Vehicle collision risk prediction method, electronic equipment and storage medium

Abstract

The invention discloses a vehicle collision risk prediction method, electronic equipment and a storage medium, and the method comprises the steps: determining a critical safety distance for a target vehicle to avoid collision in a to-be-issued target path, and the critical safety distance is affected by the environmental factors of the target path; performing collision risk prediction on the target path based on the critical safety distance of the target path to obtain a target collision risk prediction result; wherein the target collision risk prediction result is used for representing whether there is a risk of collision with an obstacle when the target vehicle runs according to the target path; and based on the target collision risk prediction result, determining whether to issue a target path to the target vehicle, so that the target vehicle can run according to the target path. In this way, the collision risk can be avoided.

Description

Technical Field

[0001] The present application relates to the field of AGV technology, and in particular to a vehicle collision risk prediction method, electronic device and storage medium. Background Art

[0002] During the operation of the AGV, if the AGV is not properly guided, collisions and frictions between vehicles will occur, making it impossible to use the AGV safely.

[0003] At present, most of the distance between vehicles is controlled based on sensors installed on AGV carts to prevent collision and friction between vehicles, but the collision risk avoidance effect is poor. Summary of the invention

[0004] The main technical problem solved by the present application is to provide a vehicle collision risk prediction method, electronic device and storage medium, which can avoid collision risks.

[0005] To solve the above technical problems, a technical solution adopted in the present application is: to provide a vehicle collision risk prediction method, the method comprising: determining a critical safety distance for a target vehicle to avoid collision under a target path to be issued, wherein the critical safety distance is affected by environmental factors of the target path; based on the critical safety distance of the target path, predicting the collision risk of the target path to obtain a target collision risk prediction result; wherein the target collision risk prediction result is used to characterize whether there is a risk of collision with an obstacle when the target vehicle travels along the target path; based on the target collision risk prediction result, determining whether to issue the target path to the target vehicle so that the target vehicle can travel along the target path.

[0006] The critical safety distance is determined by at least one environmental factor, and the at least one environmental factor includes a configuration value affected by environmental factors of the target path.

[0007] Wherein, the critical safety distance is determined by at least one distance factor and at least one environmental factor, at least one distance factor includes a motion deviation determined by vehicle performance of the target vehicle; and / or, the critical safety distance is the sum of at least one distance factor and at least one environmental factor.

[0008] Among them, before determining the critical safety distance for the target vehicle to avoid collision on the target path to be issued, the vehicle collision risk prediction method also includes: obtaining the critical safety distance configured by the user for the target path in the topological map; and / or, in response to the user's modification operation of the configuration value corresponding to the target path in the topological map, updating the critical safety distance corresponding to the target path.

[0009] Among them, the critical safety distance corresponding to the target path includes the critical safety distance corresponding to at least one node in the target path, the critical safety distance corresponding to the node is affected by the environmental factors of the node in the target path, the critical safety distance of the target path includes multiple critical safety distances corresponding to different sub-paths of the target path, and the critical safety distance corresponding to each sub-path is determined by at least the critical safety distances of at least some of the nodes in the sub-path.

[0010] Wherein, the target path includes at least two nodes arranged in sequence along the path direction corresponding to the target path, and two adjacent nodes constitute a sub-path; determining the critical safety distance for the target vehicle to avoid collision under the target path to be issued, including: taking the first sub-path as the reference path, and determining the critical safety distance of the target vehicle on the reference path based on at least the critical safety distance corresponding to the tail node of the reference path; based on the critical safety distance of the target path, predicting the collision risk of the target path to obtain a target collision risk prediction result, including: based on the critical safety distance of the target vehicle on the reference path, predicting the collision risk of the reference path to obtain a reference collision risk prediction result; wherein the reference collision risk prediction result is used to characterize whether there is a risk of collision with an obstacle when the target vehicle travels along the reference path; at the critical safety distance based on the target path, predicting the collision risk of the target path to obtain a reference collision risk prediction result; wherein the reference collision risk prediction result is used to characterize whether there is a risk of collision with an obstacle when the target vehicle travels along the reference path; After performing collision risk prediction on the reference path and obtaining the target collision risk prediction result, the vehicle collision risk prediction method also includes: in response to the reference collision risk prediction result of the reference path being that the target vehicle does not have a collision risk, taking the next sub-path as the reference path, and re-executing at least the critical safety distance corresponding to the tail node of the reference path, determining the critical safety distance of the target vehicle on the reference path and its subsequent steps, until the reference collision risk prediction results corresponding to the last sub-path are all that the target vehicle does not have a collision risk, then determining the target collision risk prediction result is that the target vehicle does not have a risk of colliding with an obstacle when traveling along the target path, or, until it is determined that the reference collision risk prediction result of the sub-path is that there is a collision risk, then determining the target collision risk prediction result is that the target vehicle has a risk of colliding with an obstacle when traveling along the target path.

[0011] Among them, based on the critical safety distance of the target path, the collision risk of the target path is predicted to obtain a target collision risk prediction result, including: based on the critical safety distance of the target path, the driving area of ​​the target vehicle on the target path is expanded to obtain a safe driving area corresponding to the target path; based on the safe driving area corresponding to the target path and the driving conditions of obstacles, the target collision risk prediction result is determined.

