Collision detection method, device, electronic equipment and vehicle

Abstract

The present application discloses a collision detection method, device, electronic device and vehicle. The method includes: obtaining the to-be-executed path and the vehicle motion information of the current vehicle; determining the detection range corresponding to the to-be-executed path based on the vehicle motion information; identifying the objects around the current vehicle based on the detection range, determining the target to be detected and the target motion information of the target to be detected; predicting the collision detection result between the current vehicle and the target to be detected based on the vehicle motion information and the target motion information. The technical solution of the embodiment of the present application can narrow the detection range, thereby helping the current vehicle to quickly determine other objects that may affect normal driving, thereby solving the problems of large calculation amount, high calculation pressure and slow calculation speed caused by blind detection, and improving the real-time and effectiveness of vehicle detection targets; and can make advance predictions for possible safety hazards of the current vehicle in the future, further ensuring the safety of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of smart vehicle technology, and in particular to a collision detection method, device, electronic equipment and vehicle. Background Art

[0002] With the development of society and the improvement of residents' living standards, public transportation can no longer meet the personalized travel needs of individuals or families. With the development of transportation and the continuous iteration of automobile technology, more and more users choose to buy private cars for transportation.

[0003] With the development of smart vehicles today, how to use smart functions to assist users in driving and ensure the safety of vehicles has become one of the research focuses of technical personnel in related fields. Summary of the invention

[0004] The present application provides a collision detection method, device, electronic device and vehicle to improve the safety of the vehicle.

[0005] According to one aspect of the present application, a collision detection method is provided, the method comprising:

[0006] Get the current vehicle's pending path and vehicle motion information;

[0007] According to the vehicle motion information, determine the detection range corresponding to the path to be executed;

[0008] Identify objects around the current vehicle based on the detection range, and determine the target to be detected and the target motion information of the target to be detected;

[0009] According to the vehicle motion information and the target motion information, the collision detection result between the current vehicle and the target to be detected is predicted.

[0010] According to another aspect of the present application, a collision detection device is provided, the device comprising:

[0011] The vehicle path acquisition module is used to obtain the current vehicle's to-be-executed path and vehicle motion information;

[0012] A detection range determination module is used to determine the detection range corresponding to the path to be executed according to the vehicle motion information;

[0013] A target determination module is used to identify objects around the current vehicle based on the detection range, determine the target to be detected and the target motion information of the target to be detected;

[0014] The target collision detection module is used to predict the collision detection result between the current vehicle and the target to be detected based on the vehicle motion information and the target motion information.

[0015] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the collision detection method described in any embodiment of the present application.

[0019] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the collision detection method described in any embodiment of the present application when executed.

[0020] According to another aspect of the present application, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the collision detection method according to any embodiment of the present application is implemented.

[0021] The technical solution of the embodiment of the present application determines the detection range corresponding to the path to be detected of the current vehicle according to the self-vehicle motion information, and identifies the objects around the current vehicle based on the detection range to determine the target to be detected, which can narrow the detection range, thereby helping the current vehicle to quickly determine other objects that may affect normal driving, thereby solving the problems of large amount of calculation, high computing pressure and slow computing speed caused by blind detection, and improving the real-time and effectiveness of vehicle detection targets; obtaining the target motion information of the target to be detected, combining the self-vehicle motion information of the current vehicle, and performing collision detection, can make early predictions on possible safety hazards of the current vehicle in the future, further ensuring the safety of the vehicle.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1Ais a flow chart of a collision detection method provided according to Embodiment 1 of the present application;

[0025] Figure 1B is a schematic diagram showing that the current vehicle may collide with a stationary vehicle on the trajectory to be executed according to the second embodiment of the present application;

[0026] Figure 1C is a schematic diagram showing that the current vehicle may collide with a stationary obstacle on the trajectory to be executed according to the second embodiment of the present application;

[0027] Figure 1D is a schematic diagram showing a possible collision between the current vehicle and the moving vehicle on the trajectory to be executed according to the second embodiment of the present application;

[0028] Figure 1E is a schematic diagram of a vehicle bounding box provided according to Embodiment 1 of the present application;

[0029] Figure 2 is a structural schematic diagram of a collision detection device provided according to Embodiment 3 of the present application;

[0030] Figure 3 It is a structural schematic diagram of an electronic device that implements the collision detection method of an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1A A flowchart of a collision detection method is provided for the first embodiment of the present application. This embodiment is applicable to collision detection under automatic driving / intelligent assisted following driving. The method can be performed by a collision detection device, which can be implemented in the form of hardware and / or software. The collision detection device can be configured in an electronic device, which can be set in a vehicle. Figure 1A As shown, the method includes:

[0035] S110, obtaining the current vehicle's to-be-executed path and vehicle motion information.

