Accident warning method, apparatus, device, medium, and program product
By acquiring accident information and using collision models to simulate vehicle trajectories, determining critical moments and conditions, and generating warning signals, the system addresses the issue of insufficient accuracy in detecting the vehicle's surrounding environment within the driver assistance system, thereby improving driving safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHONGQING JINKANG NEW ENERGY VEHICLE CO LTD
- Filing Date
- 2026-03-02
- Publication Date
- 2026-06-12
AI Technical Summary
Existing driver assistance systems lack accuracy in detecting the vehicle's surroundings, making it difficult to effectively avoid traffic accidents.
By acquiring accident information, including collision coordinates and vehicle information, and using a preset collision model to simulate vehicle trajectories, the critical moment and critical warning conditions are determined, and warning signals are generated to prevent accidents from occurring.
It enables the accurate generation of warning signals at critical moments, improving the driving safety of assisted driving and timely avoiding accidents.
Smart Images

Figure CN122201036A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vehicle control technology, and in particular to an accident early warning method, device, equipment, medium, and program product. Background Technology
[0002] Safety is paramount for assisted driving. Related technologies use sensors such as cameras or radar to collect environmental information around the vehicle, detecting nearby targets and deciding on emergency steering to avoid traffic accidents. However, accuracy remains a concern. Summary of the Invention
[0003] Based on this, the present invention provides an accident early warning method, device, equipment, medium and program product, which can improve driving safety by accurately determining the critical moment and generating early warning signals in a timely manner.
[0004] In a first aspect, embodiments of this application provide an accident early warning method, including: Obtain accident information; wherein, the accident information includes collision coordinates, first vehicle information of the accident vehicle at the moment of collision, and first movement information of the object that collided with the accident vehicle; Based on the first vehicle information and the first movement information, a time window is slid forward to the moment of collision to determine the critical moment and the critical warning condition corresponding to the critical moment; wherein, the interval between the critical moment and the moment of the unavoidable accident is less than or equal to one time window, and the critical moment is before the moment of the accident. A warning signal is generated in response to the driving information of the vehicle to be controlled meeting the critical warning conditions.
[0005] In some embodiments, the critical warning conditions include the critical distance between the accident vehicle and the object at the critical moment, the critical driving speed of the accident vehicle at the critical moment, and the critical moving speed of the object; the step of generating a warning signal in response to the driving information of the vehicle to be controlled meeting the critical warning conditions includes: Identify a suspicious target; wherein the straight-line distance between the vehicle to be controlled and the suspicious target is less than a first distance threshold; In response to the path distance between the suspected target and the vehicle to be controlled being less than or equal to the critical distance, the real-time driving speed of the vehicle to be controlled and the target real-time speed of the suspected target corresponding to the real-time driving speed are determined in real time; wherein, the path distance is the distance between the vehicle to be controlled and the suspected target along the driving path of the vehicle to be controlled. The warning signal is generated in response to the real-time driving speed of the vehicle to be controlled being greater than or equal to the critical driving speed, and / or the target real-time speed being greater than or equal to the critical moving speed.
[0006] In some embodiments, the step of determining a critical moment and a critical warning condition corresponding to the critical moment by sliding a time window before the collision time based on the first vehicle information and the first movement information includes: Multiple reference times are determined; wherein the reference times are prior to the collision time, and there is at least one time window between the reference times and the collision time; Based on the first vehicle information, determine the vehicle trajectory coordinates corresponding to the reference time, and the first coordinate information of the vehicle trajectory coordinates; and based on the first movement information, determine the object trajectory coordinates corresponding to the reference time, and the second coordinate information of the object trajectory coordinates. By using a preset collision model, the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates are processed to determine the critical moment; Based on the critical moment, the critical driving speed of the accident vehicle is queried from the first coordinate information, and the critical movement speed of the object is queried from the second coordinate information to obtain the critical warning condition.
[0007] In some embodiments, the step of processing the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates using a preset collision model to determine the critical moment includes: The first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates are input into a preset collision model for simulation to obtain the collision probability; wherein, the collision probability indicates the probability that the accident vehicle collides with the object at the reference time when the accident vehicle changes its driving rules from the vehicle trajectory coordinates. In response to a first collision probability of a first type of reference time in the reference time being greater than or equal to a preset collision threshold, and a second collision probability of a second type of reference time in the reference time being less than the preset collision threshold, the first type of reference time is determined to be the accident time, and the second type of reference time is determined to be the critical time; wherein the time interval between the second type of reference time and the first type of reference time is less than or equal to one time window.
[0008] In some embodiments, the collision model incorporates at least two driving rules, including driving direction and / or acceleration; the step of processing the second vehicle information of the accident vehicle on the vehicle trajectory coordinates and the second movement information of the object on the object trajectory coordinates using the preset collision model to determine the critical moment includes: In the collision model, the sub-probability of the accident vehicle colliding with the object at the reference time is simulated, based on the vehicle trajectory coordinates and the driving rules. The critical moment is determined based on the sub-probabilities of the first type of reference moment, the sub-probabilities of the second type of reference moment, and a preset collision threshold.
