A rear-end collision prevention warning control method, device, system and storage medium for an automobile

Abstract

This application discloses a method, device, system, and storage medium for preventing rear-end collisions in automobiles. The method includes: collecting information about targets behind the vehicle using a multi-source sensor, including at least a rear radar and a rearview camera; determining the initial collision time between the vehicle and the target based on distance and relative speed; determining correction coefficients for each type of information based on at least one of environmental information, driving status information, and lane assignment information; correcting the initial collision time based on the correction coefficients to obtain a corrected collision time; determining whether there is a collision risk between the vehicle and the target based on the corrected collision time; determining the corresponding risk level when a collision risk exists; and executing different warning actions based on at least the risk level. This solution can improve the accuracy of rear-end collision warning systems.

Description

Technical Field

[0001] This application relates to the field of automotive intelligent control technology, and in particular to a method, device, system and storage medium for automotive rear-end collision prevention warning control. Background Technology

[0002] Existing rear-end collision avoidance warning systems for automobiles suffer from the following main problems: First, these systems often rely on a single sensor (such as radar or a camera) for rearward target detection. Data is easily distorted in complex scenarios such as rain, fog, backlight, and traffic congestion. Furthermore, they lack sensor fault redundancy mechanisms; if a sensor fails, the entire system malfunctions. In addition, existing risk assessment models are mostly based on fixed collision models to determine collision risk, failing to adapt to the vehicle's environment, resulting in a high false alarm rate in complex scenarios.

[0003] Therefore, how to provide a method for preventing rear-end collisions in automobiles to improve the accuracy of rear-end collision warning systems has become an urgent technical problem to be solved. Summary of the Invention

[0004] This application provides a method, device, system, and storage medium for preventing rear-end collisions in automobiles, in order to improve the accuracy of rear-end collision warning systems.

[0005] This application provides a method for preventing rear-end collisions in automobiles, including: Using a multi-source sensor including at least a rear radar and a rearview camera, information about targets behind the vehicle is collected, wherein the information about targets behind the vehicle includes at least one of the following: distance to the target, relative speed, environmental information, driving status information, and lane assignment information. The initial collision time between the vehicle and the target behind it is determined based on the distance and relative speed. The correction coefficients for each type of information are determined based on at least one of the environmental information, driving status information, and lane affiliation information. The initial collision time is corrected according to the correction coefficient to obtain the corrected collision time; Determine whether there is a risk of collision between the vehicle and the target behind it based on the revised collision time; When a collision risk exists, the corresponding risk level is determined; At least different warning actions should be taken based on the risk level.

[0006] The beneficial effects of this application are as follows: By collecting information about targets behind the vehicle using multiple sensors such as radar and cameras, the system's data accuracy and robustness are improved under complex weather and lighting conditions, ensuring that the system can still operate basically even if a single sensor fails. Based on environmental information, driving status information, and lane assignment information, corresponding correction coefficients are determined to correct the initial collision time. The corrected collision time is used to determine whether there is a collision risk between the vehicle and the target behind it. When a collision risk exists, the corresponding risk level is determined, and different warning actions are executed at least according to the risk level. Because the correction coefficients are dynamically determined based on multiple pieces of information to correct the collision time, the accuracy of the rear-end collision warning system is improved, avoiding the high false alarm problem of traditional solutions in complex scenarios, making the warning more accurate.

[0007] In one embodiment, determining the correction coefficients corresponding to each type of information based on at least one of environmental information, driving status information, and lane affiliation information includes: Determine the correction factor for each type of information based on at least one of the following: Is the vehicle located in an accident-prone area? Are the current weather or road conditions adverse? Is the vehicle accelerating or changing lanes? The degree of overlap between the target behind and the vehicle's trajectory.

[0008] In one embodiment, correcting the initial collision time according to the correction coefficient to obtain the corrected collision time includes: The product obtained by multiplying the initial collision time by each correction coefficient is taken as the corrected collision time.

[0009] In one embodiment, the risk level includes low risk, medium risk, and high risk, and determining whether there is a collision risk between the vehicle and the rear target based on the corrected collision time includes: The corrected collision time is compared with the collision time threshold for low-risk levels; When the comparison result indicates that the corrected collision time is less than the collision time threshold for low-risk levels, it is determined that there is a collision risk between the vehicle and the target behind it.

[0010] In one embodiment, the method further includes: Obtain the type of the target behind the vehicle; When the target behind the vehicle is a truck, the collision time threshold for each risk level is increased. When the target behind the vehicle is a two-wheeled vehicle, the collision time threshold for each risk level is lowered.

[0011] In one embodiment, performing different early warning actions at least according to the risk level includes: When the risk level is high, obtain no-honking information for the area where the vehicle is currently located; When the vehicle is in a no-honking zone, it will perform a combined warning action including automatically turning on the hazard warning lights and providing a voice prompt. When the vehicle is in a non-no-honking zone, it will perform a combination of warning actions, including automatically turning on the hazard warning lights, providing voice prompts, and sounding the horn.

