Vehicle collision early warning method, controller, vehicle and storage medium
By obtaining information about the bicycle and surrounding vehicles and environmental information, calculating the expected collision time and determining the personalized collision time threshold, the problem that collision warning in the prior art cannot adapt to the driver's style is solved, and more accurate and adaptable collision warning is achieved, which improves driving safety.
Patent Information
- Application Number
- CN202510398599.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-31
- Publication Date
- 2025-07-04
AI Technical Summary
In the prior art, the unified standard vehicle collision warning cannot adapt to the driving styles of different drivers, resulting in insufficient accuracy and adaptability of the collision warning, which reduces the effectiveness of the system.
By obtaining the bicycle and vehicle information of the target vehicle, the surrounding vehicle information and the current environment information, the estimated collision time is calculated, and a personalized collision time threshold is determined based on the driving risk image information. Only when the expected collision time is less than the threshold is performed.
It improves the accuracy and adaptability of vehicle collision warning, makes collision warning more in line with the driver's driving style, and enhances driving safety.
Smart Images
Figure CN120260327A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle collision warning, and particularly to a vehicle collision warning method, a controller, a vehicle, and a storage medium. Background Art
[0002] Currently, human errors such as inaccurate driver's grasp of the surrounding road traffic conditions and inattentive driver's attention are the main causes of vehicle collision accidents. In the prior art, there are solutions for warning potential vehicle collision risks based on perception or kinematic models. However, in the above solutions, a unified standard for triggering collision warnings is often set for all drivers and all different scenarios, which will lead to insufficient accuracy and adaptability of the collision warnings, and even cause drivers to distrust the system, reducing the effectiveness of the system. Summary of the Invention
[0003] Based on this, it is necessary to provide a vehicle collision warning method, a controller, a controller, and a storage medium for the above technical problems, so as to solve the problem that the unified standard for triggering collision warnings in the prior art cannot adapt to the driving styles of all drivers, resulting in insufficient accuracy and adaptability of the collision warnings and reducing the effectiveness of the system.
[0004] A vehicle collision warning method includes: Obtaining vehicle information and the current environmental information of the target vehicle; the vehicle information includes the own vehicle information and the surrounding vehicle information of the target vehicle; Determining the predicted collision time corresponding to the target vehicle according to the own vehicle information and the surrounding vehicle information; Determining the driving risk portrait information of the target vehicle according to the current environmental information, and determining the collision time threshold corresponding to the target vehicle according to the own vehicle information and the driving risk portrait information; Performing a collision warning operation when it is determined that the predicted collision time is less than the collision time threshold.
[0005] A controller includes a processor and a memory, the memory stores an executable program, and the processor is used to execute the executable program to implement the vehicle collision warning method as described above.
[0006] A vehicle includes the above controller.
[0007] A computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a controller, the controller is caused to execute the vehicle collision warning method as described above.
[0008] In the vehicle collision warning method of the present invention, it is necessary to obtain the vehicle information of the host vehicle, the information of surrounding vehicles, and the current environment information of the target vehicle, so as to calculate the predicted collision time between the target vehicle and the surrounding vehicles based on the vehicle information of the host vehicle and the information of surrounding vehicles. Furthermore, based on the driving risk portrait information corresponding to different environment information, the driving risk portrait information corresponding to the current environment information of the target vehicle is determined, and according to the vehicle information of the host vehicle and the driving risk portrait information, the collision time threshold corresponding to the target vehicle is accurately determined, thereby realizing the determination of the personalized collision warning method, and further improving the accuracy of vehicle collision warning, making the vehicle collision warning more in line with the driving style of the driver; and, in the present invention, the collision warning operation is only executed when it is determined that the predicted collision time is less than the collision time threshold, which greatly improves the adaptability and effectiveness of vehicle collision warning, and further enhances the driving safety. Brief Description of the Drawings
[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.
[0010] Figure 1 is a flowchart of a vehicle collision warning method in an embodiment of the present invention; Figure 2 is a flowchart of step S20 of a vehicle collision warning method in an embodiment of the present invention; Figure 3 is a flowchart of step S30 of a vehicle collision warning method in an embodiment of the present invention; Figure 4 is a flowchart of step S30 of a vehicle collision warning method in another embodiment of the present invention. Detailed Description of the Embodiments
[0011] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.