[0012] Among them, based on the critical safety distance of the target path, the driving area of ​​the target vehicle on the target path is expanded to obtain the safe driving area corresponding to the target path, including: using the critical safety distance to expand the target vehicle to obtain the expanded target vehicle; obtaining the lock grid of the expanded target vehicle; based on the lock grid of the expanded target vehicle, generating the safe driving area corresponding to the target path; and / or, based on the safe driving area corresponding to the target path and the driving conditions of the obstacles, determining the target collision risk prediction result, including: obtaining the safe driving area of ​​each obstacle at a target time, the target time being the time period when the target vehicle is traveling on the target path; determining the target collision risk prediction result based on whether there is overlap between the safe driving areas of the target vehicle and each obstacle.

[0013] Among them, using the critical safety distance to expand the target vehicle to obtain the expanded target vehicle, including: taking at least one direction of the front, back, left, and right of the target vehicle as the direction to be expanded; using the critical safety distance as the expansion increment of the direction to be expanded, expanding the target vehicle along each direction to be expanded, and obtaining the expanded target vehicle.

[0014] Among them, based on the target collision risk prediction result, determining whether to send the target path to the target vehicle includes: in response to the target collision risk prediction result that there is no risk of collision with an obstacle when the target vehicle travels along the target path, performing a deadlock risk prediction on the target path to obtain a deadlock risk prediction result; wherein the deadlock risk prediction result is used to characterize whether there is a risk of deadlocking the obstacle when the target vehicle travels along the target path; based on the deadlock risk prediction result, determining whether to send the target path to the target vehicle; and / or, in response to the target collision risk prediction result that there is a risk of collision with an obstacle when the target vehicle travels along the target path, determining not to send the target path to the target vehicle.

[0015] Among them, based on the deadlock risk prediction result, it is determined whether to send the target path to the target vehicle, including: in response to the deadlock risk prediction result that there is no risk of deadlock caused to the operation of the obstacle, the target path is sent to the target vehicle; in response to the deadlock risk prediction result that there is a risk of deadlock caused to the operation of other vehicles, the target path is not sent to the target vehicle.

[0016] In order to solve the above technical problems, another technical solution adopted in the present application is: to provide an electronic device, which includes a memory and a processor, the memory stores program instructions, and the processor is used to execute the above program instructions to implement the above vehicle collision risk prediction method.

[0017] In order to solve the above technical problems, another technical solution adopted by the present application is: providing a computer-readable storage medium, which is used to store program instructions, and the program instructions can be executed to implement the above-mentioned vehicle collision risk prediction method.

[0018] The above technical solution predicts the collision risk of the target path based on the critical safety distance of the target path, obtains the target collision risk prediction result, and determines whether to send the target path to the target vehicle based on the target collision risk prediction result. Therefore, on the one hand, the collision risk prediction of the target path based on the critical safety distance of the target path will simultaneously predict the collision risk of the theoretical path and the path after the driving deviation caused by the environmental factors of the target path, which can better adapt to the real path environment and make it unaffected by environmental factors (such as humid and foggy environment, high reflective environment, etc.), and the collision prevention effect is better; on the other hand, the collision risk prediction of the target path is before sending the target path to the target vehicle, so the collision risk of the target path can be predicted before sending the target path to the target vehicle, so as to avoid the collision risk from the source and improve the safety of the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of an embodiment of a vehicle collision risk prediction method provided by the present application;

[0020] Figure 2 yes Figure 1 The flowchart of step S12 is shown as an embodiment;

[0021] Figure 3 is a schematic diagram of an embodiment of an expanded target vehicle provided by the present application;

[0022] Figure 4 It is a structural schematic diagram of an embodiment of a vehicle collision risk prediction device provided by the present application;

[0023] Figure 5 It is a structural schematic diagram of an embodiment of an electronic device provided by the present application;

[0024] Figure 6 It is a structural schematic diagram of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION

[0025] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0026] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0027] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.

[0028] See also Figure 1 , Figure 1 is a flow chart of an embodiment of a vehicle collision risk prediction method provided by the present application. It should be noted that if there are substantially the same results, this embodiment does not Figure 1 The process sequence shown is limited. Figure 1 As shown, this embodiment includes:

[0029] Step S11: Determine a critical safety distance for the target vehicle to avoid collision on the target path to be issued.

[0030] The method of this embodiment is used to predict whether there is a collision risk when the target vehicle travels along the target path to be issued, so that the target vehicle can avoid possible collision risks and improve the safety of the target vehicle.

[0031] It should be noted that the target vehicle mentioned in the present application may be an automated guided vehicle or an automated guided vehicle (AGV), which is an unmanned transport vehicle that can travel along a preset guide path and can be used for automatic handling and transportation of materials, goods or other items in factories, warehouses, hospitals and other environments.

[0032] In this embodiment, the critical safety distance for the target vehicle to avoid collision under the target path to be issued is determined, wherein the critical safety distance is affected by the environmental factors of the target path. Under normal circumstances, the target vehicle will travel according to the preset guide path, but under actual operation, the target vehicle's travel will deviate due to the environmental factors of the guide path; therefore, the critical safety distance for the target vehicle to avoid collision under the target path to be issued is determined, that is, the safety distance for the target vehicle to avoid collision under the target path to be issued, when the target vehicle is deviated due to the environmental factors of the target path. Subsequently, the target path is predicted for collision risk based on the critical safety distance of the target path, and the collision risk of the theoretical path and the path after the deviated travel due to the environmental factors of the target path are predicted at the same time. The vehicle collision risk prediction method provided by the present application can better adapt to the real path environment, so that it is not affected by environmental factors (such as humid and foggy environment, high reflective environment, etc.), and the collision prevention effect is better.

