Data processing method and device, traffic equipment, processing equipment and storage medium

Abstract

The invention relates to a data processing method and device, traffic equipment, processing equipment and a storage medium, and relates to the technical field of maps. Comprising the steps of determining a road model around an intersection area under the condition that traffic equipment is detected to pass through the intersection area; the road model comprises road information around the intersection area; sending the road model to a processing device; the processing device is used for obtaining a first road map of the intersection area according to a plurality of road models sent by a plurality of traffic devices; and receiving the first road map returned by the processing equipment. By using the data processing method provided by the invention, comprehensive road information of the intersection area can be obtained, so that an accurate driving path can be planned based on the comprehensive road information of the intersection area.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, and in particular to a data processing method, apparatus, transportation equipment, processing device and storage medium. Background Technology

[0002] In the field of autonomous driving, some automakers have adopted a technical approach of "emphasizing perception and downplaying maps". In the process of planning the vehicle's driving trajectory, the vehicle's driving trajectory can be planned by the road information perceived by the vehicle, and then the vehicle's driving can be controlled according to the driving trajectory.

[0003] However, vehicles cannot effectively perceive road information in intersection areas, resulting in gaps in the perceived road information. Consequently, the accuracy of the driving path planned based on this incomplete road information is also low. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a data processing method, apparatus, transportation equipment, processing equipment, and storage medium.

[0005] According to a first aspect of the present disclosure, a data processing method is provided, comprising:

[0006] Upon detecting that traffic equipment has passed through an intersection area, a road model surrounding the intersection area is determined; the road model includes road information surrounding the intersection area.

[0007] The road model is sent to a processing device; the processing device is used to obtain a first road map of the intersection area based on multiple road models sent by multiple traffic devices.

[0008] Receive the first road map returned by the processing device.

[0009] Optionally, before determining the road model around the intersection area, the method further includes:

[0010] Obtain the road topology around the intersection area; the road topology includes road markings on the roads traversed by the traffic equipment;

[0011] If different road signs are detected in the road topology, it is determined that the traffic equipment has passed through the intersection area.

[0012] Optionally, determining the road model around the intersection area includes:

[0013] The road model is obtained based on the location information of the traffic equipment and the road topology around the intersection area.

[0014] According to a second aspect of the present disclosure, a data processing method is provided, comprising:

[0015] Receive multiple road models sent by multiple traffic devices; the road models are determined after the traffic devices have passed through the intersection area, and the road models indicate the road information around the intersection area;

[0016] Based on the multiple road models, a first road map is obtained around the intersection area;

[0017] The first road map is sent to the plurality of transportation devices.

[0018] Optionally, obtaining a first road map around the intersection area based on the plurality of road models includes:

[0019] Cluster the multiple road models and group multiple first road models belonging to the same intersection area into the same category;

[0020] Based on multiple first road models surrounding the intersection area, a first road map surrounding the intersection area is obtained.

[0021] Optionally, the step of clustering the multiple road models to group multiple first road models belonging to the same intersection area into the same category includes repeatedly performing the following filtering steps if the stopping condition is not met:

[0022] From the plurality of road models, a second road model is selected that is less than a preset distance from the target road model and whose connecting line to the target road model does not pass through the road model; the target road model is a specified road model from the plurality of road models or the second road model selected in the previous screening.

[0023] If the stopping condition is met, the target road model and the second road model are classified as the plurality of first road models under the same category.

[0024] Optionally, the stopping condition includes any one of the following:

[0025] The distance between multiple first road models and third road models in the same category is greater than or equal to a preset distance and / or the line connecting them to the third road model passes through the road model, wherein the third road model is a road model other than the multiple first road models in the same category among the multiple road models;

[0026] The number of multiple first road models under the same category no longer changes.

[0027] Optionally, obtaining a first road map around the intersection area based on multiple first road models around the intersection area includes:

[0028] Multiple first road models around the intersection area are fused to obtain a second road map of the intersection area;

[0029] The first road map is obtained by using the stop lines at the ends of each road in the second road map.

[0030] Optionally, obtaining the first road map based on the stop lines at the ends of each road in the second road map includes:

[0031] If there is no stop line at the end of the road in the second road map, the stop line at the end of the road is fitted based on the endpoint of the road end;

[0032] The first road map is obtained by using the stop lines at the ends of each road in the second road map.

