Speed prediction method and device, storage medium and electronic device

Abstract

Embodiments of the present application provide a speed prediction method and device, a storage medium and an electronic device. In the technical solution provided by the embodiments of the present application, the method comprises: obtaining a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system; obtaining a second coordinate set according to the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system; obtaining a trajectory fitting formula of the center point of a dynamic obstacle in the at least one obstacle according to the second coordinate set; and obtaining a predicted moving speed of the dynamic obstacle according to the trajectory fitting formula, so that the vehicle can detect obstacles with both high precision and low cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and in particular to a speed prediction method and device, a storage medium and an electronic device.

BACKGROUND

[0002] At present, vehicle obstacle detection can be divided into independent detection using a laser radar and fusion detection using a laser radar and a camera. The camera can accurately perform obstacle clustering, segmentation, type classification, feature tracking and other technical difficulties due to its high resolution, while the laser radar compensates for the disadvantage that the camera cannot accurately measure the distance due to its excellent active ranging capability. Using the laser radar and camera fusion method to detect obstacles can take into account the respective characteristics of the camera and the laser radar, and the relatively accurate obstacle recognition and tracking capability improves the ability of the unmanned vehicle to predict the obstacle path, collision warning and the like, which is lacking in a single laser radar sensor. Since the camera has high resolution, using the laser radar and camera fusion method to detect obstacles will bring high computational consumption, which is not conducive to reducing the manufacturing cost of the vehicle and is also not conducive to energy consumption control in the later stage.

[0003] Therefore, the current vehicle obstacle detection cannot take into account both high accuracy and low cost.

SUMMARY

[0004] Therefore, the present application provides a speed prediction method, device, storage medium and electronic device, which can take into account both high accuracy and low cost for vehicle obstacle detection.

[0005] In a first aspect, the present application provides a speed prediction method, which comprises:

[0006] obtaining a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system;

[0007] obtaining a second coordinate set from the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system;

[0008] obtaining a trajectory fitting formula of the center point of a dynamic obstacle in the at least one obstacle from the second coordinate set;

[0009] obtaining a predicted moving speed of the dynamic obstacle from the trajectory fitting formula.

[0010] Optionally, the environmental sensor is a single laser radar.

[0011] Optionally, the obtaining, according to the second coordinate set and a characteristic of directionless of adjacent position points, a third coordinate set, the third coordinate set comprising second coordinates of a dynamic obstacle in the at least one obstacle, comprises:

[0012] The third coordinate set is obtained according to the second coordinate set and the characteristic of directionless of adjacent position points.

[0013] The target position sequence of the dynamic obstacle is obtained according to the filtering condition and the third coordinate set.

[0014] The trajectory fitting formula is obtained according to the target position sequence.

[0015] Optionally, the obtaining, according to the second coordinate set and a characteristic of directionless of adjacent position points, a third coordinate set, the third coordinate set comprising second coordinates of a dynamic obstacle in the at least one obstacle, comprises:

[0016] The dynamic and static properties of the at least one obstacle are determined according to the second coordinate set and the characteristic of directionless of adjacent position points.

[0017] The second coordinates of the obstacle with static properties in the second coordinate set are filtered to obtain the third coordinate set.

[0018] Optionally, the obtaining, according to the filtering condition and the third coordinate set, a target position sequence of the dynamic obstacle, comprises:

[0019] The first position sequence of the dynamic obstacle is obtained according to the third coordinate set, the first position sequence comprising a horizontal coordinate position sequence and a vertical coordinate position sequence in the third coordinate set.

[0020] The filtering condition is obtained according to the first position sequence and a 3σ method.

[0021] The target position sequence is obtained by filtering the horizontal coordinate position sequence and the vertical coordinate position sequence according to the filtering condition, the target position sequence comprising a target horizontal coordinate position sequence and a target vertical coordinate position sequence.

[0022] Optionally, the obtaining, according to the target position sequence, a trajectory fitting formula, comprises:

[0023] The horizontal coordinate trajectory fitting formula of the center point of the dynamic obstacle is obtained according to the target horizontal coordinate position sequence.

[0024] The vertical coordinate trajectory fitting formula of the center point of the dynamic obstacle is obtained according to the target vertical coordinate position sequence.

