Vehicle control method and apparatus, and vehicle

Abstract

A vehicle control method and apparatus. The vehicle control method comprises: when the traveling direction of an ego vehicle deviates, determining a predicted trajectory of the ego vehicle and a predicted trajectory of an obstacle vehicle (101); on the basis of the predicted trajectory of the ego vehicle and the predicted trajectory of the obstacle vehicle, determining whether there is a collision risk (102); and if it is determined that there is a collision risk, controlling the ego vehicle to keep traveling within a lane (103).

Description

Vehicle control methods, devices and vehicles

[0001] This application claims priority to Chinese patent application No. 202411207358.1, filed on August 29, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of automotive technology, and in particular to a vehicle control method, a vehicle control device, an electronic device, a vehicle, a computer program product, and a computer-readable storage medium. Background Technology

[0003] Safety has always been a focus for drivers and traffic safety researchers. In some driving scenarios, drivers may unknowingly or due to insufficient judgment cause their vehicles to deviate from their intended course. Therefore, vehicles are usually equipped with lane-keeping assist functions, which can help drivers keep the vehicle automatically within its lane in emergency situations. Summary of the Invention

[0004] This disclosure provides a vehicle control method to solve the problem in the related art where the lane keeping function of a vehicle is falsely triggered, resulting in a reduced driving experience and driving safety.

[0005] In a first aspect, a vehicle control method is provided, the method comprising:

[0006] When the vehicle deviates from its driving direction, the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle are determined.

[0007] Based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle, determine whether there is a collision risk;

[0008] If the aforementioned collision risk is determined, the vehicle is controlled to remain within the lane.

[0009] Secondly, a vehicle control device is provided, the device comprising:

[0010] The predicted trajectory determination module is used to determine the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle when the vehicle's driving direction deviates.

[0011] The collision risk determination module is used to determine whether there is a collision risk based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle.

[0012] The trajectory control module is used to control the vehicle to stay within the lane if the collision risk exists.

[0013] Thirdly, a computer-readable storage medium is provided, wherein instructions are stored therein, which, when executed on a computer, cause the computer to perform the vehicle control method described in any of the preceding aspects.

[0014] Fourthly, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the vehicle control method described in any of the preceding aspects.

[0015] Fifthly, a vehicle is provided that implements the vehicle control method described in any of the preceding aspects.

[0016] In some embodiments of this disclosure, when the vehicle deviates from its driving direction, the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle are determined. Based on the predicted trajectories of the vehicle and the obstacle vehicle, it is determined whether there is a collision risk. If a collision risk exists, the vehicle can remain within its lane. In some embodiments of this disclosure, when the vehicle deviates from its driving direction, the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle can be used to determine whether there is a collision risk. Therefore, when a collision risk exists, the vehicle can remain within its original lane to avoid false triggering of the vehicle avoidance system and lane keeping function, and to ensure the driver's driving safety and driving experience. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in some embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below.

[0018] Figure 1 is a flowchart of a vehicle control method according to some embodiments;

[0019] Figure 2 is a flowchart of a method for obtaining the collision risk between a vehicle and an obstacle vehicle according to some embodiments;

[0020] Figure 3 is a schematic diagram of a vehicle deviating from its lane in a scenario with oncoming traffic, according to some embodiments.

[0021] Figure 4 is a schematic diagram of a current moment lateral displacement calculation according to some embodiments;

[0022] Figure 5 is a schematic diagram of lateral displacement calculation at the end of longitudinal collision time TTC according to some embodiments;

[0023] Figure 6 illustrates a method for calculating the projected lateral distance Lat according to some embodiments. cur Long and projected longitudinal distance cur Flowchart;

[0024] Figure 7 is a schematic diagram of the calculation of the lateral and longitudinal distances projected by the obstacle vehicle onto the predicted deviation trajectory of the vehicle according to some embodiments;

[0025] Figure 8 is a flowchart of calculating the relative combined speed of an obstacle vehicle and a self-vehicle on a predicted trajectory of a self-vehicle, according to some embodiments.

[0026] Figure 9 is a schematic diagram of the relative velocity calculation between an obstacle vehicle and a self-propelled vehicle on a predicted trajectory of a self-propelled vehicle, according to some embodiments;

[0027] Figure 10 is a schematic diagram of vehicle relationships in a global coordinate system according to some embodiments;

[0028] Figure 11 is a schematic diagram of a longitudinal collision determination during a TTC time with both slow lateral and slow longitudinal speeds, according to some embodiments.

[0029] Figure 12 is a schematic diagram of a longitudinal collision determination during a TTC time with a slow lateral speed and a fast longitudinal speed, according to some embodiments.

[0030] Figure 13 is a schematic diagram of a longitudinal collision determination during a TTC time according to some embodiments, where the lateral speed is relatively fast and the longitudinal speed is relatively slow.

[0031] Figure 14 is a schematic diagram of a longitudinal collision determination during a TTC time according to some embodiments, where the lateral speed is relatively fast and the longitudinal speed is relatively fast.

[0032] Figure 15 is a block diagram of a vehicle control device according to some embodiments. Detailed Implementation

[0033] The technical solutions in some embodiments of this disclosure will now be described with reference to the accompanying drawings.

[0034] In related technologies, lane keeping function is usually activated when the vehicle approaches a pre-marked trigger line. However, this may lead to false triggering of the vehicle's lane keeping function, thereby reducing the driver's driving experience and driving safety.

[0035] To address the aforementioned problems, this disclosure provides a vehicle control method in some embodiments. As shown in FIG1, the method may include the following steps 101 to 103.

[0036] Step 101: When the driving direction of the vehicle deviates, determine the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle.

[0037] Step 102: Determine whether there is a collision risk based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle.

[0038] Step 103: If the collision risk is determined to exist, control the vehicle to keep it within the lane.

[0039] In some embodiments of this disclosure, while the vehicle is traveling within the lane, it is possible to detect in real time whether the vehicle's direction of travel has deviated. In practice, this can be determined by measuring the angle (deviation angle) between the vehicle's current direction of travel and the predetermined direction of travel, or by identifying whether the vehicle's current direction of travel deviates from the lane line of the lane in which the vehicle is currently located. Of course, in addition to the above methods, other methods can also be used to determine whether the vehicle's direction of travel has deviated, and this disclosure does not limit this to any particular method.

[0040] In some embodiments, when the vehicle's deviation angle exceeds a preset deviation angle, or when the vehicle's driving direction deviates from the lane line of the lane in which the vehicle is located, it can be determined that the vehicle's driving direction has deviated. When the vehicle's driving direction deviates, it can be determined whether there is a collision risk between the two based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle. Then, based on the collision risk, the vehicle's driving trajectory can be controlled, for example, controlling the vehicle to stay within the lane to avoid a collision between the two vehicles (the vehicle and the obstacle vehicle).

[0041] Here, the lane referred to in controlling the vehicle to stay within the lane can refer to the lane in which the vehicle is currently located when a collision risk is detected between the two vehicles deviating from its lane, or it can refer to the lane the vehicle was originally traveling in. Compared to related technologies that only refer to the driver's proximity to a pre-marked trigger line to determine whether to activate the lane-keeping function, some embodiments of this disclosure control the vehicle in a more precise way. By determining the predicted trajectories of the two vehicles, it is determined that the vehicle will only take corrective action when there is a risk of collision, thereby avoiding false triggering of the vehicle avoidance system and lane-keeping function, and ensuring the driver's driving safety and driving experience.

[0042] In some embodiments, in the case of oncoming vehicles, i.e., when there is an oncoming vehicle (obstacle vehicle) in the opposite lane relative to the direction of travel of the vehicle, the collision risk between the vehicle and the obstacle vehicle can be obtained. If there is a collision risk, the vehicle's trajectory can be corrected to move away from the obstacle vehicle to avoid a collision. Conversely, if there is no collision risk, the vehicle can continue to drive normally, or the driver can be reminded that there is an obstacle vehicle in the opposite lane.

[0043] In some embodiments, during overtaking, where there is a vehicle (obstacle vehicle) in the adjacent lane, the vehicle deviates from its lane towards the lane with the obstacle vehicle. In other words, if the vehicle and the obstacle vehicle are traveling in the same direction, and the vehicle deviates and moves towards the obstacle vehicle, the collision risk between the vehicle and the obstacle vehicle can be assessed. If there is a collision risk, the vehicle can be controlled to remain within its lane, thus moving away from the obstacle vehicle to avoid a collision. Conversely, if there is no collision risk, the vehicle continues to drive normally, or at least one of the following can be performed: alerting the driver to the presence of an obstacle vehicle in the adjacent lane, or alerting the driver when the vehicle deviates from its lane. Of course, the above scenarios are merely examples and are not limited to specific scenarios in actual applications.

[0044] In some embodiments of this disclosure, when the vehicle deviates from its driving direction, the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle are determined. Based on the predicted trajectories of the vehicle and the obstacle vehicle, it is determined whether there is a collision risk. If a collision risk is determined, the vehicle can be controlled to remain within the lane. In some embodiments of this disclosure, when the vehicle deviates from its driving direction, the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle can be used to determine whether there is a collision risk. This allows the vehicle to remain within its original lane when a collision risk exists, avoiding false triggering of the vehicle avoidance system and lane keeping function, and ensuring driver safety and driving experience.

[0045] In one embodiment of this disclosure, controlling the vehicle to remain within the lane if the collision risk is determined to exist includes:

[0046] If a collision risk is identified, the vehicle's emergency lane keeping assist function is activated to control the vehicle to stay within the lane and correct the vehicle's trajectory.

[0047] In implementation, vehicles typically have multiple vehicle functions to ensure driving safety. In some embodiments, the vehicle may have at least one of lane keeping functions such as Lane Keeping Assist (LKA) or Emergency Lane Keeping Assist (ELKA).

[0048] Here, the LKA function can monitor the relative position of the vehicle to the lane lines in real time, keeping the vehicle within the lane. The ELKA function can issue a real-time warning and correct the vehicle's course when it detects that the vehicle has unintentionally deviated from the lane edge or is about to collide with other vehicles in adjacent lanes, keeping the vehicle centered and avoiding danger in time.

[0049] Therefore, in some embodiments of this disclosure, when a collision risk is determined, the vehicle's lane keeping function, such as at least one of LKA or ELKA, can be automatically activated to ensure the driver's personal safety.

[0050] In practical applications, different vehicles have different lane keeping functions. For example, a vehicle may only have LKA function, only have ELKA function, or have both LKA and ELKA functions. The handling methods differ depending on the situation.