[0012] In one embodiment, as Figure 1 shown, a vehicle collision warning method is provided, including the following steps S10-S40: S10. Obtain the vehicle information and the current environment information of the target vehicle; the vehicle information includes the ego-vehicle information of the target vehicle and the information of surrounding vehicles.
[0013] Understandably, the vehicle information includes the ego-vehicle information of the target vehicle and the information of surrounding vehicles. The target vehicle refers to the vehicle for which the time to collision needs to be calculated (i.e., the ego-vehicle). The current environment information refers to the information of the environment where the target vehicle is located. For example, weather, lighting, road type, traffic flow density, etc. The ego-vehicle information refers to the driving information of the target vehicle, such as vehicle speed, vehicle acceleration, etc. The information of surrounding vehicles refers to the information of vehicles located in the same lane or adjacent lanes within a certain distance range of the target vehicle. For example, all relevant driving information of vehicles in the same lane or adjacent lanes within the lateral range of [-5.625m, 5.625m] and the longitudinal range of [-L, L] can be regarded as the information of surrounding vehicles. The size of L can be set according to specific requirements. For example, take , where is the ego-vehicle speed (m / s), and THW is the calibratable time headway parameter.
[0014] Specifically, the information of the target vehicle and the information of surrounding vehicles are collected through multiple sensors, radars, and cameras installed on the target vehicle. That is, the ego-vehicle information of the target vehicle is collected through sensors, and the information of surrounding vehicles is collected through sensors and radars. That is, the vehicle information such as the speed and acceleration of surrounding vehicles is collected according to the preset lateral range and longitudinal range, so as to obtain the ego-vehicle information and the information of surrounding vehicles of the target vehicle, and determine them as the vehicle information. At the same time, the environment information around the target vehicle is collected through multiple sensors, radars, and cameras, and the traffic flow density, weather, lighting, road type, and driving scenario around the target vehicle are collected according to the preset collection requirements, so as to obtain the current environment information of the target vehicle.
[0015] S20. Determine the predicted time to collision corresponding to the target vehicle according to the ego-vehicle information and the information of surrounding vehicles.
[0016] Understandably, the predicted time to collision refers to the estimated time remaining until the two vehicles collide determined according to the ego-vehicle information and the information of surrounding vehicles. Specifically, the relative information between the target vehicle and the surrounding vehicles, such as relative speed, relative acceleration, and relative distance, is first calculated through the ego-vehicle information and the information of surrounding vehicles. Then, a time to collision calculation model is obtained, and all relative information is input into the time to collision calculation model. The time to collision calculation model calculates according to all relative information, so as to obtain the predicted time to collision corresponding to the target vehicle.
[0017] S30. Determine the driving risk profile information of the target vehicle according to the current environmental information, and determine the collision time threshold corresponding to the target vehicle according to the information of the host vehicle and the driving risk profile information.
[0018] Understandably, the driving risk profile information includes the driving style information of the vehicle in the current environmental information. The collision time threshold refers to a pre-determined time threshold that can be used to determine whether to execute a collision warning. In the present invention, this collision time threshold is associated with the driving style information of the driver.
[0019] Specifically, to determine the driving risk profile information of the target vehicle according to the current environmental information, it is first necessary to determine the tags corresponding to each piece of information in the current environmental information. Then, based on all the tags, the driving risk profile information corresponding to the current environmental information of the target vehicle is screened out from all the driving risk images. Next, determine the collision time threshold corresponding to the target vehicle according to the information of the host vehicle and the driving risk profile information, that is, jointly screen out the collision time threshold that matches the target vehicle through information such as the vehicle speed in the host vehicle information and the driving risk profile information.
[0020] Among them, the current environmental information may include one or more of traffic flow density, current weather, current lighting, current road type, and current driving scenario, and the corresponding tags may also be multiple. In this case, setting tags corresponding to the current environmental information and matching the driving risk profile through the tags can more flexibly realize the dynamic configuration of the driving risk profile information. As long as the tags are appropriately adjusted, a new configuration strategy can be obtained. If new factors affecting the risk are found, as long as new tags are added, it can be achieved, which is easy for the rapid iteration of the software.
