Vehicle safety early warning method and vehicle

Abstract

The invention provides a vehicle safety early warning method and a vehicle, and relates to the field of vehicle control. The method comprises the following steps: acquiring a first sensing result of an own vehicle for a front vehicle and a second sensing result of the own vehicle for the front vehicle; detecting whether the second sensing result is reliable; if the second sensing result is not reliable, adjusting the vehicle and obtaining the second sensing result again, and skipping to execute the step of detecting whether the second sensing result is reliable or not until a preset condition is met, so as to obtain a final second sensing result; determining whether a collision risk exists according to the final second sensing result and the first sensing result; and if the collision risk exists, early warning is carried out, so that the vehicle collision risk under the complex road condition is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, and particularly relates to a vehicle safety warning method and a vehicle. BACKGROUND

[0002] In order to improve driving safety, an advanced driver assistance system (ADAS) has been widely applied in various types of vehicles. The basic principle is to perceive the running state of the preceding vehicle and perform real-time collision risk assessment, so as to timely issue a warning to the driver or automatically implement braking.

[0003] However, in actual road scenes, especially in complex road conditions such as dense traffic flow and frequent vehicle following, the existing system still has certain limitations. For example, when the ego vehicle follows the preceding vehicle, if the preceding vehicle suddenly changes lanes and cuts out, the ego vehicle system may fail to timely recognize the state of the vehicle in front of the preceding vehicle (i.e., the front-front vehicle), and thus cannot effectively warn or brake, resulting in a collision with the front-front vehicle. Similarly, if the preceding vehicle fails to brake in time and rear-ends the front-front vehicle, the ego vehicle system also cannot brake in time and rear-ends the preceding vehicle, resulting in a chain collision accident.

[0004] In summary, the existing system cannot effectively reduce the collision risk in complex road conditions such as dense traffic flow and frequent vehicle following. SUMMARY

[0005] The embodiments of the present application provide a vehicle safety warning method and a vehicle to reduce the collision risk of vehicles in complex road conditions.

[0006] In a first aspect, the embodiments of the present application provide a vehicle safety warning method, comprising: obtaining a first perception result of a preceding vehicle by an ego vehicle and a second perception result of a front-front vehicle by the ego vehicle; detecting whether the second perception result is reliable; if the second perception result is unreliable, adjusting the ego vehicle and re-obtaining the second perception result, jumping to the step of detecting whether the second perception result is reliable until a preset condition is reached to obtain a final second perception result; determining whether there is a collision risk according to the final second perception result and the first perception result; if there is a collision risk, issuing a warning.

[0007] Based on the above technical content, the embodiment of the present application increases the monitoring of the front vehicle on the basis of monitoring the front vehicle, and through fusing the perception results of the front vehicle and the front vehicle, the collision risk can be more comprehensively evaluated, so as to identify the potential danger at an earlier stage, and timely assist the driver to avoid or reduce the collision through early warning, and especially improve the driving safety in the complex following vehicle scene such as the front vehicle shielding; In addition, the embodiment of the present application also considers that there may be a front vehicle shielding problem between the ego vehicle and the front vehicle, which leads to that the perception result of the ego vehicle for the front vehicle is low in reliability. Therefore, the embodiment of the present application detects the perception result of the front vehicle and dynamically adjusts the ego vehicle, so as to ensure that the perception result of the front vehicle is high in reliability, thereby significantly improving the accuracy of judging the state of the front vehicle and further guaranteeing the driving safety.

[0008] In a possible implementation manner, the adjusting the ego vehicle comprises: detecting whether there is another vehicle in a set range of left and right lanes adjacent to a lane of the ego vehicle; if it is detected that there is no other vehicle in the set range of the left and right lanes adjacent to the lane of the ego vehicle, controlling the ego vehicle to shift laterally according to the first perception result and a lane line position of the ego vehicle.

[0009] Before adjusting the position of the ego vehicle, the embodiment of the present application detects whether there is another vehicle in a set range of left and right lanes adjacent to a lane of the ego vehicle, so as to determine whether the surrounding environment of the ego vehicle is safe, and avoid affecting other vehicles nearby and introducing new collision risks when adjusting the position of the ego vehicle. After confirming that the surrounding environment of the ego vehicle is safe, actively controlling the ego vehicle to shift can optimize the perception field of view of the ego vehicle, thereby solving the problem of the perception blind area caused by the front vehicle shielding, and significantly enhancing the detection ability and perception reliability of the far-end target such as the front vehicle.

[0010] In a possible implementation manner, the first perception result comprises position information of the front vehicle. The controlling the ego vehicle to shift laterally according to the first perception result and the lane line position of the ego vehicle comprises: determining a lateral direction of the front vehicle relative to the ego vehicle based on the position information of the front vehicle; determining a lateral shift direction of the ego vehicle as a reverse direction of the lateral direction; determining a lateral distance between lane lines of the ego vehicle along the lateral shift direction based on position information of the ego vehicle and the lane line position of the ego vehicle, controlling the ego vehicle to shift the lateral distance along the lateral shift direction.

[0011] The embodiment of the application can ensure that the sensing field of view of the ego vehicle can bypass the shielding of the front vehicle to the maximum extent by explicitly offsetting to the opposite direction of the front vehicle, thereby providing the best conditions for detecting the front-front vehicle that is shielded, and greatly improving the success probability of sensing and the reliability of sensing data. Meanwhile, the embodiment of the application also limits the offset distance of the ego vehicle by using the lane line of the ego vehicle, thereby greatly improving the sensing accuracy while ensuring driving safety.

[0012] In a possible implementation, the second sensing result includes a radar sensing result and a visual sensing result; the radar sensing result includes radar sensing data and a radar sensing confidence, and the visual sensing result includes visual sensing data and a visual sensing confidence; The detection of whether the second sensing result is reliable includes: detecting whether the radar sensing confidence is greater than a first confidence setting threshold and whether the visual sensing confidence is greater than a second confidence setting threshold; if the radar sensing confidence is greater than the first confidence setting threshold and the visual sensing confidence is greater than the second confidence setting threshold, detecting whether a data deviation between the radar sensing data and the visual sensing data is less than a deviation setting threshold; if the data deviation is less than the deviation setting threshold, determining that the second sensing result is reliable.

[0013] The embodiment of the application can filter out low-quality and unreliable sensing data by respectively checking the sensing confidence of the radar sensing module and the visual sensing module. On the basis of high-quality sensing data, cross verification between the radar sensing module and the visual sensing module can ensure that different sensing modules describe the same physical reality. This step-by-step verification method is computationally efficient and logically clear, and can effectively avoid the error propagation problem that may be caused by direct fusion calculation.

[0014] In a possible implementation, after the detection of whether the radar sensing confidence is greater than a first confidence setting threshold and whether the visual sensing confidence is greater than a second confidence setting threshold, the method further includes: if the radar sensing confidence is less than or equal to the first confidence setting threshold or the visual sensing confidence is less than or equal to the second confidence setting threshold, determining that the second sensing result is unreliable; after the detection of whether a data deviation between the radar sensing data and the visual sensing data is less than a deviation setting threshold, the method further includes: if the data deviation is greater than or equal to the deviation setting threshold, determining that the second sensing result is unreliable.

