Vehicle route planning method and device, electronic equipment and storage medium

Abstract

The invention discloses a vehicle route planning method and device, electronic equipment and a storage medium. The vehicle route planning method comprises the steps of collecting environment information of a target vehicle in a current driving scene; the environment information comprises object point cloud data and road data information; based on the object point cloud data, environment objects in the current driving scene are identified, and candidate obstacles are determined from the environment objects; obstacle avoidance detection is carried out on the candidate obstacle, an obstacle avoidance detection result is generated, and the obstacle avoidance detection result comprises the target obstacle; and generating a target driving route corresponding to the target vehicle based on the target obstacle and the road data information. Through the technical characteristics, the accuracy of target vehicle driving route planning can be improved, and the driving safety of the target vehicle is further improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and specifically to a vehicle route planning method, device, electronic device, and storage medium. Background Art

[0002] Due to its large size, large vehicles have many blind spots. Among large vehicles, mining transport trucks need to frequently travel back and forth between loading points, transport roads, and unloading points in complex mining environments. Therefore, while mining transport trucks have blind spots, they also face complex driving scenarios.

[0003] Traditional route planning for mining trucks mostly relies on preset fixed paths and lacks the ability of real-time environmental perception and dynamic adjustment. In recent years, with the application of driverless technology in the mining field, mining transport trucks have begun to be equipped with various sensors, such as lidar, cameras, millimeter-wave radars, etc. to achieve the perception of the surrounding environment and combine algorithms for path planning.

[0004] However, in practical applications, there are still some problems. For example, in complex road structures and multi-truck operation scenarios, there are conflicts in driving trajectories, resulting in problems such as untimely and inaccurate updates of the driving paths of mining transport trucks during operation. Summary of the Invention

[0005] In view of the above-mentioned defects of the prior art, the technical problem to be solved by this application is how to improve the accuracy of the driving route planning of the target vehicle.

[0006] To solve at least one of the above-mentioned technical problems, this application discloses a vehicle route planning method, device, electronic device, and storage medium.

[0007] According to one aspect of this application, a vehicle route planning method is provided, including:

[0008] Collect environmental information of the target vehicle in the current driving scenario; the environmental information includes object point cloud data and road data information;

[0009] Based on the object point cloud data, identify environmental objects in the current driving scenario and determine candidate obstacles from the environmental objects;

[0010] Perform obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result, and the obstacle avoidance detection result includes target obstacles;

[0011] Based on the target obstacles and the road data information, generate a target driving route corresponding to the target vehicle.

[0012] Optionally, the environmental information is collected by an ultra-wide-angle image capture device, and vehicle information parameters correspond to the target vehicle;

[0013] The ultra-wide-angle image capture device is located on the target vehicle, and the installation position of the ultra-wide-angle image capture device on the target vehicle is determined based on the vehicle information parameters.

[0014] Optionally, before determining candidate obstacles from the environmental objects, the method further includes:

[0015] Determining the object attributes corresponding to the environmental objects;

[0016] Classifying the environmental objects based on the object attributes to obtain an attribute classification result.

[0017] Optionally, the identifying environmental objects in the current driving scenario based on the object point cloud data and determining candidate obstacles from the environmental objects includes:

[0018] Determining the relative distance information of the environmental objects relative to the target vehicle based on the object point cloud data, and determining the vehicle position information of the target vehicle;

[0019] Determining candidate obstacles from the environmental objects based on the relative distance information, the vehicle position information, the attribute classification result, and a preset distance range.

[0020] Optionally, the performing obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result includes:

[0021] Obtaining the object motion information of the candidate obstacles and the vehicle motion information of the target vehicle, where the object motion information includes the object motion direction and the object motion speed; the vehicle motion information includes the vehicle motion direction and the vehicle motion speed;

[0022] Performing obstacle avoidance detection on the candidate obstacles based on the object motion direction, the object motion speed, the relative distance information, the vehicle motion direction, the vehicle motion speed, and the vehicle position information, and generating the obstacle avoidance detection result.

[0023] Optionally, the method further includes:

[0024] Generating a driving warning instruction when the obstacle avoidance detection result indicates that the distance between the target vehicle and the target obstacle is less than a warning threshold distance;

[0025] Controlling the target vehicle to brake based on the driving warning instruction.