[0021] S40. When it is determined that the predicted collision time is less than the collision time threshold, perform a collision warning operation.
[0022] Understandably, the collision warning operation refers to a collision warning prompt issued through information with a prompting nature such as text, sound, or light.
[0023] Specifically, compare the predicted collision time with the collision time threshold. When the predicted collision time is greater than or equal to the collision time threshold, it means that the risk of collision between the target vehicle and surrounding vehicles is small. At this time, the above step S10 can be returned to continue monitoring the predicted collision time. When it is determined that the predicted collision time is less than the collision time threshold, it means that the risk of collision between the target vehicle and surrounding vehicles is large at this time, and a collision warning operation needs to be performed according to the preset warning prompt (pre-set prompt information such as text, sound, or light) to prompt the driver of the target vehicle to perform corresponding deceleration, braking, turning, etc.
[0024] In this embodiment, it is necessary to obtain the vehicle information of the host vehicle, the information of surrounding vehicles, and the current environment information of the target vehicle, so as to calculate the predicted collision time between the target vehicle and the surrounding vehicles based on the vehicle information of the host vehicle and the information of surrounding vehicles. Furthermore, based on the driving risk portrait information corresponding to different environment information, the driving risk portrait information corresponding to the current environment information of the target vehicle is determined, and based on the vehicle information of the host vehicle and the driving risk portrait information, the collision time threshold corresponding to the target vehicle is accurately determined, thereby realizing the determination of the personalized collision warning method, and further improving the accuracy of vehicle collision warning, making the vehicle collision warning more in line with the driving style of the driver; moreover, in the present invention, the collision warning operation is only executed when it is determined that the predicted collision time is less than the collision time threshold, greatly improving the adaptability and effectiveness of vehicle collision warning, and further enhancing the driving safety.
[0025] In one embodiment, as Figure 2 shown, in step S20, that is, to determine the predicted collision time corresponding to the target vehicle according to the vehicle information of the host vehicle and the information of surrounding vehicles, includes: S201. Determine the relative speed, relative acceleration, and relative distance between the target vehicle and the surrounding vehicles according to the vehicle information of the host vehicle and the information of surrounding vehicles.
[0026] S202. Input the relative speed, the relative acceleration, and the relative distance into the collision time calculation model, and obtain the predicted collision time corresponding to the target vehicle output by the collision time calculation model.
[0027] It can be understood that the relative speed refers to the speed between one object and another object. The relative speed in this example refers to the speed difference between the target vehicle and the surrounding vehicles. The relative acceleration refers to the acceleration between one object and another object. The relative acceleration in this example refers to the acceleration difference between the target vehicle and the surrounding vehicles. The relative distance refers to the distance between one object and another object. The relative distance in this embodiment refers to the difference between the actual distance between the target vehicle and the surrounding vehicles and the safety distance. The collision time calculation model can refer to a pre-set collision time calculation formula.
[0028] Specifically, after obtaining vehicle information, based on the information of the host vehicle and surrounding vehicles, the relative speed, relative acceleration, and relative distance between the target vehicle and the surrounding vehicles are determined. That is, the host vehicle speed and host vehicle acceleration in the host vehicle information are obtained, as well as the other vehicle speed and other vehicle acceleration in the surrounding vehicle information, and the actual distance and preset safety distance between the two vehicles are obtained. Then, the difference between the host vehicle speed and the other vehicle speed is calculated to obtain the relative speed, and the difference between the host vehicle acceleration and the other vehicle acceleration is calculated to obtain the relative acceleration. Similarly, the difference between the actual distance and the safety distance is calculated to obtain the relative distance. Among them, the safety distance can be set according to factors such as road conditions and vehicle speed. For example, a longer safety distance is set on rainy and snowy days, and a shorter safety distance is set on cloudy and sunny days. The safety distance can also be set in combination with vehicle speed information. The faster the vehicle speed, the longer the required safety distance, and the slower the vehicle speed, the shorter the required safety distance. Further, a collision time calculation model is obtained, and the relative speed, relative acceleration, and relative distance are input into the collision time calculation model. The collision time calculation model calculates the collision time for the relative speed, relative acceleration, and relative distance, that is, calculates the collision time for the relative speed, relative acceleration, and relative distance through the collision time calculation formula learned during training, so as to obtain the predicted collision time corresponding to the target vehicle.