[0025] Optionally, the obtaining, according to the trajectory fitting formula, a predicted moving speed of the dynamic obstacle, comprises:

[0026] According to the abscissa trajectory fitting formula, a predicted abscissa moving speed of the dynamic obstacle is obtained;

[0027] According to the ordinate trajectory fitting formula, a predicted ordinate moving speed of the dynamic obstacle is obtained;

[0028] According to the predicted abscissa moving speed and the predicted ordinate moving speed, a predicted moving speed of the dynamic obstacle is obtained.

[0029] In another aspect, an embodiment of the present application provides a speed prediction device, which comprises:

[0030] An acquisition module is configured to acquire a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system;

[0031] A conversion module is configured to obtain a second coordinate set according to the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system;

[0032] A trajectory fitting module is configured to obtain a trajectory fitting formula of a center point of a dynamic obstacle in the at least one obstacle according to the second coordinate set;

[0033] A prediction module is configured to obtain a predicted moving speed of the dynamic obstacle according to the trajectory fitting formula.

[0034] In another aspect, an embodiment of the present application provides a storage medium, which comprises a stored program, wherein the program controls a device where the storage medium is located to perform the speed prediction method when the program is running.

[0035] In another aspect, an embodiment of the present application provides an electronic device, which comprises a memory and a processor, the memory is configured to store information comprising program instructions, and the processor is configured to control execution of the program instructions, characterized in that the program instructions are loaded and executed by the processor to implement steps of the speed prediction method.

[0036] The technical scheme of the speed prediction method, device, storage medium and electronic equipment provided by the embodiment of the application comprises: acquiring a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system; obtaining a second coordinate set according to the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system; obtaining a trajectory fitting formula of the center point of a dynamic obstacle in the at least one obstacle according to the second coordinate set; and obtaining a predicted moving speed of the dynamic obstacle according to the trajectory fitting formula, so that the vehicle can detect the obstacle with high precision and low cost. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical scheme of the embodiments of the application, the drawings required to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0038] Figure 1 A flowchart of a speed prediction method provided by an embodiment of the application;

[0039] Figure 2 For Figure 1 A specific flowchart of obtaining a trajectory fitting formula of a center point of a dynamic obstacle in at least one obstacle according to a second coordinate set;

[0040] Figure 3 For Figure 2 A specific flowchart of obtaining a third coordinate set according to the second coordinate set and the characteristic of adjacent position points being undirected, the third coordinate set comprising second coordinates of a dynamic obstacle in at least one obstacle;

[0041] Figure 4 A schematic diagram of at least one obstacle in the embodiment of the application;

[0042] Figure 5 For Figure 2 A specific flowchart of obtaining a target position sequence of a dynamic obstacle according to a filtering condition and a third coordinate set;

[0043] Figure 6 For Figure 2 A specific flowchart of obtaining a trajectory fitting formula according to a target position sequence;

[0044] Figure 7 For Figure 1According to the trajectory fitting formula, the specific flow chart of the predicted moving speed of the dynamic obstacle is obtained.

[0045] Figure 8 A structural schematic diagram of a speed prediction device provided by an embodiment of the application is shown in the figure.

[0046] Figure 9 A schematic diagram of an electronic device provided by an embodiment of the application is shown in the figure.

DETAILED DESCRIPTION

[0047] In order to better understand the technical solutions of the application, the embodiments of the application will be described in detail below with reference to the drawings.

[0048] It should be clear that the described embodiments are only some of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0049] The terms used in the embodiments of the application are only for the purpose of describing the specific embodiments, and are not intended to limit the application. The singular forms "a", "said" and "the" used in the embodiments of the application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0050] It should be understood that the term "and / or" used herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects have an "or" relationship.

[0051] Intelligent driving is a widely discussed topic in current social development. Intelligent driving vehicles refer to vehicles with certain intelligent capabilities, which can have certain autonomous processing capabilities on the road, such as autonomous cruise, autonomous lane changing, autonomous braking reduction, etc. Different intelligent driving capabilities may have different intelligent levels. The highest level of intelligent driving capability is unmanned driving technology, which can completely autonomously perceive the position, environment, obstacles and other external factors, has autonomous behavior decision-making ability and route planning ability, etc., and can autonomously complete specific task goals.