[0015] Here, the reliability of the sensing results is evaluated through two levels: individual unit verification (i.e., checking the sensing confidence of each sensing module) and cross-verification (i.e., checking the data consistency between each sensing module). Unreliable data can be identified from different dimensions, thereby significantly enhancing the fault tolerance capability for situations such as temporary performance degradation of a single sensing module or the generation of heterogeneous errors, and improving the stability and reliability of the system in various complex environments.

[0016] In one possible implementation, determining whether a collision risk exists based on the final second perception result and the first perception result includes: Based on the initial perception results, determine the time distance and collision time between the vehicle and the vehicle in front; Based on the second perception results, determine the time distance and collision time between the vehicle and the vehicle in front of it; Based on the time distance and collision time between the vehicle and the vehicle in front, as well as the time distance and collision time between the vehicle and the vehicle two steps ahead, determine whether there is a risk of collision.

[0017] This application embodiment establishes a dual field of vision and two lines of defense by simultaneously monitoring the distance to the vehicle ahead and the time of collision with the vehicle ahead. This enables the autonomous vehicle system to identify distant risks that cannot be detected by monitoring only the vehicle ahead, thus providing earlier warnings. The distance to the vehicle ahead is used to assess comfort risks (whether the following distance is too close), while the time of collision is used to assess safety risks (whether a collision is unavoidable). Based on the distance to the vehicle ahead and the time of collision, this application embodiment can determine different types of collision risks, allowing the system response to be precisely matched to the risk type.

[0018] In one possible implementation, the collision risks include: risk of the vehicle in front being too close, risk of a collision with the vehicle in front, risk of the vehicle in front of the vehicle being too close, and risk of a collision with the vehicle in front of the vehicle. The determination of whether a collision risk exists based on the time distance and collision time between the vehicle and the vehicle in front, and the time distance and collision time between the vehicle and the vehicle two steps ahead, includes: If the time distance between the vehicle and the vehicle in front is less than the first time distance threshold and the duration is greater than the first set time, then it is determined that there is a risk of the vehicle in front being too close. If the collision time between the vehicle and the vehicle in front is less than the first collision time threshold, and the duration is greater than the second set time, then a risk of collision with the vehicle in front is determined. If the time distance between your vehicle and the vehicle in front of you is less than the second time distance threshold, and the duration is greater than the third set time, then it is determined that there is a risk of the vehicle in front of you being too close. If the collision time between the vehicle and the vehicle in front is less than the second collision time threshold, and the duration is greater than the fourth set time, then a collision risk with the vehicle in front is determined.

[0019] This application embodiment subdivides the risk type from a single collision risk into over-closeness risk and collision risk, and independently judges the preceding vehicle and the vehicle before that. This design enables the system to identify potential threats of different levels and sources (such as following too closely, impending rear-end collision, etc.) earlier and more accurately, laying a solid foundation for achieving graded response. Furthermore, this application embodiment sets dual conditions of threshold triggering and duration for the judgment of each risk type, which can effectively filter out instantaneous jitter and false alarms caused by sensing module noise, vehicle bumps, or the brief entry and exit of the target, ensuring that only persistent real risks will trigger the system response, greatly enhancing the robustness and reliability of the system.

[0020] In one possible implementation, the second perception result includes the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself. Based on the second perception result, determine the time distance between the vehicle and the vehicle in front of it, including: The first distance is determined based on the difference between the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself, and the length of the vehicle in front. The ratio of the first distance to the vehicle's speed is used as the time distance between the vehicle and the vehicle in front of it.

[0021] This application embodiment calculates the time distance between the vehicle and the vehicle by subtracting the length of the vehicle in front from the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle in front. This time distance value can truly reflect the urgency of the vehicle in front approaching the vehicle in front, thereby providing timely warnings to the vehicle in front. In scenarios where the vehicle in front may suddenly decelerate due to a rear-end collision with the vehicle in front, the driving safety of the vehicle in front can be guaranteed.

[0022] In one possible implementation, a warning is issued if a collision risk exists, including: When there is a risk of collision, the corresponding warning method is determined based on different collision risks, and a warning is given to the driver of the vehicle. After the preset warning time, the system jumps to the steps of obtaining the first perception result of the vehicle in front and the second perception result of the vehicle in front of the first vehicle. When there is a collision risk and the collision risk is aggravated, the corresponding braking parameters are determined based on the existing collision risk, and the braking operation is performed.

[0023] This application's embodiments provide differentiated warnings based on collision risk types, avoiding the discomfort caused by frequent emergency braking due to an overly sensitive system, and significantly improving driving comfort. Furthermore, this application's embodiments re-perceive the environment after a warning, forming an intelligent cycle of warning-observation-re-decision. The system only executes braking based on the latest information when the risk persists and worsens, ensuring that each intervention is necessary and accurate, greatly reducing the probability of erroneous intervention. In addition, matching different braking parameters according to the latest risk type allows for optimal comfort during the intervention process while firmly upholding safety standards.

[0024] Secondly, embodiments of this application provide a vehicle safety warning device, comprising: The acquisition module is used to acquire the vehicle's first perception result of the vehicle in front, and the vehicle's second perception result of the vehicle in front of the vehicle in front of it. The detection module is used to detect whether the second sensing result is reliable; The early warning module is used for: If the second perception result is unreliable, the vehicle is adjusted and the second perception result is reacquired. The process then jumps to the step of checking whether the second perception result is reliable until the preset conditions are met and the final second perception result is obtained. Based on the final second perception result and the first perception result, determine whether there is a collision risk; If there is a risk of collision, a warning will be issued.

[0025] In one possible implementation, the early warning module is specifically used for: Detect whether there are other vehicles within a set range of the left and right lanes adjacent to the vehicle's lane; If no other vehicles are detected within the set range of the left and right lanes adjacent to the vehicle's lane, the vehicle will be controlled to deviate laterally based on the first perception result and the position of the vehicle's lane line.

[0026] In one possible implementation, the first perception result includes: the position information of the vehicle in front; The early warning module is specifically used for: Based on the position information of the preceding vehicle, the lateral direction of the preceding vehicle relative to the vehicle itself is determined; The opposite direction of the lateral direction is determined as the lateral offset direction of the vehicle; Based on the vehicle's location information and the lane line position, the lateral distance between the vehicle and the lane line along the lateral offset direction is determined. Along the lateral offset direction, the vehicle is controlled to offset the lateral distance.

[0027] In one possible implementation, the second perception result includes radar perception results and visual perception results; the radar perception result includes radar perception data and radar perception confidence, and the visual perception result includes visual perception data and visual perception confidence. The detection module is specifically used for: Detect whether the radar perception confidence level is greater than a first confidence level threshold, and whether the visual perception confidence level is greater than a second confidence level threshold; If the radar perception confidence level is greater than the first confidence level threshold and the visual perception confidence level is greater than the second confidence level threshold, then it is detected whether the data deviation between the radar perception data and the visual perception data is less than the deviation threshold. If the data deviation is less than the set deviation threshold, then the second perception result is determined to be reliable.

