A method, device, equipment and medium for downloading maps of an autonomous driving vehicle

Abstract

The present invention provides a method, device, equipment and medium for downloading maps of an autonomous driving vehicle, and relates to the field of map download technology. The method includes obtaining a target position, a current position and a current driving state of the autonomous driving vehicle; determining a driving route and extracting road data according to the target position and the current position; determining a map download range according to the current vehicle speed and the current acceleration; when there is straight road section data in the map download range, downloading a first high-precision map corresponding to the straight road section data in the map download range; when there is curved road section data in the map download range, downloading a second high-precision map corresponding to the curved road section data in the map download range; obtaining a current image corresponding to the current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map; comparing the current image and the historical image, generating a comparison result, and generating a map modification report according to the comparison result. The present invention can improve the stability of autonomous driving.

Description

Technical Field

[0001] The present invention relates to the field of map downloading technology, and in particular to a method, device, equipment and medium for downloading maps for an autonomous driving vehicle. Background Art

[0002] Autonomous vehicles (AVs) are cars that can drive safely and efficiently on the road without human intervention. In order to achieve autonomous driving, autonomous vehicles first need to collect environmental data through sensors such as cameras or lidar, and then match it with high-precision maps to determine the specific position of the vehicle in the lane, so that the positioning accuracy is higher, such as positioning error as low as centimeters, making autonomous driving more reliable, and further completing autonomous driving.

[0003] However, since high-precision maps are obtained by accurately marking lanes, road-surrounding buildings, traffic lights, etc. in the environment, the storage files of high-precision maps are too large. High-precision maps at the hundred-meter level require storage space in GB. Since the storage space of the vehicle's on-board system is limited, excessively large high-precision map files are generally not stored on the vehicle. Instead, real-time downloading via network communication is used to update high-precision maps during autonomous driving in real time. In the prior art, the method of real-time downloading and updating of high-precision maps is overly dependent on the quality of network communication. When the quality of network communication is poor, the update of the high-precision map may not keep up with the vehicle's driving speed. At this time, the vehicle will exit the autonomous driving mode, resulting in low stability of autonomous driving. Summary of the invention

[0004] The problem solved by the present invention is how to improve the stability of automatic driving.

[0005] To solve the above problems, in a first aspect, the present invention provides a method for downloading a map of an autonomous driving vehicle, comprising:

[0006] Obtaining a target position, a current position, and a current driving state of the autonomous driving vehicle, wherein the current driving state includes a current vehicle speed and a current acceleration;

[0007] Determine a driving route according to the target position and the current position, and extract road data in the driving route, wherein the road data includes straight road segment data and curved road segment data;

[0008] Determining a map download range according to the current vehicle speed and the current acceleration;

[0009] When the straight road segment data exists in the map download range, downloading a first high-precision map corresponding to the straight road segment data in the map download range; when the curved road segment data exists in the map download range, downloading a second high-precision map corresponding to the curved road segment data in the map download range, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map;

[0010] Acquire a current image corresponding to the current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding position are stored in the first high-precision map and the second high-precision map;

[0011] The current image and the historical image are compared to generate a comparison result, and a map modification report is generated according to the comparison result.

[0012] Optionally, determining the map download range according to the current vehicle speed and the current acceleration includes:

[0013] Determining the future vehicle speed and the vehicle arrival position after a preset time according to the current vehicle speed and the current acceleration;

[0014] The map download range is determined according to the future vehicle speed and the vehicle arrival position.

[0015] Optionally, determining the map download range according to the current vehicle speed and the current acceleration includes:

[0016] Determining a speed gear corresponding to the current vehicle speed according to the current vehicle speed and a plurality of preset different speed gears;

[0017] Determining a speed adjustment time according to the speed gear and the current acceleration;

[0018] The time is adjusted according to the speed to determine the map download range.

