provides an active lateral collision avoidance behavior decision-making device.

[0032] In one embodiment, referring to Figure 5 , Figure 5 This is a functional module diagram of the active lateral collision avoidance behavior decision-making device of this application. Figure 5 As shown, the active lateral collision avoidance behavior decision-making device includes: a calculation module and a confirmation module.

[0033] The calculation module is used to calculate the avoidance action trigger time corresponding to each avoidance action trigger time of the vehicle based on the driving status of the vehicle and the target vehicle in order to achieve the avoidance of the vehicle to the target vehicle; the confirmation module is used to use the avoidance action trigger time calculation result as the optimal avoidance strategy; wherein, the avoidance strategy includes single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance.

[0034] In a third aspect, an embodiment of the present application provides an active lateral collision avoidance behavior decision-making device, which can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0035] Reference Figure 6 , Figure 6 FIG2 is a schematic diagram of the hardware structure of the active lateral collision avoidance behavior decision-making device involved in the embodiment of the present application. In the embodiment of the present application, the active lateral collision avoidance behavior decision-making device may include a processor, a memory, a communication interface, and a communication bus.

[0036] The communication bus may be of any type and is used to interconnect the processor, memory, and communication interface.

[0037] Communication interfaces include input / output (I / O), physical, and logical interfaces, which interconnect components within the active lateral collision avoidance decision-making device and connect it to other devices (such as other computing devices or user devices). Physical interfaces can include Ethernet, fiber, or ATM interfaces; user devices can include displays and keyboards.

[0038] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0039] The processor may be a general-purpose processor that can invoke an active lateral collision avoidance behavior decision program stored in a memory and execute the active lateral collision avoidance behavior decision method provided in the embodiments of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The methods executed when the active lateral collision avoidance behavior decision program is invoked can be referenced to the various embodiments of the active lateral collision avoidance behavior decision method of the present application and will not be further described here.

[0040] Those skilled in the art will understand that Figure 6 The hardware structure shown in the figure does not constitute a limitation to the present application and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0041] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0042] An active lateral collision avoidance behavior decision program is stored on the computer-readable storage medium of the present application, wherein when the active lateral collision avoidance behavior decision program is executed by the processor, the steps of the active lateral collision avoidance behavior decision method as described above are implemented.

[0043] Among them, the method implemented when the active lateral collision avoidance behavior decision-making program is executed can refer to the various embodiments of the active lateral collision avoidance behavior decision-making method of the present application, and will not be repeated here.

[0044] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings 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 limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit the "first", "second" and "third" to different types.

[0045] In the description of the embodiments of this application, the words "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0046] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0047] In some processes described in the embodiments of the present application, multiple operations or steps are included that appear in a specific order. However, it should be understood that these operations or steps may not be performed in the order in which they appear in the embodiments of the present application or may be performed in parallel. The sequence numbers of the operations are only used to distinguish between different operations, and the sequence numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations or steps may be performed in sequence or in parallel, and these operations or steps may be combined.

[0048] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above and includes a number of instructions for enabling a terminal device to execute the methods described in each embodiment of this application.

[0049] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for active lateral collision avoidance behavior decision-making, characterized in that: The active lateral collision avoidance behavior decision-making method includes: Based on the driving status of the host vehicle and the target vehicle, the trigger time of each avoidance action corresponding to the host vehicle's avoidance strategy is calculated to achieve the host vehicle's avoidance of the target vehicle; According to the calculation results of the avoidance action triggering time, the avoidance strategy corresponding to the minimum avoidance action triggering time is taken as the optimal avoidance strategy; The avoidance strategies include single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance.

2. The active lateral collision avoidance behavior decision-making method according to claim 1, characterized in that: For single longitudinal acceleration avoidance, the avoidance action triggering time is as follows: Determine the implementation phases of single longitudinal acceleration avoidance, which include normal driving phase, uniform acceleration phase, and uniform acceleration phase in sequence; Calculate the speed and acceleration of the vehicle after the normal driving phase, as well as the distance traveled by the vehicle during the normal driving phase; Calculate the vehicle's speed after the uniform acceleration phase, as well as the distance and time traveled during the uniform acceleration phase. Calculate the speed of the vehicle after the uniform acceleration phase ends, as well as the distance traveled by the vehicle during the uniform acceleration phase; Based on the calculation results of the implementation phase of single longitudinal acceleration avoidance, the collision avoidance distance is determined, and the avoidance action triggering time corresponding to the single longitudinal acceleration avoidance is obtained.

3. The active lateral collision avoidance behavior decision-making method according to claim 2, characterized in that: For single longitudinal deceleration avoidance, the avoidance action triggering time is as follows: Based on the avoidance action trigger time corresponding to single longitudinal acceleration avoidance, compensate obj_length × sin(theta) / v_vel_lat as the avoidance action trigger time corresponding to single longitudinal deceleration avoidance; Where obj_length represents the length of the target vehicle, theta represents the heading angle of the target vehicle relative to the host vehicle, and v_vel_lat represents the current relative lateral velocity between the host vehicle and the target vehicle.