[0052] The current technology accumulation can meet the unmanned driving capability of vehicles on a specific road section, but due to the complexity of social roads and the participation of multiple road roles, it is easy to cause unnecessary personnel injury. In addition, social laws and regulations limit the use of unmanned vehicles on public roads.

[0053] The unmanned logistics vehicle has a relatively standardized traffic environment, a relatively closed road environment rule, a fixed point-to-point route and a high-intensity and high-frequency use demand due to the specificity of the factory site operation environment, and has obtained rapid development in the unmanned aspect.

[0054] The unmanned logistics vehicle is generally configured with sensors and computing devices such as a laser radar, a camera, a positioning system and a domain controller, and can meet the functions necessary for autonomous operation of the vehicle such as autonomous positioning, environment perception, behavior decision and route planning and control. Among them, the judgment and tracking of the vehicle to the obstacle are extremely important to the safety of the vehicle operation.

[0055] At present, the obstacle detection of the unmanned logistics vehicle can be divided into independent detection using a laser radar and fusion detection using a laser radar and a camera. The camera can accurately perform obstacle clustering, segmentation, type classification and feature tracking due to high resolution, and the laser radar compensates for the disadvantage that the camera cannot accurately measure the distance due to excellent active ranging capability. The relatively accurate obstacle recognition and tracking capability improves the ability of the unmanned vehicle in obstacle path prediction and collision warning, which is lacking in a single laser radar sensor.

[0056] However, the layout of multiple sensors requires high assembly precision of the unmanned vehicle during manufacturing and installation, and each vehicle needs to be subjected to sensor calibration and calibration and other operations, which has high manufacturing cost, complex process and difficult maintenance. The logistics vehicle has high use frequency, complex working environment, more working environments such as dragging, vibration and heavy load, and reducing the use of sensors can improve the safe operation mileage of the vehicle, reduce the vehicle maintenance time, improve the operation efficiency and utilization rate of the vehicle.

[0057] The visual perception system relying on the camera has high resolution, which brings high computing consumption required by high-resolution images. The visual perception system needs to use high-power computing chips for matching calculation, which is not conducive to reducing the manufacturing cost of the unmanned vehicle and is also not conducive to energy consumption control in the later operation.

[0058] In summary, the current vehicle obstacle detection cannot balance high precision and low cost.

[0059] Based on the above technical problems, the embodiments of the present application provide a speed prediction method, device, storage medium and electronic equipment, so that the vehicle obstacle detection balances high precision and low cost.

[0060] Figure 1 A flowchart of a speed prediction method provided by an embodiment of the present application is shown in Figure 1 The method comprises the following steps.

[0061] Step 101, obtaining a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of the vehicle in a first coordinate system.

[0062] The environmental sensor is a single laser radar, such as a 16-line laser radar.

[0063] The vehicle detects obstacles in the environment using a single laser radar. Due to the low density of the laser radar point cloud, the vehicle contour cannot be accurately segmented, and thus the obstacle tracking cannot be prepared, that is, the obstacle confirmed at this moment and the obstacle confirmed at the next moment cannot be accurately confirmed as one obstacle, especially in a production environment with many obstacles and irregularities. Therefore, a vehicle position point design and speed prediction method is needed to determine the speed of the obstacle.

[0064] For example, a 16-line laser radar is used as the vehicle environmental detection sensor. The laser radar can determine the point cloud position of the obstacle in the environment around the vehicle by 360-degree rotation scanning and calculating the reflection information of the emitted laser beam. Then, the position of the point is calculated based on the laser radar point cloud detected by the laser radar, and it is concluded which part of the point cloud is an independent object.

[0065] Step 102, obtaining a second coordinate set according to the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system.

[0066] In some possible embodiments, step 102 specifically comprises: converting the first coordinates in the first coordinate set into second coordinates according to a conversion relationship between the first coordinate system and the second coordinate system, to obtain the second coordinate set.

[0067] The first coordinate system is a vehicle coordinate system, and the second coordinate system is a world coordinate system.

[0068] In order to obtain sufficient obstacle samples, the historical trajectory point coordinates of the center points of all detected obstacles are converted in the embodiments of the present application to obtain the positions of the historical trajectory points of the center points of the obstacles in the world coordinate system. Then, the positions of the center points of the obstacles at each moment are recorded in the data storage according to the obstacle id as the classification basis.