[0019] Optionally, the comparing the current image with the historical image to generate a comparison result includes:

[0020] Extracting historical features of the historical image and current features of the current image respectively, wherein the historical features include historical angle features and at least one historical descriptor, and the current features include current angle features corresponding to the historical angle features and current descriptors corresponding to the historical descriptors;

[0021] Comparing the historical angle feature with the current angle feature, and comparing the historical descriptor with the current descriptor, to determine similarity;

[0022] The comparison result is generated according to the similarity.

[0023] Optionally, the extracting the historical features of the historical image and the current features of the current image respectively includes:

[0024] The historical angle feature and the current angle feature are extracted respectively by using the grayscale centroid method;

[0025] According to the historical image and the current image, determining historical key point information of the historical image and current key point information of the current image by scale space extreme value detection;

[0026] Respectively determining a historical key point neighborhood of the historical key point information and a current key point neighborhood of the current key point information;

[0027] According to the neighborhood of the historical key point and the neighborhood of the current key point, respectively extracting historical gradient information and current gradient information;

[0028] The historical descriptor and the current descriptor are constructed according to the historical gradient information and the current gradient information.

[0029] Optionally, comparing the historical angle feature with the current angle feature, and comparing the historical descriptor with the current descriptor to determine the similarity includes:

[0030] Comparing the historical angle feature with the current angle feature to generate angle similarity;

[0031] Comparing the Hamming distance between the historical descriptor and the current descriptor to generate description similarity;

[0032] The similarity is generated according to the angle similarity and the description similarity.

[0033] Optionally, after generating a map modification report according to the comparison result, the method further includes:

[0034] Delete the first high-precision map and the second high-precision map of the traveled area.

[0035] In a second aspect, the present invention provides a map downloading device for an autonomous driving vehicle, comprising:

[0036] An acquisition module, used to acquire the target position, current position and current driving state of the autonomous driving vehicle, wherein the current driving state includes the current vehicle speed and current acceleration;

[0037] A route module, used to determine a driving route according to the target location and the current location, and extract road data in the driving route, wherein the road data includes straight road segment data and curved road segment data;

[0038] A range module, configured to determine a map download range according to the current vehicle speed and the current acceleration;

[0039] A map module, configured to download a first high-precision map corresponding to the straight road segment data within the map download range when the straight road segment data exists within the map download range; and download a second high-precision map corresponding to the curved road segment data within the map download range when the curved road segment data exists within the map download range, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map;

[0040] An image module, used to obtain a current image corresponding to a current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding position are stored in the first high-precision map and the second high-precision map;

[0041] The modification module is used to compare the current image with the historical image, generate a comparison result, and generate a map modification report based on the comparison result.

[0042] In a third aspect, the present invention provides an electronic device, including a memory and a processor;

[0043] The memory is used to store computer programs;

[0044] The processor is used to implement the autonomous driving vehicle map downloading method as described in the first aspect when executing the computer program.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for downloading a map for an autonomous driving vehicle as described in the first aspect is implemented.

[0046] The beneficial effects of the method, device, equipment and medium for downloading maps for an autonomous driving vehicle of the present invention are:

[0047] By obtaining the target position, current position and current driving status of the autonomous driving vehicle, the real-time status of the autonomous driving vehicle can be understood, laying the foundation for the subsequent download of high-precision maps; the driving route is then determined through the target position and current position, and the road data in the driving route is extracted to facilitate the subsequent download of the corresponding high-precision map; then the map download range is determined based on the current vehicle speed and current acceleration, so that only the high-precision map data of the section that the vehicle is about to pass through is downloaded in the driving route, that is, the high-precision map within the map download range on the driving route is downloaded, rather than the map data of the entire driving route. This can reduce the amount of data that needs to be transmitted in real time, thereby alleviating The demand for network bandwidth is solved; at the same time, different download strategies are adopted according to the straight road section data and curved road section data within the map download range. When there is straight road section data in the map download range, the first high-precision map with small space is downloaded, and when there is curved road section data in the map download range, the second high-precision map with large space is downloaded. Under the premise of ensuring safe automatic driving, the download of non-critical information is reduced, and limited network resources are used more effectively. The success rate of data transmission is improved under limited network conditions, and the problem that the update of high-precision maps cannot keep up with the driving speed of vehicles when the network communication quality is poor is solved, and the stability of automatic driving is improved. Finally, the historical images in the first high-precision map and the second high-precision map are compared with the corresponding current images to obtain the comparison results, and a map modification report is generated to determine the difference between the actual road conditions on the driving route and the downloaded high-precision map, so as to update the high-precision map in time, thereby improving the stability and reliability of automatic driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic diagram of a process for downloading a map for an autonomous driving vehicle provided in an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of a map downloading device for an autonomous driving vehicle provided in an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be interpreted as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0052] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0053] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to"; the term "based on" means "based at least in part on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0054] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0055] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0056] In response to the problems existing in the above-mentioned related technologies, this embodiment provides a method, device, equipment and medium for downloading maps for an autonomous driving vehicle.

[0057] like Figure 1 As shown, an embodiment of the present invention provides a method for downloading a map for an autonomous driving vehicle, comprising:

[0058] Obtain the target position, current position and current driving state of the autonomous driving vehicle, wherein the current driving state includes the current vehicle speed and the current acceleration.

[0059] Specifically, the target position, current position and current driving state of the autonomous driving vehicle are first obtained to facilitate subsequent map downloading. For example, the position acquisition module, speed acquisition module and acceleration acquisition module of the processor can be used to respectively obtain the target position, current position and current driving state.

[0060] A driving route is determined according to the target position and the current position, and road data in the driving route is extracted, wherein the road data includes straight section data and curved section data.

[0061] Specifically, a path planning algorithm or navigation device can be used to determine the driving route according to the target location and the current location. For example, the Dijkstra algorithm, the Ellman-Ford algorithm, the Floyd-Warshall algorithm, etc., as well as global satellite positioning systems such as GPS, Beidou, GLONASS, and Galileo can be used to extract road data at the same time, so as to facilitate the subsequent downloading of high-precision maps of different sizes according to the straight section data and the curved section data.

[0062] A map download range is determined according to the current vehicle speed and the current acceleration.

[0063] Specifically, the map download range can be determined according to the current vehicle speed. The ratio of speed to map download range can be set according to actual conditions, and the map download range is proportional to the speed. That is, if the driving speed is fast, the download range needs to be increased so that the high-precision map downloaded by the vehicle can match the vehicle speed as soon as possible, because the car can travel farther in the same time when the driving speed is fast; if the driving speed is slow, the download range can be lowered to reduce the pressure on the vehicle to store high-precision maps. The map download range can also be determined based on the current vehicle speed and the current acceleration at the same time. For example, the map download range is determined by using a weighted method based on the current vehicle speed and the current acceleration.

[0064] For example, the map download range may be:

[0065] When the current vehicle speed is below 30km / h, the map download range is 500 meters;

[0066] When the current vehicle speed is between 30km / h and 50km / h, the map download range is 1km;

[0067] When the current vehicle speed is between 50km / h and 80km / h, the map download range is 2km;

[0068] When the current vehicle speed is between 80km / h and 100km / h, the map download range is 3km;

[0069] When the current vehicle speed is between 100km / h and 120km / h, the map download range is 4km;

[0070] When the current vehicle speed is above 120km / h, automatic driving is not recommended.

[0071] When the straight road section data exists in the map download range, the first high-precision map corresponding to the straight road section data within the map download range is downloaded; when the curved road section data exists in the map download range, the second high-precision map corresponding to the curved road section data within the map download range is downloaded, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map.