[0012] In one embodiment, performing different early warning actions at least according to the risk level includes: Before executing the first warning action, which includes a voice prompt, determine whether there is a voice call signal currently present; When a voice call signal is present, determine whether the risk level is high-risk. When the risk level is not high risk, the voice warning action is interrupted and a second warning action is executed instead; the second warning action does not include a voice prompt. When the risk level is high, the third warning action corresponding to the high risk level is executed. When executing the third warning action sequence, if a voice call signal is detected, the voice call is interrupted and the third warning action is executed.

[0013] This application also provides a vehicle rear-end collision prevention and control device, including: The acquisition module is used to acquire information about targets behind the vehicle using a multi-source sensor including at least a rear radar and a rearview camera. The information about targets behind the vehicle includes at least one of the following: distance to the target, relative speed, environmental information, driving status information, and lane assignment information. The first determining module is used to determine the initial collision time between the vehicle and the target behind it based on the distance and relative speed. The second determining module is used to determine the correction coefficients corresponding to each type of information based on at least one of environmental information, driving status information and lane attribution information. A correction module is used to correct the initial collision time according to the correction coefficient to obtain the corrected collision time; The third determination module is used to determine whether there is a risk of collision between the vehicle and the target behind it based on the corrected collision time. The fourth determination module is used to determine the corresponding risk level when there is a collision risk; An execution module is used to perform different early warning actions based at least on the risk level.

[0014] In one embodiment, the second determining module is further configured to: Determine the correction factor for each type of information based on at least one of the following: Is the vehicle located in an accident-prone area? Are the current weather or road conditions adverse? Is the vehicle accelerating or changing lanes? The degree of overlap between the target behind and the vehicle's trajectory.

[0015] In one embodiment, the correction module is further configured to: The product obtained by multiplying the initial collision time by each correction coefficient is taken as the corrected collision time.

[0016] In one embodiment, the risk level includes a low-risk level, a medium-risk level, and a high-risk level, and the third determining module includes: The comparison submodule is used to compare the corrected collision time with the collision time threshold for low-risk levels. The determination submodule is used to determine that there is a risk of collision between the vehicle and the target behind it when the comparison result indicates that the corrected collision time is less than the collision time threshold for the low-risk level.

[0017] In one embodiment, the apparatus further includes: The acquisition module is used to obtain the type of targets behind the vehicle; The adjustment module is used to increase the collision time threshold for each risk level when the target behind the vehicle is a truck. The downgrade module is used to reduce the collision time threshold for each risk level when the target behind the vehicle is a two-wheeled vehicle.

[0018] In one embodiment, the execution module includes: The acquisition submodule is used to obtain no-honking information for the area where the vehicle is currently located when the risk level is high. The first execution submodule is used to execute a combined warning action, including automatically turning on the hazard warning lights and providing a voice prompt, when the vehicle is in a no-honking zone. The second execution submodule is used to perform a combination of warning actions, including automatically turning on hazard warning lights, providing voice prompts, and sounding the horn, when the vehicle is in a non-no-honking zone.

[0019] In one embodiment, the execution module includes: The first judgment submodule is used to determine whether there is a voice call signal before executing the first warning action including voice reminder; The second judgment submodule is used to determine whether the risk level is high-risk when there is a voice call signal. The first warning submodule is used to interrupt the voice warning action and execute the second warning action when the risk level is not high risk level; wherein, the second warning action does not include voice reminder; The second early warning submodule is used to execute a third early warning action corresponding to the high risk level when the risk level is high risk level. When executing the third early warning action sequence, if a voice call signal is detected, the voice call is interrupted and the third early warning action is executed.

[0020] This application also provides a vehicle rear-end collision prevention and control system, including: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to implement the vehicle rear-end collision prevention warning control method described in any of the above embodiments.

[0021] This application also provides a computer-readable storage medium, characterized in that when the instructions in the storage medium are executed by the processor corresponding to the vehicle rear-end collision prevention warning control system, the vehicle rear-end collision prevention warning control system is able to implement the vehicle rear-end collision prevention warning control method as described in any of the above embodiments.

[0022] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0023] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0024] The accompanying drawings are provided to further illustrate the present application and form part of the specification. They are used together with the embodiments of the present application to explain the application and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a vehicle rear-end collision prevention warning control method according to an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a vehicle rear-end collision prevention and control device according to one embodiment of this application; Figure 3 This is a schematic diagram of the hardware structure of a car rear-end collision prevention and control system according to one embodiment of this application. Detailed Implementation

[0025] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application.

[0026] Figure 1 This is a flowchart of a vehicle rear-end collision prevention and control method according to an embodiment of this application, such as... Figure 1 As shown, the method can be implemented as follows: S101-S107: In step S101, information about targets behind the vehicle is collected using a multi-source sensor including at least a rear radar and a rearview camera. The information about targets behind the vehicle includes at least one of the following: distance to the target, relative speed, environmental information, driving status information, and lane assignment information. In step S102, the initial collision time between the vehicle and the target behind it is determined based on the distance and relative speed. In step S103, correction coefficients are determined based on at least one of environmental information, driving status information, and lane affiliation information. In step S104, the initial collision time is corrected according to the correction coefficient to obtain the corrected collision time; In step S105, it is determined whether there is a risk of collision between the vehicle and the target behind it based on the corrected collision time; In step S106, when there is a collision risk, the corresponding risk level is determined; In step S107, at least different warning actions are performed according to the risk level.