[0069] Step 103, obtaining a trajectory fitting formula of a center point of a dynamic obstacle in the at least one obstacle according to the second coordinate set.

[0070] In some possible embodiments, as shown in Figure 2 Step 103 specifically comprises:

[0071] Step 1031, obtaining a third coordinate set according to the second coordinate set and the characteristic of the directionless of the adjacent position points, the third coordinate set including the second coordinates of the dynamic obstacle in the at least one obstacle.

[0072] The key of detecting the speed of the obstacle by the single laser radar lies in distinguishing whether the obstacle is a dynamic obstacle or a static obstacle. Due to the reason of the density of the laser radar point cloud, the outer contour of the obstacle cannot be accurately recognized, and the center positions of the same obstacle in different time periods cannot be accurately distinguished. If the center positions are directly used for calculating the speed of the obstacle, the static obstacle is likely to have a large obstacle speed due to the jumping of the center points. Therefore, the embodiment of the present application needs to screen out the dynamic obstacle in the environment.

[0073] In some possible embodiments, as shown in Figure 3 Step 1031 specifically includes:

[0074] Step 1a, determining the dynamic and static attribute of the at least one obstacle according to the second coordinate set and the characteristic of the directionless of the adjacent position points.

[0075] The static obstacle is distributed in accordance with the general probability distribution, that is, the center points of the static obstacle are all in a smaller position range, and the directions between the adjacent position points are directionless. The embodiment of the present application uses the characteristic of the directionless of the adjacent position points to determine the dynamic and static attribute of the obstacle according to the second coordinate set. Figure 4 For the schematic diagram of the at least one obstacle in the embodiment of the present application, as shown in Figure 4 The static obstacle and the dynamic obstacle in the at least one obstacle are determined by step 1a.

[0076] Step 1b, filtering the second coordinates of the obstacle with the static dynamic and static attribute in the second coordinate set to obtain the third coordinate set.

[0077] After determining the dynamic and static attribute of the at least one obstacle, the embodiment of the present application first filters the second coordinates of the static obstacle in the second coordinate set.

[0078] Step 1032, obtaining the target position sequence of the dynamic obstacle according to the filtering condition and the third coordinate set.

[0079] The second coordinates in the third coordinate set are all the coordinates of the historical trajectory points of the center points of the dynamic obstacle. The center position points of the dynamic obstacle are linearly distributed, but the positions are also jittered and dispersed, so the center position points of the dynamic obstacle need to be filtered again.

[0080] In some possible embodiments, as shown in Figure 5 Step 1032 specifically includes:

[0081] Step 2a, obtaining a first position sequence of the dynamic obstacle according to the third coordinate set, the first position sequence comprising a horizontal coordinate position sequence and a vertical coordinate position sequence in the third coordinate set.

[0082] First, the horizontal coordinate and the vertical coordinate of the center position point of the dynamic obstacle in the third coordinate set, i.e., the x coordinate and the y coordinate, are stored separately to obtain two position sequences, i.e., a horizontal coordinate position sequence X and a vertical coordinate position sequence Y as follows:

[0083] X = [x0, x1, x2, …, x n-1 , x n ]

[0084] Y = [y0, y1, y2, …, y n-1 , y n ]

[0085] Step 2b, obtaining a filtering condition according to the first position sequence and a 3σ method.

[0086] The embodiment of the application filters the coordinates of the dynamic obstacle using the 3σ method. Assuming that the position difference of the obstacle center point before and after the frame position conforms to the normal distribution, the probability that the distance difference between the obstacle position (x T , y T ) of the period T and the obstacle position (x T-1 , y T-1 ) of the period T-1 is less than three times the variance is 98%, so the historical trajectory of the vehicle is calculated in a loop, and the position points that do not meet the condition are filtered, and the filtering condition is as follows:

[0087] △X T > 3σ △x

[0088] or

[0089] △Y T > 3σ △Y

[0090] wherein σ △x is the variance of the x coordinate difference of the adjacent position points of the obstacle, and σ △y is the variance of the y coordinate difference of the adjacent position points of the obstacle.

[0091] Step 2c, filtering the horizontal coordinate position sequence and the vertical coordinate position sequence according to the filtering condition to obtain a target position sequence, the target position sequence comprising a target horizontal coordinate position sequence and a target vertical coordinate position sequence.