[0028] In one possible implementation, the detection module is also used for: If the radar perception confidence level is less than or equal to the first confidence level threshold, or if the visual perception confidence level is less than or equal to the second confidence level threshold, then the second perception result is determined to be unreliable. If the data deviation is greater than or equal to the deviation setting threshold, then the second perception result is determined to be unreliable.

[0029] In one possible implementation, the early warning module is specifically used for: Based on the initial perception results, determine the time distance and collision time between the vehicle and the vehicle in front; Based on the second perception results, determine the time distance and collision time between the vehicle and the vehicle in front of it; Based on the time distance and collision time between the vehicle and the vehicle in front, as well as the time distance and collision time between the vehicle and the vehicle two steps ahead, determine whether there is a risk of collision.

[0030] In one possible implementation, the collision risks include: risk of the vehicle in front being too close, risk of a collision with the vehicle in front, risk of the vehicle in front of the vehicle being too close, and risk of a collision with the vehicle in front of the vehicle. The early warning module is specifically used for: If the time distance between the vehicle and the vehicle in front is less than the first time distance threshold and the duration is greater than the first set time, then it is determined that there is a risk of the vehicle in front being too close. If the collision time between the vehicle and the vehicle in front is less than the first collision time threshold, and the duration is greater than the second set time, then a risk of collision with the vehicle in front is determined. If the time distance between your vehicle and the vehicle in front of you is less than the second time distance threshold, and the duration is greater than the third set time, then it is determined that there is a risk of the vehicle in front of you being too close. If the collision time between the vehicle and the vehicle in front is less than the second collision time threshold, and the duration is greater than the fourth set time, then a collision risk with the vehicle in front is determined.

[0031] In one possible implementation, the second perception result includes the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself. Based on the second perception result, determine the time distance between the vehicle and the vehicle in front of it, including: The first distance is determined based on the difference between the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself, and the length of the vehicle in front. The ratio of the first distance to the vehicle's speed is used as the time distance between the vehicle and the vehicle in front of it.

[0032] In one possible implementation, the early warning module is specifically used for: When there is a risk of collision, the corresponding warning method is determined based on different collision risks, and a warning is given to the driver of the vehicle. After a preset warning time, the system proceeds to obtain the vehicle's first perception result of the vehicle ahead and its second perception result of the vehicle ahead of that vehicle. When a collision risk exists and the risk increases, the system determines the corresponding braking parameters based on the existing collision risk and executes the braking operation.

[0033] Thirdly, embodiments of this application provide a vehicle, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the vehicle safety warning method as described in any of the first aspects.

[0034] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle safety warning method as described in any of the first aspects.

[0035] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0036] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application; Figure 2 This is a schematic flowchart of a vehicle safety warning method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating a vehicle safety warning method provided in another embodiment of this application; Figure 4 This is a schematic diagram of the lateral offset of a vehicle provided in an embodiment of this application; Figure 5 This is a flowchart illustrating a vehicle safety warning method provided in another embodiment of this application; Figure 6 This is a schematic diagram of the structure of a vehicle safety warning device provided in one embodiment of this application; Figure 7 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application. Detailed Implementation

[0039] The present application will be described more clearly below with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the function of the present application, but do not limit the present application in any way. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application. These all fall within the protection scope of the present application.

[0040] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0041] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0042] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0043] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0044] Furthermore, the term "multiple" mentioned in the embodiments of this application should be interpreted as two or more.

[0045] The applicant has found that in complex road conditions such as heavy traffic and frequent following, existing vehicle warning methods based solely on the status of the vehicle in front have certain limitations. For example, when following another vehicle, if that vehicle suddenly changes lanes, the applicant may not be able to react in time to recognize the status of the vehicle further ahead (i.e., the vehicle before that), thus failing to provide effective warning or braking, leading to a collision. Alternatively, if the vehicle in front fails to brake in time and rear-ends the vehicle before that, the applicant may also be unable to brake in time and rear-end the vehicle before that, resulting in a chain-reaction collision. Therefore, it is necessary to consider a new vehicle safety warning method.

[0046] To reduce collision risks in complex road conditions, the embodiments of this application, during driving, not only acquire the vehicle's perception results of the vehicle in front, but also the vehicle's perception results of the vehicle before that. By fusing the perception results of the vehicle in front and the vehicle before that, collision risks can be assessed more comprehensively, improving driving safety in complex following scenarios such as when the vehicle in front is obstructed. Furthermore, the embodiments of this application also consider the possibility of obstruction between the vehicle and the vehicle in front, which could lead to lower reliability of the vehicle's perception results of the vehicle in front. Therefore, the embodiments of this application detect and dynamically adjust the vehicle based on the perception results of the vehicle in front, ensuring that the perception results of the vehicle in front are highly reliable, improving the accuracy of judging the state of the vehicle in front, and thus further ensuring driving safety.

[0047] First refer to Figure 1 , Figure 1 The illustration shows an application scenario diagram provided according to an embodiment of the present application, in which the device involved includes a vehicle host 101.

[0048] The application scenario is vehicle warning: The host 101 acquires the vehicle's first perception result of the vehicle in front and the second perception result of the vehicle in front of that vehicle in real time, and checks whether the second perception result is reliable. If the second perception result is unreliable, the vehicle is adjusted and the second perception result is acquired again until the final second perception result is obtained; based on the final second perception result and the first perception result, the collision risk is determined so as to provide timely warning.

[0049] Optionally, the devices involved in the application scenario also include a radar perception module 102 and / or a visual perception module 103 on the vehicle. Both the radar perception module 102 and / or the visual perception module 103 can communicate with the host 101. Specifically, the radar perception module 102 can perform radar perception of the preceding vehicle and the vehicle before that, obtain the radar perception results of the preceding vehicle and the vehicle before that, and send them to the host 101. The visual perception module 103 can also perform visual perception of the preceding vehicle and the vehicle before that, obtain the visual perception results of the preceding vehicle and the vehicle before that, and send them to the host 101. Based on the aforementioned radar perception results and / or visual perception results, the host 101 can determine the vehicle's first perception result of the preceding vehicle and the vehicle's second perception result of the vehicle before that, so as to perform subsequent warning operations based on the perception results.

[0050] For example, the radar sensing module 102 can be a 4D millimeter-wave radar, and the visual sensing module can be a camera.

[0051] The following is combined Figure 1 Application scenarios, refer to Figures 2-5 This application describes a vehicle safety warning method provided according to exemplary embodiments. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way. Rather, the embodiments of this application can be applied to any applicable scenario.

[0052] It should be noted that the embodiments of this application can be applied to vehicles, and the vehicle can be the host of the vehicle, that is, the vehicle safety warning method provided by the exemplary embodiments of this application can be executed on the host of the vehicle.

[0053] refer to Figure 2 , Figure 2 This is a schematic flowchart illustrating a vehicle safety warning method provided in an embodiment of this application. Figure 2 As shown, the method in the embodiments of this application may include: Step 201: Obtain the first perception result of the vehicle in front of it, and the second perception result of the vehicle in front of it.