[0033] In one embodiment, the critical safety distance is determined by at least one environmental factor, and the at least one environmental factor includes a configuration value affected by the environmental factors of the target path. That is, the critical safety distance is at least a configuration value configured by the user based on the actual environmental conditions of the target path.

[0034] For example, if target path A is relatively flat, and it is estimated that the target vehicle will have a small deviation when traveling along target path A, the configuration value configured by the user based on the actual environment of target path A can be set to be smaller. For another example, if target path B is relatively rugged, and it is estimated that the target vehicle will have a large deviation when traveling along target path B, the configuration value configured by the user based on the actual environment of target path B can be set to be larger, so that the critical safety distance is larger, avoiding underestimating the deviation of the target vehicle traveling along target path B, thereby avoiding inaccurate collision risk prediction based on the critical safety distance of the target path, and ensuring the effect of vehicle collision risk prediction.

[0035] In other embodiments, the critical safety distance is determined by at least one distance factor and at least one environmental factor, and at least one distance factor includes a motion deviation determined by the vehicle performance of the target vehicle. In theory, the vehicle performance of the target vehicle just out of the factory is better and there is no motion deviation, but in the actual operation test process, the target vehicle will have motion deviation. Therefore, the target vehicle will not only be affected by the path environment of the target path and deviate from the path, but also by its own performance and deviate from the path.

[0036] In a specific embodiment, at least one distance factor includes a point motion deviation determined by the vehicle performance of the target vehicle and an obstacle avoidance distance of a laser radar on the target vehicle, and the point motion deviation determined by the vehicle performance of the target vehicle and the obstacle avoidance distance of the laser radar on the target vehicle are fixed parameters related to the target vehicle and its vehicle performance.

[0037] In a specific embodiment, the critical safety distance is the sum of at least one distance factor and at least one environmental factor. For example, the critical safety distance S is determined by at least one distance factor and at least one environmental factor, at least one environmental factor includes a configuration value S1 affected by environmental factors of the target path, at least one distance factor includes a point motion deviation S2 determined by the vehicle performance of the target vehicle and an obstacle avoidance distance S3 of a laser radar on the target vehicle, then the critical safety distance S = configuration value S1 affected by environmental factors of the target path + point motion deviation S2 determined by the vehicle performance of the target vehicle + obstacle avoidance distance S3 of a laser radar on the target vehicle.

[0038] In one embodiment, before determining the critical safety distance for the target vehicle to avoid collision under the target path to be issued, the critical safety distance configured by the user for the target path in the topological map is obtained. Specifically, a topological map consistent with the actual operation route is drawn according to the real environment, and the corresponding topological map needs to have a corresponding interface for subsequent critical safety distance calculation, which means that a configuration that can support the configuration of the critical safety distance needs to be set on the edges and nodes of the corresponding topological map; therefore, the critical safety distance configured by the user for the target path in the topological map can be obtained later.

[0039] In other embodiments, before determining the critical safety distance for the target vehicle to avoid collision under the target path to be issued, the configuration value of the topology map configured by the user regarding the target path is obtained. That is, only the configuration value affected by the environmental factors of the target path is configured on the nodes or edges of the topology map.

[0040] In one embodiment, before determining the critical safety distance for the target vehicle to avoid collision under the target path to be issued, in response to the user's modification operation on the configuration value corresponding to the target path in the topological map, the critical safety distance corresponding to the target path is updated. Determine the size of the critical safety distance actually required for the target path to be issued, because there are multiple interference items in the real environment, which may lead to different critical safety distances required for different target paths, and such differentiation is difficult to reflect in other inputs such as sensor data, but can be done through the configuration value of the topological map, so as to balance the possible differences through the configuration value. The user can modify the configuration value corresponding to the target path in the topological map in real time to update the critical safety distance corresponding to the target path, that is, the user can modify the configuration parameters of the corresponding target path in the topological map in real time to achieve additional collision protection at a specific location, with high flexibility and environmental adaptability. That is, the user can control the risk of vehicle collision by modifying the attributes of the topological map.

[0041] Step S12: Based on the critical safety distance of the target path, a collision risk prediction is performed on the target path to obtain a target collision risk prediction result.

[0042] In this embodiment, based on the critical safety distance of the target path, the target path is predicted for collision risk, and the target collision risk prediction result is obtained, wherein the target collision risk prediction result is used to characterize whether the target vehicle has the risk of colliding with obstacles when traveling along the target path. Based on the critical safety distance for the target vehicle to avoid collision under the target path to be issued, the target path to be issued is predicted for collision risk, so as to predict whether the target vehicle has the risk of colliding with other obstacles when traveling along the target path. On the one hand, the collision risk prediction of the target path based on the critical safety distance of the target path will simultaneously predict the collision risk of the theoretical path and the path after the driving deviation caused by the environmental factors of the target path, which can better adapt to the real path environment, so that it is not affected by environmental factors (such as humid and foggy environment, high reflective environment, etc.), and the collision prevention effect is better; on the other hand, the collision risk prediction of the target path is before the target path is issued to the target vehicle, so the collision risk of the target path can be predicted before the target path is issued to the target vehicle, so as to avoid the collision risk from the source.