[0092] The embodiment of the application filters the horizontal coordinate position sequence and the vertical coordinate position sequence according to the filtering condition to obtain the target position sequence.

[0093] Step 1033, obtaining a trajectory fitting formula according to the target position sequence.

[0094] After obtaining the target position sequence, the obstacle trajectory fitting can be performed to obtain the trajectory fitting formula.

[0095] The trajectory fitting formula includes a horizontal coordinate trajectory fitting formula and a vertical coordinate trajectory fitting formula.

[0096] In some possible embodiments, as shown in Figure 6 Step 1033 specifically includes:

[0097] Step 3a, obtaining a horizontal coordinate trajectory fitting formula of the center point of the dynamic obstacle according to the target horizontal coordinate position sequence.

[0098] Step 3b, obtaining a vertical coordinate trajectory fitting formula of the center point of the dynamic obstacle according to the target vertical coordinate position sequence.

[0099] The embodiments of the present application separately fit the horizontal coordinate trajectory and the vertical coordinate trajectory of the obstacle according to the horizontal coordinate position sequence and the vertical coordinate position sequence, to obtain a function relationship between the horizontal coordinate of the center point of the dynamic obstacle and time, that is, the horizontal coordinate trajectory fitting formula is as follows:

[0100] X=a x T 3 +b x T 2 +c x T+d x

[0101] A function relationship between the vertical coordinate of the center point of the dynamic obstacle and time is obtained, that is, the vertical coordinate trajectory fitting formula is as follows:

[0102] Y=a y T 3 +b y T 2 +c y T+d y

[0103] Step 104, obtaining a predicted moving speed of the dynamic obstacle according to the trajectory fitting formula.

[0104] In some possible embodiments, as shown in Figure 7 Step 104 specifically includes:

[0105] Step 1041, obtaining a predicted horizontal coordinate moving speed of the dynamic obstacle according to the horizontal coordinate trajectory fitting formula.

[0106] Step 1042, obtaining a predicted vertical coordinate moving speed of the dynamic obstacle according to the vertical coordinate trajectory fitting formula.

[0107] Step 1043, obtaining the predicted moving speed of the dynamic obstacle according to the predicted horizontal coordinate moving speed and the predicted vertical coordinate moving speed.

[0108] For example, the time after one second is brought into the horizontal coordinate trajectory fitting formula and the vertical coordinate trajectory fitting formula for calculation, so that the coordinates of the center point of the obstacle one second after the current time can be obtained, and by calculating the position deviation of the center point of the obstacle within 1 second, the predicted horizontal coordinate moving speed and the predicted vertical coordinate moving speed of the dynamic obstacle can be calculated as follows:

[0109]

[0110]

[0111] The predicted horizontal coordinate moving speed and the predicted vertical coordinate moving speed are synthesized, so that the speed of the dynamic obstacle can be obtained as follows:

[0112]

[0113] The embodiment of the application adopts a 16-line laser radar as an environment sensor, reduces the dependence of the vehicle on the camera, and reduces the manufacturing cost of the vehicle; no multi-sensor fusion calibration is needed, which accelerates the manufacturing and modification speed of the vehicle; the environmental adaptability of the vehicle is improved, and the problem that the vehicle cannot be used due to sensor failure is reduced; only laser radar data is used for obstacle speed prediction and sensing, and the calculation load of the unmanned flow system master chip is small.

[0114] The embodiment of the application performs basic point cloud clustering and tracking operations on the detected obstacle point cloud; stores the detected obstacle information; removes bad points from the historical trajectory points of the obstacle; fits the obstacle trajectory points, judges the fitting effect; obtains the final motion trend of the vehicle according to the fitting effect, obtains the vehicle speed, reduces the calculation pressure of the vehicle control system, and reduces the manufacturing and procurement cost of the central controller. The historical trajectory point record fitting of the obstacle is performed, the position information of the historical trajectory of the obstacle is considered, the obstacle speed and position estimation can be filtered and corrected, and the obstacle speed estimation accuracy is improved. The use of the vehicle-mounted camera is cancelled, the system calculation load is reduced, the program running efficiency is improved while the accuracy is reached.