[0054] Here, the vehicle's radar perception module and / or visual perception module can be used to perceive the vehicle in front, obtaining the vehicle's initial perception result of the vehicle in front. Specifically, if the radar perception module is used to perceive the vehicle in front, the radar perception result can be directly determined as the initial perception result. If the visual perception module is used to perceive the vehicle in front, the visual perception result can be determined as the initial perception result. If both the radar perception module and the visual perception module are used simultaneously to perceive the vehicle in front, the radar perception result and the visual perception result can be determined as the initial perception result.

[0055] Similarly, the radar perception module and / or visual perception module on the vehicle can be used to perceive the vehicle in front, and a second perception result of the vehicle in front of the vehicle can be obtained.

[0056] To improve perception accuracy, in this embodiment, a radar perception module and a visual perception module can be used to obtain the radar perception results and visual perception results of the vehicle relative to the vehicle in front, thus obtaining a first perception result. Similarly, the radar perception module and the visual perception module can be used to obtain the radar perception results and visual perception results of the vehicle relative to the vehicle in front of it, thus obtaining a second perception result.

[0057] Step 202: Detect whether the second perception result is reliable.

[0058] Radar perception results include not only radar perception data such as distance, velocity, acceleration, collision time, and position, but also radar perception confidence level, which characterizes the reliability of the aforementioned radar perception data. A higher radar perception confidence level indicates higher reliability of the radar perception data.

[0059] Similarly, the visual perception results also include visual perception data such as distance, speed, acceleration, and collision time, as well as visual perception confidence level. Among these, the higher the visual perception confidence level, the more reliable the visual perception data.

[0060] When the radar perception result is the same as the second perception result, the reliability of the second perception result can be determined based on the radar perception confidence level. When the visual perception result is the same as the second perception result, the reliability of the second perception result can be determined based on the visual perception confidence level. It is understandable that the higher the radar perception confidence level / visual perception confidence level, the more reliable the second perception result.

[0061] When both radar and visual perception results fall under the category of secondary perception results, the reliability of these secondary perception results can be assessed based on both radar and visual perception confidence levels. Alternatively, the reliability of the secondary perception results can be verified by cross-checking the radar and visual perception data.

[0062] Step 203: If the second perception result is unreliable, adjust the vehicle and reacquire the second perception result, then proceed to the step of detecting whether the second perception result is reliable, until the preset conditions are met and the final second perception result is obtained.

[0063] Considering the possibility of obstruction between the vehicle and the vehicle ahead, the second perception result of the vehicle regarding the vehicle ahead may be unreliable. To address this, this embodiment of the application can adjust the vehicle when the second perception result is determined to be unreliable. The second perception result is reacquired, and its reliability is checked until an adjustment limit is reached or the second perception result is determined to be reliable. Here, the preset conditions may include reaching the vehicle's adjustment limit, or determining that the second perception result is reliable.

[0064] In this embodiment of the application, adjusting the vehicle may include adjusting the perception angle of the vehicle's radar perception module and / or visual perception module, or adjusting the vehicle's position, etc., in order to reacquire new second perception results.

[0065] Step 204: Based on the final second perception result and the first perception result, determine whether there is a collision risk.

[0066] In the case of using only a single radar perception module or visual perception module to perceive the vehicle in front and the vehicle in front of it, the embodiments of this application can directly determine the distance, speed, acceleration, position, collision time and other perception data of the vehicle in front of it relative to the vehicle in front of it based on the perception data of the vehicle in front of it, and then determine whether there is a collision risk between the vehicle in front of it and the vehicle in front of it.

[0067] Similarly, the embodiments of this application can directly determine the distance, speed, acceleration, position, collision time, and other perception data of the vehicle in front relative to the vehicle itself based on the perception data of the vehicle in front, and then determine whether there is a collision risk between the vehicle itself and the vehicle in front.

[0068] When using both radar and visual perception modules to simultaneously perceive the vehicle ahead, this embodiment of the application, after obtaining the second perception result, can first fuse the radar perception data and visual perception data to obtain final fused data such as the distance, speed, acceleration, position, and collision time of the vehicle ahead relative to the vehicle itself. Then, based on the aforementioned final fused data, it is determined whether there is a collision risk between the vehicle and the vehicle ahead.

[0069] Similarly, after obtaining the first perception result in this embodiment, the radar perception data and visual perception data can be fused to obtain final fused data such as the distance, speed, acceleration, position, and collision time of the vehicle in front relative to the vehicle itself. Then, based on the above final fused data, it is determined whether there is a collision risk between the vehicle and the vehicle in front.

[0070] Step 205: If there is a risk of collision, issue a warning.

[0071] Here, if it is determined that there is a collision risk relative to the vehicle in front or the vehicle before that, a warning can be issued through the Human-Machine Interface (HMI). To differentiate between the risk of a collision with the vehicle in front and the vehicle before that, different HMI formats can be used to warn the driver, allowing the driver to distinguish between them.

[0072] This application embodiment adds monitoring of the vehicle before the vehicle in front to the monitoring of the vehicle in front. By fusing the perception results of the vehicle in front and the vehicle before the vehicle in front, the collision risk can be assessed more comprehensively, thereby identifying potential dangers at an earlier stage and assisting the driver to avoid or mitigate collisions in a timely manner through warnings. In particular, it improves driving safety in complex following scenarios such as when the vehicle in front is obstructed. Furthermore, this application embodiment also considers the possibility of obstruction between the vehicle and the vehicle in front, which may result in low reliability of the vehicle's perception of the vehicle in front. Therefore, this application embodiment detects the perception results of the vehicle in front and dynamically adjusts the vehicle to ensure that the perception results of the vehicle in front are highly reliable, thereby significantly improving the accuracy of judging the status of the vehicle in front and further ensuring driving safety.

[0073] The following section will elaborate on the methods for detecting the reliability of the second sensing results.

[0074] To improve perception accuracy, in some embodiments, a radar perception module and a visual perception module can be used to obtain the radar perception results and visual perception results of the vehicle relative to the vehicle in front, thus obtaining a second perception result.

[0075] Here, the second perception result includes radar perception results and visual perception results. Radar perception results include radar perception data and radar perception confidence levels. Visual perception results include visual perception data and visual perception confidence levels.

[0076] Based on this, when determining the reliability of the second perception result, we can first check whether the radar perception confidence level is greater than the first confidence level threshold and whether the visual perception confidence level is greater than the second confidence level threshold. If the radar perception confidence level is greater than the first confidence level threshold and the visual perception confidence level is greater than the second confidence level threshold, then we check whether the data deviation between the radar perception data and the visual perception data is less than the deviation threshold. If the data deviation is less than the deviation threshold, then the second perception result is determined to be reliable.

[0077] Based on the above, the higher the confidence level of radar perception, the higher the reliability of radar perception data. Similarly, the higher the confidence level of visual perception, the higher the reliability of visual perception data. In this embodiment, a first confidence level threshold and a second confidence level threshold are set to detect the confidence levels of radar perception data and visual perception data, respectively.