[0043] The obstacles may be other vehicles, etc., which are not limited here.

[0044] In one embodiment, the critical safety distance corresponding to the target path includes the critical safety distance corresponding to at least one node in the target path, the critical safety distance corresponding to the node is affected by the environmental factors of the node in the target path, and the critical safety distance of the target path includes multiple critical safety distances corresponding to different sub-paths of the target path, and the critical safety distance corresponding to each sub-path is determined by at least the critical safety distances of at least some of the nodes in the sub-path.

[0045] That is to say, the target path to be sent includes at least one node in the topological map, and the critical safety distance corresponding to the target path is composed of the critical safety distances corresponding to the sub-paths constituting the target path, and the critical safety distance corresponding to each sub-path is determined by the nodes constituting it.

[0046] In a specific implementation, the critical safety distance corresponding to each subpath is determined by the critical safety distance of the tail node in the subpath. For example, the target path includes subpath A, subpath B, and subpath C, and subpath B includes nodes a3, a4, and a5 in sequence. Node a5 is the tail node of subpath B, so the critical safety distance corresponding to node a5 is used as the critical safety distance corresponding to subpath B.

[0047] In one embodiment, the target path includes at least two nodes arranged in sequence along the path direction corresponding to the target path, and two adjacent nodes constitute a sub-path. At this time, the critical safety distance for the target vehicle to avoid collision under the target path to be issued is determined, specifically: taking the first sub-path as the reference path, at least based on the critical safety distance corresponding to the tail node of the reference path, the critical safety distance of the target vehicle on the reference path is determined; based on the critical safety distance of the target path, the collision risk of the target path is predicted to obtain a target collision risk prediction result, specifically: based on the critical safety distance of the target vehicle on the reference path, the collision risk of the reference path is predicted to obtain a reference collision risk prediction result; wherein the reference collision risk prediction result is used to characterize whether there is a risk of collision with an obstacle when the target vehicle travels along the reference path; in the critical safety distance based on the target path, the target vehicle is predicted to have a collision risk of at least one obstacle. The method further comprises: in response to a reference collision risk prediction result of the reference path being that the target vehicle has no collision risk, taking the next sub-path as the reference path, and re-executing at least the critical safety distance corresponding to the tail node of the reference path, determining the critical safety distance of the target vehicle on the reference path and subsequent steps, until the reference collision risk prediction results corresponding to the last sub-path are all that the target vehicle has no collision risk, then determining the target collision risk prediction result is that the target vehicle has no risk of colliding with an obstacle when traveling along the target path, or, until it is determined that the reference collision risk prediction result of the sub-path is that there is a collision risk, then determining the target collision risk prediction result is that the target vehicle has a risk of colliding with an obstacle when traveling along the target path.

[0048] That is, the target path is cut into multiple sub-paths to determine whether the target vehicle has a risk of colliding with an obstacle when traveling along the sub-paths. If it is determined that the target vehicle has a risk of colliding with an obstacle when traveling along one of the sub-paths, the target collision risk prediction result is considered to be that the target vehicle has a risk of colliding with an obstacle when traveling along the target path.

[0049] For example, the target path includes sub-path A and sub-path B arranged in sequence along the path direction corresponding to the target path. The first sub-path (sub-path A) is used as the reference path, and based on the critical safety distance corresponding to the tail node of sub-path A, the critical safety distance of the target vehicle in sub-path A is determined; based on the critical safety distance of the target vehicle in sub-path A, a collision risk prediction is performed on sub-path A to obtain a reference collision risk prediction result; in response to the reference collision risk prediction result of sub-path A being that the target vehicle has a collision risk, a target collision risk prediction result is determined to be that the target vehicle has a risk of colliding with an obstacle when traveling along the target path; in response to the reference collision risk prediction result of sub-path A being that the target vehicle has no collision risk, based on the tail node of sub-path B, a collision risk prediction result is determined to be that the target vehicle has a risk of colliding with an obstacle when traveling along the target path. The critical safety distance of the target vehicle on sub-path B is determined according to the critical safety distance; based on the critical safety distance of the target vehicle on sub-path B, a collision risk prediction is performed on sub-path B to obtain a reference collision risk prediction result; in response to the reference collision risk prediction result of sub-path B being that the target vehicle has a collision risk, a target collision risk prediction result is determined to be that the target vehicle has a risk of colliding with an obstacle when traveling along the target path; in response to the reference collision risk prediction result of sub-path B being that the target vehicle does not have a collision risk, a target collision risk prediction result is determined to be that the target vehicle does not have a risk of colliding with an obstacle when traveling along the target path.

[0050] In other implementations, the collision risk prediction may not be started from the first sub-path, but may be randomly started from a sub-path located after the first sub-path.