[0036] Among them, the current vehicle can be any vehicle that the user is driving, and the vehicle can have an automatic driving function or an intelligent assisted following function, etc. The path to be executed can be the forward path obtained by the current vehicle after completing the path planning, and it is a path that has not been executed but is urgently needed to be executed. The vehicle motion information can be the driving data of the current vehicle on the road, for example, it can include but is not limited to the speed, acceleration, power torque, yaw angle, etc. of the current vehicle. It can be understood that the path to be executed can be directly obtained because it has been planned in advance. Of course, the path to be executed can be the route planned by the current vehicle directly through a pre-set path planning algorithm. The path planning algorithm can be set in the car computer and generated autonomously by the current vehicle, or it can be set in the server and sent to the car computer for execution by the server.

[0037] In an optional implementation, the step of obtaining the to-be-executed path of the current vehicle in S110 may include:

[0038] S111. Acquire a driving track of a vehicle being followed in front of the current vehicle when the current vehicle is performing a following operation.

[0039] The following vehicle operation may be an operation of controlling the current vehicle to follow the vehicle being followed in front, or may be an operation of following the vehicle being followed in front through the intelligent driving or following vehicle assistance function of the current vehicle itself. Therefore, the driving track of the front vehicle may be recorded.

[0040] S112: Using the driving trajectory as a path to be executed by the current vehicle.

[0041] The driving trajectory of the preceding vehicle recorded in the aforementioned step can be used as the path to be executed that the current vehicle needs to refer to.

[0042] In the above implementation, the driving trajectory of the vehicle being followed in front is used as the path to be executed by the current vehicle, which can provide a reliable vehicle following solution for the user and provide a reference basis for the path trajectory for subsequent collision detection.

[0043] Continuing from the above S110:

[0044] S120: Determine a detection range corresponding to the path to be executed according to the vehicle movement information.

[0045] Among them, the detection range can be the detection range of the current vehicle to obtain objects with collision risks outward, for example, it can be a certain range area around the current vehicle, etc., and the implementation examples of this application are not limited here.

[0046] Since the vehicle motion information includes various driving data mainly based on vehicle speed, it is more reasonable to use the vehicle motion information to determine the detection range. It is understandable that the weight of the vehicle determines the inertia of the vehicle, and the speed affects the braking distance of the vehicle. Therefore, the detection range can be set by relevant technicians based on the current vehicle's own motion information, and can also be adjusted at any time by the current vehicle based on information such as vehicle speed.

[0047] In an optional implementation, determining the detection range corresponding to the to-be-executed path according to the vehicle motion information in S120 may include:

[0048] S121. Determine a target reaction distance corresponding to the ego-vehicle motion information according to a preset correspondence relationship between the ego-vehicle motion information and the reaction distance.

[0049] The reaction distance can be the driving distance that the user or vehicle needs to avoid in case of foreseeable danger. For example, if an object that affects normal driving suddenly appears in front of the vehicle (i.e., there is a possibility of collision), the braking distance at this time can be understood as the reaction distance. The vehicle motion information and the reaction distance have a corresponding relationship. For example, the faster the vehicle speed, the longer the reaction distance required. This corresponding relationship can be pre-tested and stored in the library table.

[0050] When the current vehicle's ego motion information is known, the corresponding reaction distance is searched from the stored library table as the target reaction distance.

[0051] S122. Determine a longitudinal path range of the current vehicle in the path to be executed according to the target reaction distance.

[0052] The longitudinal path range may be a distance range in the driving direction within the current vehicle detection range. Specifically, starting from the current vehicle, along the path to be executed, the length of the target reaction distance is extended forward, and the longitudinal path range of the current vehicle is obtained.

[0053] S123, taking the path to be executed as the center, expanding the preset width value toward the left and right sides of the vehicle body to obtain the lateral path range of the current vehicle.

[0054] Among them, the lateral path range can be the distance range in the width direction of the vehicle in the current vehicle detection range. It is understandable that vehicles actually have a certain size and collisions may occur in the width direction, so the width range must be considered. The preset width value can be set by technicians in related fields according to actual conditions. For example, the width of half a lane is used as the width value of the lateral path range, and the path to be executed is used as the center line. The width of half a lane is expanded in the left and right directions of the vehicle body as the lateral path range of the current vehicle, so as to facilitate lateral collision detection. Of course, the preset width value can also be directly set to 2m.