[0033] Optionally, if there is no stop line at the end of the road in the second road map, the stop line at the end of the road is fitted based on the endpoint of the road end, including:

[0034] In the case that there is no stop line at the end of the road in the second road map, a fitting line for the end of the road is fitted based on the endpoint of the end of the road;

[0035] The outermost line of the outermost lane in the second road map is used as the end point of the fitted line to obtain the stop line at the end of the road.

[0036] According to a third aspect of the present disclosure, a data processing apparatus is provided, comprising:

[0037] The perception module is configured to determine a road model around the intersection area when it detects that a traffic device has passed through the intersection area; the road model indicates road information around the intersection area.

[0038] A first sending module is configured to send the road model to a processing device; the processing device is used to obtain a first road map of the intersection area based on multiple road models sent by multiple traffic devices.

[0039] The first receiving module is configured to receive a first road map returned by the processing device.

[0040] According to a fourth aspect of the present disclosure, a data processing apparatus is provided, comprising:

[0041] The second receiving module is configured to receive multiple road models sent by multiple traffic devices; the road models are determined when the traffic devices have passed through the intersection area, and the road models indicate road information around the intersection area;

[0042] The creation module is configured to obtain a first road map around the intersection area based on the multiple road models;

[0043] The second sending module is configured to send the first road map to the plurality of traffic devices.

[0044] According to a fifth aspect of the present disclosure, a transportation device is provided, comprising:

[0045] processor;

[0046] Memory used to store processor-executable instructions;

[0047] The processor is configured as follows:

[0048] The steps of performing the data processing method provided in the first aspect of the embodiments of this disclosure.

[0049] According to a sixth aspect of the present disclosure, a processing apparatus is provided, comprising: a processor;

[0050] Memory used to store processor-executable instructions;

[0051] The processor is configured as follows:

[0052] The steps of performing the data processing method provided in the second aspect of the embodiments of this disclosure.

[0053] According to a seventh aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of the data processing method provided in the first aspect of the present disclosure.

[0054] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0055] Firstly, the traffic equipment can receive a complete first road map of the intersection area sent by the processing equipment, and thus plan a more accurate driving route based on the complete road information of the intersection area provided by the first road map. Road information at intersection bends that the current traffic equipment cannot perceive can be perceived by other traffic equipment located at the bend and uploaded to the processing equipment. The processing equipment then sends the perceived road information back to the current traffic equipment in the form of a first road map. Similarly, road information on the opposite side of the intersection area that is outside the perception range of the current traffic equipment can also be perceived by traffic equipment located on the opposite side of the intersection area and uploaded to the processing equipment. The processing equipment then sends the perceived road information back to the current traffic equipment in the form of a first road map.

[0056] Secondly, when traffic equipment uploads the road model, it uploads the road model of the intersection area instead of the entire road segment, which reduces the amount of data uploaded. Similarly, it also reduces the amount of data processed by the processing equipment and the amount of data sent back from the processing equipment to the traffic equipment.

[0057] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0059] Figure 1 This is a schematic diagram illustrating, according to an exemplary embodiment, that the road opposite an intersection area is outside the sensing range of traffic equipment.

[0060] Figure 2 This is a schematic diagram illustrating a traffic device that cannot detect the road after a turn at an intersection area, according to an exemplary embodiment.

[0061] Figure 3 This is a flowchart illustrating the steps of a data processing method according to an exemplary embodiment.

[0062] Figure 4 This is a schematic diagram of a crossroads area according to an exemplary embodiment.

[0063] Figure 5 This is a schematic diagram of four road models in a crossroads area according to an exemplary embodiment.

[0064] Figure 6 This is a schematic diagram illustrating a road comprising multiple lanes according to an exemplary embodiment.

[0065] Figure 7 This is a schematic diagram of a straight-ahead intersection area according to an exemplary embodiment.

[0066] Figure 8 This is a flowchart illustrating the steps of a data processing method according to an exemplary embodiment.

[0067] Figure 9 This is a logical schematic diagram illustrating clustering of multiple road models according to an exemplary embodiment.

[0068] Figure 10 This is a schematic diagram illustrating a connection between a first position center point and a second position center point according to an exemplary embodiment.

[0069] Figure 11 This is a schematic diagram illustrating the connection between every two road models in a cross-shaped intersection area according to an exemplary embodiment.

[0070] Figure 12 This is a schematic diagram illustrating a model of a road with lines crossing it, according to an exemplary embodiment.

[0071] Figure 13 This is a schematic diagram illustrating an end point of a road end according to an exemplary embodiment.

[0072] Figure 14 This is a schematic diagram illustrating, according to an exemplary embodiment, the boundary of a blank area obtained by connecting the end-to-end stop lines.