[0051] For example, the target path includes sub-path A and sub-path B that are sequentially arranged along the path direction corresponding to the target path. Sub-path B is used as a reference path, and based on the critical safety distance corresponding to the tail node of sub-path B, the critical safety distance of the target vehicle in sub-path B is determined; based on the critical safety distance of the target vehicle in sub-path B, a collision risk prediction is performed on sub-path B to obtain a reference collision risk prediction result; in response to the reference collision risk prediction result of sub-path B being that the target vehicle has a collision risk, a target collision risk prediction result is determined to be that the target vehicle has a risk of colliding with an obstacle when traveling along the target path; in response to the reference collision risk prediction result of sub-path B being that the target vehicle does not have a collision risk, based on the critical safety distance corresponding to the tail node of sub-path A, a target collision risk prediction result is determined to be that the target vehicle has a risk of colliding with an obstacle when traveling along the target path; The method comprises the following steps: according to the first embodiment of the present invention, a critical safety distance of the target vehicle on subpath A is determined, and a critical safety distance of the target vehicle on subpath A is determined; based on the critical safety distance of the target vehicle on subpath A, a collision risk prediction is performed on subpath A to obtain a reference collision risk prediction result; in response to the reference collision risk prediction result of subpath A being that the target vehicle has a collision risk, a target collision risk prediction result is determined to be that the target vehicle has a risk of colliding with an obstacle when traveling along the target path; in response to the reference collision risk prediction result of subpath A being that the target vehicle does not have a collision risk, a target collision risk prediction result is determined to be that the target vehicle has no risk of colliding with an obstacle when traveling along the target path.

[0052] Step S13: Based on the target collision risk prediction result, determine whether to send a target path to the target vehicle so that the target vehicle can travel according to the target path.

[0053] In this embodiment, based on the target collision risk prediction result, it is determined whether to send the target path to the target vehicle so that the target vehicle can travel along the target path. The target collision risk prediction result reflects whether there is a risk of collision with an obstacle when the target vehicle travels along the target path. Therefore, based on the target collision risk prediction result, it is determined whether to send the target path to the target vehicle. In the case of a risk of collision with an obstacle, the target path can be not sent to the target vehicle, thereby avoiding the collision of the target vehicle with the obstacle when the target vehicle travels along the target path, achieving collision avoidance, and improving the safety of the target vehicle.

[0054] In one embodiment, based on the target collision risk prediction result, it is determined whether to send the target path to the target vehicle so that the target vehicle can travel along the target path, specifically: in response to the target collision risk prediction result that the target vehicle does not have the risk of colliding with obstacles when traveling along the target path, the target path is sent to the target vehicle so that the target vehicle can travel along the target path; in response to the target collision risk prediction result that the target vehicle has the risk of colliding with obstacles when traveling along the target path, the target path is not sent to the target vehicle. In other words, it is determined whether to send the target path to the target vehicle directly based on the target collision risk prediction result.

[0055] In other embodiments, based on the target collision risk prediction result, it is determined whether to send the target path to the target vehicle, specifically: in response to the target collision risk prediction result that the target vehicle does not have the risk of colliding with an obstacle when traveling along the target path, a deadlock risk prediction is performed on the target path to obtain a deadlock risk prediction result; wherein the deadlock risk prediction result is used to characterize whether there is a risk of deadlocking the obstacle when the target vehicle travels along the target path; based on the deadlock risk prediction result, it is determined whether to send the target path to the target vehicle. In other words, it is not directly determined whether to send the target path to the target vehicle based on the target collision risk prediction result, but when it is determined that the target collision risk prediction result is that the target vehicle does not have the risk of colliding with an obstacle when traveling along the target path, it is determined whether there is a risk of deadlocking the obstacle when the target vehicle travels along the target path. That is, when it is determined that there is no risk of collision with an obstacle, a deadlock risk determination is performed, and according to the deadlock risk determination result, it is determined whether to send the target path to the target vehicle.

[0056] In a specific implementation, based on the deadlock risk prediction result, it is determined whether to send the target path to the target vehicle, specifically: in response to the deadlock risk prediction result that there is no risk of causing deadlock to the operation of the obstacle, the target path is sent to the target vehicle; in response to the deadlock risk prediction result that there is a risk of causing deadlock to the operation of other vehicles, the target path is not sent to the target vehicle. In other words, when it is determined that there is a risk of causing deadlock to the operation of the obstacle when the target vehicle is traveling along the target path, the target path is not sent to the target vehicle to ensure that it will not cause deadlock to the operation of other obstacles in the future.

[0057] See also Figure 2 , Figure 2 yes Figure 1 FIG. 1 is a flow chart of an embodiment of step S12. It should be noted that if there is substantially the same result, this embodiment does not necessarily use Figure 2 The process sequence shown is limited. Figure 2As shown, based on the critical safety distance of the target path, the collision risk of the target path is predicted, and the target collision risk prediction result is obtained, which is specifically:

[0058] Step S21: Based on the critical safety distance of the target path, the driving area of ​​the target vehicle on the target path is expanded to obtain a safe driving area corresponding to the target path.

[0059] In this implementation, based on the critical safety distance of the target path, the driving area of ​​the target vehicle on the target path is expanded to obtain a safe driving area corresponding to the target path.

[0060] In one embodiment, based on the critical safety distance of the target path, the driving area of ​​the target vehicle on the target path is expanded to obtain a safe driving area corresponding to the target path, specifically: using the critical safety distance, the target vehicle is expanded to obtain an expanded target vehicle; the lock grid of the expanded target vehicle is obtained; based on the lock grid of the expanded target vehicle, the safe driving area corresponding to the target path is generated.

[0061] When the target vehicle is at a certain position and posture, it will occupy a certain range. This range can be represented by rectangular, circular or polygonal grids. The safe driving area of ​​the target path is composed of a series of grids. The safe driving area can be used as the driving trajectory of the target vehicle based on the target path.