[0051] For example, assuming a vehicle is equipped only with ELKA (Elastic Collision Assist), a vehicle with ELKA can detect oncoming vehicles, vehicles traveling in the same direction, and other obstacles. If there is no risk of collision between the vehicle and the obstacle (including oncoming and same-direction vehicles), the vehicle can continue driving in its original direction, maintaining its original trajectory. If there is a risk of collision, the ELKA function is triggered, thus keeping the vehicle within its lane. It's important to note that the lane referred to here can be the lane where a collision risk is detected when deviation from the lane is detected, or it can refer to the lane the vehicle was originally traveling in.

[0052] For example, suppose the vehicle is only equipped with LKA (Lane Assist) function. Since LKA function only focuses on the vehicle and the lane markings, the vehicle does not have the function of detecting oncoming vehicles, vehicles traveling in the same direction, or other obstacles. Therefore, if there is no risk of collision between the vehicle and the obstacle vehicle, the vehicle can continue to drive in its driving direction, that is, maintain its original driving trajectory. If there is a risk of collision, LKA function is triggered, which can keep the vehicle driving within the lane.

[0053] For example, assuming the vehicle is equipped with both ELKA and LKA functions, if the vehicle deviates from its driving direction and no collision risk is detected between the vehicle and the obstacle vehicle, the vehicle can continue to deviate. If the vehicle does not deviate to the lane edge (lane line), the LKA function will not be triggered. If a collision risk is detected between the vehicle and the obstacle vehicle, the ELKA function will be triggered regardless of whether the vehicle has deviated to the lane edge. If a collision risk is detected between the vehicle and the obstacle vehicle, and the vehicle has deviated to the lane edge, both the ELKA and LKA functions will be triggered simultaneously to keep the vehicle within the lane.

[0054] Since some embodiments of this disclosure can accurately predict whether there is a collision risk between the vehicle and the obstacle vehicle, and trigger at least one of the ELKA function or LKA function when there is a collision risk, it can avoid the accidental triggering of at least one of the ELKA function or LKA function, thereby ensuring the driver's driving safety and driving experience while keeping the vehicle in its original lane when there is a collision risk.

[0055] In one embodiment of this disclosure, determining whether a collision risk exists based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle includes:

[0056] If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then at least one of the longitudinal collision time or the lateral collision time is determined based on the position information of the autonomous vehicle and the position information of the obstacle vehicle.

[0057] The existence of a collision risk is determined based on at least one of the longitudinal or lateral collision times.

[0058] In some embodiments of this disclosure, when the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle intersect, there may be a collision risk between the vehicle and the obstacle vehicle. At least one of the longitudinal collision time or the lateral collision time can be determined based on the position information of the vehicle and the obstacle vehicle, and then the existence of a collision risk can be determined based on at least one of the longitudinal collision time or the lateral collision time. For example, by predicting the trajectories of the two vehicles, and then determining whether the two vehicles intersect based on the predicted trajectories of the vehicle and the obstacle vehicle, in the scenario of oncoming vehicles, when the vehicle's driving direction deviates and deviates towards the trajectory of the oncoming vehicle, the trajectories of the two vehicles will intersect. If the predicted trajectory of the vehicle deviates from the trajectory of the obstacle vehicle or the predicted trajectory of the obstacle vehicle, the two vehicles may not intersect; the same applies to vehicles traveling in the same direction.

[0059] Here, longitudinal collision time refers to the time required for the two vehicles to collide in the longitudinal direction of the specified coordinate system, that is, the time required from the current moment until the expected collision occurs; lateral collision time refers to the time required for the two vehicles to collide in the lateral direction of the specified coordinate system, that is, the time required from the current moment until the expected collision occurs.

[0060] In some embodiments, the specified coordinate system can be either the vehicle's coordinate system or the global coordinate system. When calculating the collision risk between the vehicle and the obstacle vehicle, the coordinate system used for calculating the collision risk can be selected based on factors such as the vehicle's own performance (e.g., the number and type of data acquisition devices and the vehicle information collected). For example, the longitudinal collision time can be the time required for the two vehicles to collide in the longitudinal direction in either the vehicle's coordinate system or the global coordinate system, and the lateral collision time can be the time required for the two vehicles to collide in the lateral direction in either the vehicle's coordinate system or the global coordinate system.

[0061] In some embodiments, the existence of a collision risk can be determined based on at least one of the longitudinal collision time or the lateral collision time. For example, when the longitudinal collision time equals the lateral collision time, that is, the distance between the vehicle and the obstacle vehicle is analyzed by dividing it into lateral distance and longitudinal distance. The collision time determined by the lateral distance and the collision time determined by the longitudinal distance are used to determine whether the two vehicles meet at the same moment in both the lateral and longitudinal directions, i.e., whether a collision will occur at that moment. In some embodiments, the existence of a collision risk can also be determined by comparing the longitudinal collision time and the lateral collision time and setting a time threshold, or by calculating the difference between the longitudinal collision time and the lateral collision time and setting a preset threshold.

[0062] In one embodiment of this disclosure, determining whether a collision risk exists based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle includes:

[0063] If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then the projected longitudinal distance between the autonomous vehicle and the obstacle vehicle is determined based on the current position of the autonomous vehicle and the current position of the obstacle vehicle; the longitudinal collision time is determined based on the projected longitudinal distance and the relative longitudinal speed between the autonomous vehicle and the obstacle vehicle; and the risk of collision between the autonomous vehicle and the obstacle vehicle is determined based on the longitudinal collision time.

[0064] In some embodiments of this disclosure, when the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle intersect, there may be a collision risk between the vehicle and the obstacle vehicle. In this case, the projected longitudinal distance between the vehicle and the obstacle vehicle can be determined based on their current positions.

[0065] Here, the projected longitudinal distance can refer to the projected longitudinal distance between the obstacle vehicle and the vehicle at the current moment in the vehicle's coordinate system or global coordinate system, along the predicted trajectory of the vehicle in the longitudinal direction. In some embodiments, the projected longitudinal distance can be determined based on the current positions of the vehicle and the obstacle vehicle. The relative longitudinal velocity refers to the relative velocity between the vehicle and the obstacle vehicle in the longitudinal direction. Then, based on the longitudinal collision time, it can be determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

[0066] In some embodiments, a first preset threshold is set for the longitudinal collision time. This first preset threshold can be set based on parameters such as vehicle model and series, current driving environment (e.g., night or day, highway or non-highway), and driver (whether the driver is a novice and the length of time the driver has driven the vehicle). If the longitudinal collision time is less than or equal to the first preset threshold, a collision risk can be considered to exist; if the longitudinal collision time is greater than the first preset threshold, a collision risk can be considered not to exist.

[0067] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal collision time includes: determining the relative lateral displacement based on the longitudinal collision time and the relative lateral velocity between the vehicle and the obstacle vehicle; and determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the relative lateral displacement.

[0068] In some embodiments of this disclosure, the relative lateral displacement between the vehicle and the obstacle vehicle can be determined based on the longitudinal collision time and the relative lateral velocity between the vehicle and the obstacle vehicle. Here, the relative lateral velocity refers to the relative velocity between the vehicle and the obstacle vehicle in the lateral direction. Therefore, based on the longitudinal collision time and the relative lateral velocity, the relative lateral displacement, i.e., the relative displacement distance between the vehicle and the obstacle vehicle in the lateral direction, can be calculated. Then, based on the relative lateral displacement, it can be determined whether there is a collision risk between the vehicle and the obstacle vehicle. This considers the predicted trajectories of the two vehicles in both the lateral and longitudinal directions, improving the accuracy of the prediction and avoiding false triggering of the vehicle avoidance system.

[0069] In some embodiments, a second preset threshold can be set for relative lateral displacement. The second preset threshold can be set according to parameters such as vehicle model and series, current driving environment (e.g., night or day, highway or non-highway section) and driver (whether the driver is a novice driver, the length of time the driver has driven the vehicle). If the relative lateral displacement is less than or equal to the preset threshold, it can be considered that there is a collision risk. If the relative lateral displacement is greater than the preset threshold, it can be considered that there is no collision risk.

[0070] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the relative lateral displacement includes: determining the projected lateral distance between the vehicle and the obstacle vehicle based on the current position of the vehicle and the current position of the obstacle vehicle; and determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected lateral distance and the relative lateral displacement.

[0071] In some embodiments of this disclosure, the projected lateral distance between the vehicle and the obstacle vehicle can be determined based on their current positions. Here, the projected lateral distance can be the projected distance in the lateral direction between the obstacle vehicle and the vehicle in the vehicle's coordinate system or the global coordinate system. Based on the projected lateral distance and the relative lateral displacement, it can be determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

[0072] In some embodiments, if the projected lateral distance is less than or equal to the relative lateral displacement, it indicates that the distance between the vehicle and the obstacle vehicle in the lateral direction is zero or negative (e.g., negative 3 cm), and a collision risk can be considered to exist; if the projected lateral distance is greater than the relative lateral displacement, it indicates that the distance between the vehicle and the obstacle vehicle in the lateral direction is relatively far, and a collision risk can be considered not to exist.

[0073] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected lateral distance and the relative lateral displacement includes: determining the lateral overlap based on the projected lateral distance and the relative lateral displacement; and determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral overlap.

[0074] In some embodiments of this disclosure, the lateral overlap can be determined based on the projected lateral distance and the relative lateral displacement. Here, the lateral overlap refers to the degree of overlap between the vehicle and the obstacle vehicle in the lateral direction. Based on the lateral overlap, it can be determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

[0075] In some embodiments, a preset lateral overlap can be set for the lateral overlap. The preset lateral overlap can be set according to parameters such as vehicle model and series, current driving environment (e.g., night or day, highway or non-highway section) and driver (whether the driver is a novice driver, the length of time the driver has driven the vehicle).

[0076] If the lateral overlap is less than or equal to the preset lateral overlap, for example, less than or equal to zero, it can be determined that there is a collision risk between the vehicle and the obstacle vehicle; if the lateral overlap is greater than the preset lateral overlap, for example, greater than zero, it can be determined that there is no collision risk between the vehicle and the obstacle vehicle.

[0077] In one embodiment of this disclosure, determining the lateral overlap based on the projected lateral distance and the relative lateral displacement includes: determining the inner lateral overlap based on the relative lateral displacement and the projected lateral distance; and determining the outer lateral overlap based on the relative lateral displacement, the projected lateral distance, and the width of the obstacle vehicle.