[0055] S124. Determine a detection range according to the longitudinal path range and the transverse path range.

[0056] The longitudinal path range and the lateral path range are combined to determine the detection range of the current vehicle. Only objects within the detection range are identified.

[0057] In the above implementation, the longitudinal path range and the lateral path range for the current vehicle to identify objects are determined respectively, and the two together define the detection range of the current vehicle. Only objects within the detection range are identified (external perception methods such as cameras, radars, lasers or infrared sensors), which can effectively solve the problem of excessive calculation caused by indiscriminate identification of objects near the vehicle, help the vehicle save computing power, improve object recognition efficiency, and thus help improve the accuracy and efficiency of collision detection.

[0058] Of course, it should be noted that no matter whether the identified object is a vehicle or not, or whether the object is in motion or stationary, it needs to comply with the above detection range. It is understandable that stationary obstacles need to comply with both the longitudinal path range and the lateral path range when they are identified, and stationary obstacles outside the detection range can be regarded as having no effect on the current vehicle's travel and are not processed. For vehicles on the road, whether they are traveling or stationary, they need to comply with the above longitudinal path range and lateral path range. Vehicles outside the detection range can be processed, but when vehicles outside the detection range enter the detection range, they need to be considered. In addition, in a special case, vehicles appearing behind the current vehicle can also be detected, and the detection range at this time also includes both lateral and longitudinal aspects, wherein the lateral detection range can be the same as the aforementioned lateral path range, and the longitudinal detection range can be set according to the current vehicle's driving state, vehicle type and road conditions, for example, it can be within 10m in the rear direction of the vehicle, and the embodiment of the present application does not limit this.

[0059] Continuing from the above S120:

[0060] S130: Identify objects around the current vehicle based on the detection range, and determine a target to be detected and target motion information of the target to be detected.

[0061] The target to be detected may be other objects that may affect the driving of the current vehicle (especially collision), such as motor vehicles, non-motor vehicles, stationary obstacles, people and other animals, etc., which are not limited in the present embodiment of the application. Figure 1B , Figure 1C and Figure 1D As shown, the current vehicle may collide with a stationary vehicle, a stationary obstacle, and a moving vehicle while traveling along the path to be executed.

[0062] Specifically, objects around the current vehicle are identified according to the detection range determined in the aforementioned steps, and all objects within the detection range are taken as targets to be detected, and the so-called targets to be detected may be objects that need to be subjected to collision detection. At the same time, the driving data of these targets to be detected are obtained through the outward perception system of the current vehicle (such as camera, infrared and other sensor systems) as target motion information, which may include, for example, the size, dimension, speed, acceleration, yaw angle, yaw angle, etc. of the targets to be detected, and the embodiments of the present application do not limit this.

[0063] S140: predicting a collision detection result between the current vehicle and the target to be detected based on the vehicle motion information and the target motion information.

[0064] After obtaining the current vehicle's ego motion information and the target motion information of the target to be detected in the above steps, a prediction of possible collisions in the future is made. For example, the position of the current vehicle at a certain moment can be determined based on the ego motion information combined with the path to be executed; similarly, the position of the target to be detected at a certain moment can be predicted based on the target motion information of the target to be detected, and it can be determined whether a collision will occur at that future moment.

[0065] The technical solution of the embodiment of the present application determines the detection range in the path to be detected of the current vehicle according to the self-vehicle motion information, and identifies the objects around the current vehicle based on the detection range to determine the target to be detected, which can narrow the detection range, thereby helping the current vehicle to quickly determine other objects that may affect normal driving, thereby solving the problems of large amount of calculation, high computing pressure and slow computing speed caused by blind detection, and improving the real-time and effectiveness of vehicle detection targets; obtaining the target motion information of the target to be detected, combining the self-vehicle motion information of the current vehicle, and performing collision detection, can make early predictions on possible safety hazards of the current vehicle in the future, further ensuring the safety of the vehicle.

[0066] In an optional implementation, predicting the collision detection result between the current vehicle and the target to be detected according to the vehicle motion information and the target motion information in S140 may include:

[0067] S141. Determine at least one future position point according to the vehicle motion information at a preset time interval, and use the future position point as a detection point of the current vehicle in the path to be executed.