[0026] Optionally, the environmental information further includes a target three-dimensional panoramic image corresponding to the target vehicle;

[0027] Collecting environmental information of the target vehicle in the current driving scenario includes:

[0028] Obtaining multiple driving environmental images of the target vehicle in the current driving scenario; each driving environmental image corresponds to a different image acquisition perspective; each image acquisition perspective corresponds to an ultra-wide-angle image capture device;

[0029] Performing image stitching processing on the multiple driving environmental images to obtain the target three-dimensional panoramic image corresponding to the driving environment of the target vehicle; the target three-dimensional panoramic image does not include the target vehicle.

[0030] Optionally, performing image stitching processing on the multiple driving environmental images to obtain the target three-dimensional panoramic image corresponding to the driving environment of the target vehicle includes:

[0031] Based on object point cloud data, performing stitching processing on the multiple driving environmental images to obtain a candidate three-dimensional panoramic image corresponding to the driving environment of the target vehicle;

[0032] Performing image correction processing on the candidate three-dimensional panoramic image to obtain the target three-dimensional panoramic image.

[0033] According to a second aspect of the present application, there is provided a vehicle route planning device, including:

[0034] An image acquisition module, configured to collect environmental information of the target vehicle in the current driving scenario based on an ultra-wide-angle image capture device; the environmental information includes object point cloud data and road data information;

[0035] An obstacle determination module, configured to identify environmental objects in the current driving scenario based on the object point cloud data, and determine candidate obstacles from the environmental objects;

[0036] An obstacle avoidance detection module, configured to perform obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result, and the obstacle avoidance detection result includes non-obstacles and target obstacles;

[0037] A route planning module, configured to generate a target driving route corresponding to the target vehicle based on the target obstacles and the road data information.

[0038] According to a third aspect of the present application, there is provided an electronic device, which includes a processor and a memory. At least one instruction and at least one program segment are stored in the memory, and the at least one instruction and the at least one program segment are loaded and executed by the processor to implement any one of the above vehicle route planning methods.

[0039] According to a fourth aspect of the present application, there is provided a computer storage medium storing at least one instruction and at least one program segment, and the at least one instruction and the at least one program segment are loaded and executed by a processor to implement the vehicle route planning method as described in any one of the above.

[0040] According to a fifth aspect of the present application, there is provided a computer program product including a computer program / instructions, and when the computer program / instructions are executed by a processor, the vehicle route planning method as described in any one of the above is implemented.

[0041] In the vehicle route planning method according to the embodiments of the present application, environmental information in the current driving scenario is first collected, including object point cloud data and road data information, enabling more refined environmental perception; based on the point cloud data, the system can accurately identify environmental objects and screen out candidate obstacles that may affect vehicle driving from them, improving the accuracy of obstacle recognition. In addition, through obstacle avoidance detection, the target obstacles that truly affect driving safety are further confirmed, avoiding misjudgment or omission, and further improving the accuracy of target obstacle determination. On this basis, by combining the spatial information of the target obstacles with the road data, an optimal driving route is dynamically planned, enabling the vehicle to autonomously adjust the path, thereby improving the accuracy of target driving route planning.

[0042] Other features and advantages of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] In order to more fully understand the present application and its beneficial effects, the following description will be made in conjunction with the drawings, where the same reference numerals represent the same parts in the following description.

[0045] Figure 1 It is a schematic flowchart corresponding to the vehicle route planning method provided by an exemplary embodiment of the present disclosure;

[0046] Figure 2 It is a first schematic diagram of an ultra-wide-angle image capture device provided by an exemplary embodiment of the present disclosure;

[0047] Figure 3 It is a second schematic diagram of an ultra-wide-angle image capture device provided by an exemplary embodiment of the present disclosure;

[0048] Figure 4 Schematic layout diagram of the ultra-wide-angle image capture device provided by an exemplary embodiment of the present disclosure;

[0049] Figure 5 Schematic diagram of the field of view of the ultra-wide-angle image capture device provided by an exemplary embodiment of the present disclosure;

[0050] Figure 6 Schematic structural diagram corresponding to the vehicle route planning device provided by an exemplary embodiment of the present disclosure. Detailed implementation manners

[0051] Next, the technical solutions in the embodiments of this specification will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0052] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order different from those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0053] The following will detail various exemplary embodiments, features, and aspects of the present disclosure with reference to the accompanying drawings. The same reference numerals in the drawings denote elements with the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0054] The special term "exemplary" here means "serving as an example, embodiment, or illustration". Any embodiment described as "exemplary" here does not have to be construed as superior to or better than other embodiments.

[0055] As used herein, the term "and / or" describes the relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the term "at least one" as used herein means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0056] In addition, for a better illustration of the present disclosure, numerous specific details are given in the following detailed implementation manners. Those skilled in the art should understand that the present disclosure can still be implemented without certain specific details. In some instances, methods, means, elements, and circuits well-known to those skilled in the art are not described in detail to highlight the gist of the present disclosure.