[0009] In some embodiments, determining the critical moment based on the sub-probability of the first type of reference moment, the sub-probability of the second type of reference moment, and a preset collision threshold includes: In response to the fact that at a first time in the reference time, the sub-probabilities of multiple driving rules are all greater than or equal to the preset collision threshold, and at a second time in the reference time, the sub-probability of at least one driving rule is less than the preset collision threshold, the first time is determined to be the first type of reference time, and the second time is determined to be the second type of reference time; the time interval between the first time and the second time is less than or equal to one time window; And / or, In response to the third time of the reference time, at least one of the sub-probabilities is greater than or equal to the preset collision threshold, and at the fourth time of the reference time, all the sub-probabilities are less than the preset collision threshold, the third time is determined to be the first type of reference time, and the fourth time is determined to be the second type of reference time; the time interval between the third time and the fourth time is less than or equal to one time window.
[0010] Secondly, embodiments of this application provide an accident early warning device, comprising: An accident module is used to acquire accident information; wherein, the accident information includes collision coordinates, first vehicle information of the accident vehicle at the moment of collision, and first movement information of the object that collided with the accident vehicle; The condition module is used to determine a critical moment and a critical warning condition corresponding to the critical moment by sliding a time window before the collision moment based on the first vehicle information and the first movement information; wherein the interval between the critical moment and the accident moment when the accident cannot be avoided is less than or equal to one time window, and the critical moment is before the accident moment. The early warning module is used to generate an early warning signal in response to the driving information of the vehicle to be controlled meeting the critical early warning conditions.
[0011] In some embodiments, the critical warning condition includes a critical distance, a critical driving speed of the accident vehicle at the critical moment, and a critical movement speed of the object; the critical distance indicates the distance at which a collision between the accident vehicle and the object can be avoided; the warning module is specifically used to determine a suspicious target; wherein the straight-line distance between the vehicle to be controlled and the suspicious target is less than a first distance threshold; in response to the path distance between the suspicious target and the vehicle to be controlled being less than or equal to the critical distance, the real-time target speed of the suspicious target is determined in real time; wherein the path distance is the distance between the vehicle to be controlled and the suspicious target along the driving path of the vehicle to be controlled; in response to the real-time driving speed of the vehicle to be controlled being greater than or equal to the critical driving speed, and / or the real-time target speed being greater than or equal to the critical movement speed, the warning signal is generated.
[0012] In some embodiments, the condition module is specifically used to determine multiple reference times; wherein the reference times are before the collision time, and there is at least one time window between the reference times and the collision time; based on the first vehicle information, the vehicle trajectory coordinates corresponding to the reference times and the first coordinate information of the vehicle trajectory coordinates are determined, and based on the first movement information, the object trajectory coordinates corresponding to the reference times and the second coordinate information of the object trajectory coordinates are determined; through a preset collision model, the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates are processed to determine the critical time; based on the critical time, the critical driving speed of the accident vehicle is queried from the first coordinate information, and the critical movement speed of the object is queried from the second coordinate information to obtain the critical warning condition.
[0013] In some embodiments, the condition module is specifically used to input the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates into a preset collision model for simulation to obtain a collision probability; wherein, the collision probability indicates the probability that, at the reference time, the accident vehicle changes its driving rules from the vehicle trajectory coordinates and the accident vehicle collides with the object; in response to the first collision probability of a first type of reference time in the reference time being greater than or equal to a preset collision threshold, and the second collision probability of a second type of reference time in the reference time being less than the preset collision threshold, the first type of reference time is determined to be the accident time, and the second type of reference time is determined to be the critical time; wherein, the time interval between the second type of reference time and the first type of reference time is less than or equal to one time window.
[0014] In some embodiments, the collision model incorporates at least two driving rules, which include driving direction and / or acceleration; the condition module is further configured to simulate, in the collision model, the sub-probability of the accident vehicle traveling from the vehicle trajectory coordinates at the reference time according to the driving rules and colliding with the object; and to determine the critical time based on the sub-probability of the first type of reference time, the sub-probability of the second type of reference time, and a preset collision threshold.
[0015] In some embodiments, the condition module is further configured to, in response to a first time in the reference time, where the sub-probabilities of multiple driving rules are all greater than or equal to the preset collision threshold, and at least one sub-probability of a driving rule is less than the preset collision threshold in a second time in the reference time, determine the first time as the first type of reference time and the second time as the second type of reference time; the time interval between the first time and the second time is less than or equal to one time window; and / or, in response to a third time in the reference time, where at least one sub-probability is greater than or equal to the preset collision threshold, and at a fourth time in the reference time, where the sub-probabilities are all less than the preset collision threshold, determine the third time as the first type of reference time and the fourth time as the second type of reference time; the time interval between the third time and the fourth time is less than or equal to one time window.
[0016] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein the processor executes the computer program to implement the method described in the first aspect and any of the embodiments.
[0017] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the methods described in the first aspect and any of the embodiments.
[0018] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect and any of the embodiments.
[0019] The accident warning method provided by this invention determines the critical moment at which an accident can be avoided based on accident information, and uses the parameters at this critical moment as critical warning conditions, applying them to a vehicle under control that is driving normally. In response to the driving information of the vehicle under control meeting the critical warning conditions, a warning signal is generated to achieve accurate and reliable accident warning. Because the accident warning method provided in this application accurately locates the critical moment, the warning signal is timely and reliable. Therefore, this accident warning method can avoid accidents and effectively improve the driving safety of assisted driving.
