Vehicle collision prediction method, device and equipment

Abstract

The present application discloses a vehicle collision prediction method, device and equipment, the method comprising: obtaining first driving data of a first target vehicle and a driving planning path and second driving data of a second target vehicle around the first target vehicle, the second target vehicle traveling based on the driving planning path; determining a collision risk position range corresponding to the first target vehicle based on the first driving data and the second driving data; determining collision risk information between the first target vehicle and the second target vehicle based on the driving planning path and the collision risk position range; the present application obtains the driving planning path of the second target vehicle, determines the collision risk position range of the first target vehicle based on the driving data of the first target vehicle and the second target vehicle, and performs collision prediction based on the driving planning path and the collision risk position range; the accuracy and efficiency of collision prediction can be effectively improved.

Description

Technical Field

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

[0002] V2X, which stands for vehicle to everything, refers to the information exchange between vehicles and the outside world. The Internet of Vehicles has laid a new direction for the development of automotive technology by integrating global positioning system (GPS) navigation technology, vehicle-to-vehicle communication technology, wireless communication and remote sensing technology, and can achieve information coordination between manual and autonomous vehicles.

[0003] At present, based on V2X technology, an all-weather, beyond-visual-range vehicle collision risk estimation function can be realized; each vehicle can broadcast its own GPS location, vehicle status and other information to surrounding vehicles through the V2X wireless communication system. The main vehicle analyzes the V2X information of surrounding vehicles, obtains the historical GPS location and vehicle status information of surrounding vehicles, and then predicts the driving trajectory of surrounding vehicles, and analyzes the predicted driving trajectory of surrounding vehicles with the driving trajectory of the vehicle, and estimates the collision risk and other strategies. This method has low accuracy of trajectory prediction algorithm, which is easy to cause false triggering of the scene; and it is easily affected by GPS signal errors and inaccurate prediction algorithms, and the false alarm and missed alarm rates are high. Summary of the invention

[0004] In order to solve the above technical problems, the present application discloses a vehicle collision prediction method, which obtains the planned driving path of the second target vehicle, determines the collision risk position range of the first target vehicle based on the driving data of the first target vehicle and the second target vehicle, and performs collision prediction based on the planned driving path and the collision risk position range; the accuracy and efficiency of collision prediction can be effectively improved.

[0005] In order to achieve the above-mentioned invention object, the present application provides a vehicle collision prediction method, wherein the method comprises:

[0006] Acquire first driving data of a first target vehicle and a planned driving path and second driving data of a second target vehicle around the first target vehicle, wherein the second target vehicle travels based on the planned driving path;

[0007] Determining a collision risk position range corresponding to the first target vehicle based on the first driving data and the second driving data;

[0008] According to the planned driving path and the collision risk position range, collision risk information between the first target vehicle and the second target vehicle is determined.

[0009] In some implementations, determining the collision risk position range corresponding to the first target vehicle based on the first driving data and the second driving data includes:

[0010] Determine a first driving speed, an acceleration, a first driving direction, and a first position information of the first target vehicle based on the first driving data;

[0011] Determine a second driving speed, a second driving direction, and a second position information of the second target vehicle based on the second driving data;

[0012] Determine a driving relationship between the first target vehicle and the second target vehicle based on the first driving direction, the second driving direction, the first position information, and the second position information;

[0013] When the driving relationship satisfies a preset driving condition, the collision risk position range corresponding to the first target vehicle is determined based on the first driving speed, the acceleration, the second driving speed and a preset reaction time corresponding to the first target vehicle.

[0014] In some implementations, when the driving relationship satisfies a preset driving condition, determining the collision risk position range corresponding to the first target vehicle based on the first driving speed, the acceleration, the first position information, the second driving speed, and a preset reaction time includes:

[0015] Determine lane line information of the lane where the first target vehicle is located based on the first position information;

[0016] Determine the collision risk distance of the first target vehicle based on the first driving speed, the acceleration, the second driving speed and the preset reaction time, the collision risk distance including a forward collision risk distance, a lateral collision risk distance and / or a rearward collision risk distance;

[0017] The collision risk position range corresponding to the first target vehicle is determined based on the forward collision risk distance, the lateral collision risk distance and / or the rearward collision risk distance, the lane line information and the body length of the first target vehicle.

[0018] In some embodiments, the collision risk position range includes a forward collision risk position range, a rearward collision risk position range, and a lateral collision risk position range; determining the collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance, and / or the rearward collision risk distance, the lane line information, and the body length of the first target vehicle includes:

[0019] Determining the forward collision risk position range corresponding to the first target vehicle based on the forward collision risk distance and the body length of the first target vehicle;

[0020] or,

[0021] Determining the lateral collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance, the lane line information, and the body length of the first target vehicle;

[0022] or,

[0023] The rearward collision risk position range corresponding to the first target vehicle is determined based on the rearward collision risk distance, the lane line information, and the body length of the first target vehicle.

[0024] In some embodiments, the lateral collision risk position range includes a plurality of first collision sub-position ranges and a plurality of second collision sub-position ranges; and determining the lateral collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance, the lane line information, and the body length of the first target vehicle includes:

[0025] Determining the first collision sub-position range based on the lane line information, the body length of the first target vehicle, and the forward collision risk distance;

[0026] The second collision sub-position range is determined based on the forward collision risk distance, the lateral collision risk distance, and the first collision sub-position range.