[0057] Figure 1 The flowchart corresponding to the vehicle route planning method provided for the exemplary embodiments of the present disclosure. The execution subject can be any terminal capable of executing the vehicle route planning method, such as a server, a vehicle body processor, etc. The method disclosed in the present application can be applied to the route planning of any vehicle. In the embodiments of the present application, a mining haul truck traveling in a mining operation scenario is taken as an example for illustration. As Figure 1 shown, a vehicle route planning method includes:

[0058] Step S1: Collect the environmental information of the target vehicle in the current driving scenario; the environmental information includes object point cloud data and road data information;

[0059] In a specific embodiment, since the target vehicle is a mining haul truck, the current driving scenario can correspond to a mining operation scenario, that is, the collected environmental information can be the environmental information of the mining operation scenario. The environmental information can include object point cloud data and road data information. The object point cloud data can represent the object position information of the environmental objects existing in the current driving scenario, and can also represent the three-dimensional geometric information of the objects, so that the object category and object attributes can be identified according to the three-dimensional geometric information.

[0060] The road data information can include a preset mining truck transportation route and regional location information. For example, the mining operation scenario includes a loading point, a transportation road, and an unloading point. Then the preset mining truck transportation route can be a fixed driving route of the vehicle including the loading point, the transportation road, and the unloading point. The regional location information can be the position information corresponding to the loading point, the transportation road, and the unloading point respectively. The road data information can also include the historical driving route planned at a historical moment, so that the driving route of the target vehicle at the next moment, that is, the target driving route, can be dynamically adjusted according to the historical driving route and the object point cloud data.

[0061] Specifically, the environmental information can be collected by an ultra-wide-angle image capture device. The settings of the ultra-wide-angle image capture device can ensure high-precision 3D visual perception of the external environment of the target vehicle, so as to improve the accuracy and comprehensiveness of image acquisition.

[0062] The ultra-wide-angle image capture device can be obtained by splicing and installing multiple binocular cameras. As Figure 2 and Figure 3 shown, for example, two binocular cameras are spliced and installed to expand the field of view angle of the ultra-wide-angle image capture device. In addition, a glass cover can be sleeved outside the lens of the ultra-wide-angle image capture device to protect the lens and prevent it from being damaged in the mining operation scenario. Moreover, a rolling brush and a nozzle are correspondingly arranged with the glass cover to regularly clean the dust on the glass cover and avoid the influence of excessive dust on the image acquisition ability of the ultra-wide-angle image capture device. In addition, a support is also arranged at the splicing place of the binocular cameras so that the binocular cameras can be stably installed on the target vehicle. That is, the ultra-wide-angle capture device in this embodiment can have a wide field of view, can collect the 360° driving scene corresponding to the target vehicle in real time, so that there is no blind spot in the field of view, and can work stably in the harsh mining operation scenario.

[0063] In a specific embodiment, Table 1 shows the parameters of the ultra-wide-angle image capture device, and the relevant parameters are an exemplary description. As shown in Table 1, the ultra-wide-angle image capture device has characteristics such as high resolution, wide field of view angle, depth perception, and can adapt to harsh environments, so as to ensure the reliability and accuracy of the collection of environmental information.

[0064] Table 1: Parameters of the ultra-wide-angle image capture device

[0065] Parameter Parameter Dimension 468mm * 213mm * 88mm Focal length 2.2mm Weight 15kg Ranging range 0.3～20m Operating temperature -10℃～+55℃ Ranging accuracy 0.1％～3％ Connection method Ethernet Dustproof Equipped with self - cleaning structure Resolution 1920x1200 Anti - shake Equipped with anti - vibration housing Field of view Max.200°(H)x 80°(V)

[0066] The target vehicle corresponds to vehicle information parameters; the ultra-wide-angle image capture device is located on the target vehicle, and the installation position of the ultra-wide-angle image capture device on the target vehicle is determined based on the vehicle information parameters.

[0067] In a specific embodiment, for the target vehicle, that is, for a mining transport truck, multiple ultra-wide-angle image capture devices can be installed, for example, 4 ultra-wide-angle image capture devices can be installed to achieve a full-range scan of the current driving scene and generate a 360° blind-spot-free target three-dimensional panoramic image in real time.