[0073] Figure 15 This is a schematic diagram of multiple road models in a crossroads area according to an exemplary embodiment.

[0074] Figure 16 This is a schematic diagram illustrating a data processing system according to an exemplary embodiment.

[0075] Figure 17 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment.

[0076] Figure 18 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment.

[0077] Figure 19 This is a block diagram illustrating a transportation device according to an exemplary embodiment.

[0078] Figure 20 This is a block diagram illustrating a chip system according to an exemplary embodiment.

[0079] Figure 21This is a block diagram illustrating a processing device according to an exemplary embodiment. Detailed Implementation

[0080] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0081] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0082] High-precision maps are maps used by autonomous driving vehicles or intelligent transportation systems. These maps include not only basic geographic information but also lane data such as the number of lanes, lane widths, lane markings, and speed limit signs on each road. Based on the lane data in the high-precision map, traffic equipment can automatically plan driving routes for vehicles, allowing them to safely navigate these roads while adhering to traffic rules. In the process of creating high-precision maps, road information is collected by data acquisition vehicles equipped with high-precision integrated navigation, high-beam LiDAR, and high-resolution cameras. This allows for accurate collection of road information, which is then used to create highly accurate high-precision maps.

[0083] Sensing technology involves using sensing devices on transportation equipment to perceive road information, traffic conditions, obstacles, etc. These sensing devices include radar, lidar, ultrasonic sensors, infrared sensors, global positioning system (GPS), inertial measurement unit (IMU), distance sensors, etc. By collecting road information around the transportation equipment through these sensors, a basis can be provided for the transportation equipment to plan its driving path.

[0084] Because the production process of high-precision maps is relatively complicated and costly, and because high-precision maps have a limited coverage area, most car manufacturers have adopted perception technology upstream. This technology uses traffic equipment to sense road information around the traffic equipment, thereby providing a basis for downstream driving route planning and prediction.

[0085] However, sensing technology also has its limitations, for example, please refer to [link / reference]. Figure 1As shown, when the distance between the traffic equipment and the intersection area for straight-ahead traffic is large, the road information on the opposite side of the intersection area is beyond the perception range of the traffic equipment. This results in the traffic equipment being unable to perceive the road information on the opposite side of the intersection area. The lack of road information on the opposite side of the intersection area leads to a decrease in the accuracy of the planned driving path. For example, please refer to... Figure 2 As shown, when traffic equipment turns left or right at a turning intersection, the sensing devices on the traffic equipment cannot detect the road information after the left or right turn due to obstructions such as traffic signs at the road turning point. Therefore, the lack of road information on the left or right side of the intersection area will also lead to a decrease in the accuracy of the planned driving path.

[0086] Figure 3 This is a data processing method proposed according to an exemplary embodiment. The data processing method can upload the road models of the intersection area perceived by each of the multiple traffic devices to a processing device. Since the processing device can obtain a complete first road map of the intersection area based on the multiple road models uploaded by the multiple traffic devices, after the traffic devices receive the first road map, they can obtain road information that the sensing devices cannot perceive from the first road map, thereby accurately planning the driving route based on the complete road information.

[0087] Please refer to Figure 3. This data processing method is applied to transportation equipment and includes the following steps.

[0088] The transportation equipment can be vehicles, robots, robot dogs, or other transportation equipment, and can also be applied to other equipment that requires route planning. This disclosure does not limit this.

[0089] In step S10, if it is detected that a traffic device has passed through the intersection area, the road model around the intersection area is determined.

[0090] This intersection area is a region where at least two roads intersect, and it can be a grade-separated intersection or a grade-separated intersection. Examples of grade-separated intersections include crossroads, T-shaped intersections, Y-shaped intersections, X-shaped intersections, and intersections where an X-shaped intersection meets a straight-ahead road. Examples of grade-separated intersections include areas where overpasses or elevated roads intersect.

[0091] When traffic equipment passes through the intersection area, it means that the sensing devices of the traffic equipment have constructed a road model around the intersection area. At this time, the road model around the intersection area perceived by the traffic equipment can be obtained.

[0092] The road model surrounding an intersection area includes the road models of each individual intersection area within the intersection area. For example, the road model surrounding a crossroads intersection area includes the road models of each of the four intersection areas within the crossroads intersection area; the road model surrounding a straight-ahead intersection area includes the road models of each of the two intersection areas within the straight-ahead intersection area; and the road model surrounding a T-shaped intersection area includes the road models of each of the three intersection areas within the T-shaped intersection area.