4. The active lateral collision avoidance behavior decision-making method according to claim 1, characterized in that: For single lateral avoidance, the triggering time of the avoidance action is as follows: Determine the expected lateral movement distance of the vehicle; Based on the determined expected lateral movement distance of the vehicle, the avoidance action triggering time corresponding to a single lateral avoidance is calculated.

5. The active lateral collision avoidance behavior decision-making method according to claim 4, characterized in that: When the relative speed between the vehicle and the target vehicle is less than the set speed, the maximum allowed lateral movement distance is used as the expected lateral movement distance of the vehicle; When the host vehicle's speed is greater than the target vehicle's, the expected lateral movement distance of the host vehicle is (ttc_AD - ttc_lat_collision) × v_vel_lat, where ttc_AD represents the time it takes for the rear corner of the host vehicle to meet the front corner of the target vehicle in the longitudinal direction on the opposite sides of the host vehicle. ttc_AD = s_AD / v_rel_long, where s_AD represents the distance in the axial direction between the rear corner of the host vehicle and the front corner of the target vehicle on the opposite sides of the host vehicle. v_rel_long represents the longitudinal relative phase velocity between the host vehicle and the target vehicle. When the host vehicle's speed is less than that of the target vehicle, the expected lateral movement distance of the host vehicle is (ttc_CB - ttc_lat_collision) × v_vel_lat – obj_length × sin(theta), where ttc_CB represents the time when the front angle of the host vehicle and the rear angle of the target vehicle meet in the longitudinal direction on the opposite sides of the host vehicle and the target vehicle, v_vel_lat represents the current relative lateral speed of the host vehicle and the target vehicle, theta represents the heading angle of the target vehicle relative to the host vehicle, ttc_lat_collision represents the lateral collision time between the host vehicle and the target vehicle, and ttc_lat_collision = d_lat / v_vel_lat, where d_lat represents the current lateral distance between the host vehicle and the target vehicle, and obj_length represents the length of the target vehicle.

6. The active lateral collision avoidance behavior decision-making method according to claim 1, characterized in that: The triggering time of the avoidance action corresponding to the combined horizontal and vertical avoidance is as follows: Under the set current expected lateral movement distance, the avoidance action trigger time corresponding to a single lateral avoidance is calculated, the longitudinal collision avoidance distance is corrected, and the avoidance action trigger time corresponding to a single longitudinal acceleration / deceleration avoidance is calculated; Determining the maximum time among the avoidance action triggering times calculated based on the current expected lateral movement distance as the final avoidance action triggering time corresponding to the current expected lateral movement distance; Determine whether the final avoidance action trigger time corresponding to the current expected lateral movement distance is greater than the final avoidance action trigger time corresponding to the previous expected lateral movement distance: If so, the final avoidance action triggering time corresponding to the previous expected lateral movement distance is used as the avoidance action triggering time corresponding to the lateral and longitudinal combined avoidance; If not, the expected lateral movement distance is set again by increasing the current expected lateral movement distance according to the set step size, and then the avoidance action trigger time is calculated again, the final avoidance action trigger time is determined, and the final avoidance action trigger time is judged, and the cycle continues.

7. The active lateral collision avoidance behavior decision-making method according to claim 1, characterized in that: The method of calculating the avoidance action trigger time and taking the avoidance strategy corresponding to the minimum avoidance action trigger time as the optimal avoidance strategy specifically includes: Get the corresponding avoidance action trigger time for single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance; Based on the judgment of the triggering time of each avoidance action, the avoidance strategy corresponding to the minimum avoidance action triggering time is taken as the optimal avoidance strategy.

8. An active lateral collision avoidance behavior decision-making device, characterized in that: The active lateral collision avoidance behavior decision-making device includes: A calculation module, which is used to calculate the avoidance action trigger time corresponding to each avoidance strategy of the vehicle to achieve the avoidance of the target vehicle based on the driving status of the vehicle and the target vehicle; A confirmation module is used to determine the avoidance strategy corresponding to the minimum avoidance action trigger time as the optimal avoidance strategy based on the avoidance action trigger time calculation result; The avoidance strategies include single longitudinal acceleration avoidance, single longitudinal deceleration avoidance, single lateral avoidance, and combined lateral and longitudinal avoidance.

9. An active lateral collision avoidance behavior decision-making device, characterized in that: The active lateral collision avoidance behavior decision device includes a processor, a memory, and an active lateral collision avoidance behavior decision program stored on the memory and executable by the processor, wherein when the active lateral collision avoidance behavior decision program is executed by the processor, the steps of the active lateral collision avoidance behavior decision method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an active lateral collision avoidance behavior decision program, wherein when the active lateral collision avoidance behavior decision program is executed by the processor, the steps of the active lateral collision avoidance behavior decision method as described in any one of claims 1 to 7 are implemented.

Images