[0029] In this embodiment, through the collision time calculation model, the rapid calculation of the collision time is realized, the accuracy of the collision time is improved, the collision warning is made more in line with the driving style, and thus the adaptability and effectiveness of the vehicle collision warning are improved.
[0030] In one embodiment, that is, the collision time calculation model, includes: TTC Wherein: TTC is the predicted collision time; is the relative distance between the target vehicle and the surrounding vehicles; Δ a is the relative acceleration between the target vehicle and the surrounding vehicles; is the relative speed between the target vehicle and the surrounding vehicles.
[0031] In one embodiment, in step S30, that is, determining the driving risk portrait information of the target vehicle according to the current environment information, includes: S301. Determine the environment label according to the current environment information; S302. Determine the target driving scenario of the target vehicle according to the environment label, and determine the driving risk portrait information of the target vehicle according to the target driving scenario.
[0032] Specifically, after obtaining the current environmental information, determine the environmental label according to the current environmental information, that is, obtain the label mapping relationship, and perform label matching on each piece of information in the current environmental information through the label mapping relationship, so as to obtain the environmental label corresponding to the current environmental information. Then, determine the target driving scenario of the target vehicle according to the environmental label, that is, perform scenario matching through the environmental labels corresponding to each piece of information in the current environmental information, that is, filter out the historical scenarios including the current environmental information, and determine the historical scenario as the target driving scenario of the target vehicle. Next, determine the driving risk profile information of the target vehicle according to the target driving scenario, that is, perform information matching on the preset risk profile information through the target driving scenario, so as to obtain the driving risk profile information corresponding to the target driving scenario and determine it as the driving risk profile information of the target vehicle.
[0033] This embodiment determines the environmental label through the current environmental information, realizes the determination of the environmental label, thereby realizes the matching of the target driving scenario, and further realizes the acquisition of the driving risk profile information, improving the adaptability of subsequent collision warning operations.
[0034] In one embodiment, as Figure 3 shown, in step S30, that is, determining the driving risk profile information of the target vehicle according to the current environmental information, the current environmental information includes traffic flow density, current weather, current illumination, current road type, and current driving scenario, including: S303. Determine the environmental label according to the current environmental information, where the environmental label includes a traffic density label corresponding to the traffic flow density, a weather label corresponding to the current weather, an illumination label corresponding to the current illumination, a road type label corresponding to the current road type, and a driving scenario label corresponding to the current driving scenario.
[0035] S304. Determine the target driving scenario of the target vehicle according to the traffic density label, the weather label, the illumination label, the road type label, and the driving scenario label, and determine the driving risk profile information of the target vehicle according to the target driving scenario.
[0036] Understandably, the current environmental information includes traffic flow density, current weather, current lighting, current road type, and current driving scenario. The preset time window refers to a sliding window of a preset time. For example, a sliding window of one hour. The current time point refers to the current time. For example, 17:22:33 on March 25, 2025. The environmental label refers to the label corresponding to the current environmental information. The environmental label includes a traffic density label corresponding to the traffic flow density, a weather label corresponding to the current weather, a lighting label corresponding to the current lighting, a road type label corresponding to the current road type, and a driving scenario label corresponding to the current driving scenario. The target driving scenario refers to the scenario of all label combinations. For example, a combined scenario where the traffic density label is dense, the weather label is sunny, the lighting label is daytime, the road type label is intersection, and the driving scenario label is straight ahead.