[0027] In this application, a multi-source sensor system, including at least a rear radar and a rearview camera, is used to collect information about targets behind the vehicle. This information includes at least one of the following: distance, relative speed, environmental information, driving status information, and lane assignment information of the targets behind the vehicle. Specifically, when the vehicle is in operation, the multi-source sensors simultaneously collect information about the targets behind the vehicle, the vehicle's status, spatiotemporal information, and road conditions. The radar / camera performs real-time filtering and image enhancement, while satellite navigation and high-precision maps provide the vehicle's geographical location and road traffic conditions. For example, the rear radar and / or rearview camera collect data on the distance, speed, azimuth, outline, and trajectory of the targets behind the vehicle; the vehicle clock determines the climate environment (season) and precise timestamp of the vehicle's location; navigation and high-precision maps determine the vehicle's geographical location, weather conditions, location, road attributes, and lane assignment information; and vehicle status sensors collect dynamic driving status information such as vehicle speed and acceleration, as well as environmental information such as rain, sunlight, and ground adhesion coefficient. After acquiring information about targets behind the vehicle using multiple sensors, spatiotemporal registration, deviation correction, and refresh rate adjustment are performed on data from different sources and frequencies to extract risk feature parameters. This involves precisely aligning radar point cloud data, camera image frame data, and vehicle status data based on a unified timestamp. Subsequent data cleaning, error compensation, and feature extraction are then performed to obtain information about targets behind the vehicle.

[0028] The initial collision time between the vehicle and the target behind it is determined based on the distance and relative speed. Assuming the vehicle is traveling at a constant speed of 40 km / h (approximately 11.1 m / s), and a vehicle behind it suddenly changes lanes from an adjacent lane to directly behind it, with radar detecting a distance of 60 meters and a relative speed of 15 km / h (approximately 4.2 m / s), then the collision time can be determined as distance / relative speed = 14.3 seconds. Of course, other indicators can also be combined to determine the initial collision time.

[0029] The system determines correction coefficients for each type of information based on at least one of environmental information, driving status information, and lane assignment information. To improve the model's adaptability to different scenarios, a series of scenario-based correction coefficients are applied after calculating the collision time. These coefficients include correction coefficients for accident-prone road sections, vehicle dynamics, lane changing, lane and trajectory overlap, severe weather, and traffic intersections. Alternatively, default values ​​can be selected, where the default thresholds are continuously updated and optimized based on the actual performance of vehicles using the system.

[0030] In one embodiment, the correction coefficients for each type of information are determined based on at least one of the following: whether the vehicle is in an accident-prone section; whether the current weather or road conditions are adverse; whether the vehicle is accelerating or changing lanes; and the degree of overlap between the vehicle's trajectory and that of the target behind it.

[0031] For example, the system determines whether a vehicle is in an accident-prone section based on environmental information, and adjusts the correction coefficient corresponding to the environmental information based on the determination result. Specifically, when the vehicle is in an accident-prone section, the correction coefficient corresponding to the environmental information is increased, and when the vehicle is not in an accident-prone section, the correction coefficient corresponding to the environmental information is decreased. For example, the system determines whether the current weather or road conditions are severe based on environmental information, and adjusts the correction coefficient corresponding to the environmental information based on the determination result. Specifically, when the weather or road conditions are severe, the correction coefficient corresponding to the environmental information is increased, and when the weather or road conditions are not severe, the correction coefficient corresponding to the environmental information is decreased. For example, the system determines whether the vehicle is accelerating or changing lanes based on the driving status information, and adjusts the correction coefficient corresponding to the environmental information based on the determination result. Specifically, when the vehicle is accelerating or changing lanes, the correction coefficient corresponding to the driving status information is increased, and when the vehicle is not accelerating or changing lanes, the correction coefficient corresponding to the driving status information is decreased. In addition, the system can determine the degree of overlap between the driving trajectory of the target behind and the vehicle based on the lane assignment information, and adjust the correction coefficient corresponding to the environmental information according to the determination result. Specifically, when the degree of overlap between the driving trajectory of the target behind and the vehicle is greater than the preset overlap, the correction coefficient corresponding to the lane assignment information is increased; when the degree of overlap between the driving trajectory of the target behind and the vehicle is less than the preset overlap, the correction coefficient corresponding to the lane assignment information is decreased.

[0032] The initial collision time is corrected according to the correction coefficients to obtain the corrected collision time. For example, the product of the initial collision time and each correction coefficient is used as the corrected collision time. Alternatively, a corresponding correction model can be determined based on environmental information; the correction coefficients and the initial collision time are substituted into the correction model to obtain the corrected collision time. For example, environmental information such as current road type and weather is obtained through navigation and high-precision map units, and compared with parameters in a preset database to determine the corresponding correction model, such as matching a highway model when driving on a highway and a city road model when driving on urban roads. Then, the correction coefficients and the initial collision time are substituted into the correction model to correct the initial collision time.

[0033] The system determines whether there is a risk of collision between the vehicle and the target behind it based on the corrected collision time; it compares the corrected collision time with the collision time threshold for the low-risk level; when the comparison result indicates that the corrected collision time is less than the collision time threshold for the low-risk level, it determines that there is a risk of collision between the vehicle and the target behind it.