[0068] Among them, the preset time interval can be set by relevant technical personnel according to actual conditions or manual experience, and the preset time interval is used to calculate the future position point of the current vehicle on the path to be executed. It can be understood that the path to be executed is the path that the current vehicle will travel in the future. According to the vehicle speed and the preset time interval, the position point of the current vehicle in the path to be executed at a certain moment in the future, that is, the future position point, can be determined. Multiple identical time intervals can determine multiple continuous future position points in the path to be executed. These future position points are used as detection points of the current vehicle in the path to be executed. In other words, before the current vehicle reaches these future position points, the collisions that may occur at these future position points are predicted.

[0069] S142. Determine the trajectory points of the target to be detected corresponding to each detection point according to the target motion information and at preset time intervals.

[0070] Since the target to be detected may be a stationary unit or a moving unit, the target motion information of the target to be detected can be used to know the driving direction, speed and other data of the target to be detected, and the future motion trend of the target to be detected can be predicted based on these data. It can be understood that under the calculation of the same preset time interval, the possible future position of the target to be detected can also be determined as a trajectory point, and at the same time interval, each detection point of the current vehicle has a corresponding trajectory point of the target to be detected.

[0071] S143. Predict collision detection results based on detection points and trajectory points.

[0072] At the same time in the future, based on the detection point of the current vehicle and the trajectory point of the target to be detected determined in the above steps, collision detection can be performed between the two. Any collision detection method in the relevant technology can be used for prediction of collision detection, and the embodiment of the present application is not limited here.

[0073] In the above implementation, the positions that the current vehicle and the target to be detected may reach in the future are determined according to a preset time interval, and collision detection is performed. This can predict the collision of the current vehicle and determine in advance the collision that may occur at a certain moment in the future, thereby helping the current vehicle to warn the user in time to avoid traffic accidents, which helps to improve the safety of the vehicle.

[0074] Of course, it should be noted that during the prediction process of collision detection, it is not necessary to turn on the collision detection logic when the speed is too low. For example, when the vehicle speed is less than 1M / s, the driver basically takes full control of the vehicle. During the calculation process of collision detection, in order to prevent the jump of the distance data of the identified object, some filtering or de-bouncing algorithms can be used to reduce the recognition error rate, which helps to improve the detection efficiency and accuracy. After the collision detection, if it is predicted that the current vehicle may collide with other objects, the vehicle computer needs to enable the collision flag and remind the driver to take full control of the vehicle.

[0075] In a further optional implementation, if the target to be detected is a vehicle to be detected, then predicting the collision detection result according to the detection point and the trajectory point in S143 may include:

[0076] P1. For any detection point, take the detection point as the center of mass and construct the vehicle bounding box of the current vehicle.

[0077] Among them, the bounding box is a method of performing geometric operations by replacing complex geometric bodies with simple geometric bodies that are slightly larger. The center of mass of the current vehicle's self-vehicle bounding box can be the detection point described in the aforementioned embodiment, that is, the future position point of the current vehicle in the path to be executed. The method for constructing the self-vehicle bounding box can adopt any bounding box algorithm in the relevant technology, such as a directed bounding box, an axisymmetric bounding box, a fixed-direction convex bounding box, or even a bounding sphere (or bounding circle), etc., which is not limited in the embodiments of the present application. However, in view of the fact that the present scheme involves vehicle collision detection, a directed bounding box is preferably used, which can fit the geometric shape of the vehicle as closely as possible for collision detection and improve detection efficiency.

[0078] P2. Take the trajectory point corresponding to the detection point as the centroid and construct the target bounding box of the vehicle to be detected.

[0079] In the aforementioned embodiments and implementation methods, the one-to-one correspondence between the trajectory points of the target to be detected and the detection points of the current vehicle is introduced. Due to the use of a bounding box detection method, in addition to the current vehicle needing to construct a self-vehicle bounding box, the vehicle to be detected also needs to construct a corresponding bounding box, that is, the target bounding box. It should be noted that regardless of whether the vehicle to be detected is in motion (whether it is a moving vehicle or a stationary vehicle), the bounding box method can be used for detection. Similar to the self-vehicle bounding box of the current vehicle, the target bounding box of the vehicle to be detected can also be constructed using the same bounding box algorithm, such as a directed bounding box, an axisymmetric bounding box, a fixed direction convex bounding box, or even a bounding sphere (or bounding circle) and other methods, which are not limited in the embodiments of the present application. However, in view of the fact that this scheme involves vehicle collision detection, a directed bounding box is preferably used, which can fit the geometric shape of the vehicle as closely as possible for collision detection and improve detection efficiency.

[0080] P3. Predict the collision detection results based on the vehicle bounding box and the target bounding box.