[0068] For the installation position of the ultra-wide-angle image capture device, it can be determined according to the vehicle information parameters of the target vehicle to ensure that the target vehicle can achieve a non-blind-spot monitoring of its surrounding environment during operation, while avoiding excessive visual overlap between cameras. Among them, the vehicle information parameters can include information such as vehicle length, vehicle height, and blind spot positions. For example, during the driving process of the target vehicle, the front and rear views are crucial. Therefore, the ultra-wide-angle image capture device should be installed at a position where it can completely collect the environmental information of the front and rear parts of the target vehicle to ensure clear views when the target vehicle moves forward and backward. In addition, the target vehicle is relatively large in size and has large blind spots on both sides. Especially when the target vehicle turns or parks, the side blind spots are likely to cause accidents. Therefore, ultra-wide-angle image capture devices should be installed on the left and right sides of the target vehicle to ensure full coverage of the vehicle's side area, thereby eliminating the obstruction of the driver's line of sight by the vehicle compartment of the target vehicle.

[0069] In addition, the installation angle of the ultra-wide-angle image capture device directly affects the field of view and perception effect. The ultra-wide-angle image capture device should be installed at a relatively high position from the ground to ensure that it can overlook the obstacles in front of and behind the target vehicle; the ultra-wide-angle image capture devices on both sides of the target vehicle should be adjusted according to the vehicle length to ensure that the viewing angles of the ultra-wide-angle image capture devices can cover the ground area around the target vehicle.

[0070] As Figure 4 shown, in a specific embodiment, the number of ultra-wide-angle image capture devices can be 4, and an edge computing device is simultaneously equipped to cooperate with the ultra-wide-angle image capture device for image processing. The 4 ultra-wide-angle image capture devices can be located on the left and right sides of the target vehicle respectively, and at the same time, their field of view angles can ensure that the 4 ultra-wide-angle image capture devices can obtain the environmental information of 360° full coverage around the target vehicle.

[0071] As Figure 5 shown, in a specific embodiment, the number of ultra-wide-angle image capture devices can be 4, which can be located in front of and behind the target vehicle, as well as on the left and right sides of the target vehicle, so that their field of view angles can ensure that the 4 ultra-wide-angle image capture devices can obtain the environmental information of 360° full coverage around the target vehicle.

[0072] Specifically, the environmental information also includes the target three-dimensional panoramic image corresponding to the target vehicle, and the target three-dimensional panoramic image can represent the 360° surrounding environment without blind spots of the target vehicle in the current driving scenario.

[0073] Collecting environmental information through step S1 includes:

[0074] Step S11: Obtain multiple driving environment images of the target vehicle in the current driving scenario; each driving environment image corresponds to a different image acquisition perspective; each image acquisition perspective corresponds to an ultra-wide-angle image capture device.

[0075] Step S12: Perform image stitching on the multiple driving environment images to obtain a target three-dimensional panoramic image corresponding to the driving environment of the target vehicle; when the target three-dimensional panoramic image is an image from the first perspective, it does not include the target vehicle.

[0076] In a specific embodiment, it can be considered that the perspective from which the driver directly observes the driving environment is the first perspective, and the image acquisition perspective corresponding to the ultra-wide-angle image capture device is the second perspective. The target three-dimensional panoramic image after image stitching is a second-perspective panoramic image that does not include the target vehicle.

[0077] The ultra-wide-angle image capture device can obtain the environmental information of the target vehicle in the current driving scenario from different image acquisition perspectives, obtain multiple driving environment images corresponding to the current driving scenario, and then perform image stitching on the multiple driving environment images based on the image stitching processing algorithm to obtain the target three-dimensional panoramic image, which can improve the comprehensiveness of environmental information acquisition.

[0078] Specifically, obtaining the target three-dimensional panoramic image through step S12 includes:

[0079] Step S13: Based on the object point cloud data, perform image stitching on the multiple driving environment images to obtain a candidate three-dimensional panoramic image corresponding to the driving environment of the target vehicle;

[0080] Step S14: Perform image correction processing on the candidate three-dimensional panoramic image to obtain the target three-dimensional panoramic image.

[0081] In a specific embodiment, the image stitching processing includes point cloud data processing and two-dimensional image data processing. The candidate three-dimensional panoramic image can be generated by performing image stitching according to the object point cloud data and the two-dimensional image data corresponding to each driving environment image. The driving environment images are obtained by ultra-wide-angle image capture devices at different image acquisition perspectives. Among them, the object point cloud data includes the three-dimensional data information of environmental objects. The candidate three-dimensional panoramic image can be obtained by performing stitching processing based on the three-dimensional data information of each environmental object in different driving environment images and in cooperation with the two-dimensional image data. Implementing image stitching between driving environment images by combining object point cloud data can reduce the distortion and aberration of the stitched candidate three-dimensional panoramic image, thereby improving the accuracy of the candidate three-dimensional panoramic image. Further, due to the good accuracy of the candidate three-dimensional panoramic image, it can also improve the accuracy during subsequent obstacle detection to ensure the safety of vehicle driving.