[0034] When a collision risk exists, the corresponding risk level is determined. In this application, the risk level is determined by comparing the corrected collision time with a preset threshold. In the vehicle rear-end collision prevention system settings, TTCs corresponding to high, medium, and low risk levels are set, for example, low risk TTC ≤ 13 seconds; medium risk TTC ≤ 8 seconds; high risk TTC ≤ 5 seconds.

[0035] To adapt to different vehicle types and safety scenarios, the system has made adaptive adjustments to the thresholds for specific targets. Specifically, it acquires the type of target behind the vehicle; when the target behind the vehicle is a truck, the collision time threshold for each risk level is increased; when the target behind the vehicle is a two-wheeled vehicle, the collision time threshold for each risk level is decreased. For example, for large trucks with longer braking distances, the risk threshold is increased to ≤10 seconds; for smaller, more maneuverable two-wheeled vehicles, the medium-to-high risk threshold is uniformly adjusted to ≤6 seconds.

[0036] At least according to the risk level, different warning actions are executed. When the risk level is high, the no-honking information of the current area of ​​the vehicle is obtained; when the vehicle is in a no-honking area, a combined warning action including automatically turning on the hazard warning lights and voice prompts is executed; when the vehicle is in a non-no-honking area, a combined warning action including automatically turning on the hazard warning lights, voice prompts, and honking the horn is executed.

[0037] Furthermore, to avoid excessive interference with the driver, before executing the first warning action including a voice reminder, it is determined whether a voice call signal exists. If a voice call signal exists, it is determined whether the risk level is high-risk. If the risk level is not high-risk, the voice warning action is interrupted, and a second warning action is executed instead. The second warning action does not include a voice reminder. If the risk level is high-risk, a third warning action corresponding to the high-risk level is executed. During the execution of the third warning action sequence, if a voice call signal is detected, the voice call is interrupted, and the third warning action is executed. For example, when the vehicle is in operation (including when stopped at a red light), if the central processing unit determines a low-risk warning, it sends a prompt tone warning command to the voice control module, i.e., executes the first warning action. The voice control module then provides a risk warning according to a preset prompt tone. When the system is in a voice call, the voice control module sends a call-in-progress feedback signal to the central processing unit (CPU). Upon receiving the signal, the CPU switches to sending a command to the hazard warning light controller to activate the hazard warning lights. The controller then activates the hazard warning lights. When the system is judged to be at medium risk, the CPU sends a signal to the hazard warning light controller to activate the hazard warning lights, thus executing the second warning action. The controller then activates the hazard warning lights. When the system is judged to be at high risk, and the location is a highway, suburb, or a non-urban area or a no-honking zone, the CPU simultaneously issues activation commands to the hazard warning lights, horn, and voice, thus executing the third warning action. The hazard warning lights, horn, and voice activate simultaneously. If the system is identified as being in an urban area or a no-honking zone, the horn activation command will be canceled.

[0038] Once the risk is eliminated, all warning signals will automatically stop. If the driver manually cancels the warning in advance, this operation will be recorded by the system and may be used for future risk threshold and model self-learning fine-tuning.

[0039] In one embodiment of this application, the vehicle rear-end collision prevention and control system includes a sensing unit, an information fusion unit, a risk assessment unit, and a warning execution unit. These four units work together to achieve graded warnings of rear-end collision risks. (a) The sensing unit is responsible for collecting comprehensive environmental and status data from the rear of the vehicle and the vehicle itself, including: Rear radar: such as millimeter-wave radar, lidar, etc. This radar can be equipped with a CFAR filtering algorithm to effectively eliminate interference from rain, fog, and adjacent vehicles, and can accurately obtain the relative distance and relative speed between the vehicle and rear targets. Detection parameters are 77GHz frequency band, ±60° detection angle, and 0-250m detection distance. Rearview camera: If a wide-angle camera with high dynamic range for backlighting and infrared fill light for nighttime is used, the camera integrates an image processing unit based on deep learning, which can identify lane lines in real time and detect the running trajectory of targets behind (vehicles, two-wheeled vehicles, etc.). The system only adopts the valid data output when the lane line recognition confidence reaches or exceeds 85%. Vehicle clock: It adopts a multi-source time synchronization scheme including global navigation satellite system, network time protocol and network identification time for redundant time synchronization. Its built-in real-time clock chip is powered by both supercapacitor and backup battery to ensure that it can maintain time accuracy for up to 30 days after the vehicle is completely powered off, with daily error controlled within ±5 seconds, providing accurate timestamps for multi-sensor data. Navigation and High-Precision Maps: By integrating satellite positioning data (such as GNSS) with high-precision map information, it provides the vehicle's current precise latitude and longitude location (positioning accuracy ≤ 5 meters). It also includes built-in electronic fence data marked with information such as accident-prone road sections and no-honking zones in urban areas, providing key geographic context information for the core risk assessment model. Vehicle status sensors: used to acquire vehicle speed, lateral and longitudinal acceleration, steering wheel angle, rainfall level and other driving status information.