[0081] The self-vehicle bounding box and the target bounding box constructed in the above steps are used to predict whether the two vehicles may collide at a future time node. The collision detection based on the bounding box can be processed using any bounding box collision detection algorithm in the relevant technology, and the embodiment of the present application is not limited here. For example, the separation axis method can be used to set auxiliary lines in each direction of the self-vehicle bounding box and the target bounding box, and project the two bounding boxes onto the auxiliary lines. If the projections of the two bounding boxes from any direction have no intersection, it means that the two bounding boxes have not collided.

[0082] It should be added that due to the difference in vehicle speed, the vehicle may have traveled a long distance after the preset time interval. Therefore, multiple different position points can be selected within a certain distance in front and behind the vehicle's detection point in the driving direction as the position point basis for collision detection. Corresponding bounding boxes can be generated at these extended position points for bounding box testing. The basis for selecting these extended points can be matching according to the vehicle speed or the length of the path to be executed, or the number of these extended points and the distance between them and the detection point can be manually set.

[0083] In a further optional implementation, the vehicle bounding box and the target bounding box are both rectangular oriented bounding boxes, and predicting the collision detection result according to the vehicle bounding box and the target bounding box in A3 may include:

[0084] Q1. For any vertex of the ego vehicle bounding box, determine the line vector connecting the vertex with all vertices of the target bounding box, and each line vector has an edge vector corresponding to it on the target bounding box;

[0085] Q2. Perform cross product calculations on each line vector and the corresponding edge vector to obtain two long edge cross products and two short edge cross products;

[0086] Q3. If the product of the two long side cross products and the product of the two short side cross products are not less than zero, it is determined that the vertex of the vehicle bounding box is located in the target bounding box;

[0087] Q4. In response to any vertex of the ego-vehicle bounding box being located in the target bounding box, it is determined that the current vehicle collides with the vehicle to be detected.

[0088] Among them, in order to determine whether there is a collision between the self-vehicle bounding box of the current vehicle and the target bounding box of the vehicle to be detected, it is possible to detect whether the self-vehicle bounding box and the target bounding box have an intersection. Since the present application mainly involves the detection of vehicle collisions, a rectangular directed bounding box can be used to wrap the vehicle from a bird's-eye view. Then the problem can be simplified to determining whether the two rectangles corresponding to the two bounding boxes have an intersection. Among them, it is possible to determine whether all the vertices in the self-vehicle bounding box exist in the target bounding box for collision.

[0089] Then, for any vertex of the rectangle of the ego vehicle bounding box, first, connect the vertex with the four vertices of the target bounding box rectangle to generate four connecting vectors, the direction of which points from the vertex of the ego vehicle bounding box to the vertex of the target bounding box. In addition, an edge in the target bounding box that intersects with the connecting vector is used as the edge vector associated with the connecting vector, and the direction of the vector points to the vertex of the target bounding box connected to the vertex of the ego vehicle bounding box.

[0090] Then, a cross product is calculated between the line vector and its corresponding edge vector. Since the embodiment of the present application involves a rectangular bounding box, the cross product of the two long sides of the target bounding box and the line vector, that is, the cross product of the two long sides, can be calculated; the cross product of the two short sides of the target bounding box and the line vector, that is, the cross product of the two short sides, can also be calculated.

[0091] Next, calculate the product of the long side cross product and the long side cross product, and the product of the short side cross product and the short side cross product. If the product of the two long side cross products and the product of the two short side cross products are not less than zero, that is, the two long side cross products have the same sign and the two short side cross products have the same sign, then it means that the vertex of the ego vehicle bounding box is inside the target bounding box (the edge is also inside the bounding box). It can be imagined that if any vertex of the ego vehicle bounding box is inside the target bounding box, it means that the ego vehicle bounding box and the target bounding box have an intersection, that is to say, if the current vehicle and the vehicle to be detected are driving according to the current movement tendency, a collision will occur at a corresponding position at a certain time in the future. On the contrary, if one of the products of the two long side cross products and the two short side cross products has a product result less than zero, then the vertex of the ego vehicle bounding box is not inside the target bounding box. If all vertices of the ego vehicle bounding box are not inside the target bounding box, it means that there is no collision between the two.