[0072] Specifically, within the map download range, if there is straight section data, the corresponding first high-precision map is downloaded for the straight section; if there is curved section data, the corresponding second high-precision map is downloaded for the curved section. This is because, on a straight section, the vehicle speed is generally high, and the map data needs to be loaded quickly to match the speed, and there is no need to pay attention to too many environmental details to ensure safety. Therefore, on a straight section, the first high-precision map that occupies a small space is downloaded to improve the success rate of data transmission under limited network conditions, so as to solve the problem that when the network communication quality is poor, the update of the high-precision map cannot keep up with the vehicle's driving speed, thereby improving the stability of autonomous driving. On the contrary, on a curved section, the vehicle speed is generally low, and there is no need to load map data quickly to match the speed, but more environmental details need to be paid attention to to ensure safety. Therefore, on a curved section, the second high-precision map that occupies a large space is downloaded to ensure the safety and stability of autonomous driving.

[0073] Obtain a current image corresponding to the current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding positions are stored in the first high-precision map and the second high-precision map.

[0074] Specifically, the vehicle's built-in shooting device is used to automatically capture the current image of the same position in the first high-precision map and the second high-precision map, so as to facilitate the subsequent analysis of changes in the high-precision map over time based on the current image and the historical images of the corresponding positions stored in the first high-precision map and the second high-precision map.

[0075] The current image and the historical image are compared to generate a comparison result, and a map modification report is generated according to the comparison result.

[0076] Specifically, the current image and the historical image are compared to generate a comparison result, that is, by comparing the historical image stored in the high-precision map with the current image, a comparison result describing the changes in the high-precision map over time is obtained. When the comparison result shows that the similarity ratio between the current image and the high-precision map of a certain location is lower than the preset ratio, a map modification report is generated to modify the high-precision map in time to improve the stability of autonomous driving, wherein the preset ratio is set according to actual conditions. Exemplarily, the preset ratio may be 75%. Exemplarily, multiple autonomous driving vehicles may be used to compare the historical image and the current image in the high-precision map of a certain location. When the similarity ratio of most of the comparison results is lower than the preset ratio, a map modification report is generated, and the coordinates of the location, the high-precision map and the current image are uploaded to the cloud to facilitate the modification of the high-precision map.

[0077] In this embodiment, by acquiring the target position, current position and current driving status of the autonomous driving vehicle, the real-time status of the autonomous driving vehicle can be understood, laying the foundation for the subsequent downloading of high-precision maps; the driving route is then determined through the target position and current position, and the road data in the driving route is extracted to facilitate the subsequent downloading of the corresponding high-precision map; then the map download range is determined according to the current vehicle speed and the current acceleration, so that in the driving route, only the high-precision map data of the road section that the vehicle is about to pass is downloaded, that is, the high-precision map within the map download range on the driving route is downloaded, rather than the map data of the entire driving route, which can reduce the amount of data that needs to be transmitted in real time, thereby The demand for network bandwidth is reduced; at the same time, different download strategies are adopted according to the straight road section data and curved road section data within the map download range. When there is straight road section data in the map download range, the first high-precision map with small space is downloaded, and when there is curved road section data in the map download range, the second high-precision map with large space is downloaded, so as to reduce the download of non-critical information under the premise of ensuring safe automatic driving, make more effective use of limited network resources, improve the success rate of data transmission under limited network conditions, solve the problem that the update of high-precision maps cannot keep up with the driving speed of vehicles when the network communication quality is poor, and improve the stability of automatic driving. Finally, the historical images in the first high-precision map and the second high-precision map are compared with the corresponding current images, the comparison results are obtained, and a map modification report is generated to determine the difference between the actual road conditions on the driving route and the downloaded high-precision map, so as to update the high-precision map in time, thereby improving the stability and reliability of automatic driving.

[0078] Optionally, determining the map download range according to the current vehicle speed and the current acceleration includes:

[0079] Determining the future vehicle speed and the vehicle arrival position after a preset time according to the current vehicle speed and the current acceleration;

[0080] The map download range is determined according to the future vehicle speed and the vehicle arrival position.