[0040] It should be noted that the sensing unit is designed with a fault redundancy mechanism. When the system diagnoses a fault or inaccurate data from any sensor in the rear radar or rearview camera, it can automatically and seamlessly switch to a "degraded mode" that relies solely on the other valid sensor. The system then reports the sensor's failure signal to the onboard diagnostic system via the vehicle network, alerting the user or maintenance personnel to perform repairs. This design significantly improves the system's fault tolerance and availability.

[0041] (ii) The information fusion unit, determined according to the selected electronic and electrical architecture, is integrated into the vehicle's central controller or domain controller. It supports the Automotive Open System Architecture (AUTOSAR) and communicates via the in-vehicle network. Its main functions include spatiotemporal registration, bias correction, and feature extraction of data collected by the sensing unit, as well as dynamically adjusting the data sampling period according to the risk status. Spatiotemporal registration aligns data collected by different sensors at different times and locations. Bias correction eliminates errors caused by the sensor itself and environmental interference. Dynamically adjusting the data sampling period increases the data acquisition frequency and improves the system's response speed when the risk is high, while decreasing the sampling frequency and reducing system resource consumption when the risk is low.

[0042] (III) Risk Assessment Unit: The risk assessment model uses Time-to-Collapse (TTC) as a benchmark for classification and incorporates various correction coefficients for dynamic adjustment. The basic classification thresholds for TTC include high-risk, medium-risk, and low-risk thresholds. By calculating the collision time between a rear-end target and the vehicle, a preliminary risk level is determined. Based on this, various correction coefficients are introduced, such as a high-accident-prone road section weighting coefficient, vehicle acceleration correction coefficient, rear vehicle deceleration correction coefficient, vehicle turning / lane-changing correction coefficient, lane and trajectory overlap coefficient, severe weather weighting coefficient, and traffic intersection correction coefficient, to adjust the preliminary risk level assessment and make the risk assessment results more accurate. Simultaneously, the risk assessment model supports self-learning based on actual vehicle operating data to update the classification thresholds and correction coefficients, continuously optimizing the assessment model.

[0043] For example, using TTC (Time to Collision) as the classification benchmark, the following risk levels are defined: low-risk TTC ≤ 13s; medium-risk TTC ≤ 8s, with the medium-risk threshold for trucks raised to ≤ 10s and the medium-risk threshold for two-wheeled vehicles lowered to ≤ 6s; high-risk TTC ≤ 5s, with the high-risk threshold for trucks raised to ≤ 8s and the high-risk threshold for two-wheeled vehicles lowered to ≤ 6s. Another example is the setting of correction coefficients: high-accident-prone road sections weight coefficient 1.2-1.5, vehicle acceleration coefficient 0.8, following vehicle deceleration coefficient 0.8, turning and lane changing coefficient 0.7, lane and trajectory overlap coefficient (0-1), severe weather (road surface) weight coefficient 1.3-1.5, and traffic light intersection weight coefficient 0.8. These are the system default data (which can be self-learned and corrected), and customers can also customize them in the vehicle's infotainment system according to their needs. The assessment logic is: basic risk calculation → vehicle status correction → road risk weighting → risk level classification.

[0044] (iv) The early warning execution unit shall execute graded early warning actions according to the risk level: Low risk: Customizable voice prompts, with a priority lower than emergency warnings and phone calls but higher than navigation voice prompts, to avoid excessive interference with the driver. The voice prompt content can be customized according to user needs, with two prompts spaced three seconds apart, continuing until the danger has passed. Medium risk: The vehicle's hazard warning lights will automatically turn on and flash to alert the driver of this vehicle and drivers of vehicles behind it with a conspicuous visual signal. The lights will automatically turn off after the danger has passed. Of course, they can also be turned off manually, and the manual turning-off information will be recorded in the risk threshold correction self-learning information. High-risk: Combining regional attribute information provided by high-precision maps, hazard warning lights and horns are activated simultaneously in non-no-honking zones such as highways and suburbs to warn surrounding vehicles with strong sound and light signals; in urban areas and no-honking zones, hazard warning lights and voice prompts are activated simultaneously, ensuring both warning effectiveness and compliance with traffic regulations.

[0045] In one specific embodiment, the vehicle rear-end collision avoidance safety setting option is set to default. When the vehicle is traveling at 80 km / h on a highway, a sedan appears behind it in the same lane, with a trajectory essentially the same as the vehicle in front, and the sedan is traveling at 120 km / h. The relative speed between the sedan and the vehicle in front is 40 km / h (approximately 11.1 m / s), but the sedan's TTC (Total Collision Tolerance) is ≤13 seconds (default low-risk TTC value), meaning the distance between the sedan and the vehicle is less than approximately 144.4 meters (40 km / h = 11.1 m / s). At 13 seconds, the central processing unit sends a warning tone command to the voice control module, which then provides a risk warning (e.g., "Danger behind").

[0046] Assuming the driver is on a voice call, the voice control module will send a feedback signal to the central processing unit (CPU) indicating that a call is in progress. Upon receiving the signal, the CPU will switch to sending a command to the hazard warning light controller to turn on the hazard warning lights. The controller will then activate the hazard warning lights. This operation can remind the driver to observe the situation of vehicles approaching from behind and make a judgment without interrupting the driver's normal conversation.