[0027] In some implementations, the collision risk information includes the presence of a collision risk and the absence of a collision risk, the collision risk position range includes a plurality of collision sub-position ranges, and after determining the collision risk information between the first target vehicle and the second target vehicle according to the planned driving path and the collision risk position range, the method further includes:

[0028] When the collision risk information indicates that there is a collision risk, determining a target collision sub-position range corresponding to the planned driving path based on the planned driving path and the multiple collision sub-position ranges;

[0029] Acquire the positional relationship between the plurality of collision sub-position ranges and the first target vehicle, and determine the collision risk type corresponding to each of them;

[0030] Based on the collision risk type corresponding to the target collision sub-position range, a target collision risk type corresponding to the collision risk information is determined.

[0031] In some implementations, the planned driving path is a planned path within a preset time period, and obtaining the planned driving path of the second target vehicle around the first target vehicle includes:

[0032] Get multiple time points within a preset period;

[0033] Acquire position information of the second target vehicle corresponding to each of a plurality of time points;

[0034] A planned driving path of the second target vehicle within a preset time period is determined based on the multiple position information.

[0035] In some implementations, determining the planned driving path of the second target vehicle based on the plurality of position information includes:

[0036] Determine a coordinate system conversion function based on a preset standard coordinate system and a current coordinate system corresponding to the plurality of position information;

[0037] Based on the coordinate system conversion function, the multiple position information are respectively converted into coordinate systems to obtain the target position information corresponding to each of the multiple position information in the preset standard coordinate system.

[0038] The present application also provides a vehicle collision prediction device, the device comprising:

[0039] A first acquisition module is used to acquire first driving data of a first target vehicle and a driving planning path and second driving data of a second target vehicle around the first target vehicle, wherein the second target vehicle is an autonomous driving vehicle;

[0040] A first determining module, configured to determine a collision risk position range corresponding to the first target vehicle based on the first driving data and the second driving data;

[0041] The second determination module is used to determine the collision risk information between the first target vehicle and the second target vehicle according to the planned driving path and the collision risk position range.

[0042] The present application also provides a vehicle collision prediction device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the vehicle collision prediction method as described above.

[0043] Implementing the embodiments of the present application has the following beneficial effects:

[0044] The vehicle collision prediction method disclosed in the present application obtains the planned driving path of the second target vehicle, determines the collision risk position range of the first target vehicle based on the driving data of the first target vehicle and the second target vehicle, and performs collision prediction based on the planned driving path and the collision risk position range; the accuracy and efficiency of collision prediction can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the vehicle collision prediction method, device and equipment described in the present application, the drawings required for 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 paying creative work.

[0046] Figure 1 A schematic diagram of an implementation environment for vehicle collision prediction provided in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of a process flow of a vehicle collision prediction method provided in an embodiment of the present application;

[0048] Figure 3 A flowchart of a method for obtaining a planned path provided in an embodiment of the present application;

[0049] Figure 4 A schematic flow chart of a method for determining a collision risk position range provided in an embodiment of the present application;

[0050] Figure 5 A flowchart of a method for determining a specific collision risk position range provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of the regional distribution of a collision sub-position range provided in an embodiment of the present application;

[0052] Figure 7 A flowchart of a method for determining a collision risk type provided in an embodiment of the present application;

[0053] Figure 8 A schematic diagram of the structure of a vehicle collision prediction device provided in an embodiment of the present application;

[0054] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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 making creative work are within the scope of protection of this application.

[0056] 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 of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes 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.

[0057] See also Figure 1 , which shows a schematic diagram of an implementation environment provided by an embodiment of the present application, and the implementation environment may include:

[0058] At least one terminal 01 and at least one server 02. The at least one terminal 01 and the at least one server 02 can perform data communication via a network.

[0059] In an optional embodiment, the terminal 01 may be an executor of the vehicle collision prediction method. The terminal 01 may include but is not limited to a vehicle-mounted terminal, a smart phone, a desktop computer, a tablet computer, a laptop computer, a smart speaker, a digital assistant, an augmented reality (AR) / virtual reality (VR) device, a smart wearable device, and other types of electronic devices. The operating system running on the terminal 01 may include but is not limited to Android, IOS, Linux, Windows, Unix, and the like.

[0060] The server 02 can provide preset data to the terminal 01. Optionally, the server 02 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0061] Please refer to Figure 2 , which shows a flow chart of a vehicle collision prediction method provided by an embodiment of the present application. This specification provides method operation steps as described in the embodiment or flow chart, but based on conventional; or non-creative labor, more or fewer operation steps may be included. The order of steps listed in the embodiment is only one way of executing the steps among many, and does not represent the only execution order. The vehicle collision prediction method can be executed in the order of the methods shown in the embodiment or the accompanying drawings. Specifically, Figure 2 As shown, the method includes:

[0062] S201, obtaining first driving data of a first target vehicle, a planned driving path of a second target vehicle around the first target vehicle, and second driving data, wherein the second target vehicle travels based on the planned driving path;