[0115] The technical scheme of the speed prediction method provided in the embodiment of the application comprises: obtaining a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system; obtaining a second coordinate set according to the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system; obtaining a trajectory fitting formula of the center point of a dynamic obstacle in the at least one obstacle according to the second coordinate set; and obtaining a predicted moving speed of the dynamic obstacle according to the trajectory fitting formula, so that the vehicle detects the obstacle with high precision and low cost.

[0116] Figure 8 As shown in a structural schematic diagram of a speed prediction device provided for an embodiment of the application, Figure 8 the device comprises an acquisition module 41, a conversion module 42, a trajectory fitting module 43 and a prediction module 44.

[0117] The acquisition module 41 is configured to obtain a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system.

[0118] The conversion module 42 is configured to obtain a second coordinate set according to the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system.

[0119] The trajectory fitting module 43 is configured to obtain a trajectory fitting formula of a center point of a dynamic obstacle in the at least one obstacle according to the second coordinate set.

[0120] The prediction module 44 is configured to obtain a predicted moving speed of the dynamic obstacle according to the trajectory fitting formula.

[0121] Optionally, the environmental sensor is a single laser radar.

[0122] Optionally, the trajectory fitting module 43 is specifically configured to obtain a third coordinate set comprising second coordinates of the dynamic obstacle in the at least one obstacle according to the second coordinate set and the characteristic of adjacent position points being undirected, obtain a target position sequence of the dynamic obstacle according to a filtering condition and the third coordinate set, and obtain the trajectory fitting formula according to the target position sequence.

[0123] Optionally, the trajectory fitting module 43 is specifically configured to determine a dynamic and static attribute of the at least one obstacle according to the second coordinate set and the characteristic of the adjacent position point being non-directional; filter the second coordinate of the obstacle with the dynamic and static attribute being static in the second coordinate set to obtain the third coordinate set.

[0124] Optionally, the trajectory fitting module 43 is specifically configured to obtain a first position sequence of the dynamic obstacle according to the third coordinate set, the first position sequence including a horizontal coordinate position sequence and a vertical coordinate position sequence in the third coordinate set; obtain the filtering condition according to the first position sequence and a 3σ method; filter the horizontal coordinate position sequence and the vertical coordinate position sequence according to the filtering condition to obtain a target position sequence, the target position sequence including a target horizontal coordinate position sequence and a target vertical coordinate position sequence.

[0125] Optionally, the trajectory fitting module 43 is specifically configured to obtain a horizontal coordinate trajectory fitting formula of a center point of the dynamic obstacle according to the target horizontal coordinate position sequence; obtain a vertical coordinate trajectory fitting formula of the center point of the dynamic obstacle according to the target vertical coordinate position sequence.

[0126] Optionally, the prediction module 44 is specifically configured to obtain a predicted horizontal coordinate moving speed of the dynamic obstacle according to the horizontal coordinate trajectory fitting formula; obtain a predicted vertical coordinate moving speed of the dynamic obstacle according to the vertical coordinate trajectory fitting formula; and obtain a predicted moving speed of the dynamic obstacle according to the predicted horizontal coordinate moving speed and the predicted vertical coordinate moving speed.

[0127] The speed prediction device provided by the embodiment of the application can be used to implement the speed prediction method described above. Figures 1 to 2 The speed prediction device provided by the embodiment of the application can be used to implement the speed prediction method described above.

[0128] In the technical scheme of the speed prediction device provided by the embodiment of the application, the first coordinate set of the at least one obstacle is obtained, the first coordinate set including a first coordinate of a historical trajectory point of a center point of the at least one obstacle detected by an environmental sensor of the vehicle in a first coordinate system; the second coordinate set is obtained according to the first coordinate set, the second coordinate set including a second coordinate of the historical trajectory point of the center point of the at least one obstacle in a second coordinate system; the trajectory fitting formula of the center point of the dynamic obstacle in the at least one obstacle is obtained according to the second coordinate set; and the predicted moving speed of the dynamic obstacle is obtained according to the trajectory fitting formula, so that the vehicle can detect the obstacle with high precision and low cost.

[0129] Figure 9A schematic diagram of an electronic device according to an embodiment of the present application is shown in Figure 9 The electronic device can include at least one processor and at least one memory communicatively connected with the processor, wherein the memory stores program instructions executable by the processor, and the processor invokes the program instructions to perform the functions of the embodiments of the present application. Figures 1 to 7 The speed prediction method according to the embodiment shown in

[0130] Figure 9 A block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present application is shown. Figure 9 The electronic device shown is merely an example and should not limit the function and scope of use of the embodiments of the present application.