[0020] Other features and advantages of the invention will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not intended to limit this disclosure. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0022] Figure 1 This is a flowchart illustrating an accident warning method in one embodiment; Figure 2A This is a schematic diagram illustrating the driving directions of the accident vehicle and the object in one embodiment; Figure 2B This is a schematic diagram illustrating the direction of travel of the accident vehicle and the object in another embodiment; Figure 3 This is a schematic diagram illustrating the straight-line distance and critical distance between the vehicle to be controlled and the suspected target in one embodiment; Figure 4 This is a flowchart illustrating a method for determining a critical moment in one embodiment; Figure 5 This is a schematic diagram of multiple reference times determined based on a time window in one embodiment; Figure 6A This is a schematic diagram illustrating the relationship between the critical moment, the collision moment, and the accident identification point in one embodiment. Figure 6B This is a schematic diagram illustrating the relationship between the accident identification point, the critical moment, the accident moment, and the collision moment in one embodiment. Figure 7This is a structural block diagram of an accident early warning device in one embodiment; Figure 8 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation
[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.
[0024] It should be noted that the illustrations provided in this embodiment are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show components relevant to the present invention and are not drawn according to the actual number, shape, and size of components in implementation. In actual implementation, the form, quantity, and proportion of each component can be arbitrarily changed, and the component layout may be more complex. The structures, proportions, sizes, etc., depicted in the accompanying drawings are only for illustrative purposes to aid those skilled in the art and are not intended to limit the implementation conditions of the present invention. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in proportions, or adjustments to size, without affecting the effects and objectives of the present invention, should still fall within the scope of the technical content disclosed in the present invention. Furthermore, the terms such as "upper," "lower," "left," "right," "middle," and "one" used in this specification are only for clarity of description and are not intended to limit the scope of the present invention. Changes or adjustments to their relative relationships, without substantially altering the technical content, should also be considered within the scope of the present invention.
[0025] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the document does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0026] As illustrated herein, unless the context clearly indicates otherwise, the words “a,” “an,” “an,” and / or “the” do not specifically refer to the singular and may also include the plural. Generally speaking, the terms “comprising” and “including” only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.
[0027] The definitions used herein, such as the terms “having,” “may have,” “comprising,” or “may include,” indicate the presence of the corresponding function, operation, element, etc., and do not limit the presence of one or more other functions, operations, elements, etc. Furthermore, it should be understood that the terms “comprising” or “having” as used herein indicate the presence of the features, figures, steps, operations, elements, components, or combinations thereof described in the specification, without excluding the presence or addition of one or more other features, figures, steps, operations, elements, components, or combinations thereof.
[0028] In this embodiment of the invention, prefixes such as "first" and "second" are used merely to distinguish different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application does not constitute a limitation on the described objects. For statements regarding the described objects, please refer to the claims or the context of the embodiments. The use of such prefixes should not constitute unnecessary limitations. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.
[0029] To improve safety during assisted driving, this application provides an accident warning method to ensure user experience, avoid generating warning signals too early or incorrectly, and improve driving safety by generating warning signals in a timely manner.
[0030] It is worth noting that, in this application embodiment, the assisted driving means that the controller intervenes in vehicle control during driving through sensor data and / or cloud information, such as steering, acceleration, and braking. This assisted driving can control the vehicle and make decisions about its movement. Furthermore, in the event of manual intervention, the initiative is relinquished to the user, who then continues to control the vehicle.
[0031] Please refer to Figure 1 The following describes the aforementioned accident early warning method, which includes at least the following implementation steps: Step 101: Obtain accident information.
[0032] The accident information includes collision coordinates, the first vehicle information of the accident vehicle at the moment of collision, and the first movement information of the object that collided with the accident vehicle.
[0033] Specifically, the aforementioned objects include, but are not limited to, pedestrians and / or vehicles that can move continuously.
[0034] This collision coordinate corresponds to the moment of collision. That is, at the moment of collision, the accident occurred at the collision coordinate.
[0035] The first vehicle information includes the vehicle's speed at the time of the collision and its speed before the collision.
[0036] The first movement information includes the object's movement speed at the moment of collision, and its movement speed before the moment of collision.
[0037] Optionally, the aforementioned first vehicle information can be obtained by querying the corresponding sensors or control units installed in the vehicle.
[0038] Optionally, the first movement information can be obtained by processing data collected in real time from one or more sensors mounted on the accident vehicle according to preset rules.
[0039] Alternatively, this initial movement information can be obtained by the accident vehicle sending a request to the cloud.
[0040] Step 102: Based on the first vehicle information and the first movement information, slide the time window before the collision time to determine the critical time and the critical warning conditions corresponding to the critical time.
[0041] Wherein, the interval between the critical moment and the moment of the unavoidable accident is less than or equal to one time window, and the critical moment is before the moment of the accident.
[0042] Specifically, the critical moment is used to avoid accidents. At this critical moment, if the vehicle involved in the accident changes its driving rules (e.g., changes its direction of travel and / or acceleration), it can avoid colliding with the object at the moment of impact.