[0082] Through the coordinated work of multiple ultra-wide-angle image capture devices, after image stitching processing of multiple driving environment images, a candidate three-dimensional panoramic image is first obtained. Since there may be image distortion during the image stitching process, and there may be situations such as uneven illumination and image color difference in the driving environment images, the stitched candidate three-dimensional panoramic image can be subjected to image correction processing to obtain a target three-dimensional panoramic image, thereby reducing image distortion and errors caused by image stitching processing, and further improving the accuracy of the target three-dimensional panoramic image.

[0083] In another specific embodiment, multiple ultra-wide-angle image capture devices can also cooperate with edge computing devices to process multiple driving environment images to obtain a target three-dimensional panoramic image.

[0084] Step S2: Based on the object point cloud data, identify the environmental objects in the current driving scene, and determine candidate obstacles from the environmental objects;

[0085] In a specific embodiment, since the object point cloud data can represent the object position information and three-dimensional geometric information of the object, therefore, according to the object point cloud data, candidate obstacles can be determined from the environmental objects identified in the current driving scene. Among them, the candidate obstacles are environmental objects that affect the safe driving of the target vehicle or have the possibility of affecting the safe driving of the target vehicle.

[0086] Before determining the candidate obstacles from the environmental objects, the method further includes:

[0087] Determine the object attributes corresponding to the environmental objects;

[0088] Based on the object attributes, classify the environmental objects to obtain an attribute classification result.

[0089] In a specific embodiment, the object attributes may include static objects and dynamic objects. Since the static objects and dynamic objects have different impacts on the driving safety of the target vehicle, therefore, before determining the candidate obstacles from the environmental objects, the object attributes corresponding to the environmental objects included in the environmental information can be determined first.

[0090] Specifically, the environmental objects can be identified by combining the three-dimensional geometric information of each environmental object, so as to determine the object attributes of the environmental objects according to the identification results. For example, when the identification result obtained after identifying the three-dimensional geometric information of an environmental object is a road sign, the attribute classification result of the environmental object is determined to be a static object; when the identification result obtained after identifying the three-dimensional geometric information of an environmental object is another vehicle, the attribute classification result of the environmental object is determined to be a dynamic object.

[0091] In addition, when the target vehicle is equipped with a car machine display screen, the attribute classification result can be sent to the car machine display screen, enabling the driver to accurately and real-time understand the environmental information in the current driving scenario.

[0092] Moreover, clustering analysis can be performed on the object point cloud data, and the object point cloud data with the same or similar depth can be regarded as components of the same environmental object.

[0093] Before determining the candidate obstacles, first determine the object attributes of the environmental objects, so as to avoid misidentifying or misjudging obstacles in complex or uncertain environments, reduce mis-collisions or wrong decisions, and improve the driving safety of the vehicle.

[0094] Based on the object point cloud data, identify the environmental objects in the current driving scenario, and determine candidate obstacles from the environmental objects, including:

[0095] Determine the relative distance information of the environmental objects relative to the target vehicle based on the object point cloud data, and determine the vehicle position information of the target vehicle;

[0096] Determine candidate obstacles from the environmental objects based on the relative distance information, vehicle position information, attribute classification result, and preset distance range.

[0097] In a specific embodiment, the preset distance range can be determined based on the preset mining truck transportation route and the specific situation of the current driving scenario. For example, when there are many mining transport trucks operating in the mining area operation scenario, a larger preset distance range can be set to ensure the safety of multiple vehicles driving.

[0098] Specifically, the relative distance information between the environmental object and the target vehicle can be determined by combining the object position information of the environmental object and the vehicle position information of the target vehicle; further, determine whether the environmental object is an obstacle by combining the object attribute of the environmental object, the preset distance range, and the relative distance information. For example, when the object attribute of the environmental object is a static object and the relative distance information is greater than the preset distance range, the environmental object will not become a candidate obstacle at this time; when the object attribute of the environmental object is a static object and the relative distance information is less than the preset distance range, it can be considered that the environmental object is located on the preset mining truck transportation route corresponding to the target vehicle, and the environmental object becomes a candidate obstacle; when the environmental object is a dynamic object, it is determined that the environmental object becomes a candidate obstacle.