[0078] Based on the premise that the radar perception confidence level is greater than a first confidence level threshold and the visual perception confidence level is greater than a second confidence level threshold, this embodiment of the application further verifies the radar perception data and the visual perception data. Specifically, it calculates the data deviation between the radar perception data and the visual perception data and detects whether the data deviation is less than a deviation threshold.

[0079] Both radar and visual perception data include distance, velocity, acceleration, position, and collision time. Correspondingly, data deviations include distance deviation, velocity deviation, acceleration deviation, position deviation, and collision time deviation.

[0080] If at least one of the above-mentioned distance deviation, velocity deviation, acceleration deviation, position deviation, and collision time deviation is less than the deviation setting threshold, then the second perception result is determined to be reliable.

[0081] Here, the first confidence level setting threshold, the second confidence level setting threshold, and the deviation setting threshold can be determined according to the actual situation, and this application embodiment does not specifically limit them.

[0082] This application's embodiments filter out low-quality, unreliable perception data by separately checking the perception confidence levels of the radar and visual perception modules. Based on high-quality perception data, cross-validation between the radar and visual perception modules ensures that different perception modules describe the same physical reality. This step-by-step verification method is computationally efficient and logically clear, effectively avoiding error propagation problems that may arise from direct fusion calculations.

[0083] In some embodiments, if the radar perception confidence level is less than or equal to a first confidence level threshold, or if the visual perception confidence level is less than or equal to a second confidence level threshold, then the second perception result is determined to be unreliable. Alternatively, if the data deviation is greater than or equal to a deviation level threshold, the second perception result is also determined to be unreliable.

[0084] In other words, the second perception result is considered reliable only if the radar perception confidence level is greater than the first confidence level threshold, the visual perception confidence level is greater than the second confidence level threshold, and the data deviation is less than the deviation threshold. Otherwise, the second perception result is considered unreliable.

[0085] Here, the reliability of the sensing results is evaluated through two levels: individual unit verification (i.e., checking the sensing confidence of each sensing module) and cross-verification (i.e., checking the data consistency between each sensing module). Unreliable data can be identified from different dimensions, thereby significantly enhancing the fault tolerance capability for situations such as temporary performance degradation of a single sensing module or the generation of heterogeneous errors, and improving the stability and reliability of the system in various complex environments.

[0086] Based on the above assessment of the reliability of the second sensing result, see [link / reference]. Figure 3 This application provides another embodiment for a detailed description of the adjustment method of the vehicle.

[0087] Step 301: Obtain the first perception result of the vehicle in front and the second perception result of the vehicle in front ...

[0088] Step 302: Detect whether the second sensing result is reliable.

[0089] Here, the implementation of steps 301-302 is described in the relevant description in the above embodiments, and will not be repeated here.

[0090] Step 303: If the second perception result is unreliable, then detect whether there are other vehicles within the set range of the left and right lanes adjacent to the vehicle's lane.

[0091] Here, if the second perception result is unreliable, the vehicle's position can be adjusted, thereby adjusting the perception angle of the radar perception module and the visual perception module to obtain a more reliable second perception result.

[0092] Before adjusting the vehicle's position, this embodiment detects whether there are other vehicles within a set range of the left and right lanes adjacent to the vehicle's lane, in order to determine whether the vehicle's surrounding environment is safe and to avoid affecting other nearby vehicles and introducing new collision risks when adjusting the vehicle's position.

[0093] For example, the set range can be a dynamic range defined by taking the vehicle as the center and a set distance as the radius. The specific value of the set distance can be determined according to actual circumstances, and this embodiment of the invention does not impose a specific limitation on it.

[0094] Step 304: If no other vehicles are detected within the set range of the left and right lanes adjacent to the vehicle's lane, then the vehicle is controlled to deviate laterally based on the first perception result and the position of the vehicle's lane line.

[0095] When there are no other vehicles within the set range of the left and right lanes adjacent to the vehicle's lane, the vehicle's surrounding environment is determined to be safe. At this time, the vehicle can be controlled to shift laterally to adjust its position, overcome the problem of the vehicle in front blocking the vehicle in front of it, and thus obtain a more reliable second perception result.

[0096] In this embodiment of the application, after confirming that the surrounding environment of the vehicle is safe, actively controlling the vehicle's deviation can optimize the vehicle's perception field of view, thereby solving the problem of blind spots caused by the obstruction of the vehicle in front, and significantly enhancing the detection capability and perception reliability of distant targets such as the vehicle in front.

[0097] In controlling the lateral deviation of the vehicle, the lateral deviation direction and lateral deviation distance of the vehicle can be determined based on the position of the vehicle in front and the position of the vehicle in the lane.

[0098] In some embodiments, the first perception result includes: the location information of the vehicle in front.

[0099] When using a single radar or visual perception module to perceive the vehicle in front, the position information of the vehicle in front output by the radar or visual perception module can be directly used as the final position information of the vehicle in front.

[0100] When using both radar and visual perception modules to perceive the vehicle ahead, the position information of the vehicle ahead output by the radar and line-of-sight perception modules can be fused together to obtain the final position information of the vehicle ahead.

[0101] In this embodiment of the application, when controlling the lateral deviation of the vehicle, the lateral direction of the preceding vehicle relative to the vehicle can be determined based on the position information of the preceding vehicle, and the opposite direction of the lateral direction can be determined as the lateral deviation direction of the vehicle. Next, based on the position information of the vehicle and the position of the lane line, the lateral distance between the vehicle and the lane line along the lateral deviation direction is determined. Finally, the lateral deviation distance of the vehicle is controlled along the lateral deviation direction.

[0102] Here, combined Figure 4 To explain the lateral offset process of the vehicle, see [link / reference]. Figure 4 When the vehicle in front obstructs the view of the vehicle in front of it, only the radar perception module can receive the radar perception result of the vehicle in front of it. The visual perception module is also obstructed by the vehicle in front and cannot obtain the visual perception result, resulting in a lower reliability of the second perception result. In this case, the lateral direction of the vehicle in front relative to the vehicle can be determined based on the position information of the vehicle in front, and the opposite direction of this lateral direction can be used as the lateral offset direction of the vehicle. For example... Figure 4 As shown, in the lateral direction, the vehicle in front is located to the right of the vehicle. The left side of the vehicle is taken as the lateral offset direction of the vehicle. Next, along the left side of the vehicle, the lateral distance between the vehicle and the left lane line of the vehicle's lane is determined. Finally, the vehicle is controlled to offset the above lateral distance along the left side, so that both the radar perception module and the visual perception module can effectively perceive the vehicle in front, and obtain a more reliable second perception result.

[0103] The purpose of controlling the lateral offset of the vehicle in this embodiment is to bypass the obstruction of the vehicle in front and obtain reliable perception results of the vehicle ahead. Considering that the greater the lateral offset of the vehicle, the more significant the improvement in the viewing angle of the radar perception module and the visual perception module, this embodiment directly controls the vehicle to offset to the edge of the vehicle's lane line, which can quickly create a maximized unobstructed viewing angle, provide the best perception conditions for the radar perception module and the visual perception module, and maximize the reliability of the second perception result.