[0062] In a specific embodiment, a target vehicle is inflated using a critical safety distance to obtain an inflated target vehicle, specifically: at least one direction among the front, back, left, and right of the target vehicle is used as a direction to be inflated; the critical safety distance is used as an expansion increment in the direction to be inflated, and the target vehicle is inflated along each direction to be inflated to obtain an inflated target vehicle.

[0063] For example, if Figure 3 As shown, Figure 3 It is a schematic diagram of an embodiment of an expanded target vehicle provided by the present application, and the target vehicle is expanded in front, behind, left, right and center.

[0064] Step S22: Determine the target collision risk prediction result based on the safe driving area corresponding to the target path and the driving conditions of the obstacles.

[0065] In this embodiment, the target collision risk prediction result is determined based on the safe driving area corresponding to the target path and the driving conditions of the obstacles.

[0066] In one embodiment, based on the safe driving area corresponding to the target path and the driving conditions of the obstacle, the target collision risk prediction result is determined, specifically: the safe driving area of ​​each obstacle at the target time is obtained, and the target time is the time period when the target vehicle is driving on the target path; based on whether there is overlap between the safe driving area of ​​the target vehicle and each obstacle, the target collision risk prediction result is determined. In other words, it is determined whether the driving trajectory of the target vehicle based on the target path overlaps with the driving trajectory of the obstacle. If there is overlap, it is confirmed that there is a risk of collision between the target vehicle and the obstacle when driving based on the target path.

[0067] See also Figure 4 , Figure 4 It is a structural schematic diagram of an embodiment of a vehicle collision risk prediction device provided by the present application. The vehicle collision risk prediction device 40 includes a determination module 41, a prediction module 42 and a sending module 43; the determination module 41 is used to determine the critical safety distance for the target vehicle to avoid collision under the target path to be sent, wherein the critical safety distance is affected by the environmental factors of the target path; the prediction module 42 is used to predict the collision risk of the target path based on the critical safety distance of the target path, and obtain a target collision risk prediction result; wherein the target collision risk prediction result is used to characterize whether there is a risk of collision with an obstacle when the target vehicle travels along the target path; the sending module 43 is used to determine whether to send the target path to the target vehicle based on the target collision risk prediction result, so that the target vehicle can travel along the target path.

[0068] The critical safety distance is determined by at least one environmental factor, and the at least one environmental factor includes a configuration value affected by the environmental factors of the target path.

[0069] Wherein, the above-mentioned critical safety distance is determined by at least one distance factor and at least one environmental factor, and at least one distance factor includes a motion deviation determined by the vehicle performance of the target vehicle; and / or, the above-mentioned critical safety distance is the sum of at least one distance factor and at least one environmental factor.

[0070] Among them, the vehicle collision risk prediction device 40 also includes an acquisition module 44, which is used to, before determining the critical safety distance for the target vehicle to avoid collision under the target path to be issued, also include: obtaining the critical safety distance configured by the user for the target path in the topological map; and / or, the vehicle collision risk prediction device 40 also includes an update module 45, which is used to update the critical safety distance corresponding to the target path in response to the user's modification operation on the configuration value corresponding to the target path in the topological map.

[0071] Among them, the critical safety distance corresponding to the above-mentioned target path includes the critical safety distance corresponding to at least one node in the target path, the critical safety distance corresponding to the node is affected by the environmental factors of the node in the target path, and the critical safety distance of the target path includes multiple critical safety distances corresponding to different sub-paths of the target path, and the critical safety distance corresponding to each sub-path is determined by at least the critical safety distances of at least some of the nodes in the sub-path.

[0072] The target path includes at least two nodes arranged in sequence along the path direction corresponding to the target path, and two adjacent nodes constitute a sub-path; the determination module 41 is used to determine the critical safety distance for the target vehicle to avoid collision under the target path to be issued, including: taking the first sub-path as the reference path, at least based on the critical safety distance corresponding to the tail node of the reference path, determine the critical safety distance of the target vehicle on the reference path; the prediction module 42 is used to predict the collision risk of the target path based on the critical safety distance of the target path, and obtain a target collision risk prediction result, including: based on the critical safety distance of the target vehicle on the reference path, predict the collision risk of the reference path, and obtain a reference collision risk prediction result; wherein the reference collision risk prediction result is used to characterize whether the target vehicle has a collision risk with an obstacle when traveling along the reference path; the prediction module 42 is used to predict the collision risk of the target path based on the critical safety distance of the target path, and obtain a reference collision risk prediction result; wherein the reference collision risk prediction result is used to characterize whether the target vehicle has a collision risk with an obstacle when traveling along the reference path; the prediction module 42 is used to predict the collision risk of the target path based on the critical safety distance of the target path. At a critical safety distance of the target path, a collision risk prediction is performed on the target path. After obtaining the target collision risk prediction result, the method also includes: in response to a reference collision risk prediction result of the reference path being that the target vehicle does not have a collision risk, taking the next sub-path as the reference path, and re-executing at least the critical safety distance corresponding to the tail node of the reference path, determining the critical safety distance of the target vehicle on the reference path and subsequent steps, until the reference collision risk prediction results corresponding to the last sub-path are all that the target vehicle does not have a collision risk, then determining the target collision risk prediction result is that the target vehicle does not have a risk of colliding with an obstacle when traveling along the target path, or, until it is determined that the reference collision risk prediction result of the sub-path is that there is a collision risk, then determining the target collision risk prediction result is that the target vehicle has a risk of colliding with an obstacle when traveling along the target path.