[0099] Step S3: Perform obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result, and the obstacle avoidance detection result includes the target obstacle;

[0100] In a specific embodiment, the candidate obstacle does not necessarily affect the normal driving of the target vehicle. Therefore, in order to avoid misjudgment of the obstacle during the driving of the target vehicle, reduce the number of changes in the driving route of the target vehicle, and ensure the stability and safety of the driving of the target vehicle, obstacle avoidance detection can be performed on the candidate obstacle, and then the driving route of the target vehicle can be adjusted according to the obstacle avoidance detection result to obtain the target driving route.

[0101] Perform obstacle avoidance detection on the candidate obstacle to generate an obstacle avoidance detection result, including:

[0102] Obtain the object motion information of the candidate obstacle and the vehicle motion information of the target vehicle. The object motion information includes the object motion direction and the object motion speed; the vehicle motion information includes the vehicle motion direction and the vehicle motion speed;

[0103] Based on the object motion direction, the object motion speed, the relative distance information, the vehicle motion direction, the vehicle motion speed, and the vehicle position information, perform obstacle avoidance detection on the candidate obstacle and generate an obstacle avoidance detection result.

[0104] In a specific embodiment, among the candidate obstacles, there are dynamic environmental objects and static environmental objects located on the preset mining truck transportation route. First, perform obstacle avoidance detection on the dynamic environmental objects among the candidate obstacles. Specifically, the map data corresponding to the current driving scenario can be generated according to the road data information first, and the map data can be updated in real time in combination with the ultra-wide-angle image capture device.

[0105] Furthermore, calculations are performed in combination with the object motion direction, the object motion speed, the relative distance information, the vehicle motion direction, the vehicle motion speed, and the vehicle position information to determine whether the dynamic environmental object is still within the preset distance range when the target vehicle continues to drive along the preset mining truck transportation route, and an obstacle avoidance detection result is generated. Among them, the obstacle avoidance detection result is used to indicate whether the candidate obstacle is a target obstacle and to characterize whether the distance between the target vehicle and the target obstacle is less than the preset distance range.

[0106] In the case where the obstacle avoidance detection result indicates that the distance between the target vehicle and the target obstacle is less than the warning threshold distance, a driving warning instruction is generated;

[0107] Based on the driving warning instruction, control the target vehicle to brake.

[0108] In a specific embodiment, the warning threshold distance is the relative distance between the target vehicle and the target obstacle when the target vehicle cannot change its driving route in time. When the distance between the target vehicle and the target obstacle is less than or equal to the warning threshold distance, a driving warning instruction is generated, and the driving warning instruction is transmitted to the driver in the form of voice prompt through the in-vehicle speaker, and / or the driving warning instruction is transmitted to the driver in the form of multimedia prompt through the vehicle-mounted display screen. At the same time, the target vehicle is controlled to brake according to the driving warning instruction to avoid the collision risk between the target vehicle and other objects when the driving route is inaccurate, and improve the driving safety of the target vehicle.

[0109] Step S4: Generate a target driving route corresponding to the target vehicle based on the target obstacle and the road data information.

[0110] In a specific embodiment, when the distance between the target vehicle and the target obstacle is greater than the warning threshold distance, at this time, the driving route of the target vehicle can be updated in real time according to the target obstacle and the road data information, combined with the vehicle position information and the vehicle movement information, to obtain the target driving route.

[0111] During the driving process of the target vehicle, when there is a target obstacle affecting the target vehicle from driving along the driving route, dynamic obstacle avoidance can be achieved through the above technical features, and the target driving route can be re-planned in combination with the movement trajectory of the dynamic target obstacle to ensure the safe operation of the target vehicle. In addition, the target driving route can meet the optimal operation requirements, so as to improve the operation efficiency of the target vehicle while ensuring safety.

[0112] Correspondingly, the technical solution of the present application also discloses a vehicle route planning device, as Figure 6 shown, the vehicle route planning device includes:

[0113] An image acquisition module 610, configured to collect environmental information of the target vehicle in the current driving scene based on an ultra-wide-angle image capture device; the environmental information includes object point cloud data and road data information;

[0114] An obstacle determination module 620, configured to identify environmental objects in the current driving scene based on the object point cloud data, and determine candidate obstacles from the environmental objects;

[0115] An obstacle avoidance detection module 630, configured to perform obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result, and the obstacle avoidance detection result includes non-obstacles and target obstacles;

[0116] A route planning module 640, configured to generate a target driving route corresponding to the target vehicle based on the target obstacle and the road data information.

[0117] In some exemplary embodiments, the vehicle route planning device further includes:

[0118] An attribute determination module, configured to determine the object attribute corresponding to the environmental object;

[0119] An object classification module, configured to perform attribute classification on the environmental object based on the object attribute to obtain an attribute classification result.