[0047] If the driver is too engrossed in their phone call and fails to notice the hazard warning lights are on, and simultaneously, the driver of the car behind is fatigued or distracted and fails to slow down quickly, the central processing unit will determine the situation as medium risk when the following distance (TTC) is less than 8 seconds (the default preset medium-risk TTC value). Since the driver in the preceding car was on a phone call and had already activated the hazard warning lights, the hazard warning lights will remain flashing.

[0048] When TTC ≤ 5S (default high-risk TTC value), meaning the following distance between the car and this vehicle is less than approximately 55.6 meters, the central processing unit (CPU) determines it to be high-risk. Since the vehicle is on a highway, not in a busy urban area or a no-honking zone, the CPU simultaneously issues activation commands to the hazard warning lights, horn, and voice controller. The hazard warning lights, horn, and voice are activated simultaneously. Under the high-risk warning, even if the driver is using voice communication, it will be interrupted and switched to hazard warning to ensure the safety of the occupants. The warning is automatically canceled after the risk is eliminated, but can also be manually canceled in advance (manual cancellation will be recorded in the self-learning experience).

[0049] In another specific embodiment, the vehicle rear-end collision avoidance safety setting option is set to default. In winter, during rain or snow, when the vehicle is traveling at 40 km / h on a national highway, a large truck is detected behind it in the same lane. The radar detects the truck's speed as 65 km / h. At this time, data from the camera, vehicle sensors, and the vehicle's infotainment system indicates rain or snow, making the road slippery (severe weather weight 1.3). The camera and radar detect the vehicles in the same lane with consistent trajectories, resulting in a lane trajectory weight coefficient of 1. The relative speed between the two vehicles is 25 km / h (approximately 6.9 m / s). Based on the default value TTC≤13S... 1.3 (Severe Weather Weighting) 1 (Lane Trajectory Coefficient). This means that when the distance between the large truck and the vehicle in front is less than approximately 116.6 meters (6.9...),... 13 1.3 1) If the central processing unit (CPU) analyzes and determines that the risk is low, the CPU will send a warning prompt to the voice control module. The voice control module will then provide a risk warning according to the preset prompt (e.g., "Danger behind").

[0050] After receiving the voice warning of the danger, the driver of the vehicle in front accelerated and quickly increased the speed to about 65 km / h, thus eliminating the danger.

[0051] The beneficial effects of this application are as follows: By collecting information about targets behind the vehicle using multiple sensors such as radar and cameras, the system's data accuracy and robustness are improved under complex weather and lighting conditions, ensuring that the system can still operate basically even if a single sensor fails. Based on environmental information, driving status information, and lane assignment information, corresponding correction coefficients are determined to correct the initial collision time. The corrected collision time is used to determine whether there is a collision risk between the vehicle and the target behind it. When a collision risk exists, the corresponding risk level is determined, and different warning actions are executed at least according to the risk level. Because the correction coefficients are dynamically determined based on multiple pieces of information to correct the collision time, the accuracy of the rear-end collision warning system is improved, avoiding the high false alarm problem of traditional solutions in complex scenarios, making the warning more accurate.

[0052] In one embodiment, step S103 above can be implemented as follows: Determine the correction factor for each type of information based on at least one of the following: Is the vehicle located in an accident-prone area? Are the current weather or road conditions adverse? Is the vehicle accelerating or changing lanes? The degree of overlap between the target behind and the vehicle's trajectory.

[0053] In one embodiment, step S104 above can be implemented as follows: The product obtained by multiplying the initial collision time by each correction coefficient is taken as the corrected collision time.

[0054] In one embodiment, the risk level includes a low-risk level, a medium-risk level, and a high-risk level, and step S103 above can be implemented as steps A1-A2 as follows: In step A1, the corrected collision time is compared with the collision time threshold for the low-risk level; In step A2, when the comparison result indicates that the corrected collision time is less than the collision time threshold for the low-risk level, it is determined that there is a collision risk between the vehicle and the target behind it.

[0055] In one embodiment, the method may also be implemented as steps B1-B3: In step B1, the type of the target behind the vehicle is obtained; In step B2, when the target behind the vehicle is a truck, the collision time threshold for each risk level is increased. In step B3, when the target behind the vehicle is a two-wheeled vehicle, the collision time threshold for each risk level is lowered.

[0056] In one embodiment, step S107 above can be implemented as steps C1-C3 as follows: In step C1, when the risk level is high, obtain the no-honking information for the area where the vehicle is currently located; In step C2, when the vehicle is in a no-honking zone, a combined warning action including automatically turning on the hazard warning lights and providing a voice prompt is executed; In step C3, when the vehicle is in a non-no-honking zone, a combined warning action is performed, including automatically turning on the hazard warning lights, providing a voice prompt, and sounding the horn.

[0057] In one embodiment, step S107 above can be implemented as steps D1-D4 as follows: In step D1, before executing the first warning action including a voice prompt, it is determined whether there is a voice call signal at present; In step D2, when a voice call signal is present, it is determined whether the risk level is high risk. In step D3, when the risk level is not high risk, the voice warning action is interrupted and a second warning action is executed instead; wherein, the second warning action does not include a voice reminder; In step D4, when the risk level is high, the third warning action corresponding to the high risk level is executed. If a voice call signal is detected during the execution of the third warning action sequence, the voice call is interrupted and the third warning action is executed.