[0073] Among them, the prediction module 42 is used to predict the collision risk of the target path based on the critical safety distance of the target path, and obtain a target collision risk prediction result, including: based on the critical safety distance of the target path, expanding the driving area of ​​the target vehicle on the target path to obtain a safe driving area corresponding to the target path; based on the safe driving area corresponding to the target path and the driving conditions of obstacles, determining the target collision risk prediction result.

[0074] Among them, the prediction module 42 is used to expand the driving area of ​​the target vehicle on the target path based on the critical safety distance of the target path to obtain the safe driving area corresponding to the target path, including: using the critical safety distance to expand the target vehicle to obtain the expanded target vehicle; obtaining the lock grid of the expanded target vehicle; generating the safe driving area corresponding to the target path based on the lock grid of the expanded target vehicle; and / or, the prediction module 42 is used to determine the target collision risk prediction result based on the safe driving area corresponding to the target path and the driving conditions of the obstacle, including: obtaining the safe driving area of ​​each obstacle at the target time, the target time is the time period when the target vehicle travels on the target path; determining the target collision risk prediction result based on whether there is overlap between the safe driving area of ​​the target vehicle and each obstacle.

[0075] Among them, the prediction module 42 is used to use the critical safety distance to expand the target vehicle to obtain the expanded target vehicle, including: taking at least one direction of the front, back, left, and right of the target vehicle as the direction to be expanded; using the critical safety distance as the expansion increment of the direction to be expanded, expanding the target vehicle along each direction to be expanded, and obtaining the expanded target vehicle.

[0076] Among them, the sending module 43 is used to determine whether to send the target path to the target vehicle based on the target collision risk prediction result, including: in response to the target collision risk prediction result that the target vehicle does not have the risk of colliding with an obstacle when traveling along the target path, a deadlock risk prediction is performed on the target path to obtain a deadlock risk prediction result; wherein the deadlock risk prediction result is used to characterize whether there is a risk of deadlocking the obstacle when the target vehicle travels along the target path; based on the deadlock risk prediction result, determine whether to send the target path to the target vehicle; and / or, the sending module 43 is used to determine not to send the target path to the target vehicle in response to the target collision risk prediction result that the target vehicle has the risk of colliding with an obstacle when traveling along the target path.

[0077] Among them, the sending module 43 is used to determine whether to send the target path to the target vehicle based on the deadlock risk prediction result, including: in response to the deadlock risk prediction result that there is no risk of deadlock caused to the operation of the obstacle, sending the target path to the target vehicle; in response to the deadlock risk prediction result that there is a risk of deadlock caused to the operation of other vehicles, not sending the target path to the target vehicle.

[0078] See also Figure 5 , Figure 5: is a schematic diagram of the structure of an embodiment of an electronic device provided by the present application. The electronic device 50 includes a memory 51 and a processor 52 coupled to each other, and the processor 52 is used to execute program instructions stored in the memory 51 to implement the steps of any of the above-mentioned vehicle collision risk prediction method embodiments. In a specific implementation scenario, the electronic device 50 may include but is not limited to: a microcomputer, a server, and in addition, the electronic device 50 may also include a mobile device such as a laptop computer and a tablet computer, which is not limited here.

[0079] Specifically, the processor 52 is used to control itself and the memory 51 to implement the steps of any of the above-mentioned vehicle collision risk prediction method embodiments. The processor 52 can also be called a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with signal processing capabilities. The processor 52 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 52 can be implemented by an integrated circuit chip.

[0080] See also Figure 6 , Figure 6 It is a structural diagram of an embodiment of a computer-readable storage medium provided by the present application. The computer-readable storage medium 60 of the embodiment of the present application stores a program instruction 61, and when the program instruction 61 is executed, it implements the method provided by any embodiment of the vehicle collision risk prediction method of the present application and any non-conflicting combination. Among them, the program instruction 61 can form a program file and be stored in the above-mentioned computer-readable storage medium 60 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) executes all or part of the steps of the methods of each embodiment of the present application. The aforementioned computer-readable storage medium 60 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, and a tablet.

[0081] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0082] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle collision risk prediction method, It is characterized in that The method comprises: Determine a critical safety distance for the target vehicle to avoid collision under the target path to be issued, wherein the critical safety distance is affected by environmental factors of the target path; Based on the critical safety distance of the target path, a collision risk prediction is performed on the target path to obtain a target collision risk prediction result; wherein the target collision risk prediction result is used to characterize whether there is a risk of collision between the target vehicle and an obstacle when the target vehicle travels along the target path; Based on the target collision risk prediction result, it is determined whether to send the target path to the target vehicle so that the target vehicle can travel according to the target path.

2. The method according to claim 1, It is characterized in that The critical safety distance is determined by at least one environmental factor, and the at least one environmental factor includes a configuration value affected by the environmental factors of the target path.

3. The method according to claim 2, It is characterized in that The critical safety distance is determined by at least one distance factor and the at least one environmental factor, the at least one distance factor including a motion deviation determined by a vehicle performance of the target vehicle; And / or, the critical safety distance is the sum of the at least one distance factor and the at least one environmental factor.