[0081] Specifically, according to the current vehicle speed and the current acceleration, the future vehicle speed after a preset time is determined through the time-speed formula, and the position that the vehicle can reach after the preset time, that is, the vehicle arrival position, is determined, so as to determine the map download range. The first map download range can be determined according to the acceleration. The greater the acceleration, the larger the first map download range. The map download range determined for the second time and thereafter can be determined according to the future vehicle speed and the vehicle arrival position. Among them, when determining the map download range for the second time and thereafter, the preset time can be determined by the current map range and the current vehicle speed, that is, the minimum time for the current vehicle speed to complete the current map range is determined, and the difference between the minimum time and the cache time threshold is used as the preset time, so as to download the high-precision map according to the next map download range before the current map range is completed, thereby ensuring that the high-precision map of the next map download range has been downloaded when the current map range is completed, that is, ensuring that the current map range and the map range determined next time are effectively connected, and no excessive map overlap will be generated, so as to reduce the amount of data that needs to be transmitted in real time and alleviate the demand for network bandwidth.

[0082] Optionally, determining the map download range according to the current vehicle speed and the current acceleration includes:

[0083] Determining a speed gear corresponding to the current vehicle speed according to the current vehicle speed and a plurality of preset different speed gears;

[0084] Determining a speed adjustment time according to the speed gear and the current acceleration;

[0085] The time is adjusted according to the speed to determine the map download range.

[0086] Specifically, the speed gear of the autonomous driving vehicle can be pre-set, and each speed gear corresponds to a vehicle speed interval. According to the current vehicle speed, the speed gear closest to the current vehicle speed is determined, and then the speed adjustment time for accelerating or decelerating to the target speed corresponding to the speed gear is determined by the speed gear and the current acceleration. The current acceleration of the autonomous driving vehicle can be positive or negative. When it is positive, the vehicle accelerates, the target speed corresponding to the speed gear is the maximum speed of the speed gear, and the speed adjustment time is the acceleration adjustment time; when it is negative, the vehicle decelerates, the target speed corresponding to the speed gear is the minimum speed of the speed gear, and the speed adjustment time is the deceleration adjustment time. Among them, the speed adjustment time can be determined by the difference between the target speed corresponding to the speed gear and the current speed and the quotient of the current acceleration, and then the map download range is determined according to the speed adjustment time, so as to download the high-precision map in advance. Exemplarily, the map download range is inversely proportional to the acceleration adjustment time. The shorter the acceleration adjustment time, the larger the map download range; the map download range is proportional to the deceleration adjustment time. The shorter the deceleration adjustment time, the smaller the map download range.

[0087] Optionally, the comparing the current image with the historical image to generate a comparison result includes:

[0088] Extracting historical features of the historical image and current features of the current image respectively, wherein the historical features include historical angle features and at least one historical descriptor, and the current features include current angle features corresponding to the historical angle features and current descriptors corresponding to the historical descriptors;

[0089] Comparing the historical angle feature with the current angle feature, and comparing the historical descriptor with the current descriptor, to determine similarity;

[0090] The comparison result is generated according to the similarity.

[0091] Specifically, by respectively extracting the historical features of the historical image and the current features of the current image, the historical features at the pixel level and the current features at the pixel level can be accurately compared to determine whether the location has changed, thereby facilitating the subsequent generation of a map modification report.

[0092] Optionally, the extracting the historical features of the historical image and the current features of the current image respectively includes:

[0093] The historical angle feature and the current angle feature are extracted respectively by using the grayscale centroid method;

[0094] According to the historical image and the current image, determining historical key point information of the historical image and current key point information of the current image by scale space extreme value detection;

[0095] Respectively determining a historical key point neighborhood of the historical key point information and a current key point neighborhood of the current key point information;

[0096] According to the neighborhood of the historical key point and the neighborhood of the current key point, respectively extracting historical gradient information and current gradient information;

[0097] The historical descriptor and the current descriptor are constructed according to the historical gradient information and the current gradient information.