[0058] Figure 2 This is a schematic diagram of the structure of a car rear-end collision prevention and control device according to one embodiment of this application, as shown below. Figure 2 As shown, the device includes: The acquisition module 201 is used to acquire information about targets behind the vehicle using a multi-source sensor including at least a rear radar and a rear-view camera. The information about targets behind the vehicle includes at least one of the following: distance to the target, relative speed, environmental information, driving status information, and lane assignment information. The first determining module 202 is used to determine the initial collision time between the vehicle and the target behind the vehicle based on the distance and relative speed. The second determining module 203 is used to determine the correction coefficients corresponding to each type of information based on at least one of environmental information, driving status information and lane attribution information. The correction module 204 is used to correct the initial collision time according to the correction coefficient to obtain the corrected collision time; The third determination module 205 is used to determine whether there is a risk of collision between the vehicle and the target behind it based on the corrected collision time. The fourth determination module 206 is used to determine the corresponding risk level when there is a collision risk; The execution module 207 is used to perform different warning actions at least according to the risk level.

[0059] In one embodiment, the second determining module is further configured to: Determine the correction factor for each type of information based on at least one of the following: Is the vehicle located in an accident-prone area? Are the current weather or road conditions adverse? Is the vehicle accelerating or changing lanes? The degree of overlap between the target behind and the vehicle's trajectory.

[0060] In one embodiment, the correction module is further configured to: The product obtained by multiplying the initial collision time by each correction coefficient is taken as the corrected collision time.

[0061] In one embodiment, the risk level includes a low-risk level, a medium-risk level, and a high-risk level, and the third determining module includes: The comparison submodule is used to compare the corrected collision time with the collision time threshold for low-risk levels. The determination submodule is used to determine that there is a risk of collision between the vehicle and the target behind it when the comparison result indicates that the corrected collision time is less than the collision time threshold for the low-risk level.

[0062] In one embodiment, the apparatus further includes: The acquisition module is used to obtain the type of targets behind the vehicle; The adjustment module is used to increase the collision time threshold for each risk level when the target behind the vehicle is a truck. The downgrade module is used to reduce the collision time threshold for each risk level when the target behind the vehicle is a two-wheeled vehicle.

[0063] In one embodiment, the execution module includes: The acquisition submodule is used to obtain no-honking information for the area where the vehicle is currently located when the risk level is high. The first execution submodule is used to execute a combined warning action, including automatically turning on the hazard warning lights and providing a voice prompt, when the vehicle is in a no-honking zone. The second execution submodule is used to perform a combination of warning actions, including automatically turning on hazard warning lights, providing voice prompts, and sounding the horn, when the vehicle is in a non-no-honking zone.

[0064] In one embodiment, the execution module includes: The first judgment submodule is used to determine whether there is a voice call signal before executing the first warning action including voice reminder; The second judgment submodule is used to determine whether the risk level is high-risk when there is a voice call signal. The first warning submodule is used to interrupt the voice warning action and execute the second warning action when the risk level is not high risk level; wherein, the second warning action does not include voice reminder; The second early warning submodule is used to execute a third early warning action corresponding to the high risk level when the risk level is high risk level. When executing the third early warning action sequence, if a voice call signal is detected, the voice call is interrupted and the third early warning action is executed.

[0065] Figure 3 This is a schematic diagram of the hardware structure of a car rear-end collision prevention and control system according to one embodiment of this application, as shown below. Figure 3 As shown, the vehicle rear-end collision prevention and control system includes: At least one processor 320; and, Memory 304 communicatively connected to the at least one processor 320; wherein, The memory 304 stores instructions that can be executed by the at least one processor 320 to implement the vehicle rear-end collision prevention warning control method described in any of the above embodiments.

[0066] Reference Figure 3 The vehicle rear-end collision avoidance warning control system 300 may include one or more of the following components: processing component 302, memory 304, power supply component 306, input / output (I / O) interface 308, sensor component 310, and communication component 312.

[0067] Processing component 302 typically controls the overall operation of the vehicle rear-end collision avoidance warning control system 300. Processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the above-described method. Furthermore, processing component 302 may include one or more modules to facilitate interaction between processing component 302 and other components. The processor 320 may 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 may be a microprocessor or any conventional processor.

[0068] Memory 304 is configured to store various types of data to support the operation of the vehicle rear-end collision avoidance warning control system 300. Examples of this data include instructions for any application or method operating on the vehicle rear-end collision avoidance warning control system 300. Memory 304 can be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. Memory 304 can also be an external storage device of the terminal device, such as a plug-in hard disk equipped on the terminal device. Memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Memory 304 is used to store programs and data required by this application. Memory 304 can also be used to temporarily store data that has been output or will be output.

[0069] Power supply component 306 provides power to various components of the vehicle rear-end collision avoidance warning control system 300. Power supply component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the vehicle rear-end collision avoidance warning control system 300.

[0070] I / O interface 308 provides an interface between processing component 302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc.