[0043] The phrase "adjacent to the critical moment and the accident moment" means that the interval between the critical moment and the accident moment is less than or equal to one time window. In this case, at the accident moment, the vehicle involved in the accident has not yet collided with the object, but at that moment, a collision between the vehicle and the object is inevitable.
[0044] Therefore, the temporal relationship between the critical moment, the accident moment, and the collision moment is as follows: the critical moment is before the accident moment, and the accident moment is before the collision moment.
[0045] The interval between the critical moment and the collision moment is measured in seconds. For example, this time window can be 5 seconds, 4 seconds, 3 seconds, etc.
[0046] In this embodiment of the application, the driving rules can also be understood as driving rules, control rules, movement rules, driving strategies, etc.
[0047] Furthermore, the aforementioned critical warning conditions include critical distance, critical driving speed of the accident vehicle at the critical moment, and critical movement speed of the object at the critical moment.
[0048] The critical distance indicator defines the distance at which a collision between the vehicle and the object should be avoided. It should be understood that when the distance between the vehicle and the object is greater than this critical distance, a collision is virtually impossible. When the distance is less than this critical distance, a collision is highly likely. Especially assuming the vehicle maintains its pre-collision driving pattern, and the object also maintains its pre-collision speed and direction of movement, a collision is almost certain when the distance between the vehicle and the object is less than this critical distance.
[0049] In one embodiment, the aforementioned critical distance may correspond to the direction of travel of the accident vehicle.
[0050] The direction of travel in the accident can indicate whether the vehicle involved in the accident turned within a preset time period prior to the moment of collision. Accordingly, the direction of travel in the accident includes a first type of direction and a second type of direction.
[0051] For example, the first type of direction can be straight without turning, and the second type of direction is turning; then the critical distance corresponding to the first type of direction is the distance between the accident vehicle and the object along the driving path (dashed line) of the accident vehicle; please refer to Figure 2A The critical distance corresponding to the second type of direction is determined by extending the road where the collision coordinates are located, and then determining the projections of the accident vehicle and the object onto the extended line, and finally determining the relative distance between their projections; please refer to... Figure 2B . Figure 2A and Figure 2B The dashed line in the middle represents the respective travel paths of the accident vehicle and the object involved.
[0052] Furthermore, the aforementioned critical warning conditions can be determined by the critical moment. Specifically, based on the first vehicle information in the accident information, the vehicle trajectory coordinates of the accident vehicle at the critical moment, and the object trajectory coordinates of the object at the critical moment, can be determined on the vehicle trajectory of the accident vehicle. Then, based on the vehicle trajectory coordinates and the object trajectory coordinates, the critical distance between them can be determined. That is, the critical distance is the travel distance between the accident vehicle and the object at the critical moment. At the same time, the critical travel speed of the accident vehicle on the corresponding vehicle trajectory coordinates and the critical movement speed on the corresponding object trajectory coordinates can be obtained from the first vehicle information. Thus, the critical warning conditions are obtained.
[0053] Step 103: In response to the driving information of the vehicle to be controlled meeting the critical warning conditions, a warning signal is generated.
[0054] Specifically, firstly, a suspicious target can be identified for the vehicle to be controlled. The relative distance between the vehicle to be controlled and the suspicious target is determined when the straight-line distance between them is less than a first distance threshold. This first distance threshold may be slightly greater than or equal to the aforementioned critical distance. Then, in response to the path distance between the suspicious target and the vehicle to be controlled being less than or equal to the critical distance, the real-time target speed of the suspicious target is determined in real time. This path distance is the distance between the vehicle to be controlled and the suspicious target along the vehicle's driving lane. Preferably, the real-time target speed of the suspicious target is determined in real time in response to the path distance between the suspicious target and the vehicle to be controlled being equal to the critical distance.
[0055] Finally, a warning signal is generated in response to the real-time driving speed of the vehicle to be controlled being greater than or equal to the critical driving speed, and / or the target real-time speed being greater than or equal to the critical moving speed. Preferably, the warning signal is generated in response to the real-time driving speed of the vehicle to be controlled being greater than or equal to the critical driving speed, and the target real-time speed being greater than or equal to the critical moving speed.
[0056] In this embodiment, the difference between straight-line distance and path distance is particularly evident in distinguishing critical distances by the direction of travel, while there are situations where the road between the vehicle to be controlled and the suspected target has a turn (please refer to...). Figure 3 When identifying suspicious targets, first filter them by straight-line distance to avoid the problem of too many suspicious targets causing a decrease in the driving speed of the vehicle to be controlled.
[0057] Furthermore, after generating an early warning signal, an emergency mode can be entered to prevent accidents from occurring or to protect personal safety to the greatest extent possible.
[0058] For example, in emergency mode, at least one of the following can be generated based on the warning signal: an accident warning signal, a seat control signal, and a telescopic anti-collision beam control signal. The accident warning signal is used to control the suspension height to rise by a preset dimension; the seat control signal is used to control the seat to return from a user-defined state to a preset safe state (mainly including backrest angle and seat cushion height); and the telescopic anti-collision beam control signal is used to control the telescopic anti-collision beam to enter a pre-specified folding state.