[0063] In an embodiment of the present application, the driving planning path may be a planned path that can guide the second target vehicle to travel during the driving process of the second target vehicle; the driving planning path may be a driving path within a preset period of time planned based on a prediction cycle; for example, the duration of the preset cycle may be 90-110 milliseconds, and the duration of the preset period may be 6-10s; in an example, when the duration of the prediction cycle is 100 milliseconds and the duration of the preset period is 8s, an 8-second driving planning path may be planned every 100 milliseconds. The second target vehicle may include an automatic driving mode; at this time, the driving planning path may be a path planned in real time by the automatic driving system during the driving of the second target vehicle in the automatic driving mode. The first target vehicle may include an automatic driving mode or may not include an automatic driving mode. Both the first target vehicle and the second target vehicle include a V2X (vehicle to everything, vehicle-to-external information exchange) system. Both the first driving data and the second driving data may be data generated by the vehicle during driving. For example, the first driving data may include a first driving speed, an acceleration, a first driving direction, a first position information, and lane line information of the road where the first target vehicle is located; the second driving data includes a second driving speed, a second driving direction, and a second position information.

[0064] Optionally, the second target vehicle may be the vehicle closest to the first target vehicle in the front, rear or side direction among the vehicles operating in the automatic driving mode around the first target vehicle.

[0065] Optionally, the driving planning path and the second driving data of the second target vehicle can be obtained from the automatic driving system on the second target vehicle through the V2X system of the second target vehicle. The driving data of the first target vehicle is obtained through the V2X system on the first target vehicle, and the driving planning path and the second driving data of the second target vehicle sent by the V2X system of the second target vehicle are received.

[0066] In some exemplary embodiments, the first driving speed, acceleration, first driving direction, first position information of the first target vehicle and the lane line information of the road where the first target vehicle is located can be obtained in real time; as well as the driving planned path, second driving speed, second driving direction and second position information of the second target vehicle. The lane line information may include the width information between two adjacent lane lines.

[0067] The present application directly uses the planned driving path of the second target vehicle as the basis for judgment, thereby not only obtaining a relatively accurate driving path, but also avoiding the calculation process of the driving trajectory of the second target vehicle.

[0068] S202: Determine a collision risk position range corresponding to the first target vehicle based on the first driving data and the second driving data.

[0069] In the embodiment of the present application, the collision risk position range may refer to the position range where the second target vehicle may have a collision risk with the first target vehicle. Here, the collision risk position range may be located on any side or any multiple sides around the first target vehicle; for example, it may be located in the front, side and / or rear direction of the first target vehicle. That is, the collision risk position range may include a forward collision risk position range, a rearward collision risk position range and a lateral collision risk position range.

[0070] Optionally, the driving relationship between the second target vehicle and the first target vehicle can be determined based on the first driving data and the second driving data; when the driving relationship meets the preset driving conditions, the collision risk position range corresponding to the first target vehicle is determined based on the first driving data and the second driving data. The driving relationship may refer to the correlation relationship between the position relationship and the heading relationship between the first target vehicle and the second target vehicle. Among them, the heading relationship may include the first target vehicle and the second target vehicle having the same heading and crossing headings; the position relationship may include the second target vehicle being located in the front, side and rear of the first target vehicle. The preset driving conditions may include at least one of the second target vehicle being located in the front direction of the vehicle and having the same heading as the first target vehicle, the second target vehicle being located in the rear direction of the vehicle and having the same heading as the first target vehicle, and the second target vehicle being located in the side direction of the vehicle and having an intersection with the heading of the first target vehicle.

[0071] In one example, when the driving relationship meets the preset driving conditions, the collision risk distance of the first target vehicle is determined based on the first driving data, the second driving data and the preset reaction time corresponding to the first target vehicle; wherein the collision risk distance includes the forward collision risk distance, the lateral collision risk distance and / or the rearward collision risk distance; based on the forward collision risk distance, the lateral collision risk distance and / or the rearward collision risk distance, the lane line information and the body length of the first target vehicle, the collision risk position range corresponding to the first target vehicle is determined. This method can obtain a more accurate collision risk position range.

[0072] S203: Determine collision risk information between the first target vehicle and the second target vehicle according to the planned driving path and the collision risk position range.

[0073] In an embodiment of the present application, the collision risk information may be information on the possibility of collision between the first target vehicle and the second target vehicle; the collision risk information here may include the existence of a collision risk and the absence of a collision risk. The existence of a collision risk may mean that the first target vehicle and the second target vehicle may collide. The absence of a collision risk may mean that the first target vehicle and the second target vehicle are unlikely to collide.

[0074] Optionally, the collision risk information between the first target vehicle and the second target vehicle may be determined based on a positional relationship between a trajectory of the planned driving path and a collision risk position range.

[0075] In some exemplary embodiments, when there is no intersection in the trajectory collision risk position range of the planned driving path, it can be determined that there is no collision risk between the first target vehicle and the second target vehicle.

[0076] In some other exemplary embodiments, when there is an intersection in the trajectory collision risk position range of the planned driving path, it can be determined that there is a collision risk between the first target vehicle and the second target vehicle.

[0077] Optionally, when the collision risk information indicates that there is a collision risk, a collision warning process is performed. Specifically, the collision warning process may be performed in the form of a signal such as sound or light.