[0037] Specifically, after obtaining the current environmental information of the target vehicle, obtain the preset time window, and determine the current environmental information within the preset time window before the current time point through the preset time window. Then, through the label mapping relationship, according to the traffic flow density, current weather, current lighting, current road type, and current driving scenario included in the current environmental information, determine the environmental label corresponding to the current environmental information, that is, determine the label corresponding to each piece of information in the current environmental information one by one through the mapping relationship, and determine all the labels as the environmental label. Further, determine the target driving scenario of the target vehicle according to the traffic density label, weather label, lighting label, road type label, and driving scenario label, that is, perform scenario matching on the traffic density label, weather label, lighting label, road type label, and driving scenario label, that is, filter out the historical combined scenarios that simultaneously include the traffic density label, weather label, lighting label, road type label, and driving scenario label, and determine them as the target driving scenario. In another embodiment, calculate the historical combined scenario with the highest similarity to the traffic density label, weather label, lighting label, road type label, and driving scenario label, and determine it as the target driving scenario. Then, determine the driving risk profile information of the target vehicle according to the target driving scenario, that is, perform information matching on the preset risk profile information through the target driving scenario, so as to obtain the driving risk profile information corresponding to the target driving scenario, and determine it as the driving risk profile information of the target vehicle.
[0038] This embodiment determines the environmental label through the current environmental information, realizes the determination of the traffic density label, weather label, lighting label, road type label, and driving scenario label, thereby realizes the matching of the target driving scenario and the determination of the driving risk profile information, and further ensures the accuracy of the subsequent time-to-collision threshold and improves the adaptability of the subsequent execution of the collision warning operation.
[0039] In one embodiment, as Figure 4As shown in the figure, in step S30, that is, determining the collision time threshold corresponding to the target vehicle according to the self-vehicle information and the driving risk profile information includes: S305. Obtain the current collision time threshold associated with the driver of the target vehicle.
[0040] S306. Determine the risk response time of the driver of the target vehicle to the collision risk according to the self-vehicle information and the driving risk profile information.
[0041] S307. Adjust the current collision time threshold according to the risk response time to obtain the collision time threshold corresponding to the target vehicle.
[0042] Understandably, the current collision time threshold refers to the collision time threshold currently used by the driver. If no adjustment has been made to the collision event threshold currently, the current collision time threshold is the initial collision time threshold, which is the initial value default set when the vehicle leaves the factory. If an adjustment has been made to the collision event threshold currently, the current collision time threshold is the collision time threshold adjusted for this driver last time. The risk time refers to the reaction time from encountering a risk to taking corresponding measures. The identity identifier refers to the unique identity identifier of the driver. The driver monitoring system refers to the DriveMonitor System, abbreviated as DMS, which mainly monitors details such as the driver's head, eyes, and face in real time through a camera facing the driver. In this embodiment, it is used to identify the identity identifier of the driver.
[0043] Specifically, after determining the driving risk profile information, identify the identity identifier of the driver of the target vehicle through the driver monitoring system installed on the vehicle, that is, collect the driver image of the driver of the target vehicle through the driver monitoring system installed on the vehicle, and identify the identity identifier of the driver according to the driver image. Then, obtain the current collision time threshold associated with the driver of the target vehicle through the environment label. Then, perform risk clustering processing on the self-vehicle information according to the traffic density label, weather label, light label, road type label, and driving scene label, that is, cluster the traffic density label, weather label, light label, road type label, and driving scene label respectively to obtain risk clustering clusters. Obtain the central values corresponding to the first risk clustering cluster, second risk clustering cluster, third risk clustering cluster, fourth risk clustering cluster, and fifth risk clustering cluster in the risk clustering clusters, and determine the risk response time according to all the central values. Then, adjust the current collision time threshold according to the risk response time, that is, adjust the size of the current collision time threshold through the risk response time. That is, the faster the risk response time, the smaller the collision time threshold. On the contrary, the slower the risk response time, the larger the collision time threshold, so as to obtain the collision time threshold corresponding to the target vehicle.
[0044] In this embodiment, through the vehicle information of the host vehicle and the driving risk profile information, the calculation of the driver's risk response time is realized, and then the adjustment of the current collision time threshold is realized, the determination of the collision time threshold is realized, the accuracy of collision warning is improved, and the warning collision is made more in line with the driving style of the driver.