4. The method according to claim 3, It is characterized in that Before determining the critical safety distance for the target vehicle to avoid collision under the target path to be issued, the method further includes: Obtaining a critical safety distance configured by a user for the target path in the topology map; and / or, In response to a user's modification operation on a configuration value corresponding to the target path in the topology map, a critical safety distance corresponding to the target path is updated.

5. The method according to claim 3, It is characterized in that The critical safety distance corresponding to the target path includes the critical safety distance corresponding to at least one node in the target path, the critical safety distance corresponding to the node is affected by the environmental factors of the node in the target path, the critical safety distance of the target path includes multiple critical safety distances corresponding to different sub-paths of the target path, and the critical safety distance corresponding to each sub-path is determined by at least the critical safety distances of at least some of the nodes in the sub-path.

6. The method according to claim 5, It is characterized in that The target path includes at least two nodes arranged in sequence along the path direction corresponding to the target path, and two adjacent nodes constitute the subpath; Determining a critical safety distance for the target vehicle to avoid collision under the target path to be issued includes: Taking the first sub-path as a reference path, determining the critical safety distance of the target vehicle on the reference path based at least on the critical safety distance corresponding to the tail node of the reference path; The step of performing collision risk prediction on the target path based on the critical safety distance of the target path to obtain a target collision risk prediction result includes: Based on the critical safety distance of the target vehicle on the reference path, a collision risk prediction is performed on the reference path to obtain a reference collision risk prediction result; wherein the reference collision risk prediction result is used to characterize whether there is a risk of collision with an obstacle when the target vehicle travels along the reference path; After performing collision risk prediction on the target path based on the critical safety distance of the target path to obtain a target collision risk prediction result, the method further includes: In response to the reference collision risk prediction result of the reference path being that the target vehicle does not have the collision risk, the next sub-path is used as the reference path, and the critical safety distance corresponding to at least the tail node of the reference path is re-executed to determine the critical safety distance of the target vehicle on the reference path and its subsequent steps, until the reference collision risk prediction results corresponding to the last sub-path are all that the target vehicle does not have the collision risk, then it is determined that the target collision risk prediction result is that there is no risk of collision with an obstacle when the target vehicle travels along the target path, or, until it is determined that the reference collision risk prediction result of the sub-path is that there is the collision risk, then it is determined that the target collision risk prediction result is that there is a risk of collision with an obstacle when the target vehicle travels along the target path.

7. The method according to claim 1, It is characterized in that The step of performing collision risk prediction on the target path based on the critical safety distance of the target path to obtain a target collision risk prediction result includes: Based on the critical safety distance of the target path, the driving area of ​​the target vehicle on the target path is expanded to obtain a safe driving area corresponding to the target path; The target collision risk prediction result is determined based on the safe driving area corresponding to the target path and the driving conditions of the obstacles.

8. The method according to claim 7, It is characterized in that The step of expanding the driving area of ​​the target vehicle on the target path based on the critical safety distance of the target path to obtain a safe driving area corresponding to the target path includes: Using the critical safety distance, the target vehicle is expanded to obtain an expanded target vehicle; Acquire the lock grid of the expanded target vehicle; Based on the expanded lock grid of the target vehicle, generating a safe driving area corresponding to the target path; And / or, determining the target collision risk prediction result based on the safe driving area and the driving conditions of the obstacles corresponding to the target path includes: Obtaining a safe driving area for each obstacle at a target time, where the target time is a time period during which the target vehicle travels on the target path; The target collision risk prediction result is determined based on whether there is overlap between the safe driving areas of the target vehicle and each of the obstacles.

9. The method according to claim 8, It is characterized in that The method of expanding the target vehicle by using the critical safety distance to obtain the expanded target vehicle includes: Taking at least one direction of the front, back, left, and right of the target vehicle as a direction to be expanded; The critical safety distance is used as the expansion increment of the direction to be expanded, and the target vehicle is expanded along each direction to be expanded to obtain the expanded target vehicle.

10. The method according to claim 1, It is characterized in that The determining whether to send the target path to the target vehicle based on the target collision risk prediction result includes: In response to the target collision risk prediction result being that there is no risk of collision between the target vehicle and an obstacle when the target vehicle travels along the target path, a deadlock risk prediction is performed on the target path to obtain a deadlock risk prediction result; wherein the deadlock risk prediction result is used to characterize whether there is a risk of deadlocking with an obstacle when the target vehicle travels along the target path; Based on the deadlock risk prediction result, determining whether to send the target path to the target vehicle; And / or, in response to the target collision risk prediction result being that there is a risk of collision between the target vehicle and an obstacle when the target vehicle travels along the target path, determining not to issue the target path to the target vehicle.

11. The method according to claim 10, It is characterized in that The determining whether to send the target path to the target vehicle based on the deadlock risk prediction result includes: In response to the deadlock risk prediction result being that there is no risk of causing deadlock to the obstacle operation, sending the target path to the target vehicle; In response to the deadlock risk prediction result being that there is a risk of causing deadlock to the operation of other vehicles, the target path is not issued to the target vehicle.

12. An electronic device, It is characterized in that The electronic device comprises a memory and a processor, the memory stores program instructions, and the processor is used to execute the program instructions to implement the method according to any one of claims 1-11.

13. A computer-readable storage medium, It is characterized in that The computer-readable storage medium is used to store program instructions, and the program instructions can be executed to implement the method according to any one of claims 1-11.

Images