[0098] Specifically, the grayscale centroid method is used to extract historical angle features and current angle features respectively. According to the historical image and the current image, the position of the key point is determined by the scale space extreme value detection, and the direction is assigned to the key point to obtain the key point information containing the position and direction, that is, the historical key point information of the historical image and the current key point information of the current image are determined; then, with the key point as the center, the appropriate neighborhood size is selected according to its scale and direction, that is, the historical key point neighborhood of the historical key point information and the current key point neighborhood of the current key point information are determined respectively; then, the direction and amplitude of the image gradient are calculated in the neighborhood of each key point to obtain the gradient information containing the gradient direction and amplitude, that is, according to the historical key point neighborhood and the current key point neighborhood, the historical gradient information and the current gradient information are extracted respectively; finally, the descriptor histogram is constructed according to the gradient direction and amplitude information, and the descriptor vector is normalized to enhance the robustness, and a descriptor with scale and rotation invariance is obtained, that is, according to the historical gradient information and the current gradient information, the historical descriptor and the current descriptor are constructed.

[0099] In one embodiment, the historical image and the current image may be reduced to obtain historical descriptors and current descriptors at multiple scales.

[0100] Optionally, comparing the historical angle feature with the current angle feature, and comparing the historical descriptor with the current descriptor to determine the similarity includes:

[0101] Comparing the historical angle feature with the current angle feature to generate angle similarity;

[0102] Comparing the Hamming distance between the historical descriptor and the current descriptor to generate description similarity;

[0103] The similarity is generated according to the angle similarity and the description similarity.

[0104] Specifically, the historical angle features and the current angle features can be compared using methods such as Euclidean distance, cosine similarity, the angle between direction vectors, and minimum angle difference to generate angle similarity; the description similarity is generated by comparing the Hamming distance between the historical descriptor and the current descriptor. If the Hamming distance is less than a preset threshold, the features are considered to be the same. Finally, the angle similarity and the description similarity are integrated to generate similarity, thereby comprehensively evaluating the similarity between the historical features and the current features.

[0105] Optionally, after generating a map modification report according to the comparison result, the method further includes:

[0106] Delete the first high-precision map and the second high-precision map of the traveled area.

[0107] Specifically, when driving, the high-precision map of the area that has been traveled is deleted to save the storage space of the vehicle and facilitate the subsequent loading of the high-precision map of the area that has not been traveled.

[0108] like Figure 2 As shown, an automatic driving vehicle map downloading device 200 provided in an embodiment of the present invention includes:

[0109] An acquisition module 210 is used to acquire a target position, a current position, and a current driving state of the autonomous driving vehicle, wherein the current driving state includes a current vehicle speed and a current acceleration;

[0110] A route module 220, for determining a driving route according to the target location and the current location, and extracting road data in the driving route, wherein the road data includes straight road segment data and curved road segment data;

[0111] A range module 230, configured to determine a map download range according to the current vehicle speed and the current acceleration;

[0112] The map module 240 is configured to download a first high-precision map corresponding to the straight road segment data within the map download range when the straight road segment data exists within the map download range; and download a second high-precision map corresponding to the curved road segment data within the map download range when the curved road segment data exists within the map download range, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map;

[0113] An image module 250 is used to obtain a current image corresponding to a current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding position are stored in the first high-precision map and the second high-precision map;

[0114] The modification module 260 is used to compare the current image with the historical image, generate a comparison result, and generate a map modification report based on the comparison result.

[0115] like Figure 3 As shown, an electronic device 300 provided by an embodiment of the present invention includes a memory 310 and a processor 320; the memory 310 is used to store a computer program; the processor 320 is used to implement the above-mentioned method for downloading a map for an autonomous driving vehicle when executing the computer program.