[0059] Furthermore, an embodiment is provided below to illustrate the determination of the critical moment and the determination of the critical warning condition. Please refer to [reference needed]. Figure 4 : Step 401: Determine multiple reference times.
[0060] The reference time is prior to the collision time, and there is at least one time window between the reference time and the collision time.
[0061] Specifically, multiple reference times can be obtained by shifting backward from the collision time based on a time window, and the critical time can be determined through these reference times. For example, Figure 5 This is a schematic diagram illustrating the relationship between a reference time and a collision time on a timeline, provided as an embodiment of this application. The relationship between the reference times t1, t2, t3... and the collision time T0 is as follows: Figure 5 As shown, there is a time window △T between two adjacent reference times.
[0062] Step 402: Based on the first vehicle information, determine the vehicle trajectory coordinates corresponding to the reference time and the first coordinate information of the vehicle trajectory coordinates; and based on the first movement information, determine the object trajectory coordinates corresponding to the reference time and the second coordinate information of the object trajectory coordinates.
[0063] Specifically, the first coordinate information includes the velocity and / or acceleration of the accident vehicle on the vehicle trajectory coordinates. The first coordinate information may also include the direction of the accident vehicle on the vehicle trajectory coordinates.
[0064] The second coordinate information includes the object's velocity and / or acceleration along the object's trajectory coordinates. The second coordinate information may also include the object's orientation along the object's trajectory coordinates.
[0065] In one embodiment, the vehicle trajectory coordinates and the vehicle trajectory information on the vehicle trajectory coordinates can be directly obtained from the first vehicle information based on the reference time.
[0066] Alternatively, if the vehicle trajectory coordinates are not found in the first vehicle information, then the two trajectory times closest to the reference time are determined from the first vehicle information, along with the vehicle trajectory information for these two trajectory times, and the vehicle trajectory coordinates for the reference time are determined.
[0067] Similarly, when determining the trajectory coordinates of an object, they can be obtained from the first movement information based on the reference time.
[0068] In one embodiment, the trajectory of the accident vehicle before the collision can be determined based on the first vehicle information. Simultaneously, the trajectory of the object before the collision can be determined based on the first movement information. Then, the vehicle trajectory coordinates corresponding to the reference time are located in the accident vehicle's trajectory, and the object trajectory coordinates corresponding to the reference time are located in the object's movement trajectory.
[0069] Step 403: Using a preset collision model, process the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates to determine the critical moment.
[0070] Specifically, the aforementioned first coordinate information and second coordinate information have a temporal correspondence. That is, the first coordinate information and the second coordinate information correspond to the same reference time.
[0071] The preset collision model can be a model installed in any of the following software, including but not limited to PC-Crash (PC-CRASH, traffic accident reconstruction and simulation software), MADYMO (MAthematical DYnamic MOdels, digital dynamics model software), or PreScan (PreScan Simulation Platform, intelligent driving simulation platform).
[0072] The preset collision model is used to simulate whether a collision will occur between an accident vehicle on the vehicle trajectory coordinates that continues to travel along its trajectory with the first coordinate information and an object on the object trajectory coordinates that continues to move along its movement trajectory with the second coordinate information.
[0073] Thus, the first coordinate information of the vehicle's trajectory and the second coordinate information of the object's trajectory can be input into a preset collision model for simulation to obtain the collision probability. That is, in the collision model, the possibility of a collision occurs when the accident vehicle changes its driving rules at a reference time, while keeping the object's second coordinate information unchanged. The collision probability indicates the probability that, at the reference time, the accident vehicle will collide with the object when its driving rules change.
[0074] Then, in response to the first collision probability of the first type of reference time in the reference time being greater than or equal to a preset collision threshold, and the second collision probability of the second type of reference time in the reference time being less than the preset collision threshold, the first type of reference time is determined to be the aforementioned accident time, and the second type of reference time is determined to be the critical time.
[0075] The time interval between the second type of reference time and the first type of reference time is less than or equal to one time window. The second type of reference time is after the first type of reference time.
[0076] Optionally, the above driving rules may include at least one of the following rules: Rule 1: Full braking, no acceleration. Rule 2: Left turn, no braking, no acceleration. Rule 3: Right turn, no braking, no acceleration. Rule 4: Left turn and braking. Rule 5: Right turn and braking. Rule 6: Left turn and acceleration. Rule 7: Right turn and acceleration. Rule 8: Accelerate while driving straight. In this example, the difference between full braking and braking is that full braking is emergency braking, controlling the brake pedal to quickly reach the floor; while braking is mainly for smooth deceleration, controlling the brake pedal with appropriate force.
[0077] Therefore, in one embodiment, the purpose of changing the driving rules can be achieved by altering at least one of the braking method, acceleration rules, and driving direction in the driving rules. For example, changing "no braking" in the driving rules to "full braking" or "braking". For instance, changing "acceleration" in the driving rules to "no acceleration" or "acceleration when turning right", etc.
[0078] The critical moment obtained according to the above embodiments can be before the collision moment and after the accident identification point. This critical moment is the point at which the accident vehicle can just avoid the collision. The aforementioned accident identification point is the moment when the occupants of the accident vehicle observe the collision with the object.