[0104] In other embodiments, if other vehicles are detected within a set range in the left and right lanes adjacent to the vehicle's lane, the vehicle's lateral deviation is not controlled. Considering that the perception results of the vehicle ahead are unreliable, a collision risk can be determined solely based on the perception results of the vehicle ahead, and a collision warning can then be issued.

[0105] At the same time, it still detects in real time whether there are other vehicles within the set range of the left and right lanes adjacent to the vehicle's lane. Once it is determined that there are no other vehicles within the set range of the left and right lanes adjacent to the vehicle's lane, it controls the vehicle to shift laterally in order to reacquire the second perception result.

[0106] Step 305: Reacquire the second perception result, jump to the step of checking whether the second perception result is reliable, until the preset conditions are met, and obtain the final second perception result.

[0107] After controlling the vehicle's lateral deviation, a new second perception result is acquired, and its reliability is checked. If the second perception result is reliable or the vehicle has reached its lateral deviation limit, the current second perception result is determined as the final second perception result.

[0108] See here. Figure 4 In the lateral direction, when a vehicle deviates to the left, the left lane line of the vehicle's lane is the vehicle's lateral deviation limit. When a vehicle deviates to the right, the right lane line of the vehicle's lane is the vehicle's lateral deviation limit.

[0109] Step 306: Based on the final second perception result and the first perception result, determine whether there is a collision risk.

[0110] Here, the second perception result mainly includes data such as the distance, speed, acceleration, position, and collision time of the vehicle in front relative to the vehicle itself. The first perception result mainly includes data such as the distance, speed, acceleration, position, and collision time of the vehicle in front relative to the vehicle itself.

[0111] This application embodiment can determine the collision risk between the vehicle and the vehicle in front based on the second perception result. The collision risk between the vehicle and the vehicle in front is determined based on the first perception result.

[0112] In some embodiments, the time distance and collision time between the vehicle and the vehicle in front can be determined based on the first perception result; the time distance and collision time between the vehicle and the vehicle in front of it can be determined based on the second perception result; and the existence of a collision risk can be determined based on the time distance and collision time between the vehicle and the vehicle in front of it, and the time distance and collision time between the vehicle and the vehicle in front of it.

[0113] In the second perception result, the distance between the vehicle in front and the vehicle itself can be the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself.

[0114] Based on this, in this embodiment of the application, a first distance can be determined based on the difference between the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself and the length of the vehicle in front; then, the ratio of the first distance to the vehicle speed is used as the time distance between the vehicle and the vehicle in front.

[0115] Here, the difference between the distance between the rear bumper of the car in front and the front bumper of the car itself, and the length of the car in front, is the first distance.

[0116] In this embodiment, the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself is calculated by subtracting the length of the vehicle in front, and then calculating the time distance between the vehicle and the vehicle in front. This time distance value can truly reflect the urgency of the vehicle approaching the vehicle in front, so as to provide timely warnings to the vehicle in front. In scenarios where the vehicle in front may suddenly decelerate due to a rear-end collision with the vehicle in front, the driving safety of the vehicle in front can be guaranteed.

[0117] Similarly, in the first perception result, the distance between the car in front and the car in front can be the distance between the rear bumper of the car in front and the front bumper of the car in front.

[0118] Based on this, in this embodiment of the application, a second distance can be determined according to the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself; then, the ratio of the second distance to the vehicle speed is used as the time distance between the vehicle and the vehicle in front.

[0119] Here, the distance between the rear bumper of the car in front and the front bumper of the car itself is the second distance.

[0120] This application's embodiments primarily determine the collision risk between the vehicle and the vehicle in front based on the time distance and collision time between the vehicle and the vehicle in front.

[0121] In some embodiments, collision risks include: risk of being too close to the vehicle in front, risk of a collision with the vehicle in front, risk of being too close to the vehicle in front of ...

[0122] If the time distance between the vehicle and the vehicle in front is less than the first time distance threshold and the duration is greater than the first set time, then the risk of the vehicle in front being too close is determined.

[0123] If the collision time between the vehicle and the vehicle in front is less than the first collision time threshold, but the duration is greater than the second set time, then a Level 1 forward collision risk is determined.

[0124] If the time distance between your vehicle and the vehicle in front of you is less than the second time distance threshold, and the duration is greater than the third set time, then a risk of the vehicle in front of you being too close is determined.

[0125] If the collision time between the vehicle and the vehicle in front is less than the second collision time threshold, and the duration is greater than the fourth set time, then a Level 1 collision risk with the vehicle in front is determined.

[0126] Here, the first collision time threshold, the second collision time threshold, the first time interval threshold, the second time interval threshold, the first set time, the second set time, the third set time, and the fourth set time can all be set according to the actual situation, and this application embodiment does not make specific limitations on this.

[0127] This application embodiment subdivides the risk type from a single collision risk into over-closeness risk and collision risk, and independently judges the preceding vehicle and the vehicle before that. This design enables the system to identify potential threats of different levels and sources (such as following too closely, impending rear-end collision, etc.) earlier and more accurately, laying a solid foundation for achieving graded response. Furthermore, this application embodiment sets dual conditions of threshold triggering and duration for the judgment of each risk type, which can effectively filter out instantaneous jitter and false alarms caused by sensing module noise, vehicle bumps, or the brief entry and exit of the target, ensuring that only persistent real risks will trigger the system response, greatly enhancing the robustness and reliability of the system.

[0128] Step 307: When there is a collision risk, determine the corresponding warning method based on different collision risks and issue a warning to the driver of the vehicle.

[0129] Based on the different collision risks mentioned above, different HMI (Hazard Management Interface) formats can be used to warn drivers, making it easier for them to distinguish between different types of collision risks. For example, different HMI formats may include different types of icon flashing or voice prompts.

[0130] Step 308: After the preset warning time, proceed to the step of obtaining the first perception result of the vehicle in front and the second perception result of the vehicle in front ...

[0131] After the warning has been in effect for a preset time, the first and second perception results are reacquired to re-detect the collision risk of the vehicle ahead and the vehicle in front. If the collision risk of the vehicle ahead or the vehicle in front still exists and the collision risk has increased, braking is initiated.

[0132] Here, based on the collision time between the vehicle and the vehicle in front, and the collision time between the vehicle and the vehicle in front, it is possible to detect whether the risk of collision with the vehicle in front and the vehicle in front of it has increased.

[0133] Specifically, if the collision time between the vehicle and the vehicle in front is less than the third collision time threshold, but the duration is greater than the fifth set time, then the risk of collision with the vehicle in front is determined to be increased. The third collision time threshold is less than the first collision time threshold.

[0134] If the collision time between the vehicle and the vehicle in front is less than the fourth collision time threshold, but the duration is greater than the sixth set time, then the risk of collision with the vehicle in front is determined to be increased. The fourth collision time threshold is less than the second collision time threshold.