[0078] In this embodiment, the present application obtains the planned driving path of the second target vehicle, determines the collision risk position range of the first target vehicle based on the driving data of the first target vehicle and the second target vehicle, and performs collision prediction based on the planned driving path and the collision risk position range; the present application obtains a relatively accurate planned driving path sent by the second target vehicle, and accurately determines the collision risk position range of the first target vehicle based on the driving data of the first target vehicle and the second target vehicle, and performs collision prediction based on two relatively accurate data. Compared with the method in the prior art of predicting the driving trajectory of the first target vehicle and / or the second target vehicle and then performing collision judgment based on the predicted data, the present application can effectively improve the accuracy and efficiency of collision prediction.

[0079] In some exemplary embodiments, Figure 3 , which is a flow chart of a method for obtaining a planned path provided in an embodiment of the present application; the details are as follows.

[0080] S301, obtaining multiple time points within a preset period;

[0081] In the embodiment of the present application, the time point may be a planned time point within a preset time period; by using the planned time point, the position of the second target vehicle at the time point is planned.

[0082] Optionally, multiple time points are evenly distributed; wherein the distribution density of the multiple time points can be set according to pre-set planning configuration information.

[0083] S302, obtaining position information of a second target vehicle corresponding to each of a plurality of time points;

[0084] In the embodiment of the present application, the location information may be the vehicle coordinate information corresponding to a certain point in time; each point in time corresponds to a planned location information.

[0085] Optionally, the position information corresponding to each time point can be determined by model one;

[0086] Model 1: TP t =(et,nt,ut,θ,k,k',v,a,a',t),t∈(t1,t2)

[0087] Among them, TP t is the position information at time point t; et, nt, ut are the coordinate values ​​of the second target vehicle in the current coordinate system; θ is the front wheel turning angle; k is the trajectory curvature; k' is the trajectory curvature derivative; v is the longitudinal vehicle speed; a is the longitudinal acceleration; a' is the longitudinal impact degree; t1 and t2 are the starting and ending times of the preset time period respectively.

[0088] S303: Determine a planned driving path of the second target vehicle within a preset time period based on the multiple position information.

[0089] In the embodiment of the present application, the connection line between the plurality of position information may be determined as the driving plan path within the preset time period, wherein the connection line may be a smooth curve.

[0090] Optionally, the coordinate system of multiple position information may be converted to obtain target position information; and then the multiple target position information may be connected to obtain the planned driving path of the second target vehicle within a preset time period.

[0091] In one embodiment, a first coordinate system conversion function can be determined based on a geocentric earth-fixed rectangular coordinate system and a northeast celestial coordinate system; based on the first coordinate system conversion function, coordinate system conversions are performed on multiple position information respectively to obtain first target position information in a geocentric earth-fixed rectangular coordinate system; then a second coordinate system conversion function is determined based on the WGS-84 coordinate system and the geocentric earth-fixed rectangular coordinate system; then based on the second coordinate system conversion function, coordinate system conversions are performed on multiple position information respectively to obtain second target position information in a WGS-84 coordinate system; and the second target position information is determined as the target position information. Among them, the northeast celestial coordinate system is also called the station-centered coordinate system, with the position P of the target object as the coordinate origin. Here, the target object can be a second target vehicle.

[0092] Specifically, the first target position information may be determined by model 2;

[0093] Model 2:

[0094]

[0095]

[0096] Among them, (x, y, z) is the coordinate corresponding to the first target position information; P0 = (x0, y0, z0) is the coordinate corresponding to the position information P0 in the northeast celestial coordinate system; (lon0, lat0, alt0) is the GPS coordinate of the position information P0. Among them, z0 is equal to alt0.

[0097] Furthermore, the second target position information can be determined by model three;

[0098] Model 3:

[0099]

[0100] e 2 =f(2-f).

[0101] Among them, a = 6378137.0m is the major radius of the reference ellipsoid; f = 1 / 298.257223565 is the extreme flattening of the reference ellipsoid; e is the eccentricity of the ellipsoid; N is the radius of curvature of the reference ellipsoid; p is the modulus of x, y.

[0102] In another embodiment, a coordinate system conversion function can be determined based on a preset standard coordinate system and a current coordinate system corresponding to a plurality of position information; then, based on the coordinate system conversion function, coordinate system conversion is performed on the plurality of position information respectively to obtain target position information corresponding to each of the plurality of position information in the preset standard coordinate system. The preset standard coordinate system includes a geocentric earth-fixed rectangular coordinate system or a WGS-84 coordinate system (longitude and latitude coordinate system). The current coordinate system can be a northeast celestial coordinate system.

[0103] In this embodiment, the present application can obtain a relatively accurate driving planning path by planning corresponding fixed position information at multiple time points, thereby improving the accuracy of collision prediction.

[0104] In some exemplary embodiments, Figure 4 , which is a flow chart of a method for determining a collision risk position range provided in an embodiment of the present application; the details are as follows.

[0105] S401, determining a first driving speed, an acceleration, a first driving direction, and a first position information of a first target vehicle based on first driving data.

[0106] In the embodiment of the present application, the acceleration may be the maximum deceleration of the first target vehicle.

[0107] S402, determining a second driving speed, a second driving direction, and a second position information of a second target vehicle based on the second driving data;

[0108] S403, determining a driving relationship between the first target vehicle and the second target vehicle based on the first driving direction, the second driving direction, the first position information, and the second position information;

[0109] In the embodiment of the present application, the driving relationship may refer to the relationship between the position relationship and the heading relationship between the first target vehicle and the second target vehicle. The heading relationship may include the first target vehicle and the second target vehicle having the same heading or crossing headings; the position relationship may include the second target vehicle being located in the front, side, and rear direction of the first target vehicle.