[0078] Here, lateral overlap can include: inner lateral overlap and outer lateral overlap. Inner lateral overlap refers to the degree of lateral overlap between the vehicle and the obstacle vehicle in the lateral direction. That is, inner lateral overlap can be used to represent the degree of lateral overlap between the vehicle and the obstacle vehicle at the initial moment, or it can be used to represent the overlap when the two vehicles are moving along their respective trajectories and tending to approach each other in the lateral direction. Inner lateral overlap can be determined based on relative lateral displacement and projected lateral distance. In some embodiments, inner lateral overlap is equal to the difference between projected lateral distance and relative lateral displacement. When the relative lateral displacement is less than the projected lateral distance, that is, when inner lateral overlap is greater than 0, it indicates that the vehicle still has distance relative to the obstacle vehicle in the lateral direction, meaning there is no risk of collision between the two vehicles in the lateral direction. Lateral overlap refers to the degree of lateral overlap between the vehicle and the obstacle vehicle at the predicted intersection time (i.e., the time to reach longitudinal collision). Lateral overlap indicates whether the lateral displacement of the vehicle and the obstacle vehicle at the time of longitudinal collision has exceeded the lateral displacement of the obstacle vehicle. In other words, it ensures that when the inner lateral overlap of the vehicle and the obstacle vehicle indicates a collision risk, the lateral overlap is calculated to comprehensively determine whether a collision risk exists. Lateral overlap can be determined based on lateral displacement, projected lateral distance, and the width of the obstacle vehicle. In some embodiments, lateral overlap is equal to the difference between the relative lateral displacement and the projected lateral distance and the width of the obstacle vehicle. That is, it is necessary to determine whether the relative lateral displacement of the two vehicles is greater than the sum of the projected lateral distance and the width of the obstacle vehicle. When the relative lateral displacement is greater than the sum of the projected lateral distance and the width of the obstacle vehicle, it indicates that the vehicle has already surpassed the obstacle vehicle in the lateral direction, meaning that at the time of longitudinal collision, the lateral displacement of the vehicle has exceeded that of the obstacle vehicle, and there is no collision risk. In some embodiments, if the projected lateral distance is determined based on the lateral distance between the vehicle and the obstacle vehicle and the width of the two vehicles, then the width of the vehicle needs to be considered in conjunction with the lateral distance of the vehicle.

[0079] It should be noted that vehicle width refers to the width of the vehicle body. Vehicle width is usually a fixed value measured when the vehicle is traveling straight. However, when the vehicle is tilted, such as when the vehicle is tilting towards an obstacle vehicle, it is not accurate to predict the collision risk directly based on the vehicle width. Therefore, some embodiments of this disclosure can combine the steering angles of the vehicle and the obstacle vehicle to determine the vehicle width used to predict the collision risk, so as to further improve the accuracy of the collision risk prediction.

[0080] In one embodiment of this disclosure, determining the inner lateral overlap based on the relative lateral displacement and the projected lateral distance includes: determining the inner lateral overlap between the vehicle and the obstacle vehicle based on the relative lateral displacement, the projected lateral distance, and a first safety margin. Determining the outer lateral overlap based on the relative lateral displacement, the projected lateral distance, and the obstacle vehicle's width includes: determining the outer lateral overlap between the vehicle and the obstacle vehicle based on the relative lateral displacement, the projected lateral distance, a second safety margin, and the obstacle vehicle's width.

[0081] In practical applications, to further ensure driver safety, when calculating the inner and outer lateral overlap, a preset safety margin can be added for comprehensive calculation based on actual needs. In some embodiments, a first safety margin can be added to calculate the inner lateral overlap, i.e., the inner lateral overlap is calculated based on the first safety margin, relative lateral displacement, and projected lateral distance. In some embodiments, a second safety margin can be added to calculate the outer lateral overlap, i.e., the outer lateral overlap is determined based on the second safety margin, relative lateral displacement, projected lateral distance, and the width of the obstacle vehicle.

[0082] Here, the first safety margin and the second safety margin can be set according to actual needs. The values ​​of the first safety margin and the second safety margin can be the same or different.

[0083] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral overlap includes: if it is determined that the inner lateral overlap and the outer lateral overlap are respectively less than or equal to zero, then it is determined that there is a collision risk between the vehicle and the obstacle vehicle.

[0084] In some embodiments of this disclosure, if the inner lateral overlap and the outer lateral overlap are both less than or equal to zero, it indicates that the lateral distance between the vehicle and the obstacle vehicle is less than or equal to zero at both the initial moment and the time of longitudinal collision. In other words, if the two vehicles overlap at both the initial moment and the time of longitudinal collision in the lateral direction, it can be determined that there is a risk of collision between the vehicle and the obstacle vehicle. In this case, the driver can be alerted to move away from the obstacle vehicle, or the vehicle's trajectory can be automatically controlled to move away from the obstacle vehicle.

[0085] In one embodiment of this disclosure, the method may further include: determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal collision time and a preset longitudinal collision time threshold.

[0086] In some embodiments of this disclosure, the preset longitudinal collision time threshold can be set based on parameters such as vehicle type and model, current driving environment (e.g., night or day, highway or non-highway), and driver (whether a novice driver, duration of driving experience). If the longitudinal collision time is less than the preset longitudinal collision time threshold, the vehicle and the obstacle vehicle may collide in the longitudinal direction within a short period of time, which can be considered as a collision risk.

[0087] As described above, some embodiments of this disclosure, when determining whether there is a collision risk between the vehicle and the obstacle vehicle in the longitudinal direction, can judge the existence of a collision risk by considering the displacement of the vehicle and the obstacle vehicle in the lateral direction, which can improve the accuracy of collision risk assessment. Some embodiments of this disclosure can also consider ensuring that when there is a collision risk between the vehicle and the obstacle vehicle in the longitudinal direction, there is also a lateral collision risk during the longitudinal collision time. In this case, the longitudinal collision time can be combined to comprehensively determine whether there is a collision risk, thereby improving the accuracy of collision risk assessment, avoiding the triggering of vehicle avoidance maneuvers, improving driving safety, and enhancing the robustness of the system.

[0088] In some embodiments of this disclosure, when determining whether there is a collision risk between the vehicle and the obstacle vehicle in the lateral direction, the displacement of the vehicle and the obstacle vehicle in the longitudinal direction can be used to determine whether there is a collision risk, which can improve the accuracy of the collision risk assessment.

[0089] In one embodiment of this disclosure, determining whether a collision risk exists based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle further includes:

[0090] If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then the projected lateral distance is determined based on the current position of the autonomous vehicle and the current position of the obstacle vehicle; the lateral collision time is determined based on the projected lateral distance and relative lateral velocity of the autonomous vehicle and the obstacle vehicle; and the risk of collision between the autonomous vehicle and the obstacle vehicle is determined based on the lateral collision time.

[0091] In some embodiments of this disclosure, when the predicted trajectories of the autonomous vehicle and the obstacle vehicle intersect, a collision risk may exist between them. The projected lateral distance between the autonomous vehicle and the obstacle vehicle can then be determined based on their current positions. Here, the projected lateral distance can refer to the projected distance in the lateral direction of the obstacle vehicle's predicted trajectory on the autonomous vehicle's coordinate system or global coordinate system, representing the lateral distance between the autonomous vehicle and the obstacle vehicle at the current moment. In some embodiments, the projected lateral distance can be determined based on the current positions of the autonomous vehicle and the obstacle vehicle. The relative lateral velocity refers to the relative velocity between the autonomous vehicle and the obstacle vehicle in the lateral direction. Then, based on the lateral collision time, it can be determined whether a collision risk exists between the autonomous vehicle and the obstacle vehicle.

[0092] In some embodiments, a third preset threshold is set for the lateral collision time. This third preset threshold can be set according to parameters such as vehicle model and series, current driving environment (e.g., night or day, highway or non-highway section), and driver (whether the driver is a novice driver, the length of time the driver has driven the vehicle). If the lateral collision time is less than or equal to the third preset threshold, it can be considered that there is a collision risk; if the lateral collision time is greater than the third preset threshold, it can be considered that there is no collision risk.

[0093] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral collision time includes: determining the relative longitudinal displacement based on the lateral collision time and the relative longitudinal velocity between the vehicle and the obstacle vehicle; and determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the relative longitudinal displacement.

[0094] In some embodiments of this disclosure, the relative longitudinal displacement between the vehicle and the obstacle vehicle can be determined based on the lateral collision time and the relative longitudinal velocity between the vehicle and the obstacle vehicle. Here, the relative longitudinal velocity refers to the relative velocity between the vehicle and the obstacle vehicle in the longitudinal direction. Therefore, the relative longitudinal displacement, i.e., the relative displacement distance between the vehicle and the obstacle vehicle in the longitudinal direction, can be calculated based on the lateral collision time and the relative longitudinal velocity. Then, based on the relative longitudinal displacement, it can be determined whether there is a risk of collision between the vehicle and the obstacle vehicle. This means that the predicted states of the two vehicles in both the lateral and longitudinal directions are considered on the predicted trajectory, improving the accuracy of the prediction and avoiding false triggering of the vehicle avoidance system.

[0095] In some embodiments, a fourth preset threshold can be set for relative longitudinal displacement. The fourth preset threshold can be set according to parameters such as vehicle model and series, current driving environment (e.g., night or day, highway or non-highway section) and driver (whether the driver is a novice driver, the length of time the driver has driven the vehicle). If the relative longitudinal displacement is less than or equal to the fourth preset threshold, it can be considered that there is a collision risk. If the relative longitudinal displacement is greater than the fourth preset threshold, it can be considered that there is no collision risk.

[0096] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the relative longitudinal displacement includes: determining the projected longitudinal distance between the vehicle and the obstacle vehicle based on the current position of the vehicle and the current position of the obstacle vehicle; and determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected longitudinal distance and the relative longitudinal displacement.

[0097] In some embodiments of this disclosure, the projected longitudinal distance between the vehicle and the obstacle vehicle can be determined based on their current positions. Here, the projected longitudinal distance can be the projected distance in the longitudinal direction between the obstacle vehicle and the vehicle in the vehicle's coordinate system or the global coordinate system. Based on the projected longitudinal distance and the relative longitudinal displacement, it can be determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

[0098] In some embodiments, if the projected longitudinal distance is less than or equal to the relative longitudinal displacement, it means that the distance between the vehicle and the obstacle vehicle in the longitudinal direction is zero or negative (e.g., negative 3 cm), and a collision risk can be considered to exist; if the projected longitudinal distance is greater than the relative longitudinal displacement, the distance between the vehicle and the obstacle vehicle in the longitudinal direction is relatively far, and a collision risk can be considered not to exist.

[0099] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected longitudinal distance and the relative longitudinal displacement includes: determining the longitudinal overlap based on the projected longitudinal distance and the relative longitudinal displacement; and determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal overlap.

[0100] In some embodiments of this disclosure, the longitudinal overlap can be determined based on the projected longitudinal distance and the relative longitudinal displacement. Here, the longitudinal overlap refers to the degree of overlap between the vehicle and the obstacle vehicle in the longitudinal direction. Based on the longitudinal overlap, it can be determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

[0101] In some embodiments, a preset longitudinal overlap can be set for the longitudinal overlap. The preset longitudinal overlap can be set according to parameters such as vehicle model and series, current driving environment (e.g., night or day, highway or non-highway section, etc.) and driver (whether it is a novice driver, the length of time the driver has been driving the vehicle).