[0071] The sensor assembly 310 includes one or more sensors for providing various aspects of the status assessment of the vehicle rear-end collision avoidance warning control system 300. Additionally, the sensor assembly 310 can detect the on / off state of the vehicle rear-end collision avoidance warning control system 300, the relative positioning of components, and the operational status of the vehicle rear-end collision avoidance warning control system 300 or one of its components. In some embodiments, the sensor assembly 310 may include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor, etc.

[0072] Communication component 312 is configured to enable the vehicle rear-end collision avoidance warning control system 300 to provide wired or wireless communication capabilities with other devices and cloud platforms. The vehicle rear-end collision avoidance warning control system 300 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0073] In an exemplary embodiment, the vehicle rear-end collision prevention warning control system 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the vehicle rear-end collision prevention warning control method described in any of the above embodiments.

[0074] This application also provides a computer-readable storage medium, characterized in that when the instructions in the storage medium are executed by the processor corresponding to the vehicle rear-end collision prevention warning control system, the vehicle rear-end collision prevention warning control system is able to implement the vehicle rear-end collision prevention warning control method as described in any of the above embodiments.

[0075] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0076] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for preventing rear-end collisions in automobiles, characterized in that, include: Using a multi-source sensor including at least a rear radar and a rearview camera, information about targets behind the vehicle is collected, wherein the information about targets behind the vehicle includes at least one of the following: distance to the target, relative speed, environmental information, driving status information, and lane assignment information. The initial collision time between the vehicle and the target behind it is determined based on the distance and relative speed. The correction coefficients for each type of information are determined based on at least one of the environmental information, driving status information, and lane affiliation information. The initial collision time is corrected according to the correction coefficient to obtain the corrected collision time; Determine whether there is a risk of collision between the vehicle and the target behind it based on the revised collision time; When a collision risk exists, the corresponding risk level is determined; At least different warning actions should be taken based on the risk level.

2. The method according to claim 1, characterized in that, The step of determining the correction coefficients for each type of information based on at least one of environmental information, driving status information, and lane affiliation information includes: Determine the correction factor for each type of information based on at least one of the following: Is the vehicle located in an accident-prone area? Are the current weather or road conditions adverse? Is the vehicle accelerating or changing lanes? The degree of overlap between the target behind and the vehicle's trajectory.

3. The method as described in claim 1, characterized in that, The step of correcting the initial collision time according to the correction coefficient to obtain the corrected collision time includes: The product obtained by multiplying the initial collision time by each correction coefficient is taken as the corrected collision time.

4. The method as described in claim 1, characterized in that, The risk levels include low risk, medium risk, and high risk. The step of determining whether there is a collision risk between the vehicle and a rear target based on the corrected collision time includes: The corrected collision time is compared with the collision time threshold for low-risk levels; When the comparison result indicates that the corrected collision time is less than the collision time threshold for low-risk levels, it is determined that there is a collision risk between the vehicle and the target behind it.

5. The method as described in claim 1, characterized in that, The method further includes: Obtain the type of the target behind the vehicle; When the target behind the vehicle is a truck, the collision time threshold for each risk level is increased. When the target behind the vehicle is a two-wheeled vehicle, the collision time threshold for each risk level is lowered.

6. The method according to claim 1, characterized in that, The execution of different early warning actions based at least on the risk level includes: When the risk level is high, obtain no-honking information for the area where the vehicle is currently located; When the vehicle is in a no-honking zone, it will perform a combined warning action including automatically turning on the hazard warning lights and providing a voice prompt. When the vehicle is in a non-no-honking zone, it will perform a combination of warning actions, including automatically turning on the hazard warning lights, providing voice prompts, and sounding the horn.

7. The method according to claim 1, characterized in that, The execution of different early warning actions based at least on the risk level includes: Before executing the first warning action, which includes a voice prompt, determine whether there is a voice call signal currently present; When a voice call signal is present, determine whether the risk level is high-risk. When the risk level is not high risk, the voice warning action is interrupted and a second warning action is executed instead; the second warning action does not include a voice prompt. When the risk level is high, the third warning action corresponding to the high risk level is executed. When executing the third warning action sequence, if a voice call signal is detected, the voice call is interrupted and the third warning action is executed.

8. A vehicle rear-end collision prevention and control device, characterized in that, include: The acquisition module is used to acquire information about targets behind the vehicle using a multi-source sensor including at least a rear radar and a rearview camera. The information about targets behind the vehicle includes at least one of the following: distance to the target, relative speed, environmental information, driving status information, and lane assignment information. The first determining module is used to determine the initial collision time between the vehicle and the target behind it based on the distance and relative speed. The second determining module is used to determine the correction coefficients corresponding to each type of information based on at least one of environmental information, driving status information and lane attribution information. A correction module is used to correct the initial collision time according to the correction coefficient to obtain the corrected collision time; The third determination module is used to determine whether there is a risk of collision between the vehicle and the target behind it based on the corrected collision time. The fourth determination module is used to determine the corresponding risk level when there is a collision risk; An execution module is used to perform different early warning actions based at least on the risk level.

9. A vehicle rear-end collision prevention and control system, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to implement the vehicle rear-end collision prevention warning control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor corresponding to the vehicle rear-end collision prevention warning control system, the vehicle rear-end collision prevention warning control system is able to implement the vehicle rear-end collision prevention warning control method as described in any one of claims 1-7.

Images