[0110] Optionally, the heading relationship between the first target vehicle and the second target vehicle may be determined based on the first driving direction and the second driving direction; and the position relationship between the first target vehicle and the second target vehicle may be determined based on the first position information and the second position information.

[0111] S404, when the driving relationship meets the preset driving conditions, determine the collision risk position range corresponding to the first target vehicle based on the first driving speed, acceleration, first position information, second driving speed and the preset reaction time corresponding to the first target vehicle.

[0112] In an embodiment of the present application, the preset reaction time may refer to the driver's reaction time when receiving information or the reaction time of the automatic driving system in the automatic driving mode.

[0113] Optionally, when the driving relationship meets the preset driving conditions, the collision risk distance of the first target vehicle can be determined based on the first driving speed, acceleration, first position information, second driving speed and the preset reaction time corresponding to the first target vehicle; further, the collision risk position range is determined based on the collision risk distance of the first target vehicle and the body length of the first target vehicle. Among them, the collision risk distance may refer to the distance relative to the circumference of the first target vehicle; for example, it may be the distance relative to the front of the first target vehicle, the distance relative to the rear of the first target vehicle, and the lateral distance relative to the side of the first target vehicle. The first position information may refer to the road information where the first target vehicle is located and its position on the road. The second position information may refer to the road where the second target vehicle is located and its position on the road.

[0114] In this embodiment, the present application predicts the heading relationship and position relationship between the first target vehicle and the second target vehicle; and then determines the collision risk position range based on the prediction result; this not only simplifies the complexity of data processing, but also improves the accuracy of the collision risk position range.

[0115] In some exemplary embodiments, Figure 5 , which is a flow chart of a specific method for determining a collision risk position range provided in an embodiment of the present application; the details are as follows.

[0116] S501, determining lane line information of a lane where a first target vehicle is located based on first position information.

[0117] In an embodiment of the present application, the lane line information may include the width between lane lines; that is, the lane width.

[0118] Optionally, the width between two adjacent lane lines of the lane where the first target vehicle is located may be determined based on the road information in the first position information.

[0119] S502, determining a collision risk distance of the first target vehicle based on the first driving speed, the acceleration, the second driving speed and the preset reaction time, wherein the collision risk distance includes a forward collision risk distance, a lateral collision risk distance and / or a rearward collision risk distance.

[0120] In the embodiment of the present application, the collision risk distance may refer to the distance relative to the circumference of the first target vehicle; the collision risk distance may include a forward collision risk distance, a lateral collision risk distance and / or a rearward collision risk distance. Among them, the forward collision risk distance may be the distance relative to the front of the first target vehicle; the rearward collision risk distance may be the distance relative to the rear of the first target vehicle; and the lateral collision risk distance may be the lateral distance relative to the side of the first target vehicle.

[0121] Optionally, the forward collision risk distance may be determined by Model 4;

[0122] Model 4:

[0123] Wherein, F_L represents the forward collision risk distance, v1 is the first driving speed, v2 is the second driving speed, t1 is the reaction time, and a is the maximum deceleration of the vehicle.

[0124] Optionally, the lateral collision risk distance may be determined by Model 5;

[0125] Model 5:

[0126] Wherein, R_L represents the lateral collision risk distance, v1 is the first driving speed, v2 is the second driving speed, t1 is the reaction time, and a is the maximum deceleration of the vehicle.

[0127] Optionally, the rear collision risk distance may be determined by Model VI;

[0128] Model 6:

[0129] Wherein, B_L represents the lateral collision risk distance, v1 is the first driving speed, v2 is the second driving speed, t1 is the reaction time, and a is the maximum deceleration of the vehicle.

[0130] S503: Determine a collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance and / or the rearward collision risk distance, the lane line information and the body length of the first target vehicle.

[0131] In the embodiment of the present application, the vehicle body length may refer to the total length from the front to the rear of the first target vehicle.

[0132] Optionally, the collision risk position range may include multiple sub-collision position ranges.

[0133] Optionally, the forward collision risk position range, lateral collision risk position range and / or rear collision risk position range corresponding to the first target vehicle may be determined based on the forward collision risk distance, lateral collision risk distance and / or rear collision risk distance, lane line information and the body length of the first target vehicle. Among them, the forward collision risk position range, lateral collision risk position range and rear collision risk position range may have an intersection area.

[0134] In some exemplary embodiments, the forward collision risk position range corresponding to the first target vehicle is determined based on the forward collision risk distance and the body length of the first target vehicle.

[0135] In one example, taking the forward collision risk position range as an example, the forward collision risk position range may include a plurality of third collision sub-position ranges. Figure 6 In the example, the B3 region, the B4 region and the B5 region may be the third collision sub-position range.

[0136] In other exemplary embodiments, the lateral collision risk position range corresponding to the first target vehicle is determined based on the forward collision risk distance, the lateral collision risk distance, the lane line information, and the body length of the first target vehicle.

[0137] In one example, taking the lateral collision risk position range as an example, the lateral collision risk position range may include a plurality of first collision sub-position ranges and a plurality of second collision sub-position ranges.