[0102] If the longitudinal overlap is less than or equal to the preset longitudinal overlap, for example, less than or equal to zero, it can be determined that there is a collision risk between the vehicle and the obstacle vehicle; if the longitudinal overlap is greater than the preset longitudinal overlap, for example, greater than zero, it can be determined that there is no collision risk between the vehicle and the obstacle vehicle.

[0103] In one embodiment of this disclosure, the longitudinal overlap includes: inner longitudinal overlap and outer longitudinal overlap.

[0104] The step of determining the longitudinal overlap based on the projected longitudinal distance and relative longitudinal displacement includes:

[0105] The inner longitudinal overlap is determined based on the relative longitudinal displacement and the projected longitudinal distance;

[0106] The outer longitudinal overlap is determined based on the relative longitudinal displacement, the projected longitudinal distance, and the length of the obstacle vehicle.

[0107] Here, longitudinal overlap can include: inner longitudinal overlap and outer longitudinal overlap.

[0108] Here, the inner longitudinal overlap refers to the degree of longitudinal overlap between the vehicle and the obstacle vehicle at the initial moment. It can also be used to represent the overlap when the two vehicles are moving along their respective trajectories and tending to approach each other in the longitudinal direction. The inner longitudinal overlap can be determined based on the relative longitudinal displacement and the projected longitudinal distance. In some embodiments, the inner longitudinal overlap is equal to the difference between the projected longitudinal distance and the relative longitudinal displacement. When the relative longitudinal displacement is less than the projected longitudinal distance, that is, when the inner longitudinal overlap is greater than 0, it means that there is still a distance between the vehicle and the obstacle vehicle in the longitudinal direction, and that is, there is no risk of collision between the two vehicles in the longitudinal direction.

[0109] The outer longitudinal overlap refers to the degree of longitudinal overlap between the vehicle and the obstacle vehicle at the predicted intersection time (i.e., the time to lateral collision). It indicates whether the longitudinal displacement of the vehicle and the obstacle vehicle at the time of longitudinal collision has exceeded the longitudinal displacement of the obstacle vehicle. In other words, it ensures that when the inner longitudinal overlap of the vehicle and the obstacle vehicle indicates a collision risk, the outer longitudinal overlap is calculated to comprehensively determine whether a collision risk exists. The outer longitudinal overlap can be determined based on lateral displacement, projected longitudinal distance, and the length of the obstacle vehicle. In some embodiments, the outer longitudinal overlap is equal to the difference between the relative longitudinal displacement and the projected longitudinal distance and the length of the obstacle vehicle. That is, it is necessary to determine whether the relative longitudinal displacement of the two vehicles is greater than the sum of the projected longitudinal distance and the length of the obstacle vehicle. When the relative longitudinal displacement is greater than the sum of the projected longitudinal distance and the length of the obstacle vehicle, it indicates that the vehicle has already surpassed the obstacle vehicle in the longitudinal direction. This means that at the time of lateral collision, the vehicle's longitudinal displacement has exceeded that of the obstacle vehicle, and there is no collision risk.

[0110] In some embodiments, if the projected longitudinal distance is determined based on the distance between the vehicle and the obstacle vehicle and the lengths of the two vehicles, then it is necessary to make a comprehensive judgment by combining the length of the vehicle.

[0111] It is important to note that vehicle length is a fixed value measured when the vehicle is traveling straight. However, when the vehicle is tilted, such as when it is tilting towards an obstacle, directly predicting collision risk based on vehicle length is not accurate. Therefore, some embodiments of this disclosure can combine the steering angles of the vehicle and the obstacle to determine the vehicle length used for predicting collision risk, thereby further improving the accuracy of collision risk prediction.

[0112] In one embodiment of this disclosure, determining the inner longitudinal overlap based on the relative longitudinal displacement and the projected longitudinal distance includes: determining the inner longitudinal overlap between the vehicle and the obstacle vehicle based on the relative longitudinal displacement, the projected longitudinal distance, and a third safety margin. Determining the outer longitudinal overlap based on the relative longitudinal displacement, the projected longitudinal distance, and the length of the obstacle vehicle includes: determining the outer longitudinal overlap between the vehicle and the obstacle vehicle based on the relative longitudinal displacement, the projected longitudinal distance, a fourth safety margin, and the length of the obstacle vehicle.

[0113] In practical applications, to further ensure driver safety, when calculating the inner and outer longitudinal overlap, a preset safety margin can be added for comprehensive calculation based on actual needs. In some embodiments, a third safety margin can be added to calculate the inner longitudinal overlap, i.e., the inner longitudinal overlap is calculated based on the third safety margin, relative longitudinal displacement, and projected longitudinal distance. A fourth safety margin can be added to calculate the outer longitudinal overlap, i.e., the outer longitudinal overlap is determined based on the fourth safety margin, relative longitudinal displacement, projected longitudinal distance, and the length of the obstacle vehicle. Here, the third and fourth safety margins can be set according to actual needs, and their values ​​can be the same or different.

[0114] In one embodiment of this disclosure, determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal overlap includes: if it is determined that the inner longitudinal overlap and the outer longitudinal overlap are respectively less than or equal to zero, then it is determined that there is a collision risk between the vehicle and the obstacle vehicle.

[0115] In some embodiments of this disclosure, if the inner longitudinal and lateral overlap and the outer longitudinal overlap are both less than or equal to zero, it means that at the initial moment and at the moment of the lateral collision, the distance between the vehicle and the obstacle vehicle in the longitudinal direction is less than or equal to zero. In other words, the two vehicles overlap in the longitudinal direction at both the initial moment and the moment of the lateral collision. It can be determined that there is a risk of collision between the vehicle and the obstacle vehicle. At this time, the driver can be reminded to stay away from the obstacle vehicle, or the vehicle's driving trajectory can be automatically controlled to stay away from the obstacle vehicle.

[0116] In one embodiment of this disclosure, the method may further include: determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral collision time and a preset lateral collision time threshold.

[0117] In some embodiments of this disclosure, the preset lateral collision time threshold can be set based on parameters such as vehicle type and model, current driving environment (e.g., night or day, highway or non-highway), and driver (whether a novice driver, duration of driving experience). If the lateral collision time is less than the preset lateral collision time threshold, the vehicle and the obstacle vehicle may collide in the lateral direction within a short period of time, which can be considered a collision risk.

[0118] As can be seen from the foregoing, some embodiments of this disclosure can determine whether there is a collision risk between the vehicle and the obstacle vehicle in the lateral direction by measuring the displacement of the vehicle and the obstacle vehicle in the longitudinal direction, which can improve the accuracy of the collision risk assessment.

[0119] In summary, some embodiments of this disclosure can determine whether there is a collision risk between the vehicle and the obstacle vehicle in the longitudinal direction by assessing their displacement in the lateral direction. Some embodiments of this disclosure can also determine whether there is a collision risk between the vehicle and the obstacle vehicle in the lateral direction by assessing their displacement in the longitudinal direction. Of course, both methods can be combined to comprehensively determine the existence of a collision risk, and this disclosure does not impose any limitations on this approach.

[0120] In one embodiment of this disclosure, determining whether a collision risk exists based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle further includes: if it is determined that the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle intersect, then determining the projected longitudinal distance and projected lateral distance between the vehicle and the obstacle vehicle based on the current position of the vehicle and the current position of the obstacle vehicle; determining the longitudinal collision time based on the projected longitudinal distance; determining the lateral collision time based on the projected lateral distance; and determining whether a collision risk exists based on the longitudinal collision time and the lateral collision time.

[0121] In some embodiments of this disclosure, when the predicted trajectories of the autonomous vehicle and the obstacle vehicle intersect, a collision risk may exist between them. In this case, the projected longitudinal distance and projected lateral distance between the autonomous vehicle and the obstacle vehicle can be determined based on their current positions. Then, the longitudinal collision time in the longitudinal direction is determined based on the projected longitudinal distance, and the lateral collision time in the lateral direction is determined based on the projected lateral distance. Based on the longitudinal and lateral collision times, it can be determined whether the autonomous vehicle and the obstacle vehicle can simultaneously reach the collision point in both directions. In some embodiments, if the longitudinal and lateral collision times are the same or their difference is within a preset range, a collision risk between the autonomous vehicle and the obstacle vehicle can be considered present.

[0122] In one embodiment of this disclosure, determining the longitudinal collision time based on the projected longitudinal distance includes: determining the longitudinal collision time based on the projected longitudinal distance and relative longitudinal velocity of the vehicle and the obstacle vehicle; determining the lateral collision time based on the projected lateral distance includes: determining the lateral collision time based on the projected lateral distance and relative lateral velocity of the vehicle and the obstacle vehicle.

[0123] In some embodiments of this disclosure, the longitudinal collision time can be determined based on the projected longitudinal distance and relative longitudinal velocity of the vehicle and the obstacle vehicle, and the lateral collision time can be determined based on the projected lateral distance and relative lateral velocity of the vehicle and the obstacle vehicle. In some embodiments, when calculating the longitudinal or lateral collision time, safety margins (e.g., a first safety margin, a second safety margin, a third safety margin, and a fourth safety margin) can also be used to further ensure the driver's personal safety. In one embodiment of this disclosure, the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle can be determined as follows: obtaining vehicle information of the vehicle and vehicle information of the obstacle vehicle; the vehicle information of the vehicle includes at least the heading and position of the vehicle, and the vehicle information of the obstacle vehicle includes at least the heading and position of the obstacle vehicle; calculating the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle based on the vehicle information of the vehicle and the vehicle information of the obstacle vehicle.

[0124] Here, the vehicle information for both the autonomous vehicle and the obstacle vehicle can include heading and position. Of course, the vehicle information for both can also include parameters such as speed and acceleration. In practical applications, vehicles are generally equipped with data acquisition devices such as cameras, radar, and sensors. Therefore, vehicle information for both the autonomous vehicle and the obstacle vehicle can be collected through these devices without incurring additional costs.

[0125] In some embodiments of this disclosure, the predicted trajectories of the vehicle and the obstacle vehicle can be calculated based on the heading and position of the vehicle and the heading and position of the obstacle vehicle, respectively. Then, based on whether the predicted trajectories of the vehicle and the obstacle vehicle intersect, it can be predicted whether there is a collision risk between the vehicle and the obstacle vehicle. If the predicted trajectories intersect, the collision risk can be further determined by combining the data of the vehicle and the obstacle vehicle in the lateral and longitudinal directions.