[0079] In one embodiment, the interval between the accident recognition point and the collision time includes the reaction time of the occupants after realizing the danger, the time it takes to lift their foot and press the brake, and the time it takes to control the steering wheel to turn the wheels. For the relationship between the accident recognition point, the critical moment, and the collision time, please see [link to relevant documentation]. Figure 6A Alternatively, in one embodiment, the incident identification point may coincide with the critical moment.
[0080] Figure 6B This is a schematic diagram illustrating the temporal relationship between the accident identification point, critical moment, accident moment, and collision moment, provided for embodiments of this application. Figure 6B As shown, the accident occurrence point precedes the critical moment, and the critical moment is adjacent to the accident occurrence point.
[0081] Furthermore, the aforementioned preset collision model incorporates at least two driving rules, which include driving direction and / or acceleration. Therefore, in the aforementioned collision model, the difference between any two driving rules can be that their driving directions and / or accelerations are different. Each driving rule can correspond to a sub-probability. The aforementioned collision probability includes multiple sub-probabilities corresponding to driving rules. In one embodiment, the critical moment can be determined through the following implementation method: First, in the collision model, the simulation considers multiple sub-probabilities of a collision occurring between the accident vehicle and an object, assuming the vehicle's trajectory coordinates from the reference time and following at least two of the aforementioned driving rules. Each sub-probability corresponds one-to-one with a driving rule. The reference time may include a first-type reference time and a second-type reference time with a time interval less than or equal to one time window.
[0082] Then, based on multiple sub-probabilities of the first type of reference time, multiple sub-probabilities of the second type of reference time, and a preset collision threshold, the critical time is determined.
[0083] To elaborate further: the reference times include the first time point, the second time point, the third time point, the fourth time point, and so on. If the first time point and the second time point are adjacent, then the time interval between the first time point and the second time point is less than or equal to one time window. If the third time point and the fourth time point are adjacent, then the time interval between the third time point and the fourth time point is less than or equal to one time window.
[0084] Thus, in response to the first time point in the reference time, where the sub-probabilities of multiple driving rules are all greater than or equal to a preset collision threshold, and at least one sub-probability of a driving rule is less than the preset collision threshold in the second time point in the reference time, the first time point is determined to be a first type of reference time, and the second time point is determined to be a second type of reference time. In this embodiment, the first time point can be the aforementioned accident time. Then, the second time point is the critical time point located before the first time point.
[0085] And / or, In response to the following scenario: at the third time point, at least one sub-probability is greater than or equal to a preset collision threshold; and at the fourth time point, the sub-probabilities of all driving rules are less than the preset collision threshold, the third time point is determined as a first type of reference time, and the fourth time point as a second type of reference time. In this embodiment, the third time point can be the time when an accident cannot be avoided by using driving rules with sub-probabilities greater than the preset collision threshold. Therefore, the fourth time point is the critical time point preceding the third time point. Thus, this embodiment is specifically applicable to control scenarios with high requirements for driving rules, such as lanes that do not allow corresponding vehicles to turn.
[0086] Understandably, the time intervals between the first and second moments, as well as between the third and fourth moments, are two adjacent reference moments separated by one time window.
[0087] Furthermore, to further enhance user experience and maximize user safety, the second moment can be designated as the first critical moment, and the fourth moment as the second critical moment. In this embodiment, the second critical moment is located before the first critical moment. Thus, when the critical moment includes both the first and second critical moments, a first type of warning signal and a second type of warning signal can be configured for the first and second critical moments respectively, adapting corresponding safety control strategies for the vehicle to be controlled. This allows the vehicle to adopt a first set of protection strategies based on the first type of warning signal, preventing the generation of the second type of warning signal and avoiding accidents. If the protection strategy corresponding to the first type of warning signal fails to prevent the generation of the second type of warning signal, a second set of protection strategies can be executed after receiving the second type of warning signal, thereby maximizing the avoidance of accidents and ensuring the safety of people and vehicles.
[0088] It should be understood that, although Figure 1 , Figure 4The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 , Figure 4 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
[0089] Based on the same inventive concept, such as Figure 7 As shown, this application embodiment provides an accident early warning device, including: an accident module 701, a condition module 702, and an early warning module 703, wherein: Accident module 701 is used to obtain accident information.
[0090] The accident information includes collision coordinates, first vehicle information of the accident vehicle at the moment of collision, and first movement information of the object that collided with the accident vehicle.
[0091] The condition module 702 is used to determine the critical moment and the critical warning condition corresponding to the critical moment by sliding a time window before the collision moment based on the first vehicle information and the first movement information.
[0092] Wherein, the interval between the critical moment and the moment of the unavoidable accident is less than or equal to one time window, and the critical moment is before the moment of the accident.
[0093] The early warning module 703 is used to generate an early warning signal in response to the driving information of the vehicle to be controlled meeting the critical early warning conditions.
[0094] In one embodiment, the condition module 702 is specifically used to determine multiple reference times; wherein the reference times are before the collision time, and there is at least one time window between the reference times and the collision time; based on the first vehicle information, the vehicle trajectory coordinates corresponding to the reference times and the first coordinate information of the vehicle trajectory coordinates are determined, and based on the first movement information, the object trajectory coordinates corresponding to the reference times and the second coordinate information of the object trajectory coordinates are determined; through a preset collision model, the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates are processed to determine the critical time; based on the critical time, the critical driving speed of the accident vehicle is queried from the first coordinate information, and the critical movement speed of the object is queried from the second coordinate information to obtain the critical warning condition.