[0138] Specifically, the first collision sub-position range can be determined based on the lane line information, the body length of the first target vehicle, and the forward collision risk distance; wherein the first collision sub-position range can be a position range adjacent to the first target vehicle; the second collision sub-position range is determined based on the forward collision risk distance, the lateral collision risk distance, and the first collision sub-position range. Furthermore, the body length or the forward collision risk distance can be determined as the length of the first collision sub-position range, and the lane width corresponding to the lane line information can be determined as the width of the first collision sub-position range. The difference between the lateral wind risk distance and the width of the first collision sub-position range and the sum of the forward collision risk distance and the body length can be determined as the width and length of the second collision sub-position range. Specifically, as Figure 6 In the figure, the B1 area, the B2 area, the B3 area, the B5 area, the B9 area and the B10 area are all lateral collision risk position ranges. Among them, the B1 area, the B2 area, the B3 area and the B5 area can be the first collision sub-position range; the B9 area and the B10 area are the second collision sub-position range.

[0139] In some other exemplary embodiments, the rearward collision risk position range corresponding to the first target vehicle is determined based on the rearward collision risk distance, lane line information, and the body length of the first target vehicle.

[0140] In one example, taking the rearward collision risk position range as an example, the rearward collision risk position range may include a plurality of fourth collision sub-position ranges. Figure 6 In the example, the B6 region, the B7 region and the B8 region may be the fourth collision sub-position range.

[0141] In this embodiment, the present application determines the collision risk distances in each direction of the collision risk position range through the real-time driving data of the first target vehicle and the second target vehicle, and then based on the lane line information and the body length of the first target vehicle; the collision risk position range of each defense line can be accurately calculated; and the accuracy of collision prediction is further improved.

[0142] In some exemplary embodiments, Figure 7 , which is a flow chart of a method for determining a collision risk type provided in an embodiment of the present application; the details are as follows.

[0143] S701: When the collision risk information indicates that there is a collision risk, determine a target collision sub-position range corresponding to the planned driving path based on the planned driving path and multiple collision sub-position ranges.

[0144] In the embodiment of the present application, the target collision sub-position range may refer to a position range that has an intersection with the target planned path.

[0145] Optionally, a target collision sub-position range having an intersection with the planned driving path may be determined based on the planned driving path and a plurality of collision sub-position ranges.

[0146] S702: Obtain positional relationships between a plurality of collision sub-position ranges and the first target vehicle, and determine the collision risk types corresponding to the respective ranges.

[0147] In the embodiment of the present application, the collision risk types may include forward collision risk, lateral collision risk, and rearward collision risk.

[0148] Optionally, the collision risk type corresponding to each collision sub-position range may be determined based on the position of the collision sub-position range relative to the first target vehicle.

[0149] In some exemplary embodiments, if the collision sub-position range is located in the B4 area, it can be determined that there is a risk of a forward collision between the first target vehicle and the second target vehicle. If the collision sub-position range is located in any of the B4 area, the B1 area, the B2 area, the B6 area, and the B8 area, the driver is reminded that there is a second target vehicle in the area; if the second target vehicle in the area turns on the turn signal and plans to change lanes, it can be determined that there is a risk of a blind spot collision. If the collision sub-position range is located in any of the B9 area and the B10 area, the driver is reminded that there is a second target vehicle in the area; when the collision sub-position range is located in any of the B3 area and the B5 area, it can be determined that there is a risk of a lateral collision. If the collision sub-position range is located in the B7 area, it can be determined that there is a risk of a rearward collision between the first target vehicle and the second target vehicle.

[0150] S703: Determine the target collision risk type corresponding to the collision risk information based on the collision risk type corresponding to the target collision sub-position range.

[0151] In this embodiment, the present application can effectively improve the accuracy of collision risk prediction by dividing the collision position range into regions and determining the collision risk type based on the collision sub-position ranges obtained by the division.

[0152] The present application also provides a vehicle collision prediction device, such as Figure 8 As shown, it is a structural schematic diagram of a vehicle collision prediction device provided by an embodiment of the present application; specifically, the device includes:

[0153] A first acquisition module 801 is used to acquire first driving data of a first target vehicle and a driving planning path and second driving data of a second target vehicle around the first target vehicle, where the second target vehicle is an autonomous driving vehicle;

[0154] A first determining module 802, configured to determine a collision risk position range corresponding to the first target vehicle based on the first driving data and the second driving data;

[0155] The second determination module 803 is used to determine the collision risk information between the first target vehicle and the second target vehicle according to the planned driving path and the collision risk position range.

[0156] In the embodiment of the present application, the first determining module 802 includes:

[0157] A first determining unit, configured to determine a first driving speed, an acceleration, a first driving direction, and a first position information of the first target vehicle based on the first driving data;

[0158] a second determining unit, configured to determine a second driving speed, a second driving direction, and a second position information of the second target vehicle based on the second driving data;

[0159] a third determining unit, configured to determine a driving relationship between the first target vehicle and the second target vehicle based on the first driving direction, the second driving direction, the first position information, and the second position information;

[0160] The fourth determination unit is used to determine the collision risk position range corresponding to the first target vehicle based on the first driving speed, the acceleration, the second driving speed and the preset reaction time corresponding to the first target vehicle when the driving relationship meets the preset driving conditions.