[0131] As shown in Figure 9 The electronic device is in the form of a general purpose computing device. The components of the electronic device can include, but are not limited to, one or more processors 21, a memory 23, and a communication bus 24 connecting the different system components, including the memory 23 and the processing unit 21.

[0132] The communication bus 24 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures including Industry Standard Architecture (ISA), Micro Channel Architecture (MCA), Enhanced ISA (EISA), Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0133] The electronic device typically includes a variety of computer system readable media. These media can be any available media that is accessible by the electronic device and includes both volatile and non-volatile media, removable and non-removable media.

[0134] The memory 23 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device can further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 23 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the present disclosure.

[0135] Program / utility, having a set (at least one) of program modules, can be stored in memory 23, for example, include an operating system, one or more application programs, other program modules, and program data, each or some combination thereof, can include implementation of the network environment. The program modules are generally executed by the processor 21 to implement the functions and / or method of embodiments described herein.

[0136] The processor 21 performs various function applications and data processing by running programs stored in the memory 23, for example, to implement embodiments of the present disclosure Figures 1 to 7 The speed prediction method provided by the embodiment.

[0137] The embodiment of the present disclosure provides a non-transitory computer readable storage medium storing computer instructions, the computer instructions causing the computer to perform the speed prediction method of the embodiment of the present disclosure. Figures 1 to 7 The speed prediction method provided by the embodiment.

[0138] The non-transitory computer readable storage medium described above can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, be but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, 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 above. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0139] Computer readable signal media can include a propagated data signal with computer readable program code embodied therein. For example, a propagated signal can be an electromagnetic signal, an optical signal, and / or any other suitable type of signal. Such a propagated signal can carry computer readable program code in the form of electrical signals, optical signals, and / or magnetic

[0140] A computer readable medium storing the program code can be any medium, including but not limited to, volatile, non-volatile, removable, non-removable, and / or non-tangible media.

[0141] Computer program code for carrying out operations of the present specification can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0142] The specific embodiments of the present specification have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the process depicted in the figures does not necessarily require the particular order shown or sequential order to achieve desirable results. In certain implementations, multitasking and parallel processing can be advantageous.

[0143] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the specification. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples, without contradiction.

[0144] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the specification, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0145] Any process or method descriptions in flow charts or described elsewhere herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing specific logic functions (or steps) in the process, and the various embodiments of the specification include alternative implementations of the code in which the order of the steps can be changed, including use of concurrent, distributed, or otherwise parallel processing functions, and the specification's embodiments shall not be construed as limited to the order of the steps described or illustrated unless specifically specified.

[0146] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to the determination" or "in response to the detection." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon it being determined" or "upon detecting [the stated condition or event]" or "in response to determining" or "in response to detecting [the stated condition or event]."

[0147] It should be noted that the terminal involved in the embodiments of the specification can include, but is not limited to, a personal computer (Personal Computer; hereinafter referred to as PC), a personal digital assistant (Personal Digital Assistant; hereinafter referred to as PDA), a wireless handheld device, a tablet computer, a mobile phone, an MP3 player, an MP4 player, etc.

[0148] In several embodiments provided in the present specification, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0149] In addition, each function unit in the various embodiments of the present specification can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware, or in the form of hardware plus software function units.

[0150] The integrated unit implemented in the form of software function units can be stored in a computer readable storage medium. The software function unit stored in the storage medium includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in the various embodiments of the present specification. The aforementioned storage medium includes a variety of media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0151] The above merely provides the preferred embodiments of the present specification, but is not intended to limit the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the protection scope of the present specification.