[0116] In other words, an electronic device 300 includes a memory 310 and a processor 320 coupled to the memory 310; the memory 310 is configured to store a computer program; and the processor 320 is configured to perform the following operations when executing the computer program:

[0117] Obtaining a target position, a current position, and a current driving state of the autonomous driving vehicle, wherein the current driving state includes a current vehicle speed and a current acceleration;

[0118] Determine a driving route according to the target position and the current position, and extract road data in the driving route, wherein the road data includes straight road segment data and curved road segment data;

[0119] Determining a map download range according to the current vehicle speed and the current acceleration;

[0120] When the straight road segment data exists in the map download range, downloading a first high-precision map corresponding to the straight road segment data in the map download range; when the curved road segment data exists in the map download range, downloading a second high-precision map corresponding to the curved road segment data in the map download range, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map;

[0121] Acquire a current image corresponding to the current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding position are stored in the first high-precision map and the second high-precision map;

[0122] The current image and the historical image are compared to generate a comparison result, and a map modification report is generated according to the comparison result.

[0123] A computer-readable storage medium is provided in an embodiment of the present invention, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the method for downloading a map for an autonomous driving vehicle as described above is implemented.

[0124] In other words, a non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor performs the following operations:

[0125] Obtaining a target position, a current position, and a current driving state of the autonomous driving vehicle, wherein the current driving state includes a current vehicle speed and a current acceleration;

[0126] Determine a driving route according to the target position and the current position, and extract road data in the driving route, wherein the road data includes straight road segment data and curved road segment data;

[0127] Determining a map download range according to the current vehicle speed and the current acceleration;

[0128] When the straight road segment data exists in the map download range, downloading a first high-precision map corresponding to the straight road segment data in the map download range; when the curved road segment data exists in the map download range, downloading a second high-precision map corresponding to the curved road segment data in the map download range, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map;

[0129] Acquire a current image corresponding to the current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding position are stored in the first high-precision map and the second high-precision map;

[0130] The current image and the historical image are compared to generate a comparison result, and a map modification report is generated according to the comparison result.

[0131] An electronic device 300 that can be used as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device 300 is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 300 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present invention described and / or required herein.

[0132] The electronic device 300 includes a computing unit, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for the operation of the device can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0133] A person of ordinary skill in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. In the present application, the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present invention. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0134] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A method for downloading a map for an autonomous driving vehicle, characterized in that: include: Obtaining a target position, a current position, and a current driving state of the autonomous driving vehicle, wherein the current driving state includes a current vehicle speed and a current acceleration; Determine a driving route according to the target position and the current position, and extract road data in the driving route, wherein the road data includes straight road segment data and curved road segment data; Determining a map download range according to the current vehicle speed and the current acceleration, wherein the map download range is proportional to the current vehicle speed and the current acceleration; When the straight road segment data exists in the map download range, downloading a first high-precision map corresponding to the straight road segment data in the map download range; when the curved road segment data exists in the map download range, downloading a second high-precision map corresponding to the curved road segment data in the map download range, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map; Acquire a current image corresponding to the current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding position are stored in the first high-precision map and the second high-precision map; Comparing the current image with the historical image to generate a comparison result, and generating a map modification report based on the comparison result; Delete the first high-precision map and the second high-precision map of the traveled area; The comparing the current image with the historical image to generate a comparison result includes: Extracting historical features of the historical image and current features of the current image respectively, wherein the historical features include historical angle features and at least one historical descriptor, and the current features include current angle features corresponding to the historical angle features and current descriptors corresponding to the historical descriptors; Comparing the historical angle feature with the current angle feature, and comparing the historical descriptor with the current descriptor, to determine similarity; generating the comparison result according to the similarity; The extracting the historical features of the historical image and the current features of the current image respectively includes: The historical angle feature and the current angle feature are extracted respectively by using the grayscale centroid method; According to the historical image and the current image, determining historical key point information of the historical image and current key point information of the current image by scale space extreme value detection; Respectively determining a historical key point neighborhood of the historical key point information and a current key point neighborhood of the current key point information; According to the neighborhood of the historical key point and the neighborhood of the current key point, respectively extracting historical gradient information and current gradient information; The historical descriptor and the current descriptor are constructed according to the historical gradient information and the current gradient information.