[0161] In the embodiment of the present application, the fourth determining unit includes:

[0162] A first determining subunit, configured to determine lane line information of a lane where the first target vehicle is located based on the first position information;

[0163] A second determination subunit is used to determine the collision risk distance of the first target vehicle based on the first driving speed, the acceleration, the second driving speed and the preset reaction time, wherein the collision risk distance includes a forward collision risk distance, a lateral collision risk distance and / or a rearward collision risk distance;

[0164] The third determination subunit is used to determine the collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance and / or the rearward collision risk distance, the lane line information and the body length of the first target vehicle.

[0165] In the embodiment of the present application, the collision risk position range includes a forward collision risk position range, a rearward collision risk position range and a lateral collision risk position range; the third determining subunit includes:

[0166] A first determination submodule, configured to determine the forward collision risk position range corresponding to the first target vehicle based on the forward collision risk distance and the body length of the first target vehicle;

[0167] or,

[0168] a second determination submodule, configured to determine the lateral collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance, the lane line information, and the body length of the first target vehicle;

[0169] or,

[0170] The third determination submodule is used to determine the rear collision risk position range corresponding to the first target vehicle based on the rear collision risk distance, the lane line information and the body length of the first target vehicle.

[0171] In an embodiment of the present application, the lateral collision risk position range includes a plurality of first collision sub-position ranges and a plurality of second collision sub-position ranges; the second determination submodule includes:

[0172] a fourth determination subunit, configured to determine the first collision sub-position range based on the lane line information, the body length of the first target vehicle, and the forward collision risk distance;

[0173] A fifth determining subunit is configured to determine the second collision sub-position range based on the forward collision risk distance, the lateral collision risk distance, and the first collision sub-position range.

[0174] In an embodiment of the present application, the collision risk information includes whether there is a collision risk and whether there is no collision risk, the collision risk position range includes a plurality of collision sub-position ranges, and the method further includes:

[0175] A third determination module is used to determine, when the collision risk information indicates that there is a collision risk, a target collision sub-position range corresponding to the driving plan path based on the driving plan path and the multiple collision sub-position ranges;

[0176] a fourth determination module, configured to obtain a positional relationship between the plurality of collision sub-position ranges and the first target vehicle, and determine a corresponding collision risk type;

[0177] A fifth determination module is configured to determine a target collision risk type corresponding to the collision risk information based on the collision risk type corresponding to the target collision sub-position range.

[0178] In the embodiment of the present application, the first acquisition module includes:

[0179] A first acquisition unit, used to acquire multiple time points within a preset time period;

[0180] A second acquisition unit is used to acquire the position information of the second target vehicle corresponding to each of a plurality of time points;

[0181] A fifth determination unit is used to determine the planned driving path of the second target vehicle within a preset time period based on multiple position information.

[0182] In the embodiment of the present application, the fifth determining unit includes:

[0183] a sixth determining subunit, configured to determine a coordinate system conversion function based on a preset standard coordinate system and a current coordinate system corresponding to the plurality of position information;

[0184] The seventh determination subunit is used to perform coordinate system conversion on the multiple position information respectively based on the coordinate system conversion function to obtain target position information corresponding to each of the multiple position information in the preset standard coordinate system.

[0185] It should be noted that the device in the device embodiment and the method embodiment are based on the same inventive concept.

[0186] An embodiment of the present application provides a vehicle collision prediction device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the vehicle collision prediction method as described in the above method embodiment.

[0187] Further, Fig. 9 A hardware structure diagram of an electronic device for implementing the vehicle collision prediction method provided in the embodiment of the present application is shown. The electronic device may participate in or include the vehicle collision prediction device provided in the embodiment of the present application. Fig. 9 As shown, the electronic device 90 may include one or more (902a, 902b, ..., 902n are used to illustrate) processors 902 (the processor 902 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 904 for storing data, and a transmission device 906 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Fig. 9 The structure shown is for illustration only and does not limit the structure of the above electronic device. Fig. 9 More or fewer components may be shown, or may have a different configuration than shown.

[0188] It should be noted that the above-mentioned one or more processors 902 and / or other vehicle collision prediction circuits may generally be referred to as "vehicle collision prediction circuits" in this article. The vehicle collision prediction circuit may be embodied in whole or in part as software, hardware, firmware or any other combination. In addition, the vehicle collision prediction circuit may be a single independent processing module, or may be fully or partially integrated into any of the other components in the electronic device 90 (or mobile device). As involved in the embodiments of the present application, the vehicle collision prediction circuit is controlled as a processor (e.g., selection of a variable resistor terminal path connected to an interface).

[0189] The memory 904 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the vehicle collision prediction method described in the embodiment of the present application. The processor 902 executes various functional applications and vehicle collision prediction by running the software programs and modules stored in the memory 904, that is, to implement the above-mentioned vehicle collision prediction method. The memory 904 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 904 may further include a memory remotely arranged relative to the processor 902, and these remote memories may be connected to the electronic device 90 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0190] The transmission device 906 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the electronic device 90. In one example, the transmission device 906 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one embodiment, the transmission device 906 can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0191] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 90 (or mobile device).

[0192] An embodiment of the present application also provides a computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to a vehicle collision prediction method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the vehicle collision prediction method provided by the above method embodiment.