[0092] like Figure 1B As shown in the figure, any vertex M of the current vehicle's bounding box is connected to the four vertices A, B, C and D of the target bounding box of the vehicle to be detected, and four connection vectors are generated. Each connection vector has an edge vector corresponding to it on the target bounding box, and a cross product calculation is performed. The calculation method is as follows:

[0093] JA=(BX-AX)×(MY-AY)-(MX-AX)×(BY-AY)

[0094] JC=(DX-CX)×(MY-CY)-(MX-CX)×(DY-CY)

[0095] JB=(CX-BX)×(MY-BY)-(MX-BX)×(CY-BY)

[0096] JD=(AX-DX)×(MY-DY)-(MX-DX)×(AY-DY)

[0097] Among them, X is the horizontal coordinate data, and Y is the vertical coordinate data. JA is the cross product result between the line vector of M and A and the edge vector of BA; JC is the cross product result between the line vector of M and C and the edge vector of DC; JB is the cross product result between the line vector of M and B and the edge vector of CB; JD is the cross product result between the line vector of M and D and the edge vector of AD. Of course, M refers to any vertex of the ego vehicle bounding box. When calculating collision detection, all vertices of the ego vehicle bounding box need to be calculated as above.

[0098] When the two product results of JA×JC and JB×JD are not less than zero (that is, greater than or equal to 0), it can be determined that the vertex M is within the target bounding box, and then it is predicted that at this moment, the current vehicle and the vehicle to be detected will collide; conversely, if at least one of the above two product results is less than zero, it is determined that M is not within the target bounding box.

[0099] In the above implementation, by verifying whether any vertex of the vehicle's bounding box is within the target bounding box, it is predicted whether the current vehicle is likely to collide with the vehicle to be detected, thereby providing a feasible calculation method for collision prediction of moving vehicles and ensuring the safety of vehicle driving.

[0100] In another optional implementation, the target to be detected includes a stationary obstacle, and the method may further include:

[0101] R1, determine the shortest distance between the current vehicle and the obstacle mass center of the stationary obstacle;

[0102] R2. If the shortest distance is less than the preset distance threshold, it is determined that the current vehicle collides with a stationary obstacle.

[0103] It is understandable that the current vehicle can not only identify motor vehicles, non-motor vehicles and pedestrians when driving on the road, but also identify stationary objects on the road, such as roadblocks, cones, road signs, guardrails, etc. These obstacles may also affect the vehicle. Therefore, through the inherent extroverted perception system of the current vehicle, these stationary obstacles can be identified, and the shape of these obstacles and the relative position between them and the current vehicle can be determined. Through coordinate calculation, the shortest distance between the obstacle centroid and the current vehicle is obtained. For example, the current vehicle is also regarded as a mass point, and the line segment between the two points is the shortest. Based on the comparison between the shortest distance between the mass point of the vehicle and the obstacle centroid and the preset distance threshold, it is determined whether the current vehicle and the stationary obstacle collide. Of course, the method in the aforementioned embodiments can also be continued to determine the various detection points of the current vehicle on the path to be executed, and determine the distance between the stationary obstacle and the detection point that the current vehicle may reach in the future. Since the current vehicle is driving along the path to be executed, it is only necessary to determine whether a collision occurs when the path is closest to the obstacle centroid, and the collision risk of the stationary obstacle can be eliminated.

[0104] Then, based on the distances between all detection points and obstacles obtained by coordinate calculation, for example, the coordinates of the obstacle can be converted from a Cartesian coordinate system to a frenet coordinate system, thereby calculating the shortest distance between the vehicle and the obstacle in the L-axis direction in the frenet coordinate system. If the shortest distance is within a preset distance threshold, it means that the current vehicle collides with a stationary obstacle when it reaches the detection point. On the contrary, if the shortest distance is greater than the preset distance threshold, it means that the current vehicle will not collide with the stationary obstacle. Of course, the preset distance threshold can be set by technicians in the relevant field according to actual conditions or manual experience, for example, it can be adaptively adjusted according to the current vehicle width, and the embodiments of the present application are not limited thereto.

[0105] In the above implementation, by identifying the stationary obstacles that may be encountered in the path to be executed, the shortest distance between the current vehicle and the stationary obstacles while traveling along the path to be executed is calculated, and a collision is determined based on the shortest distance. This provides a practical detection method for collision detection between the vehicle and stationary objects while driving, and does not require excessive computing resources. It can achieve rapid collision prediction, improve prediction efficiency, and ensure vehicle driving safety.