Claims

1. A speed prediction method characterized by, The method comprises: obtaining a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system; obtaining a second coordinate set from the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system; obtaining a trajectory fitting formula of the center point of a dynamic obstacle in the at least one obstacle from the second coordinate set; obtaining a predicted moving speed of the dynamic obstacle from the trajectory fitting formula; the obtaining of the trajectory fitting formula of the center point of the dynamic obstacle in the at least one obstacle from the second coordinate set comprises: obtaining a third coordinate set from the second coordinate set and a characteristic of adjacent position points being undirected, the third coordinate set comprising second coordinates of the dynamic obstacle in the at least one obstacle; obtaining a target position sequence of the dynamic obstacle from a filtering condition and the third coordinate set; obtaining the trajectory fitting formula from the target position sequence; the obtaining of the target position sequence of the dynamic obstacle from the filtering condition and the third coordinate set comprises: obtaining a first position sequence of the dynamic obstacle from the third coordinate set, the first position sequence comprising a horizontal coordinate position sequence and a vertical coordinate position sequence in the third coordinate set; obtaining the filtering condition from the first position sequence and a 3σ method; filtering the horizontal coordinate position sequence and the vertical coordinate position sequence according to the filtering condition to obtain a target position sequence, the target position sequence comprising a target horizontal coordinate position sequence and a target vertical coordinate position sequence; the obtaining of the trajectory fitting formula from the target position sequence comprises: obtaining a horizontal coordinate trajectory fitting formula of the center point of the dynamic obstacle from the target horizontal coordinate position sequence; obtaining a vertical coordinate trajectory fitting formula of the center point of the dynamic obstacle from the target vertical coordinate position sequence.

2. The method of claim 1, wherein, The environmental sensor is a single laser radar.

3. The method of claim 1, wherein, the obtaining of the third coordinate set from the second coordinate set and the characteristic of adjacent position points being undirected comprises: determining a dynamic and static attribute of the at least one obstacle from the second coordinate set and the characteristic of adjacent position points being undirected; filtering second coordinates of an obstacle with a static attribute in the second coordinate set to obtain the third coordinate set.

4. The method of claim 1, wherein, the obtaining of the predicted moving speed of the dynamic obstacle from the trajectory fitting formula comprises: obtaining a predicted horizontal coordinate moving speed of the dynamic obstacle from the horizontal coordinate trajectory fitting formula; obtaining a predicted vertical coordinate moving speed of the dynamic obstacle from the vertical coordinate trajectory fitting formula; obtaining the predicted moving speed of the dynamic obstacle from the predicted horizontal coordinate moving speed and the predicted vertical coordinate moving speed.

5. A speed prediction device characterized by comprising: The device comprises: The acquisition module is configured to acquire a first coordinate set of at least one obstacle, the first coordinate set comprising first coordinates of historical trajectory points of a center point of the at least one obstacle detected by an environmental sensor of a vehicle in a first coordinate system; The conversion module is configured to obtain a second coordinate set from the first coordinate set, the second coordinate set comprising second coordinates of the historical trajectory points of the center point of the at least one obstacle in a second coordinate system; The trajectory fitting module is configured to obtain a trajectory fitting formula of the center point of a dynamic obstacle in the at least one obstacle from the second coordinate set; The prediction module is configured to obtain a predicted moving speed of the dynamic obstacle from the trajectory fitting formula; The trajectory fitting module is specifically configured to obtain a third coordinate set comprising second coordinates of the dynamic obstacle in the at least one obstacle from the second coordinate set and a characteristic of adjacent position points being undirected, obtain a target position sequence of the dynamic obstacle from a filtering condition and the third coordinate set, and obtain the trajectory fitting formula from the target position sequence. The trajectory fitting module is specifically configured to obtain a first position sequence of the dynamic obstacle from the third coordinate set, the first position sequence comprising a horizontal coordinate position sequence and a vertical coordinate position sequence in the third coordinate set, obtain the filtering condition from the first position sequence and a 3σ method, filter the horizontal coordinate position sequence and the vertical coordinate position sequence according to the filtering condition to obtain a target position sequence, and the target position sequence comprises a target horizontal coordinate position sequence and a target vertical coordinate position sequence. The trajectory fitting module is specifically configured to obtain a horizontal coordinate trajectory fitting formula of the center point of the dynamic obstacle from the target horizontal coordinate position sequence, and obtain a vertical coordinate trajectory fitting formula of the center point of the dynamic obstacle from the target vertical coordinate position sequence.

6. A storage medium, characterized by The storage medium comprises a stored program, wherein the program controls a device where the storage medium is located to execute the method in any one of claims 1-4 when the program is running.

7. An electronic device comprising a memory for storing information including program instructions, and a processor for controlling execution of the program instructions, characterized in that, The program instructions are loaded and executed by the processor to implement the steps of the method in any one of claims 1-4.

Images