[0126] In one embodiment of this disclosure, the method includes: determining the relative longitudinal speed and the relative lateral speed based on the speed of the vehicle and the speed of the obstacle vehicle.

[0127] In some embodiments of this disclosure, the relative longitudinal speed of the vehicle and the obstacle vehicle in the longitudinal direction, and the relative lateral speed in the lateral direction, can be determined based on the speed of the vehicle and the speed of the obstacle vehicle.

[0128] In one embodiment of this disclosure, determining the relative longitudinal speed and the relative lateral speed based on the speed of the vehicle and the speed of the obstacle vehicle includes: determining the lateral speed and longitudinal speed of the vehicle and the lateral speed and longitudinal speed of the obstacle vehicle based on the speed of the vehicle and the speed of the obstacle vehicle, respectively; and determining the relative longitudinal speed and the relative lateral speed based on the lateral speed and longitudinal speed of the vehicle and the lateral speed and longitudinal speed of the obstacle vehicle, respectively.

[0129] In some embodiments of this disclosure, the speed of the vehicle can be determined by its lateral component and its longitudinal component. Similarly, the speed of the obstacle vehicle can be determined by its lateral component and its longitudinal component. Then, a relative longitudinal speed can be determined based on the lateral speeds of the vehicle and the obstacle vehicle, and a relative lateral speed can be determined based on the longitudinal speeds of both vehicles.

[0130] In one embodiment of this disclosure, determining whether there is a collision risk based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle further includes: if it is determined that the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle do not intersect, then it is determined that there is no collision risk.

[0131] In some embodiments of this disclosure, when the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle do not intersect, it can be determined that there is no risk of collision between the vehicle and the obstacle vehicle, and no subsequent related calculation steps are required, thus reducing unnecessary waste of computing resources.

[0132] In another embodiment of this disclosure, the method further includes maintaining the vehicle's driving trajectory if it is determined that there is no risk of collision.

[0133] In some embodiments of this disclosure, when it is determined that there is no risk of collision, the current driving trajectory of the vehicle is maintained, or the driver of the vehicle is reminded that there is an obstacle vehicle nearby that needs to be noticed.

[0134] In one embodiment of this disclosure, the relative longitudinal velocity and relative lateral velocity can also be determined based on the relative resultant velocity. The method may further include: calculating the relative resultant velocity of the vehicle and the obstacle vehicle on the predicted trajectory of the vehicle; and determining the relative longitudinal velocity and relative lateral velocity of the vehicle in the vehicle coordinate system based on the relative resultant velocity.

[0135] Here, the relative resultant velocity refers to the combined velocity of the relative vehicular velocity (which can be determined based on the vehicular velocity and the obstacle velocity) on the predicted trajectory of the vehicular vehicle. Therefore, based on the relative resultant velocity, the relative longitudinal velocity in the longitudinal direction and the relative lateral velocity in the lateral direction can be separated.

[0136] It should be noted that the relative longitudinal velocity and the relative lateral velocity can be obtained based on the vehicle coordinate system or based on the global coordinate system, and this disclosure does not impose any restrictions on this.

[0137] It should be noted that the relative longitudinal velocity, relative lateral velocity, and relative resultant velocity can be obtained based on the vehicle coordinate system or based on the global coordinate system, and this disclosure does not impose any restrictions on this.

[0138] Subsequently, after calculating the relative longitudinal velocity and relative lateral velocity through the relative resultant velocity, the longitudinal collision time can be determined based on the projected longitudinal distance and relative longitudinal velocity of the vehicle and the obstacle vehicle, and the lateral collision time can be determined based on the projected lateral distance and relative lateral velocity of the vehicle and the obstacle vehicle.

[0139] To enable those skilled in the art to better understand the embodiments of this disclosure, the following example illustrates the implementation process of this disclosure by determining whether there is a collision risk between the vehicle and the obstacle vehicle in the longitudinal direction through the displacement of the vehicle and the obstacle vehicle in the lateral direction. Of course, some embodiments of this disclosure are not limited to this. If the determination of whether there is a collision risk between the vehicle and the obstacle vehicle in the lateral direction is based on the displacement of the vehicle and the obstacle vehicle in the longitudinal direction, only adaptive substitutions to the relevant data in the following embodiments are needed. For example, the vehicle width can be replaced with the vehicle length, and the lateral direction can be replaced with the longitudinal direction, etc.

[0140] Figure 2 is a flowchart of a method for obtaining the collision risk of a vehicle and an obstacle vehicle according to some embodiments. As shown in Figure 2, the method for obtaining the collision risk of a vehicle and an obstacle vehicle may include steps 201 to 206.

[0141] Step 201: Obtain vehicle information for the vehicle itself and vehicle information for the obstacle vehicle.

[0142] In practice, the vehicle is equipped with data acquisition devices such as cameras, radar, and sensors, which can collect vehicle information of both the vehicle itself and oncoming vehicles.

[0143] Figure 3 is a schematic diagram of a vehicle deviating from its lane in a scenario with oncoming vehicles, according to some embodiments. As shown in Figure 3, from top to bottom are the obstacle vehicle and the vehicle. Based on the vehicle's camera and front radar, the vehicle information such as the vehicle's heading, position, speed and acceleration can be obtained, as well as the vehicle information such as the heading, position, speed and acceleration of the obstacle vehicle in front.

[0144] In Figure 3, v e v is the speed of the vehicle. e,y v is the lateral velocity of the vehicle. e,x v is the longitudinal velocity of the vehicle. o v is the speed of the obstacle vehicle. o,y v is the lateral velocity of the obstacle vehicle. o,x Let Lat be the longitudinal velocity of the obstacle vehicle, Lat be the relative lateral distance between the obstacle vehicle and the vehicle in the vehicle's coordinate system, and Long be the relative longitudinal distance between the obstacle vehicle and the vehicle in the vehicle's coordinate system.

[0145] Step 202: Calculate the predicted trajectories of the self-vehicle and the obstacle vehicle based on the vehicle information of the self-vehicle and the vehicle information of the obstacle vehicle, respectively.

[0146] In some embodiments of this disclosure, a predicted trajectory of the vehicle can be calculated based on the vehicle's information (e.g., heading and position), and then the predicted trajectory can be used to determine whether the vehicle is deviating from the obstacle vehicle. The predicted trajectory can also be referred to as a turning path. In some embodiments, a predicted trajectory of the obstacle vehicle can be calculated based on the obstacle vehicle's information (e.g., heading and position).

[0147] Step 203: Calculate the relative combined speed, projected lateral distance, and projected longitudinal distance between the vehicle and the obstacle vehicle.

[0148] In some embodiments of this disclosure, the relative resultant velocity vlong,rel,cur of the vehicle and the obstacle vehicle, and the projected longitudinal distance Long of the relative longitudinal distance Long between the obstacle vehicle and the vehicle in the vehicle coordinate system onto the longitudinal direction are calculated. cur And the projected lateral distance Lat, the relative lateral distance between the obstacle vehicle and the vehicle in the vehicle coordinate system, onto the lateral direction. cur .

[0149] Step 204: Calculate the longitudinal collision time based on the projected longitudinal distance and the relative resultant velocity.

[0150] In some embodiments of this disclosure, the projected longitudinal distance Long can be obtained by projecting the relative longitudinal distance Long onto the longitudinal direction. cur And the longitudinal collision time vlong,rel,cur is calculated using the relative resultant velocity vlong,rel,cur.

[0151] In some embodiments, the formula for calculating the longitudinal collision time TTC of the vehicle and the obstacle vehicle projected on the predicted trajectory is formula (1).

[0152] Step 205: Calculate the lateral overlap between the vehicle and the obstacle vehicle based on the longitudinal collision time and the projected lateral distance.

[0153] Step 206: Based on the longitudinal collision time, the preset longitudinal collision time threshold, and the lateral overlap, predict the collision risk between the vehicle and the obstacle vehicle.

[0154] In some embodiments of this disclosure, the lateral overlap between the vehicle and the obstacle vehicle can be calculated based on the longitudinal collision time (TTC), and then, based on the longitudinal collision time (TTC), a preset longitudinal collision time threshold, and the lateral overlap, the risk of collision between the vehicle and the obstacle vehicle can be predicted.

[0155] In some embodiments, the lateral overlap may include the inner lateral overlap c at the current moment and the outer lateral overlap C at the longitudinal collision time TTC. In this case, some embodiments of the present disclosure may predict whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal collision time TTC, a preset longitudinal collision time threshold, the inner lateral overlap c, and the outer lateral overlap C.

[0156] Figure 4 is a schematic diagram of current overlap calculation according to some embodiments, and Figure 5 is a schematic diagram of lateral overlap calculation at the end of longitudinal collision time (TTC) according to some embodiments. As shown in Figures 4 and 5, the collision risk assessment of the two vehicles (the vehicle and the obstacle vehicle) can currently be based on the overlap between the two vehicles. This will bring two problems: first, judging based only on information after the incident will cause a delay in processing speed; second, even if the lateral displacement of the vehicle at the current moment meets the safety threshold, it does not mean that the lateral displacement of the vehicle throughout the entire vehicle-vehicle intersection process meets the safety threshold. Lateral displacement judgment is performed for lateral and longitudinal decoupling. Since the two vehicles have an initial lateral distance, it is necessary to determine whether the lateral displacement of the two vehicles is also zero when the longitudinal distance between the two vehicles is zero. If so, it can be determined that there is a collision risk between the two vehicles. In some embodiments, the formula for calculating the lateral displacement (inner lateral overlap c) at the initial moment can be formula (2). c = dW e / 2-W o / 2-2·Buffer-TTC·v lat,rel (2)

[0157] Where d is the projected lateral distance Lat between the obstacle vehicle and the vehicle in the vehicle coordinate system given by the perception. cur W e W is the width of the car. oThe width of the obstacle vehicle is denoted by v, and Buffer is the set safety margin. lat,rel The relative lateral speeds of the two vehicles are given.

[0158] If the lateral overlap between the two vehicles is less than or equal to 0, it means that there is a risk of collision between the two vehicles considering the safety margin. In this case, the vehicle's trajectory should be controlled to deviate from the obstacle vehicle. Since the initial collision or non-collision between the two vehicles does not mean that there is no risk of collision during the entire deviation process (the vehicle completely deviates from one side of the obstacle vehicle to the other side of the obstacle vehicle), it is necessary to determine whether the overlap on the other side (lateral overlap C) meets the safety requirements when the longitudinal distance between the two vehicles is zero, based on state prediction. In some embodiments, the formula for calculating the lateral overlap C can be formula (3). C = TTC·v lat,rel -W e / 2-dW o / 2-2·Buffer (3)

[0159] Where C represents the outer lateral overlap, W e W is the width of the car. o d represents the width of the obstacle vehicle, Buffer represents the set safety margin, d represents the projected lateral distance between the obstacle vehicle and the vehicle in the vehicle's coordinate system provided by the perception, and v represents the width of the obstacle vehicle. lat,rel The relative lateral speeds of the two vehicles are given.