[0045] In one embodiment, in step S304, that is, according to the vehicle information of the host vehicle and the driving risk profile information, the risk response time of the driver of the target vehicle to the collision risk is determined, and the driving risk profile information includes a target driving scenario, and the target driving scenario includes a traffic density label, a weather label, a light label, a road type label, and a driving scenario label; it includes: S3041. Perform risk clustering processing on the vehicle information of the host vehicle according to the traffic density label, the weather label, the light label, the road type label, and the driving scenario label to obtain risk clustering clusters; the risk clustering clusters include a first risk clustering cluster corresponding to the traffic density label, a second risk clustering cluster corresponding to the weather label, a third risk clustering cluster corresponding to the light label, a fourth risk clustering cluster corresponding to the road type label, and a fifth risk clustering cluster corresponding to the driving scenario label.
[0046] S3042. Determine the central values corresponding to the first risk clustering cluster, the second risk clustering cluster, the third risk clustering cluster, the fourth risk clustering cluster, and the fifth risk clustering cluster one by one, and determine the risk response time according to all the central values.
[0047] Understandably, the driving risk profile information includes a target driving scenario, and the target driving scenario includes a traffic density label, a weather label, a light label, a road type label, and a driving scenario label. The risk clustering clusters include a first risk clustering cluster corresponding to the traffic density label, a second risk clustering cluster corresponding to the weather label, a third risk clustering cluster corresponding to the light label, a fourth risk clustering cluster corresponding to the road type label, and a fifth risk clustering cluster corresponding to the driving scenario label.
[0048] Specifically, risk clustering processing is performed on the ego-vehicle information according to the traffic density label, weather label, lighting label, road type label, and driving scenario label. That is, first, all preset clustering clusters corresponding to the ego-vehicle information are obtained, and then risk clustering is performed on the traffic density label to obtain a first risk clustering cluster corresponding to the traffic density label; risk clustering is performed on the weather label to obtain a second risk clustering cluster corresponding to the weather label; risk clustering is performed on the lighting label to obtain a third risk clustering cluster corresponding to the lighting label; risk clustering is performed on the road type label to obtain a fourth risk clustering cluster corresponding to the road type label; risk clustering is performed on the driving scenario label to obtain a fifth risk clustering cluster corresponding to the driving scenario label; and the first risk clustering cluster, the second risk clustering cluster, the third risk clustering cluster, the fourth risk clustering cluster, and the fifth risk clustering cluster are determined as risk clustering clusters. Next, the central values corresponding to the first risk clustering cluster, the second risk clustering cluster, the third risk clustering cluster, the fourth risk clustering cluster, and the fifth risk clustering cluster are respectively obtained, and the risk response time is determined according to all the central values. In some embodiments, the maximum central value among all the central values can be determined as the risk response time. For example, if the central values are 5 seconds, 6 seconds, 7 seconds, 5 seconds, and 7 seconds respectively, the risk response time is 7 seconds. Or, the weighted result of all the central values is determined as the risk response time. If the central values are 4 seconds, 5 seconds, 6 seconds, 4 seconds, and 5 seconds respectively, the risk response time is 4.8 seconds.
[0049] In this embodiment, through the driver monitoring system, the identification of the driver's identity is realized. Through the environmental label, the determination of each risk clustering cluster is realized, thereby realizing the acquisition of the central value of the risk clustering cluster and the calculation of the risk response time, and further improving the accuracy of collision warning and realizing the determination of driving style.
[0050] In one embodiment, in step S40, that is, after performing the collision warning operation when it is determined that the predicted collision time is less than the collision time threshold, the following is further included: S501. Obtain the warning duration of the collision warning operation, and compare the warning duration with the risk takeover time threshold.
[0051] S502. When the warning duration is greater than or equal to the risk takeover time threshold, control the target vehicle to perform a risk takeover operation.
[0052] It can be understood that the warning duration refers to the prompt duration of the collision warning, for example, 3 seconds, 5 seconds, etc. The risk takeover time threshold refers to the time threshold for performing the risk takeover operation, for example, 6 seconds, 8 seconds, etc. The risk takeover operation refers to the operation of taking over and controlling the target vehicle.