2. The method for downloading a map for an autonomous driving vehicle according to claim 1, characterized in that: The determining the map download range according to the current vehicle speed and the current acceleration includes: Determining the future vehicle speed and the vehicle arrival position after a preset time according to the current vehicle speed and the current acceleration; The map download range is determined according to the future vehicle speed and the vehicle arrival position.

3. The method for downloading a map for an autonomous driving vehicle according to claim 1, characterized in that: The determining the map download range according to the current vehicle speed and the current acceleration includes: Determining a speed gear corresponding to the current vehicle speed according to the current vehicle speed and a plurality of preset different speed gears; Determining a speed adjustment time according to the speed gear and the current acceleration; The time is adjusted according to the speed to determine the map download range.

4. The method for downloading a map for an autonomous driving vehicle according to claim 1, characterized in that: The comparing the historical angle feature with the current angle feature, and comparing the historical descriptor with the current descriptor to determine the similarity, includes: Comparing the historical angle feature with the current angle feature to generate angle similarity; Comparing the Hamming distance between the historical descriptor and the current descriptor to generate description similarity; The similarity is generated according to the angle similarity and the description similarity.

5. A map downloading device for an autonomous driving vehicle, characterized in that: include: An acquisition module, used to acquire the target position, current position and current driving state of the autonomous driving vehicle, wherein the current driving state includes the current vehicle speed and current acceleration; A route module, used to determine a driving route according to the target location and the current location, and extract road data in the driving route, wherein the road data includes straight road segment data and curved road segment data; A range module, configured to determine a map download range according to the current vehicle speed and the current acceleration, wherein the map download range is proportional to the current vehicle speed and the current acceleration; A map module, configured to download a first high-precision map corresponding to the straight road segment data within the map download range when the straight road segment data exists within the map download range; and download a second high-precision map corresponding to the curved road segment data within the map download range when the curved road segment data exists within the map download range, wherein the space occupied by the first high-precision map is smaller than the space occupied by the second high-precision map; An image module, used to obtain a current image corresponding to a current position and a historical image corresponding to the current position in the first high-precision map or the second high-precision map, wherein the historical images of the corresponding position are stored in the first high-precision map and the second high-precision map; A modification module, used for comparing the current image with the historical image, generating a comparison result, and generating a map modification report according to the comparison result; deleting the first high-precision map and the second high-precision map of the traveled area; The comparing the current image with the historical image to generate a comparison result includes: Extracting historical features of the historical image and current features of the current image respectively, wherein the historical features include historical angle features and at least one historical descriptor, and the current features include current angle features corresponding to the historical angle features and current descriptors corresponding to the historical descriptors; Comparing the historical angle feature with the current angle feature, and comparing the historical descriptor with the current descriptor, to determine similarity; generating the comparison result according to the similarity; The extracting the historical features of the historical image and the current features of the current image respectively includes: The historical angle feature and the current angle feature are extracted respectively by using the grayscale centroid method; According to the historical image and the current image, determining historical key point information of the historical image and current key point information of the current image by scale space extreme value detection; Respectively determining a historical key point neighborhood of the historical key point information and a current key point neighborhood of the current key point information; According to the neighborhood of the historical key point and the neighborhood of the current key point, respectively extracting historical gradient information and current gradient information; The historical descriptor and the current descriptor are constructed according to the historical gradient information and the current gradient information.

6. An electronic device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is used to implement the autonomous driving vehicle map downloading method as described in any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the method for downloading a map for an autonomous driving vehicle as described in any one of claims 1 to 4 is implemented.

Images