[0160] If the overlap C between the outer sides of the two vehicles is less than or equal to 0, it means that there is a risk of collision between the two vehicles considering the safety margin. In this case, the vehicle's trajectory should be controlled to deviate from the obstacle vehicle. If c > 0 and C > 0, that is, at the start and end of the longitudinal collision time TTC, there is no risk of collision between the vehicle and the obstacle vehicle.

[0161] In some embodiments of this disclosure, vehicle information of the vehicle and vehicle information of the obstacle vehicle (oncoming vehicle) are obtained. A predicted trajectory of the vehicle is calculated based on the vehicle information, and the relative combined velocity, projected lateral distance, and relative longitudinal distance between the vehicle and the obstacle vehicle are calculated along the predicted trajectory. The longitudinal collision time can then be calculated based on the relative longitudinal distance and relative combined velocity. The lateral displacement of the vehicle and the obstacle vehicle is calculated based on the longitudinal collision time. Finally, based on the longitudinal collision time, a preset longitudinal collision time threshold, and the lateral displacement, the collision risk between the vehicle and the obstacle vehicle is predicted. These embodiments of the present disclosure accurately predict the collision risk between the vehicle and the obstacle vehicle based on the longitudinal collision time and lateral displacement, allowing for proactive measures to be taken to avoid collisions and ensure the safety of the driver.

[0162] Referring to Figure 6, in one embodiment of this disclosure, the projected lateral distance Lat cur Long and projected longitudinal distancecur Calculations are performed through steps 601 to 604.

[0163] Step 601: Calculate the turning radius of the vehicle deviation based on the vehicle information.

[0164] In some embodiments of this disclosure, referring to FIG7, the turning radius of the vehicle deviation can be estimated based on an empirical engineering formula. In some embodiments, the empirical engineering formula can be formula (4).

[0165] in, The turning radius is estimated based on engineering experience, δ is the steering wheel angle, i is the transmission ratio from the steering wheel angle to the wheel angle, K is the steering stability coefficient, a1 is the distance from the center of gravity to the front axle, b1 is the distance from the center of gravity to the rear axle, and ε is a minimum value to prevent the denominator from being zero.

[0166] Considering the existence of vehicle yaw rate, it is necessary to base the transient compensation radius. Transient compensation is applied to the turning radius. In some embodiments, the transient compensation radius is... The calculation formula is formula (5).

[0167] in, The turning radius is for transient compensation. This refers to the yaw rate.

[0168] Therefore, the final turning radius R of the vehicle can be calculated according to formula (6).

[0169] Step 602: Calculate the angle corresponding to the arc length between the predicted intersection point of the predicted trajectory of the self-vehicle and the obstacle vehicle based on the turning radius and the vehicle information.

[0170] In some embodiments of this disclosure, based on geometric relationships, the lateral distance between the vehicle and the obstacle vehicle transmitted by perception is removed. The lateral distance between the obstacle vehicle and the turning center of the predicted trajectory of the vehicle can be calculated according to formula (7). ROC = R - Lat (7)

[0171] Where ROC is the lateral distance between the obstacle vehicle and the turning center of the vehicle, Lat is the lateral distance between the obstacle vehicle and the vehicle in the vehicle coordinate system transmitted by the sensor, and R is the turning radius when the vehicle deviates.

[0172] The formula for calculating the angle σ corresponding to the turning trajectory (predicted trajectory) between the predicted intersection point and the vehicle is formula (8).

[0173] Where Long represents the longitudinal distance between the obstacle vehicle and the vehicle in the vehicle's coordinate system as perceived by the sensor.

[0174] Step 603: Calculate the projected longitudinal distance of the obstacle vehicle and the vehicle in the longitudinal direction according to the angle.

[0175] After obtaining the angle corresponding to the turning trajectory between the predicted intersection point and the vehicle, the arc length (Long) between the predicted intersection point and the vehicle can be calculated according to formula (9). cur Long cur =R·σ (9)

[0176] Among them, Long cur Besides being called arc length, it can also be called the projected longitudinal distance of the obstacle vehicle on the turning trajectory of the vehicle.

[0177] Step 604: Calculate the projected lateral distance of the obstacle vehicle and the vehicle in the lateral direction according to the angle.

[0178] The distance from the obstacle vehicle to the predicted intersection point is the projected lateral distance Lat between the vehicle and the obstacle vehicle after the turning radius is projected. cur It can be calculated according to formula (10).

[0179] Among them, Lat cur This represents the horizontal distance of the projected image. This is the vehicle's heading angle.

[0180] Referring to Figure 8, in one embodiment of this disclosure, the relative resultant velocity can be calculated through steps 801 to 804.

[0181] Step 801: Obtain the relative lateral speed based on the lateral speed of the vehicle and the obstacle vehicle at the current moment.

[0182] The relative lateral velocity v between the obstacle vehicle and the vehicle at the current moment lat,rel It equals the difference between the lateral velocity of the vehicle and the lateral velocity of the obstacle vehicle at the current moment, and the relative lateral velocity v. lat,rel The calculation formula is formula (11). v lat,rel =v e,y -v o,y (11)

[0183] Among them, v lat,rel Let v be the relative lateral velocity between the two vehicles. o,y v is the lateral velocity of the obstacle vehicle. e,y This represents the lateral speed of the vehicle.

[0184] Step 802: Obtain the relative longitudinal speed based on the longitudinal speed of the vehicle and the longitudinal speed of the obstacle vehicle at the current moment.

[0185] The relative longitudinal velocity v between the obstacle vehicle and the vehicle at the current moment long,rel It equals the difference between the longitudinal velocity of the vehicle and the longitudinal velocity of the obstacle vehicle at the current moment, and the relative longitudinal velocity v. long,rel The calculation formula is formula (12). v long,rel =v e,x -v o,x (12)

[0186] Among them, v long,rel v is the relative longitudinal velocity between the two vehicles. o,x v is the longitudinal velocity of the obstacle vehicle. e,x The longitudinal speed of the vehicle.

[0187] Step 803: Calculate the angle between the obstacle vehicle and the direction of travel of the vehicle at the current moment based on the relative lateral velocity and the relative longitudinal velocity.

[0188] The angle θ between the obstacle vehicle and the direction of travel of the vehicle at the current moment. rel The tangent value is the ratio of the relative lateral velocity to the relative longitudinal velocity (relative lateral velocity divided by relative longitudinal velocity), so the angle θ between the obstacle vehicle and the vehicle's direction of travel is... rel The solution formula is formula (13).

[0189] Where, θ rel The angle between the obstacle vehicle and the direction of travel of the vehicle itself.

[0190] Step 804: Calculate the relative resultant velocity based on the included angle, the relative lateral velocity, and the relative longitudinal velocity.

[0191] Referring to Figure 9, the relative longitudinal velocity between the obstacle vehicle and the vehicle can be calculated using formula (14) based on the relative combined velocity of the obstacle vehicle and the obstacle vehicle. vlong,rel,cur=v long,rel cos(θ rel )+v lat,rel sin(θ rel (14)

[0192] Where vlong,rel,cur are the predicted relative longitudinal motion velocities (relative resultant velocities) on the deviation trajectory.

[0193] In some embodiments, the relative lateral displacement can also be compared with a second preset threshold to determine whether there is a collision risk. For example, if the relative lateral displacement is less than or equal to the second preset threshold, it indicates that the vehicle may not have enough time to avoid the collision, and a collision risk can be determined. In some embodiments, the second preset threshold can be determined by combining parameters such as the driver's reaction time, vehicle model, and driving scenario.

[0194] In other embodiments, the lateral displacement of the vehicles during the longitudinal collision time can be calculated by measuring the lateral distance between the two vehicles during pre-aiming, in order to determine whether a risk exists. In some embodiments, if the lateral displacement is greater than the lateral distance, it is also necessary to determine whether the lateral displacement is less than the sum of the lateral distance and the width of the obstacle vehicle. If the lateral displacement is less than the sum of the lateral distance and the width of the obstacle vehicle, it is determined that there is no collision risk; if the lateral displacement is greater than or equal to the sum of the lateral distance and the width of the obstacle vehicle, it is determined that there is a collision risk.

[0195] In other embodiments, the relative lateral velocity and relative longitudinal velocity may be determined based on the speeds of the two vehicles. In some embodiments, the relative lateral velocity and relative longitudinal velocity may also be determined based on the combined relative velocity and angle, where the angle is the angle corresponding to the arc length between the predicted intersection point of the vehicle and the obstacle vehicle on the predicted trajectory of the vehicle.

[0196] In one embodiment of this disclosure, the method further includes: calculating the turning radius of the vehicle deviation based on the vehicle information; calculating the angle corresponding to the arc length between the vehicle and the obstacle vehicle at the predicted intersection point of the vehicle's predicted trajectory based on the turning radius and the vehicle information; calculating the straight-line distance between the vehicle and the predicted intersection point of the predicted trajectory in the global coordinate system based on the angle and the turning radius; calculating the collision time in the global coordinate system based on the straight-line distance and the relative lateral velocity; and calculating the longitudinal collision time based on the collision time in the global coordinate system.

[0197] In the aforementioned embodiment, the projected lateral distance Lat from the vehicle to the predicted intersection point is calculated based on the vehicle's coordinate system. cur Long and projected longitudinal distance cur Information such as these can be used to determine the collision risk between the vehicle and the obstacle vehicle. If the vehicle information collected by the vehicle's data acquisition device is richer and global coordinate system information can be obtained, then the aforementioned steps 601-604 can be replaced by calculations under the global coordinate system. Referring to Figure 10, in some embodiments, the longitudinal distance from the vehicle to the predicted intersection point can be calculated using global information according to formula (15).

[0198] Among them, L gloLet TTC be the straight-line distance between the vehicle and the predicted intersection point in the global coordinate system. glo It can be calculated according to formula (16).

[0199] Based on collision time TTC glo The longitudinal collision time (TTC) can be separated, and then the lateral displacement during the longitudinal intersection of the two vehicles can be determined based on the longitudinal collision time (TTC) to meet the collision risk assessment.

[0200] It should be noted that the above calculations in the global coordinate system can be combined with the previous calculations in the non-global coordinate system (i.e., the vehicle coordinate system) to achieve a more comprehensive collision risk assessment, thereby further improving the accuracy of the collision risk assessment.