[0053] Specifically, when it is determined that the predicted collision time is less than the collision time threshold, after performing the collision warning operation, obtain the warning duration of the collision warning operation and the risk takeover time threshold. That is, the time point when the collision warning operation starts can be recorded as zero, and then start timing to obtain the warning duration. Then compare the warning duration with the risk takeover time threshold. When the warning duration is less than the risk takeover time threshold, confirm not to start the risk takeover operation, and continue to monitor the warning duration of the collision warning operation until the warning duration is greater than or equal to the risk takeover time threshold, then control the target vehicle and perform the risk takeover operation.
[0054] In another embodiment, obtain the start time point of the collision warning and record it as the zero moment. Then, add the obtained risk takeover time threshold to the start time point of the collision warning to obtain the target time point. Next, monitor whether the duration of the collision warning reaches the target time point. If the duration of the collision warning does not reach the target time point, confirm not to start the risk takeover operation, and continue to monitor the warning duration of the collision warning operation until the duration of the collision warning does not reach the target time point, then control the target vehicle and perform the risk takeover operation. For example, if the start time point of the collision warning is the 0 moment and the risk takeover time threshold is 1 second, then the target time point is the 1 second moment; if the initial collision time point is the 0 moment and the preset time threshold is 5 seconds, then the target time point is the 5 second moment.
[0055] In this embodiment, by comparing the warning duration with the risk takeover time threshold, it is realized to judge whether the warning duration reaches the risk takeover time threshold. When the warning duration is greater than or equal to the risk takeover time threshold, it is realized to perform the risk takeover operation on the target vehicle, thereby enhancing the driving safety.
[0056] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
[0057] In one embodiment, the present invention provides a controller, including a processor and a memory. The memory stores an executable program, and the processor is used to execute the executable program to implement the vehicle collision warning method as described above.
[0058] For the specific limitations of the controller, reference can be made to the limitations on the vehicle collision warning method in the above text, which will not be elaborated here. Each module in the above controller can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the controller in the vehicle in hardware form or independent of it, or stored in the memory in the vehicle in software form, so as to facilitate the controller to call and execute the operations corresponding to the above modules.
[0059] In one embodiment, the present invention provides a vehicle including the above-mentioned controller. Further limitations on the controller can be referred to the limitations on the vehicle collision warning method in the foregoing text, which will not be elaborated herein. Further, the vehicle further includes a plurality of sensors, radars, cameras, etc., so as to collect information of the target vehicle and information of surrounding vehicles. Specifically, the vehicle information of the target vehicle can be collected by sensors, and the information of surrounding vehicles can be collected by sensors and radars, that is, the vehicle information such as the speed and acceleration of surrounding vehicles is collected according to a preset lateral range and longitudinal range, so as to obtain the vehicle information of the target vehicle and the information of surrounding vehicles, and determine it as vehicle information. At the same time, the environmental information around the target vehicle is collected by a plurality of sensors, radars and cameras, and the traffic flow density, weather, light, road type and driving scene around the target vehicle are collected according to preset collection requirements, so as to obtain the current environmental information of the target vehicle.
[0060] In one embodiment, the present invention provides a computer-readable storage medium storing computer-readable instructions. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium. Computer-readable instructions are stored on the readable storage medium. When the computer-readable instructions are executed by the controller, the following steps are implemented: Obtain vehicle information and the current environmental information of the target vehicle; the vehicle information includes the vehicle information of the target vehicle itself and the information of surrounding vehicles; Determine the predicted collision time corresponding to the target vehicle according to the vehicle information of the target vehicle itself and the information of surrounding vehicles; Determine the driving risk profile information of the target vehicle according to the current environmental information, and determine the collision time threshold corresponding to the target vehicle according to the vehicle information of the target vehicle itself and the driving risk profile information; When it is determined that the predicted collision time is less than the collision time threshold, perform a collision warning operation.
[0061] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.
[0062] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the controller is divided into different functional units or modules to complete all or part of the functions described above.
[0063] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A vehicle collision warning method, characterized in that, Including: Obtain vehicle information and the current environment information of the target vehicle; The vehicle information includes the ego-vehicle information of the target vehicle and the information of surrounding vehicles; Determine the predicted time to collision (TTC) corresponding to the target vehicle according to the ego-vehicle information and the information of surrounding vehicles; Determine the driving risk portrait information of the target vehicle according to the current environment information, and determine the collision time threshold corresponding to the target vehicle according to the ego-vehicle information and the driving risk portrait information; When it is determined that the predicted TTC is less than the collision time threshold, perform a collision warning operation.