[0120] In some exemplary embodiments, the obstacle determination module 620 includes:

[0121] A first information determination module, configured to determine the relative distance information of the environmental object relative to the target vehicle based on the object point cloud data, and determine the vehicle position information of the target vehicle;

[0122] An object screening module, configured to determine candidate obstacles from the environmental objects based on the relative distance information, the vehicle position information, the attribute classification result, and a preset distance range.

[0123] In some exemplary embodiments, the obstacle avoidance detection module 630 includes:

[0124] A second information determination module, configured to obtain the object motion information of the candidate obstacle and the vehicle motion information of the target vehicle, where the object motion information includes the object motion direction and the object motion speed; the vehicle motion information includes the vehicle motion direction and the vehicle motion speed;

[0125] An object detection module, configured to perform obstacle avoidance detection on the candidate obstacle based on the object motion direction, the object motion speed, the relative distance information, the vehicle motion direction, the vehicle motion speed, and the vehicle position information, and generate an obstacle avoidance detection result.

[0126] In some exemplary embodiments, the vehicle route planning device further includes:

[0127] A driving warning module, configured to generate a driving warning instruction when the obstacle avoidance detection result indicates that the distance between the target vehicle and the target obstacle is less than the preset distance range;

[0128] A vehicle control module, configured to control the target vehicle to brake based on the driving warning instruction.

[0129] In some exemplary embodiments, the image acquisition module 610 includes:

[0130] An image acquisition module, configured to acquire multiple driving environment images of the target vehicle in the current driving scenario; each driving environment image corresponds to a different image acquisition perspective;

[0131] An image stitching module, configured to perform image stitching processing on multiple driving environment images to obtain a target three-dimensional panoramic image corresponding to the driving environment of the target vehicle.

[0132] In some exemplary embodiments, the image stitching module includes:

[0133] A candidate image module, configured to perform image stitching processing on multiple driving environment images to obtain a candidate three-dimensional panoramic image corresponding to the driving environment of the target vehicle;

[0134] An image correction module, configured to perform image correction processing on the candidate three-dimensional panoramic image to obtain the target three-dimensional panoramic image.

[0135] The device in the device embodiment and the method embodiment are based on the same inventive concept and are used to implement the vehicle route planning method.

[0136] Correspondingly, the technical solution of the present application also discloses an electronic device, which includes a processor and a memory. At least one instruction and at least one program segment are stored in the memory, and the at least one instruction and the at least one program segment are loaded and executed by the processor to implement the vehicle route planning method in any of the above embodiments.

[0137] Correspondingly, the technical solution of the present application also discloses a computer storage medium, in which at least one instruction and at least one program segment are stored, and the at least one instruction and the at least one program segment are loaded and executed by the processor to implement the vehicle route planning method in any of the above embodiments.

[0138] Optionally, in the embodiments of the present application, the above storage medium may be located in at least one of multiple network servers in a computer network. Optionally, in the embodiments of the present application, the above storage medium may include, but is not limited to: USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical disks, etc., various media that can store program codes.

[0139] Correspondingly, the technical solution of the present application also discloses a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the vehicle route planning method in any of the above embodiments is implemented.

[0140] Through the above vehicle route planning method, the environmental information in the current driving scenario is first collected, including object point cloud data and road data information, enabling more refined environmental perception. Based on the point cloud data, the system can accurately identify environmental objects and screen out candidate obstacles that may affect vehicle driving from them, improving the accuracy of obstacle recognition. Additionally, through obstacle avoidance detection, the target obstacles that truly affect driving safety are further confirmed, avoiding misjudgment and omission, and further improving the accuracy of determining target obstacles. On this basis, combining the spatial information of the target obstacles and the road data information, the optimal driving route is dynamically planned, enabling the vehicle to autonomously adjust its path, thereby improving the accuracy of target driving route planning to ensure the safety of the target vehicle's driving.

[0141] In the description of the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more features. In the description of the present application, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0142] In the above embodiments, the descriptions of the various embodiments have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] The embodiments, implementation manners and related technical features of the present application can be combined and replaced with each other without conflict.

[0144] The above are the preferred embodiments of the present application, and there is no restriction on the present application in any form. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application still fall within the scope of the technical solution of the present application. The selection of terms used herein is intended to best explain the principles of each embodiment, practical applications or improvements to the technology in the market, or enable other ordinary technicians in the technical field to understand the embodiments disclosed herein.