[0095] In one embodiment, the condition module 702 is specifically used to input the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates into a preset collision model for simulation to obtain a collision probability; wherein, the collision probability indicates the probability that the accident vehicle changes its driving rules from the vehicle trajectory coordinates and collides with the object at the reference time; in response to the first collision probability of the first type of reference time in the reference time being greater than or equal to a preset collision threshold, and the second collision probability of the second type of reference time in the reference time being less than the preset collision threshold, the first type of reference time is determined to be the accident time, and the second type of reference time is determined to be the critical time; wherein, the time interval between the second type of reference time and the first type of reference time is less than or equal to one time window.
[0096] In one embodiment, the collision model incorporates at least two driving rules, the driving rules including driving direction and / or acceleration; the condition module 702 is further configured to: In the collision model, the sub-probability of the accident vehicle colliding with the object at the reference time is simulated, based on the vehicle trajectory coordinates at the reference time and the driving rules; the critical time is determined based on the sub-probability of the first type of reference time, the sub-probability of the second type of reference time, and a preset collision threshold.
[0097] In some embodiments, the condition module 702 is further configured to, in response to a first time in the reference time, where the sub-probabilities of a plurality of driving rules are all greater than or equal to the preset collision threshold, and at least one sub-probability of a driving rule is less than the preset collision threshold in a second time in the reference time, determine the first time as the first type of reference time and the second time as the second type of reference time; the time interval between the first time and the second time is less than or equal to one time window; and / or, in response to a third time in the reference time, where at least one sub-probability is greater than or equal to the preset collision threshold, and at a fourth time in the reference time, where the sub-probabilities are all less than the preset collision threshold, determine the third time as the first type of reference time and the fourth time as the second type of reference time; the time interval between the third time and the fourth time is less than or equal to one time window.
[0098] In one embodiment, the critical warning condition includes a critical distance, a critical driving speed of the accident vehicle at the critical moment, and a critical movement speed of the object; the critical distance indicates the distance at which the accident vehicle and the object can be avoided; the warning module 703 is specifically used to: determine a suspicious target; wherein the straight-line distance between the vehicle to be controlled and the suspicious target is less than a first distance threshold; in response to the path distance between the suspicious target and the vehicle to be controlled being less than or equal to the critical distance, determine the real-time target speed of the suspicious target in real time; wherein the path distance is the distance between the vehicle to be controlled and the suspicious target along the driving path of the vehicle to be controlled; in response to the real-time driving speed of the vehicle to be controlled being greater than or equal to the critical driving speed, and / or the real-time target speed being greater than or equal to the critical movement speed, generate the warning signal.
[0099] Specific limitations regarding the accident warning device can be found in the limitations of the accident warning method described above, and will not be repeated here. Each module in the aforementioned accident warning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independently of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.
[0100] Based on the same inventive concept, please refer to Figure 8 This application also provides an electronic device. In one embodiment, the electronic device, as shown in the figure, may include a memory 801, a communication module 803, and one or more processors 802.
[0101] The memory 801 is used to store computer programs executed by the processor 802. The memory 801 mainly includes a program storage area and a data storage area. The program storage area can store the operating system, and the data storage area can store various operation instruction sets, etc.
[0102] Memory 801 may be volatile memory, such as random-access memory (RAM); memory 801 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 801 may be any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 801 may be a combination of the above-mentioned memories.
[0103] Processor 802 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 802 is used to implement the above-mentioned method of accident warning when calling the computer program stored in memory 801.
[0104] The communication module 803 is used to communicate with terminal equipment, site equipment or other network equipment.
[0105] This application embodiment does not limit the specific connection medium between the memory 801, communication module 803, and processor 802 described above. This application embodiment... Figure 8 The memory 801 and the processor 802 are connected via a bus 804, and the bus 804 is in Figure 8 The diagram uses thick lines to describe the connections between other components; these are for illustrative purposes only and should not be considered limiting. The 804 bus can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 8 It is described using only a thick line, but does not indicate that there is only one bus or one type of bus.
[0106] The memory 801 stores a computer storage medium, which stores computer-executable instructions. These instructions are used to implement the method for determining accident warnings according to embodiments of this application. The processor 802 is used to execute the accident warning methods of the embodiments described above using the computer-executable instructions.
[0107] Those skilled in the art will understand that Figure 8The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0108] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, performs the following steps: Obtain accident information; wherein, the accident information includes collision coordinates, first vehicle information of the accident vehicle at the moment of collision, and first movement information of the object that collided with the accident vehicle; Based on the first vehicle information and the first movement information, a time window is slid forward to the moment of collision to determine the critical moment and the critical warning conditions corresponding to the critical moment. A warning signal is generated in response to the driving information of the vehicle to be controlled meeting the critical warning conditions.
[0109] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0110] Based on the same inventive concept, embodiments of this application also provide a computer program product, including a computer program, which, when executed by a processor, implements the accident warning method described in any of the above claims.
[0111] The program code for executing the computer program product of this application can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.
[0112] 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 embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0113] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0114] 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.