[0135] Here, the third collision time threshold, the fourth collision time threshold, the fifth set time, and the sixth set time can all be set according to the actual situation, and this application embodiment does not make specific limitations on this.

[0136] It should be noted that in this embodiment, braking is only performed when the risk of collision with the vehicle in front increases and / or the risk of collision with the vehicle in front of that vehicle increases. Braking is not actively performed for risks of the vehicle in front being too close or the vehicle in front of that vehicle being too close, in order to minimize driving interference for the driver and avoid disrupting the driver's driving experience due to frequent braking.

[0137] In this embodiment, the braking parameter can be deceleration. Considering that the risk of a collision with a preceding vehicle is a direct and urgent survival risk, while the risk of a collision with a vehicle two steps ahead is an indirect and predictable early warning risk, this embodiment can apply a larger deceleration when performing braking operations to address the risk of a collision with a preceding vehicle. Conversely, when performing braking operations to address the risk of a collision with a vehicle two steps ahead, a smaller deceleration can be applied, thereby maximizing comfort and driving experience while ensuring safety and avoiding frequent sudden braking.

[0138] Considering that unreliable forward collision detection results may affect the accuracy of collision risk perception, potentially leading to false triggering of warnings or braking actions, this application also provides another vehicle safety warning method, detailed in [link to details]. Figure 5 : After obtaining the perception results of the vehicle ahead (i.e., the second perception result), the reliability of the perception results of the vehicle ahead is checked. If the perception results of the vehicle ahead are reliable, the collision risk of the vehicle ahead and the collision risk of the vehicle ahead are calculated based on the perception results of the vehicle ahead (i.e., the first perception result) and the perception results of the vehicle ahead, and then it is determined whether there is a collision risk. If it is determined that there is a collision risk, a warning or braking operation is performed.

[0139] If the perception result of the preceding vehicle is unreliable, an environmental condition check is performed, which checks whether there are other vehicles within a set range in the left and right lanes adjacent to the vehicle's lane. If the environmental conditions meet the requirements, i.e., there are no other vehicles within the set range, the vehicle is controlled to laterally shift within its own lane, and the perception result of the preceding vehicle is reacquired to check its reliability. If the environmental conditions do not meet the requirements, the process jumps to the environmental condition check step until the environmental conditions meet the requirements, at which point the vehicle is controlled to laterally shift, and the perception result of the preceding vehicle is reacquired.

[0140] In this embodiment, if the perception results of the preceding vehicle are unreliable, the time delay and collision time can be calculated based solely on the perception results of the preceding vehicle, thereby determining the collision risk and enabling the execution of warning or braking operations.

[0141] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0142] Figure 6 This is a schematic diagram of the structure of a vehicle safety warning device provided in one embodiment of this application. Figure 6 As shown, the vehicle safety warning device provided in this embodiment may include: an acquisition module 601, a detection module 602, and a warning module 603.

[0143] The acquisition module 601 is used to acquire the first perception result of the vehicle in front of it and the second perception result of the vehicle in front of it.

[0144] The processing module 602 is used to detect whether the second sensing result is reliable.

[0145] Early warning module 603 is used for: If the second perception result is unreliable, the vehicle is adjusted and the second perception result is reacquired. The process then jumps to the step of checking whether the second perception result is reliable until the preset conditions are met and the final second perception result is obtained. Based on the final second perception results and the first perception results, determine whether there is a risk of collision; If there is a risk of collision, a warning will be issued.

[0146] In one possible implementation, the early warning module 603 is specifically used for: Detect whether there are other vehicles within a set range of the left and right lanes adjacent to the vehicle's lane; If no other vehicles are detected within the set range of the left and right lanes adjacent to the vehicle's lane, the vehicle will be controlled to deviate laterally based on the first perception result and the position of the vehicle's lane line.

[0147] In one possible implementation, the first perception result includes: the position information of the vehicle in front; Early warning module 603 is specifically used for: Based on the position information of the vehicle in front, determine the lateral direction of the vehicle in front relative to the vehicle itself; The opposite direction of the lateral direction is determined as the lateral offset direction of the vehicle; Based on the vehicle's location information and lane line position, determine the lateral distance between the vehicle and the lane line along the lateral offset direction. Control the lateral distance of the vehicle's offset along the lateral offset direction.

[0148] In one possible implementation, the second perception result includes radar perception result and visual perception result; the radar perception result includes radar perception data and radar perception confidence, and the visual perception result includes visual perception data and visual perception confidence. Detection module 602 is specifically used for: The system detects whether the radar perception confidence level is greater than a first confidence level threshold and whether the visual perception confidence level is greater than a second confidence level threshold. If the radar perception confidence level is greater than the first confidence level threshold and the visual perception confidence level is greater than the second confidence level threshold, then it is detected whether the data deviation between the radar perception data and the visual perception data is less than the deviation threshold. If the data deviation is less than the deviation setting threshold, then the second perception result is determined to be reliable.

[0149] In one possible implementation, the detection module 602 is further configured to: If the radar perception confidence level is less than or equal to the first confidence level threshold, or the visual perception confidence level is less than or equal to the second confidence level threshold, then the second perception result is determined to be unreliable. If the data deviation is greater than or equal to the deviation setting threshold, the second perception result is determined to be unreliable.

[0150] In one possible implementation, the early warning module 603 is specifically used for: Based on the initial perception results, determine the time distance and collision time between the vehicle and the vehicle in front; Based on the second perception results, determine the time distance and collision time between the vehicle and the vehicle in front of it; Based on the time distance and collision time between the vehicle and the vehicle in front, as well as the time distance and collision time between the vehicle and the vehicle two steps ahead, determine whether there is a risk of collision.

[0151] In one possible implementation, collision risks include: risk of the vehicle in front being too close, risk of a collision with the vehicle in front, risk of the vehicle in front being too close, and risk of a collision with the vehicle in front of the vehicle in front. Early warning module 603 is specifically used for: If the time distance between the vehicle and the vehicle in front is less than the first time distance threshold and the duration is greater than the first set time, then it is determined that there is a risk of the vehicle in front being too close. If the collision time between the vehicle and the vehicle in front is less than the first collision time threshold, and the duration is greater than the second set time, then a risk of collision with the vehicle in front is determined. If the time distance between your vehicle and the vehicle in front of you is less than the second time distance threshold, and the duration is greater than the third set time, then it is determined that there is a risk of the vehicle in front of you being too close. If the collision time between the vehicle and the vehicle in front is less than the second collision time threshold, and the duration is greater than the fourth set time, then a collision risk with the vehicle in front is determined.

[0152] In one possible implementation, the second perception result includes the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself. Early warning module 603 is specifically used for: The first distance is determined by the difference between the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle in front, and the length of the vehicle in front. The ratio of the first distance to the vehicle's speed is used as the time distance between the vehicle and the vehicle in front of it.

[0153] In one possible implementation, the early warning module 603 is specifically used for: When there is a risk of collision, the corresponding warning method is determined based on different collision risks, and a warning is given to the driver of the vehicle. After the preset warning time, the system jumps to the steps of obtaining the first perception result of the vehicle in front and the second perception result of the vehicle in front of the first vehicle. When there is a collision risk and the collision risk is aggravated, the corresponding braking parameters are determined based on the existing collision risk, and the braking operation is performed.