2. The vehicle collision warning method according to claim 1, wherein The determining the driving risk portrait information of the target vehicle according to the current environment information includes: Determine an environment label according to the current environment information; Determine the target driving scenario of the target vehicle according to the environment label, and determine the driving risk portrait information of the target vehicle according to the target driving scenario.
3. The vehicle collision warning method according to claim 2, characterized in that, The current environment information includes traffic flow density, current weather, current illumination, current road type, and current driving scenario; The determining the driving risk portrait information of the target vehicle according to the current environment information includes: Determine an environment label according to the current environment information, where the environment label includes a traffic density label corresponding to the traffic flow density, a weather label corresponding to the current weather, an illumination label corresponding to the current illumination, a road type label corresponding to the current road type, and a driving scenario label corresponding to the current driving scenario; Determine the target driving scenario of the target vehicle according to the traffic density label, the weather label, the illumination label, the road type label, and the driving scenario label, and determine the driving risk portrait information of the target vehicle according to the target driving scenario.
4. The vehicle collision warning method according to claim 1, characterized in that, The determining the collision time threshold corresponding to the target vehicle according to the ego-vehicle information and the driving risk portrait information includes: Obtain the current collision time threshold associated with the driver of the target vehicle; Determine the risk response time of the driver of the target vehicle to the collision risk according to the ego-vehicle information and the driving risk portrait information; Adjust the current collision time threshold according to the risk response time to obtain the collision time threshold corresponding to the target vehicle.
5. The vehicle collision warning method according to claim 4, characterized in that, The driving risk portrait information includes a target driving scenario, and the target driving scenario includes a traffic density label, a weather label, an illumination label, a road type label, and a driving scenario label; The determining the risk response time of the driver of the target vehicle to the collision risk according to the ego-vehicle information and the driving risk portrait information includes: Perform risk clustering processing on the ego vehicle information according to the traffic density label, the weather label, the lighting label, the road type label, and the driving scenario label to obtain risk clustering clusters; the risk clustering clusters include a first risk clustering cluster corresponding to the traffic density label, a second risk clustering cluster corresponding to the weather label, a third risk clustering cluster corresponding to the lighting label, a fourth risk clustering cluster corresponding to the road type label, and a fifth risk clustering cluster corresponding to the driving scenario label; Determine the central values corresponding to the first risk clustering cluster, the second risk clustering cluster, the third risk clustering cluster, the fourth risk clustering cluster, and the fifth risk clustering cluster one by one, and determine the risk response time according to all the central values.
6. The vehicle collision warning method according to claim 1, characterized in that The determining the predicted collision time corresponding to the target vehicle according to the ego vehicle information and the surrounding vehicle information includes: According to the ego vehicle information and the surrounding vehicle information, determine the relative speed, relative acceleration, and relative distance between the target vehicle and the surrounding vehicles; Input the relative speed, the relative acceleration, and the relative distance into the collision time calculation model to obtain the predicted collision time corresponding to the target vehicle output by the collision time calculation model.
7. The vehicle collision warning method according to claim 6, wherein The collision time calculation model includes: TTC Wherein: TTC is the predicted collision time; is the relative distance between the target vehicle and surrounding vehicles; Δ a is the relative acceleration between the target vehicle and surrounding vehicles; is the relative speed between the target vehicle and surrounding vehicles.
8. The vehicle collision warning method according to claim 1, characterized in that, After performing the collision warning operation when it is determined that the predicted collision time is less than the collision time threshold, further include: Obtain the warning duration of the collision warning operation, and compare the warning duration with the risk takeover time threshold; When the warning duration is greater than or equal to the risk takeover time threshold, control the target vehicle to perform a risk takeover operation.
9. A controller, characterized in that, Comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the vehicle collision warning method according to any one of claims 1 to 8 when executing the computer program.
10. A vehicle, characterized in that, Comprising a controller as claimed in claim 9.
11. A computer-readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instruction is executed by the controller, the controller is caused to execute the vehicle collision warning method according to any one of claims 1 to 8.