[0106] Embodiment 2

[0107] Figure 2 This is a schematic diagram of the structure of a collision detection device provided in Example 3 of the present application. Figure 2 As shown, the device 200 may include:

[0108] The vehicle path acquisition module 210 is used to obtain the current vehicle's to-be-executed path and vehicle motion information;

[0109] A detection range determination module 220, for determining a detection range corresponding to a path to be executed according to the vehicle motion information;

[0110] The target determination module 230 is used to identify objects around the current vehicle based on the detection range, determine the target to be detected and the target motion information of the target to be detected;

[0111] The target collision detection module 240 is used to predict the collision detection result between the current vehicle and the target to be detected based on the vehicle motion information and the target motion information.

[0112] The technical solution of the embodiment of the present application determines the detection range in the path to be detected of the current vehicle according to the self-vehicle motion information, and identifies the objects around the current vehicle based on the detection range to determine the target to be detected, which can narrow the detection range, thereby helping the current vehicle to quickly determine other objects that may affect normal driving, thereby solving the problems of large amount of calculation, high computing pressure and slow computing speed caused by blind detection, and improving the real-time and effectiveness of vehicle detection targets; obtaining the target motion information of the target to be detected, combining the self-vehicle motion information of the current vehicle, and performing collision detection, can make early predictions on possible safety hazards of the current vehicle in the future, further ensuring the safety of the vehicle.

[0113] In an optional implementation, the target collision detection module 240 may include:

[0114] A detection point determination unit, used to determine at least one future position point according to the vehicle motion information at a preset time interval, and use the future position point as a detection point of the current vehicle in the path to be executed;

[0115] A trajectory point determination unit, used to determine the trajectory points of the target to be detected corresponding to each detection point according to the target motion information and at a preset time interval;

[0116] The collision detection unit is used to predict the collision detection result based on the detection points and trajectory points.

[0117] In an optional implementation, if the target to be detected is a vehicle to be detected, the collision detection unit may include:

[0118] The ego vehicle bounding box determination subunit is used to construct the ego vehicle bounding box of the current vehicle for any detection point with the detection point as the center of mass;

[0119] A target bounding box determination subunit is used to construct a target bounding box of the vehicle to be detected with the trajectory point corresponding to the detection point as the centroid;

[0120] The detection subunit is used to predict the collision detection result based on the ego vehicle bounding box and the target bounding box.

[0121] In an optional implementation, the vehicle bounding box and the target bounding box are both rectangular oriented bounding boxes, and the detection subunit may include:

[0122] The line vector determination slave unit is used to determine the line vectors connecting any vertex of the ego vehicle bounding box with all vertices of the target bounding box, and each line vector has an edge vector corresponding to it on the target bounding box;

[0123] The edge cross product determination slave unit is used to perform cross product calculations on each line vector and the corresponding edge vector to obtain two long edge cross products and two short edge cross products;

[0124] A vertex judgment slave unit is used to determine that the vertex of the ego vehicle bounding box is located in the target bounding box if the product of the two long edge cross products and the product of the two short edge cross products are not less than zero;

[0125] The collision judgment slave unit is used to determine that the current vehicle collides with the vehicle to be detected in response to any vertex of the vehicle bounding box being located in the target bounding box.

[0126] In another optional implementation, the target to be detected includes a stationary obstacle, and the device 200 may further include:

[0127] an obstacle distance determination unit, for determining the shortest distance between the current vehicle and the obstacle mass centroid of the stationary obstacle;

[0128] The obstacle collision determination unit is used to determine that the current vehicle collides with a stationary obstacle if the shortest distance is less than a preset distance threshold.

[0129] In an optional implementation, the detection range determination module 220 may include:

[0130] A reaction distance determination unit, used to determine a target reaction distance corresponding to the ego vehicle motion information according to a preset correspondence relationship between the ego vehicle motion information and the reaction distance;

[0131] a longitudinal range determination unit, for determining a longitudinal path range of the current vehicle in the path to be executed according to the target reaction distance;

[0132] A lateral range determination unit is used to expand a preset width value toward the left and right sides of the vehicle body with the path to be executed as the center to obtain the lateral path range of the current vehicle;

[0133] The detection range determination unit is used to determine the detection range according to the longitudinal path range and the transverse path range.

[0134] In an optional implementation, the vehicle path acquisition module 210 may include:

[0135] A following vehicle trajectory determination unit, used to obtain the driving trajectory of the vehicle being followed in front of the current vehicle when performing a following vehicle operation;

[0136] The to-be-executed path determination unit is used to use the driving trajectory as the to-be-executed path of the current vehicle.

[0137] The collision detection device provided in the embodiments of the present application can execute the collision detection method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing each collision detection method.

[0138] Embodiment 3

[0139] Figure 3 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0140] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0141] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0142] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a collision detection method.