[0154] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0155] Figure 7 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application. Figure 7 As shown, the vehicle 700 of this embodiment includes a processor 710 and a memory 720, wherein the memory 720 stores a computer program 721 that can run on the processor 710. When the processor 710 executes the computer program 721, it implements the steps in any of the above method embodiments, for example... Figure 2 Steps 201 to 205 are shown. Alternatively, when processor 710 executes computer program 721, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 6The functions of modules 601 to 603 are shown.

[0156] For example, computer program 721 may be divided into one or more modules / units, one or more of which are stored in memory 720 and executed by processor 710 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 721 in vehicle 700.

[0157] Those skilled in the art will understand that Figure 7 This is merely an example of a vehicle and does not constitute a limitation on the vehicle. It may include more or fewer components than shown, or combinations of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0158] The processor 710 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0159] The memory 720 can be an internal storage unit of the vehicle, such as a hard drive or memory, or an external storage device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. The memory 720 can also include both internal and external storage devices. The memory 720 is used to store computer programs and other programs and data required by the vehicle. The memory 720 can also be used to temporarily store data that has been output or will be output.

[0160] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0161] An embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle safety warning method.

[0162] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0163] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0164] In the embodiments provided in this application, it should be understood that the disclosed devices / vehicles and methods can be implemented in other ways. For example, the device / vehicle embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0165] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0166] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0167] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0168] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A vehicle safety early warning method, characterized in that, include: Obtain the vehicle's first perception of the vehicle in front, and the vehicle's second perception of the vehicle in front of that vehicle; To determine whether the results of the second sensing are reliable; If the second perception result is unreliable, the vehicle is adjusted and the second perception result is reacquired. The process then jumps to the step of checking whether the second perception result is reliable until the preset conditions are met and the final second perception result is obtained. Based on the final second perception result and the first perception result, determine whether there is a collision risk; If there is a risk of collision, a warning will be issued.

2. The vehicle safety early warning method according to claim 1, characterized in that, The adjustments made to the vehicle include: Detect whether there are other vehicles within a set range of the left and right lanes adjacent to the vehicle's lane; If no other vehicles are detected within the set range of the left and right lanes adjacent to the vehicle's lane, the vehicle will be controlled to deviate laterally based on the first perception result and the position of the vehicle's lane line.

3. The vehicle safety early warning method according to claim 2, characterized in that, The first perception result includes: the position information of the vehicle in front; The step of controlling the lateral deviation of the vehicle based on the first perception result and the position of the vehicle's lane line includes: Based on the position information of the preceding vehicle, the lateral direction of the preceding vehicle relative to the vehicle itself is determined; The opposite direction of the lateral direction is determined as the lateral offset direction of the vehicle; Based on the vehicle's location information and the lane line position, the lateral distance between the vehicle and the lane line along the lateral offset direction is determined. Along the lateral offset direction, the vehicle is controlled to offset the lateral distance.

4. The vehicle safety early warning method according to any one of claims 1 to 3, characterized in that, The second perception result includes radar perception result and visual perception result; the radar perception result includes radar perception data and radar perception confidence level, and the visual perception result includes visual perception data and visual perception confidence level. The determination of whether the second sensing result is reliable includes: Detect whether the radar perception confidence level is greater than a first confidence level threshold, and whether the visual perception confidence level is greater than a second confidence level threshold; If the radar perception confidence level is greater than the first confidence level threshold and the visual perception confidence level is greater than the second confidence level threshold, then it is detected whether the data deviation between the radar perception data and the visual perception data is less than the deviation threshold. If the data deviation is less than the deviation setting threshold, then the second perception result is determined to be reliable.

5. The vehicle safety early warning method according to claim 4, characterized in that, After detecting whether the radar perception confidence level is greater than a first confidence level threshold and whether the visual perception confidence level is greater than a second confidence level threshold, the method further includes: If the radar perception confidence level is less than or equal to the first confidence level threshold, or if the visual perception confidence level is less than or equal to the second confidence level threshold, then the second perception result is determined to be unreliable. After detecting whether the data deviation between the radar sensing data and the visual sensing data is less than a set deviation threshold, the method further includes: If the data deviation is greater than or equal to the deviation setting threshold, then the second perception result is determined to be unreliable.

6. The vehicle safety early warning method according to any one of claims 1 to 3, characterized in that, The step of determining whether there is a collision risk based on the final second perception result and the first perception result includes: Based on the initial perception results, determine the time distance and collision time between the vehicle and the vehicle in front; Based on the second perception results, determine the time distance and collision time between the vehicle and the vehicle in front of it; Based on the time distance and collision time between the vehicle and the vehicle in front, as well as the time distance and collision time between the vehicle and the vehicle two steps ahead, determine whether there is a risk of collision.

7. The vehicle safety early warning method according to claim 6, characterized in that, The collision risks include: the risk of the vehicle in front being too close, the risk of a collision with the vehicle in front, the risk of the vehicle in front of the vehicle being too close, and the risk of a collision with the vehicle in front of the vehicle. The determination of whether a collision risk exists based on the time distance and collision time between the vehicle and the vehicle in front, and the time distance and collision time between the vehicle and the vehicle two steps ahead, includes: If the time distance between the vehicle and the vehicle in front is less than the first time distance threshold and the duration is greater than the first set time, then it is determined that there is a risk of the vehicle in front being too close. If the collision time between the vehicle and the vehicle in front is less than the first collision time threshold, and the duration is greater than the second set time, then a risk of collision with the vehicle in front is determined. If the time distance between your vehicle and the vehicle in front of you is less than the second time distance threshold, and the duration is greater than the third set time, then it is determined that there is a risk of the vehicle in front of you being too close. If the collision time between the vehicle and the vehicle in front is less than the second collision time threshold, and the duration is greater than the fourth set time, then a collision risk with the vehicle in front is determined.

8. The vehicle safety early warning method according to claim 6, characterized in that, The second perception result includes the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself; Based on the second perception result, determine the time distance between the vehicle and the vehicle in front of it, including: The first distance is determined based on the difference between the distance between the rear bumper of the vehicle in front and the front bumper of the vehicle itself, and the length of the vehicle in front. The ratio of the first distance to the vehicle's speed is used as the time distance between the vehicle and the vehicle in front of it.

9. The vehicle safety early warning method according to any one of claims 1 to 3, characterized in that, If a collision risk exists, a warning will be issued, including: When there is a risk of collision, the corresponding warning method is determined based on different collision risks, and a warning is given to the driver of the vehicle. After the preset warning time, the system jumps to the steps of obtaining the first perception result of the vehicle in front and the second perception result of the vehicle in front of the first vehicle. When there is a collision risk and the collision risk is aggravated, the corresponding braking parameters are determined based on the existing collision risk, and the braking operation is performed.

10. A vehicle comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the vehicle safety warning method as described in any one of claims 1 to 9.

Images