[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of user-operated steps to be executed 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.
[0116] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. An accident early warning method, characterized in that, include: Obtain accident information; wherein, the accident information includes first vehicle information of the vehicle involved in the accident at the moment of collision, and first movement information of the object that collided with the vehicle involved in the accident; Based on the first vehicle information and the first movement information, a time window is slid forward to the moment of collision to determine the critical moment and the critical warning condition corresponding to the critical moment; wherein, the interval between the critical moment and the moment of the unavoidable accident is less than or equal to one time window, and the critical moment is before the moment of the accident. A warning signal is generated in response to the driving information of the vehicle to be controlled meeting the critical warning conditions.
2. The method as described in claim 1, characterized in that, The critical warning conditions include the critical distance between the accident vehicle and the object at the critical moment, the critical driving speed of the accident vehicle at the critical moment, and the critical moving speed of the object. The step of generating a warning signal in response to the driving information of the vehicle to be controlled meeting the critical warning condition includes: Identify a suspicious target; wherein the straight-line distance between the vehicle to be controlled and the suspicious target is less than a first distance threshold; In response to the path distance between the suspected target and the vehicle to be controlled being less than or equal to the critical distance, the real-time driving speed of the vehicle to be controlled and the target real-time speed of the suspected target corresponding to the real-time driving speed are determined in real time; wherein, the path distance is the distance between the vehicle to be controlled and the suspected target along the driving path of the vehicle to be controlled. The warning signal is generated in response to the real-time driving speed being greater than or equal to the critical driving speed, and / or the target real-time speed being greater than or equal to the critical moving speed.
3. The method as described in claim 1 or 2, characterized in that, The step of determining a critical moment and a corresponding critical warning condition by sliding a time window before the collision moment based on the first vehicle information and the first movement information includes: Multiple reference times are determined; wherein the reference times are prior to the collision time, and there is at least one time window between the reference times and the collision time; Based on the first vehicle information, determine the vehicle trajectory coordinates corresponding to the reference time, and the first coordinate information of the vehicle trajectory coordinates; and based on the first movement information, determine the object trajectory coordinates corresponding to the reference time, and the second coordinate information of the object trajectory coordinates. By using a preset collision model, the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates are processed to determine the critical moment; Based on the critical moment, the critical driving speed of the accident vehicle is queried from the first coordinate information, and the critical movement speed of the object is queried from the second coordinate information to obtain the critical warning condition.
4. The method as described in claim 3, characterized in that, The step of processing the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates using a preset collision model to determine the critical moment includes: The first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates are input into a preset collision model for simulation to obtain the collision probability; wherein, the collision probability indicates the probability that the accident vehicle collides with the object at the reference time when the accident vehicle changes its driving rules from the vehicle trajectory coordinates. In response to a first collision probability of a first type of reference time in the reference time being greater than or equal to a preset collision threshold, and a second collision probability of a second type of reference time in the reference time being less than the preset collision threshold, the first type of reference time is determined to be the accident time, and the second type of reference time is determined to be the critical time; wherein the time interval between the second type of reference time and the first type of reference time is less than or equal to one time window.
5. The method as described in claim 3, characterized in that, The collision model has at least two built-in driving rules; The step of processing the first coordinate information of the vehicle trajectory coordinates and the second coordinate information of the object trajectory coordinates through a preset collision model to determine the critical moment includes: In the collision model, at the reference time, the accident vehicle travels from the vehicle trajectory coordinates according to at least two of the driving rules, and multiple sub-probabilities of colliding with the object are simulated. The critical moment is determined based on multiple sub-probabilities of the first type of reference moment, multiple sub-probabilities of the second type of reference moment, and a preset collision threshold.
6. The method as described in claim 5, characterized in that, Determining the critical moment based on the sub-probabilities of the first type of reference moment, the sub-probabilities of the second type of reference moment, and a preset collision threshold includes: In response to the fact that at a first time in the reference time, the sub-probabilities of multiple driving rules are all greater than or equal to the preset collision threshold, and at a second time in the reference time, the sub-probability of at least one driving rule is less than the preset collision threshold, the first time is determined to be the first type of reference time, and the second time is determined to be the second type of reference time; the time interval between the first time and the second time is less than or equal to one time window; And / or, In response to the third time of the reference time, at least one of the sub-probabilities is greater than or equal to the preset collision threshold, and at the fourth time of the reference time, all the sub-probabilities are less than the preset collision threshold, the third time is determined to be the first type of reference time, and the fourth time is determined to be the second type of reference time; the time interval between the third time and the fourth time is less than or equal to one time window.
7. An accident early warning device, characterized in that, include: An accident module is used to acquire accident information; wherein, the accident information includes collision coordinates, first vehicle information of the accident vehicle at the moment of collision, and first movement information of the object that collided with the accident vehicle; The condition module is used to determine a critical moment and a critical warning condition corresponding to the critical moment by sliding a time window before the collision moment based on the first vehicle information and the first movement information; wherein the interval between the critical moment and the accident moment when the accident cannot be avoided is less than or equal to one time window, and the critical moment is before the accident moment. The early warning module is used to generate an early warning signal in response to the driving information of the vehicle to be controlled meeting the critical early warning conditions.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.