Claims

1. A vehicle route planning method, characterized in that, The method includes: Collecting environmental information of a target vehicle in a current driving scenario; the environmental information includes object point cloud data and road data information; Identifying environmental objects in the current driving scenario based on the object point cloud data, and determining candidate obstacles from the environmental objects; Performing obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result, where the obstacle avoidance detection result includes a target obstacle; Generating a target driving route corresponding to the target vehicle based on the target obstacle and the road data information.

2. The vehicle route planning method according to claim 1, characterized in that The environmental information is collected by an ultra-wide-angle image capture device, and the target vehicle corresponds to vehicle information parameters; The ultra-wide-angle image capture device is located on the target vehicle, and the installation position of the ultra-wide-angle image capture device on the target vehicle is determined based on the vehicle information parameters.

3. The vehicle route planning method according to claim 1, wherein, Before determining candidate obstacles from the environmental objects, the method further includes: Determining the object attributes corresponding to the environmental objects; Performing attribute classification on the environmental objects based on the object attributes to obtain an attribute classification result.

4. The vehicle route planning method according to claim 3, characterized in that The step of identifying environmental objects in the current driving scenario based on the object point cloud data and determining candidate obstacles from the environmental objects includes: Determining the relative distance information of the environmental objects with respect to the target vehicle based on the object point cloud data, and determining the vehicle position information of the target vehicle; Determining candidate obstacles from the environmental objects based on the relative distance information, the vehicle position information, the attribute classification result, and a preset distance range.

5. The vehicle route planning method according to claim 4, wherein, The step of performing obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result includes: Obtaining the object motion information of the candidate obstacles and the vehicle motion information of the target vehicle, where the object motion information includes the object motion direction and the object motion speed; the vehicle motion information includes the vehicle motion direction and the vehicle motion speed; Performing obstacle avoidance detection on the candidate obstacles based on the object motion direction, the object motion speed, the relative distance information, the vehicle motion direction, the vehicle motion speed, and the vehicle position information, and generating the obstacle avoidance detection result.

6. The vehicle route planning method according to claim 1, wherein, The method further includes: Generating a driving warning instruction when the obstacle avoidance detection result indicates that the distance between the target vehicle and the target obstacle is less than a warning threshold distance; Controlling the target vehicle to brake based on the driving warning instruction.

7. The vehicle route planning method according to claim 2, wherein The environmental information further includes a target three-dimensional panoramic image corresponding to the target vehicle; The step of collecting environmental information of the target vehicle in the current driving scenario includes: Obtaining multiple driving environment images of the target vehicle in the current driving scenario; each driving environment image corresponds to a different image acquisition perspective; each image acquisition perspective corresponds to one of the ultra-wide-angle image capture devices; Performing image stitching processing on the multiple driving environment images to obtain the target three-dimensional panoramic image corresponding to the driving environment of the target vehicle; the target three-dimensional panoramic image does not include the target vehicle.

8. The vehicle route planning method according to claim 7, characterized in that Performing image stitching processing on the multiple driving environment images to obtain the target three-dimensional panoramic image corresponding to the driving environment of the target vehicle, including: Based on the object point cloud data, performing image stitching processing on the multiple driving environment images to obtain a candidate three-dimensional panoramic image corresponding to the driving environment of the target vehicle; Performing image correction processing on the candidate three-dimensional panoramic image to obtain the target three-dimensional panoramic image.

9. A vehicle route planning device, characterized in that, The device includes: An image acquisition module, configured to collect environmental information of a target vehicle in a current driving scenario based on an ultra-wide-angle image capture device; the environmental information includes object point cloud data and road data information; An obstacle determination module, configured to identify environmental objects in the current driving scenario based on the object point cloud data, and determine candidate obstacles from the environmental objects; An obstacle avoidance detection module, configured to perform obstacle avoidance detection on the candidate obstacles to generate an obstacle avoidance detection result, where the obstacle avoidance detection result includes non-obstacles and target obstacles; A route planning module, configured to generate a target driving route corresponding to the target vehicle based on the target obstacles and the road data information.

10. An electronic device, characterized in that, The device includes a processor and a memory, where at least one instruction and at least one program segment are stored in the memory, and the at least one instruction and the at least one program segment are loaded and executed by the processor to implement the vehicle route planning method according to any one of claims 1-8.

11. A computer storage medium, characterized in that, At least one instruction and at least one program segment are stored in the computer storage medium, and the at least one instruction and the at least one program segment are loaded and executed by a processor to implement the vehicle route planning method according to any one of claims 1-8.

12. A computer program product comprising computer programs / instructions, characterized in that, When the computer program / instructions are executed by a processor, the vehicle route planning method according to any one of claims 1-8 is implemented.

Images