[0201] In some embodiments of this disclosure, a TTC threshold table (preset longitudinal collision time threshold) is calibrated based on the vehicle speed and relative speed. Activating the ELKA function is only necessary when the longitudinal collision time (TTC) meets the TTC threshold. This is because even when the relative speed is high, if the vehicle speed is low, the lateral speed deviation is also small. Therefore, even when the longitudinal distance between the two vehicles is zero, there may be no lateral collision risk. Thus, a two-dimensional table with relative vehicle speed and vehicle speed as inputs and TTC thresholds as outputs needs to be calibrated based on real-vehicle testing.

[0202] In some embodiments of this disclosure, predicting whether there is a collision risk between the vehicle and the obstacle vehicle requires three conditions to be met. The three conditions are: (1) the longitudinal collision time TTC is less than the TTC threshold; (2) the lateral overlap between the inner and outer sides c ≤ 0 and the lateral overlap between the outer sides C ≤ 0; and (3) the vehicle has a lateral velocity that deviates towards the obstacle vehicle.

[0203] When all three conditions are met, the ELKA function of the vehicle is activated when predicting the collision risk between the vehicle and the obstacle vehicle. It should be noted that if one, two, or none of the above conditions (1), (2), and (3) are met, the ELKA function of the vehicle will not be activated.

[0204] The core idea of ​​some embodiments of this disclosure is that when calculating the collision risk between the vehicle and an obstacle vehicle, whether there is lateral overlap is considered. If there is a longitudinal collision risk, but the lateral vehicle positions are offset, then there is no overall collision risk. Therefore, based on a comprehensive assessment of both lateral and longitudinal directions, the ELKA (Emergency Lane Keeping Assist) function is not activated. This combination of lateral and longitudinal assessments avoids accidental activation, making the function more closely match the driver's behavior at any given moment, thus improving driving safety and driver experience. Similarly, when there is a lateral collision risk, whether there is longitudinal overlap can also be calculated. If there is both a lateral collision risk and longitudinal overlap, then a collision risk is comprehensively determined, and the ELKA function is activated; otherwise, the ELKA function is not activated.

[0205] In some embodiments, l represents the longitudinal distance between the two vehicles obtained through perception, L1 represents the longitudinal relative displacement when the two vehicles intersect laterally when the lateral speed is relatively slow, and L2 represents the longitudinal relative displacement when the two vehicles intersect laterally when the lateral speed is relatively fast. The above judgment method is mainly divided into several cases as shown in Figures 11-14. Figure 11-12 shows the case where the lateral speed is relatively slow and there is a risk of lateral collision between the left half of the vehicle and the left half of the obstacle vehicle. Figures 13-14 show the case where the lateral speed is relatively fast and there is a risk of lateral collision between the right half of the vehicle and the right half of the obstacle vehicle. When the lateral speed is different, the scenario needs to be further subdivided according to the longitudinal speed. The calculation idea can be referred to the above description. Regardless of whether the vehicle coordinate system or the global coordinate system is used, the lateral overlap time is calculated. The longitudinal relative running distance is calculated based on this time. Then, using this distance, plus a certain safety margin, it is determined whether there is a risk of collision between the two vehicles in the longitudinal direction, and thus decides whether the ELKA function is activated to ensure the personal safety of the driver.

[0206] In summary, some embodiments of this disclosure can solve the problem of collisions caused by drivers of oncoming vehicles deviating from the direction of the oncoming vehicle due to unconsciousness or insufficient judgment. Current solutions have the following shortcomings: they only judge based on the current vehicle state, without considering lateral and longitudinal predictions; emergency avoidance conditions are only determined by lane distance, without considering the influence of the vehicle's lateral movement; they only consider the initial speed and acceleration of the vehicle's deviation, without considering the overlap of the vehicle's lateral position during the initial and subsequent deviations, which can easily lead to false activation. To address these problems, some embodiments of this disclosure propose a collision prediction calculation method for oncoming vehicle scenarios and an activation strategy for an emergency lane keeping function.

[0207] This disclosure presents a collision prediction calculation scheme for oncoming vehicle scenarios. First, it differs from a large class of calculation methods that rely on high-precision maps and positioning functions. Second, some embodiments of this disclosure include collision prediction schemes based on the requirements of emergency lane keeping assist functions, including both conscious and unconscious lane departure states of the vehicle. The scheme is described as follows: based on the basic information of the vehicle ahead (relative lateral and longitudinal positions, relative lateral and longitudinal speeds, and relative lateral and longitudinal accelerations) perceived by the vehicle's front corner radar.

[0208] This disclosure proposes an activation strategy for an emergency lane keeping function (ELKA) based on several embodiments. Unlike related technologies, these embodiments predict the trajectories of the vehicle and obstacle vehicles based on the current state, and calculate the predicted lateral and longitudinal distances more accurately than related technologies by projecting the predicted trajectories. Combining lateral displacement and longitudinal collision time, a comprehensive judgment is made on whether to activate the function, avoiding false activation. Furthermore, compared to related technologies that only consider the distance to the lane line edge as one of the activation conditions, addressing the issue of false activation and correction when the driver is driving close to the lane line edge and there is an oncoming vehicle, this disclosure incorporates the vehicle's speed of deviating from the lane line as a reference. In such scenarios, since there is no tendency to deviate from the vehicle's lane, the ELKA function will not be activated.

[0209] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that some embodiments of this disclosure are not limited to the described order of actions, because according to some embodiments of this disclosure, certain steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to some embodiments of this disclosure.

[0210] Figure 15 is a block diagram of a vehicle control device according to some embodiments. As shown in Figure 15, the vehicle control device may include a predicted trajectory determination module 1501, a collision risk determination module 1502, and a trajectory control module 1503.

[0211] The predicted trajectory determination module 1501 is configured to determine the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle when the vehicle's driving direction deviates.

[0212] The collision risk determination module 1502 is configured to determine whether there is a collision risk based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle.

[0213] The trajectory control module 1503 is configured to control the vehicle to stay within the lane if the collision risk exists.

[0214] In one embodiment of this disclosure, the collision risk determination module 1502 is used for:

[0215] If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then at least one of the longitudinal collision time or the lateral collision time is determined based on the position information of the autonomous vehicle and the position information of the obstacle vehicle.

[0216] The existence of a collision risk is determined based on at least one of the longitudinal or lateral collision times.

[0217] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: if it is determined that the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle intersect, determine the projected longitudinal distance between the vehicle and the obstacle vehicle based on the current position of the vehicle and the current position of the obstacle vehicle; determine the longitudinal collision time based on the projected longitudinal distance and the relative longitudinal speed between the vehicle and the obstacle vehicle; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal collision time.

[0218] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the relative lateral displacement based on the longitudinal collision time and the relative lateral velocity between the vehicle and the obstacle vehicle; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the relative lateral displacement.

[0219] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the projected lateral distance between the vehicle and the obstacle vehicle based on the current position of the vehicle and the current position of the obstacle vehicle; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected lateral distance and the relative lateral displacement.

[0220] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the lateral overlap based on the projected lateral distance and the relative lateral displacement; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral overlap.

[0221] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the inner lateral overlap based on the relative lateral displacement and the projected lateral distance; and determine the outer lateral overlap based on the relative lateral displacement, the projected lateral distance, and the width of the obstacle vehicle.

[0222] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the inner lateral overlap between the vehicle and the obstacle vehicle based on the relative lateral displacement, the projected lateral distance, and a first safety margin; and determine the outer lateral overlap between the vehicle and the obstacle vehicle based on the relative lateral displacement, the projected lateral distance, a second safety margin, and the width of the obstacle vehicle.

[0223] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine that there is a collision risk between the vehicle and the obstacle vehicle if it is determined that both the inner lateral overlap and the outer lateral overlap are less than or equal to zero.

[0224] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal collision time and a preset longitudinal collision time threshold.

[0225] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: if it is determined that the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle intersect, determine the projected lateral distance based on the current position of the vehicle and the current position of the obstacle vehicle; determine the lateral collision time based on the projected lateral distance and relative lateral velocity of the vehicle and the obstacle vehicle; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral collision time.

[0226] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the relative longitudinal displacement based on the lateral collision time and the relative longitudinal velocity between the vehicle and the obstacle vehicle; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the relative longitudinal displacement.

[0227] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the projected longitudinal distance between the vehicle and the obstacle vehicle based on the current position of the vehicle and the current position of the obstacle vehicle; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected longitudinal distance and the relative longitudinal displacement.

[0228] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the longitudinal overlap based on the projected longitudinal distance and the relative longitudinal displacement; and determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal overlap.

[0229] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the inner longitudinal overlap based on the relative longitudinal displacement and the projected longitudinal distance; and determine the outer longitudinal overlap based on the relative longitudinal displacement, the projected longitudinal distance, and the length of the obstacle vehicle.

[0230] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the inner longitudinal overlap between the vehicle and the obstacle vehicle based on the relative longitudinal displacement, the projected longitudinal distance, and a third safety margin; and determine the outer longitudinal overlap between the vehicle and the obstacle vehicle based on the relative longitudinal displacement, the projected longitudinal distance, a fourth safety margin, and the length of the obstacle vehicle.

[0231] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to:

[0232] If it is determined that both the inner longitudinal overlap and the outer longitudinal overlap are less than or equal to zero, then it is determined that there is a collision risk between the vehicle and the obstacle vehicle.

[0233] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to determine whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral collision time and a preset lateral collision time threshold.

[0234] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: if it is determined that the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle intersect, then determine the projected longitudinal distance and projected lateral distance between the vehicle and the obstacle vehicle based on the current position of the vehicle and the current position of the obstacle vehicle; determine the longitudinal collision time based on the projected longitudinal distance; determine the lateral collision time based on the projected lateral distance; and determine whether there is a collision risk based on the longitudinal collision time and the lateral collision time.

[0235] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to:

[0236] The longitudinal collision time is determined based on the projected longitudinal distance and relative longitudinal velocity of the vehicle and the obstacle vehicle;

[0237] Determining the lateral collision time based on the projected lateral distance includes: determining the lateral collision time based on the projected lateral distance and relative lateral velocity between the vehicle and the obstacle vehicle.

[0238] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: acquire vehicle information of the vehicle and vehicle information of the obstacle vehicle; the vehicle information of the vehicle includes at least the heading and position of the vehicle, and the vehicle information of the obstacle vehicle includes at least the heading and position of the obstacle vehicle.

[0239] The predicted trajectories of the autonomous vehicle and the obstacle vehicle are calculated based on the vehicle information of the autonomous vehicle and the vehicle information of the obstacle vehicle, respectively.

[0240] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to determine the relative longitudinal speed and the relative lateral speed based on the speed of the vehicle and the speed of the obstacle vehicle.

[0241] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to: determine the lateral and longitudinal speeds of the vehicle and the obstacle vehicle based on the speed of the vehicle and the speed of the obstacle vehicle; and determine the relative longitudinal speed and the relative lateral speed based on the lateral and longitudinal speeds of the vehicle and the obstacle vehicle.