[0143] An embodiment of the present application also provides a vehicle, which may be provided with the above-mentioned electronic device for executing a collision detection method described in the aforementioned embodiments and implementation methods of the present application.

[0144] In some embodiments, the collision detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the collision detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the collision detection method in any other appropriate manner (e.g., by means of firmware).

[0145] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0147] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0148] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0149] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0150] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0151] The present application also discloses a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the collision detection method provided in any embodiment of the present application. The program product and the collision detection method disclosed in each embodiment of the present application belong to the same inventive concept, so it will not be described here.

[0152] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0153] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A collision detection method, characterized in that: The method comprises: Get the current vehicle's pending path and vehicle motion information; Determining a detection range corresponding to the path to be executed according to the vehicle motion information; Identify objects around the current vehicle based on the detection range, and determine a target to be detected and target motion information of the target to be detected; The collision detection result between the current vehicle and the target to be detected is predicted according to the vehicle motion information and the target motion information.

2. The method according to claim 1, characterized in that The predicting, based on the vehicle motion information and the target motion information, a collision detection result between the current vehicle and the target to be detected includes: Determine at least one future position point according to the vehicle motion information at a preset time interval, and use the future position point as a detection point of the current vehicle in the path to be executed; Determining, according to the target motion information, the trajectory points of the target to be detected corresponding to each of the detection points at the preset time intervals; The collision detection result is predicted according to the detection point and the trajectory point.

3. The method according to claim 2, characterized in that If the target to be detected is a vehicle to be detected, predicting the collision detection result according to the detection point and the trajectory point includes: For any detection point, taking the detection point as the centroid, construct the vehicle bounding box of the current vehicle; Taking the trajectory point corresponding to the detection point as the centroid, constructing a target bounding box of the vehicle to be detected; The collision detection result is predicted according to the ego-vehicle bounding box and the target bounding box.

4. The method according to claim 3, characterized in that: The vehicle bounding box and the target bounding box are both rectangular oriented bounding boxes, and predicting the collision detection result according to the vehicle bounding box and the target bounding box includes: For any vertex of the vehicle bounding box, determine the line vector connecting the vertex with all vertices of the target bounding box, and each of the line vectors has an edge vector corresponding to it on the target bounding box; Perform cross product calculations on each line vector and the corresponding edge vector to obtain two long edge cross products and two short edge cross products; If the product of the two long side cross products and the product of the two short side cross products are not less than zero, it is determined that the vertex of the ego vehicle bounding box is located in the target bounding box; In response to any vertex of the ego-vehicle bounding box being located in the target bounding box, it is determined that the current vehicle collides with the vehicle to be detected.

5. The method according to claim 1, characterized in that The target to be detected includes a stationary obstacle, and the method further includes: Determining the shortest distance between the current vehicle and the obstacle mass centroid of the stationary obstacle; If the shortest distance is less than a preset distance threshold, it is determined that the current vehicle collides with the stationary obstacle.

6. The method according to any one of claims 1 to 5, characterized in that: The step of determining the detection range corresponding to the to-be-executed path according to the vehicle motion information includes: Determining a target reaction distance corresponding to the ego-vehicle motion information according to a preset correspondence relationship between the ego-vehicle motion information and the reaction distance; determining a longitudinal path range of the current vehicle in the to-be-executed path according to the target reaction distance; Taking the path to be executed as the center, expanding the preset width value toward the left and right sides of the vehicle body to obtain the lateral path range of the current vehicle; The detection range is determined according to the longitudinal path range and the transverse path range.

7. The method according to any one of claims 1 to 5, characterized in that: The step of obtaining the path to be executed of the current vehicle includes: Acquire the driving track of the vehicle being followed in front of the current vehicle when the vehicle is performing the following operation; The driving trajectory is used as a path to be executed by the current vehicle.

8. A collision detection device, characterized in that: The device comprises: The vehicle path acquisition module is used to obtain the current vehicle's to-be-executed path and vehicle motion information; A detection range determination module, used to determine the detection range corresponding to the to-be-executed path according to the vehicle motion information; A target determination module, used to identify objects around the current vehicle based on the detection range, determine the target to be detected and target motion information of the target to be detected; The target collision detection module is used to predict the collision detection result between the current vehicle and the target to be detected based on the vehicle motion information and the target motion information.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the collision detection method according to any one of claims 1 to 7.

10. A vehicle, characterized in that: The vehicle is provided with an electronic device as claimed in claim 9.

Images