[0193] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0194] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0195] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0196] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and electronic device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0197] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0198] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A vehicle collision prediction method, characterized in that: The method comprises: Acquire first driving data of a first target vehicle and a planned driving path of a second target vehicle around the first target vehicle and second driving data, wherein the second target vehicle travels based on the planned driving path; the first driving data includes a first driving speed, an acceleration, a first driving direction, first position information, and lane line information of a road where the first target vehicle is located; the second driving data includes a second driving speed, a second driving direction, and second position information; Determine a driving relationship between the first target vehicle and the second target vehicle based on the first driving direction, the second driving direction, the first position information, and the second position information; Determine the collision risk distance of the first target vehicle based on the first driving speed, the acceleration, the second driving speed and the preset reaction time; the collision risk distance includes a forward collision risk distance, a lateral collision risk distance and / or a rearward collision risk distance; Determining the collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance and / or the rearward collision risk distance, the lane line information and the body length of the first target vehicle; According to the planned driving path and the collision risk position range, collision risk information between the first target vehicle and the second target vehicle is determined.

2. The vehicle collision prediction method according to claim 1, characterized in that: The collision risk position range includes a forward collision risk position range, a rearward collision risk position range, and a lateral collision risk position range; determining the collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance, and / or the rearward collision risk distance, the lane line information, and the body length of the first target vehicle includes: Determining the forward collision risk position range corresponding to the first target vehicle based on the forward collision risk distance and the body length of the first target vehicle; or, Determining the lateral collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance, the lane line information, and the body length of the first target vehicle; or, The rearward collision risk position range corresponding to the first target vehicle is determined based on the rearward collision risk distance, the lane line information, and the body length of the first target vehicle.

3. The vehicle collision prediction method according to claim 2, characterized in that: The lateral collision risk position range includes a plurality of first collision sub-position ranges and a plurality of second collision sub-position ranges; determining the lateral collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance, the lane line information, and the body length of the first target vehicle includes: Determining the first collision sub-position range based on the lane line information, the body length of the first target vehicle, and the forward collision risk distance; The second collision sub-position range is determined based on the forward collision risk distance, the lateral collision risk distance, and the first collision sub-position range.

4. The vehicle collision prediction method according to claim 1, characterized in that: The collision risk information includes whether there is a collision risk and whether there is no collision risk, the collision risk position range includes a plurality of collision sub-position ranges, and after determining the collision risk information between the first target vehicle and the second target vehicle according to the planned driving path and the collision risk position range, the method further includes: When the collision risk information indicates that there is a collision risk, determining a target collision sub-position range corresponding to the planned driving path based on the planned driving path and the multiple collision sub-position ranges; Acquire the positional relationship between the plurality of collision sub-position ranges and the first target vehicle, and determine the collision risk type corresponding to each of them; Based on the collision risk type corresponding to the target collision sub-position range, a target collision risk type corresponding to the collision risk information is determined.

5. The vehicle collision prediction method according to claim 1, characterized in that: The planned driving path is a planned path within a preset time period, and the obtaining of the planned driving path of the second target vehicle around the first target vehicle includes: Get multiple time points within a preset period; Acquire position information of the second target vehicle corresponding to each of a plurality of time points; A planned driving path of the second target vehicle within a preset time period is determined based on the multiple position information.

6. The vehicle collision prediction method according to claim 5, characterized in that: The determining the travel planning path of the second target vehicle based on the multiple position information includes: Determine a coordinate system conversion function based on a preset standard coordinate system and a current coordinate system corresponding to the plurality of position information; Based on the coordinate system conversion function, the multiple position information are respectively converted into coordinate systems to obtain the target position information corresponding to each of the multiple position information in the preset standard coordinate system.

7. A vehicle collision prediction device, characterized in that: The device comprises: A first acquisition module is used to acquire first driving data of a first target vehicle and a driving planning path and second driving data of a second target vehicle around the first target vehicle, wherein the second target vehicle is an autonomous driving vehicle; the first driving data includes a first driving speed, an acceleration, a first driving direction, a first position information, and lane line information of a road where the first target vehicle is located; the second driving data includes a second driving speed, a second driving direction, and a second position information; A first determining module, configured to determine a collision risk position range corresponding to the first target vehicle based on the first driving data and the second driving data; A second determination module is used to determine the collision risk information between the first target vehicle and the second target vehicle according to the driving plan path and the collision risk position range. Wherein, the first determination module includes a third determination unit for determining the driving relationship between the first target vehicle and the second target vehicle based on the first driving direction, the second driving direction, the first position information and the second position information; a fourth determination unit for determining the collision risk position range corresponding to the first target vehicle based on the first driving speed, the acceleration, the second driving speed and the preset reaction time corresponding to the first target vehicle when the driving relationship satisfies the preset driving condition; Among them, the fourth determination unit includes a second determination sub-unit, which is used to determine the collision risk distance of the first target vehicle based on the first driving speed, the acceleration, the second driving speed and the preset reaction time, and the collision risk distance includes a forward collision risk distance, a lateral collision risk distance and / or a rear collision risk distance; a third determination sub-unit, which is used to determine the collision risk position range corresponding to the first target vehicle based on the forward collision risk distance, the lateral collision risk distance and / or the rear collision risk distance, the lane line information and the body length of the first target vehicle.

8. A vehicle collision prediction device, characterized in that: The device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the vehicle collision prediction method as described in any one of claims 1 to 6.

Images