[0242] In one embodiment of this disclosure, the collision risk determination module 1502 is configured to determine that there is no collision risk if it is determined that the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle do not intersect.

[0243] In one embodiment of this disclosure, the trajectory control module 1503 is configured to activate the vehicle's emergency lane keeping assist function if the collision risk is determined to exist, so as to control the vehicle to keep driving within the lane.

[0244] In one embodiment of this disclosure, the trajectory control module 1503 is configured to maintain the vehicle's driving trajectory if it is determined that there is no collision risk.

[0245] The above-described apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple. For relevant details, please refer to the description of the method embodiments.

[0246] In another embodiment provided in this disclosure, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the vehicle control method described in any of the embodiments above.

[0247] In yet another embodiment provided in this disclosure, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform the vehicle control method described in any of the embodiments above.

[0248] In yet another embodiment provided in this disclosure, a vehicle is also provided that implements the vehicle control method described in any of the above embodiments.

[0249] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0250] It should be noted that in this disclosure, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0251] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0252] The above description is merely a preferred embodiment of this disclosure and is not intended to limit the scope of protection of this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure are included within the scope of protection of this disclosure.

Claims

1. A vehicle control method, comprising: When the vehicle deviates from its driving direction, the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle are determined. Based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle, determine whether there is a collision risk; If the collision risk is determined to exist, the vehicle is controlled to remain within the lane.

2. The method according to claim 1, wherein, The step of determining whether there is a collision risk based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle includes: If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then at least one of the longitudinal collision time or the lateral collision time is determined based on the position information of the autonomous vehicle and the position information of the obstacle vehicle. The existence of a collision risk is determined based on at least one of the longitudinal collision time or the lateral collision time.

3. The method according to claim 2, wherein, The step of determining whether there is a collision risk based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle further includes: If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then the projected longitudinal distance between the autonomous vehicle and the obstacle vehicle is determined based on the current position of the autonomous vehicle and the current position of the obstacle vehicle. The longitudinal collision time is determined based on the projected longitudinal distance and relative longitudinal velocity of the vehicle and the obstacle vehicle; Based on the longitudinal collision time, it is determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

4. The method according to claim 3, wherein, The step of determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal collision time includes: The relative lateral displacement is determined based on the longitudinal collision time and the relative lateral velocity between the vehicle and the obstacle vehicle. Based on the relative lateral displacement, it is determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

5. The method according to claim 4, wherein, The step of determining whether there is a risk of collision between the vehicle and the obstacle vehicle based on the relative lateral displacement includes: Based on the current position of the autonomous vehicle and the current position of the obstacle vehicle, determine the projected lateral distance between the autonomous vehicle and the obstacle vehicle; Based on the projected lateral distance and the relative lateral displacement, it is determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

6. The method according to claim 5, wherein, The step of determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected lateral distance and the relative lateral displacement includes: The lateral overlap is determined based on the projected lateral distance and the relative lateral displacement; Based on the lateral overlap, determine whether there is a risk of collision between the vehicle and the obstacle vehicle.

7. The method according to claim 6, wherein, The lateral overlap includes: inner lateral overlap and outer lateral overlap; The step of determining the lateral overlap based on the projected lateral distance and the relative lateral displacement includes: The inner lateral overlap is determined based on the relative lateral displacement and the projected lateral distance. The outer lateral overlap is determined based on the relative lateral displacement, the projected lateral distance, and the width of the obstacle vehicle.

8. The method according to claim 7, wherein, Determining the inner lateral overlap based on the relative lateral displacement and the projected lateral distance includes: The inner lateral overlap between the vehicle and the obstacle vehicle is determined based on the relative lateral displacement, the projected lateral distance, and the first safety margin. Determining the outer lateral overlap based on the relative lateral displacement, the projected lateral distance, and the width of the obstacle vehicle includes: The lateral overlap between the vehicle and the obstacle vehicle is determined based on the relative lateral displacement, the projected lateral distance, the second safety margin, and the width of the obstacle vehicle.

9. The method according to claim 7 or 8, wherein, The step of determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral overlap includes: If the inner lateral overlap and the outer lateral overlap are determined to be less than or equal to zero, then a collision risk is determined between the vehicle and the obstacle vehicle.

10. The method according to any one of claims 2-9, further comprising: Based on the longitudinal collision time and the preset longitudinal collision time threshold, it is determined whether there is a collision risk between the vehicle and the obstacle vehicle.

11. The method according to claim 2, wherein, The step of determining whether there is a collision risk based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle further includes: If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then the projected lateral distance is determined based on the current position of the autonomous vehicle and the current position of the obstacle vehicle. The lateral collision time is determined based on the projected lateral distance and relative lateral velocity of the vehicle and the obstacle vehicle; Based on the lateral collision time, it is determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

12. The method according to claim 11, wherein, The step of determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the lateral collision time includes: The relative longitudinal displacement is determined based on the lateral collision time and the relative longitudinal velocity between the vehicle and the obstacle vehicle. Based on the relative longitudinal displacement, it is determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

13. The method according to claim 12, wherein, The step of determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the relative longitudinal displacement includes: Based on the current position of the autonomous vehicle and the current position of the obstacle vehicle, determine the projected longitudinal distance between the autonomous vehicle and the obstacle vehicle; Based on the projected longitudinal distance and the relative longitudinal displacement, it is determined whether there is a risk of collision between the vehicle and the obstacle vehicle.

14. The method according to claim 13, wherein, The step of determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the projected longitudinal distance and the relative longitudinal displacement includes: The longitudinal overlap is determined based on the projected longitudinal distance and the relative longitudinal displacement; Based on the longitudinal overlap, determine whether there is a risk of collision between the vehicle and the obstacle vehicle.

15. The method according to claim 14, wherein, The longitudinal overlap includes: inner longitudinal overlap and outer longitudinal overlap; The step of determining the longitudinal overlap based on the projected longitudinal distance and the relative longitudinal displacement includes: The inner longitudinal overlap is determined based on the relative longitudinal displacement and the projected longitudinal distance; The outer longitudinal overlap is determined based on the relative longitudinal displacement, the projected longitudinal distance, and the length of the obstacle vehicle.

16. The method according to claim 15, wherein, Determining the inner longitudinal overlap based on the relative longitudinal displacement and the projected longitudinal distance includes: The inner longitudinal overlap between the vehicle and the obstacle vehicle is determined based on the relative longitudinal displacement, the projected longitudinal distance, and the third safety margin. Determining the outer longitudinal overlap based on the relative longitudinal displacement, the projected longitudinal distance, and the length of the obstacle vehicle includes: The longitudinal overlap between the vehicle and the obstacle vehicle is determined based on the relative longitudinal displacement, the projected longitudinal distance, the fourth safety margin, and the length of the obstacle vehicle.

17. The method according to claim 15 or 16, wherein, The step of determining whether there is a collision risk between the vehicle and the obstacle vehicle based on the longitudinal overlap includes: If the inner longitudinal overlap and the outer longitudinal overlap are determined to be less than or equal to zero, then a collision risk is determined between the vehicle and the obstacle vehicle.

18. The method according to any one of claims 11-17, further comprising: Based on the lateral collision time and the preset lateral collision time threshold, it is determined whether there is a collision risk between the vehicle and the obstacle vehicle.

19. The method according to claim 2, wherein, The step of determining whether there is a collision risk based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle further includes: If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle intersect, then the projected longitudinal distance and projected lateral distance between the autonomous vehicle and the obstacle vehicle are determined based on the current position of the autonomous vehicle and the current position of the obstacle vehicle. The longitudinal collision time is determined based on the projected longitudinal distance; The lateral collision time is determined based on the projected lateral distance; Based on the longitudinal collision time and the lateral collision time, determine whether there is a collision risk.

20. The method according to claim 19, wherein, Determining the longitudinal collision time based on the projected longitudinal distance includes: The longitudinal collision time is determined based on the projected longitudinal distance and relative longitudinal velocity between the vehicle and the obstacle vehicle; Determining the lateral collision time based on the projected lateral distance includes: The lateral collision time is determined based on the projected lateral distance and relative lateral velocity of the vehicle and the obstacle vehicle.

21. The method according to any one of claims 1-20, wherein, The predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle are determined in the following way: Obtain vehicle information of the autonomous vehicle and vehicle information of the obstacle vehicle; the vehicle information of the autonomous vehicle includes at least the heading and position of the autonomous vehicle, and the vehicle information of the obstacle vehicle includes at least the heading and position of the obstacle vehicle. Based on the vehicle information of the autonomous vehicle and the vehicle information of the obstacle vehicle, the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle are calculated.

22. The method according to claim 4, 12, or 20, further comprising: The relative longitudinal speed and the relative lateral speed are determined based on the speed of the vehicle and the speed of the obstacle vehicle.

23. The method according to claim 22, wherein, Determining the relative longitudinal speed and the relative lateral speed based on the speed of the vehicle and the speed of the obstacle vehicle includes: Based on the speed of the vehicle and the speed of the obstacle vehicle, determine the lateral and longitudinal speeds of the vehicle and the obstacle vehicle. The relative longitudinal speed and the relative lateral speed are determined based on the lateral and longitudinal speeds of the vehicle and the obstacle vehicle.

24. The method according to any one of claims 1-22, wherein, The step of determining whether there is a collision risk based on the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle further includes: If it is determined that the predicted trajectory of the autonomous vehicle and the predicted trajectory of the obstacle vehicle do not intersect, then it is determined that there is no risk of collision.

25. The method according to any one of claims 1-24, wherein, If the collision risk is determined to exist, controlling the vehicle to remain within the lane includes: If the collision risk is determined to exist, the vehicle's emergency lane keeping assist function is activated to control the vehicle to stay within the lane.

26. The method according to any one of claims 1-24, further comprising: If it is determined that there is no collision risk, the vehicle's driving trajectory is maintained.

27. A vehicle control device, comprising: The predicted trajectory determination module is configured to determine the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle when the vehicle's driving direction deviates. The collision risk determination module is configured to determine whether there is a collision risk based on the predicted trajectory of the vehicle and the predicted trajectory of the obstacle vehicle. and The trajectory control module is configured to control the vehicle to stay within the lane if the collision risk is determined to exist.

28. An electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein, The processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is configured to store computer programs; When the processor is configured to execute a program stored in the memory, it implements the method according to any one of claims 1-26.

29. A computer-readable storage medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method according to any one of claims 1-26.

30. A vehicle, wherein, The vehicle implements the method according to any one of claims 1-26.

31. A computer program product comprising a computer program or instructions, wherein, When the computer program or the instructions are executed by the processor, they implement the method according to any one of claims 1-26.

Images