[0093] The road model includes road information surrounding the intersection area, which includes at least the road, lanes within the road, and lane centerlines. Please refer to [link / reference]. Figure 4 As shown, taking a cross-shaped intersection area as an example, each of the four intersection areas (up, down, left, and right) in this cross-shaped intersection area contains two roads, and each road contains three lanes. Each of the three lanes has its own lane centerline. Figure 4 The dashed line in the image is the lane center line.

[0094] In step S20, the road model is sent to the processing device.

[0095] Whenever a traffic device is in an intersection area, it creates a road model based on the collected road information and uploads the road model to the processing device. The processing device then obtains the first road map of the intersection area based on the multiple road models sent by the traffic devices.

[0096] The road model uploaded by each traffic device to the processing device includes the intersection road models of two intersection areas in the intersection area that the traffic device passes through. The processing device stitches together the two intersection road models uploaded by each traffic device to create a complete first road map of the intersection area.

[0097] Please see Figure 5As shown, taking a crossroads-shaped intersection area as an example, this area comprises four intersection zones, each with two roads. The roads surrounding this crossroads-shaped intersection area include roads 1 through 8. Assuming traffic device A travels from road 1 to road 2 within this crossroads-shaped intersection area, traffic device A will upload a road model containing both roads 1 and 2 to the processing device. Similarly, if traffic device B travels from road 3 to road 4, it will upload a road model containing both roads 3 and 4 to the processing device. If traffic device C travels from road 5 to road 6, it will upload a road model containing both roads 5 and 6 to the processing device. If traffic device D travels from road 7 to road 8, it will upload a road model containing both roads 7 and 8 to the processing device. After collecting the four road models uploaded by traffic devices A through D, the processing equipment stitches these four road models together to form a... Figure 5 The first road map of the crossroads area shown.

[0098] Of course, the above Figure 5 As an example, during the fitting of a first road map of a crossroads area, the road models uploaded by different traffic devices may contain the same two intersection road models, but the driving trajectories in the road models uploaded by different traffic trajectories will be different. For example, multiple traffic devices may upload road models associated with intersection road model 1 and intersection road model 2, but the driving trajectories of each traffic device through the intersection area between intersection road model 1 and intersection road model 2 will be different, thus causing the road models uploaded by each traffic device to be associated with road 1 and road 2 to be different. This embodiment of the disclosure can match and fuse the intersection road models at these locations based on the road models uploaded by multiple traffic devices that are associated with the same intersection road model, to obtain a more accurate road model, ultimately forming a road model as shown below. Figure 15 The first road map shown.

[0099] The first road map is a complete road map of the intersection area, which contains road information for each intersection area in the intersection area. It includes road information that can be detected by traffic equipment and road information that cannot be detected by traffic equipment.

[0100] In step S30, the first road map returned by the processing device is received.

[0101] Since a road model is built around the intersection area every time a traffic device passes through it, and the road model is uploaded to the processing device, the processing device can create a complete first road map of the intersection area based on the road models uploaded by each traffic device. When a traffic device passes through the intersection area later, the processing device can send the first road map to the traffic device. The traffic device can accurately determine the road information of each intersection area in the intersection area based on the first road map, and then plan an accurate driving route to ensure vehicle driving safety.

[0102] Furthermore, after the processing equipment has completed the first road map, it can update the first road map of the intersection area in real time based on the road model subsequently uploaded by the traffic equipment, thus ensuring the freshness of the first road map.

[0103] For example, see Figure 5 In the first road map of the crossroads area created by the processing equipment, road 5 originally had three lanes. However, when subsequent traffic equipment passes through the crossroads area, it detects that the right lane has a road surface fault, making it unusable. Therefore, only two lanes are available. The two lanes detected in real time can be uploaded to the processing equipment. The processing equipment then updates the first road map in real time based on the updated information of the two lanes, changing the three lanes of road 5 to two lanes.

[0104] Through the above technical solution, when each traffic device passes through the intersection area, it will upload the road model around the intersection area to the processing device. The processing device will then stitch together a complete first road map of the intersection area based on the road model uploaded by each traffic device and return it to the traffic device.

[0105] Firstly, the traffic equipment can receive a complete first road map of the intersection area sent by the processing equipment, and thus plan a more accurate driving route based on the complete road information of the intersection area provided by the first road map. Road information at intersection bends that the current traffic equipment cannot perceive can be perceived by other traffic equipment located at the bend and uploaded to the processing equipment, which then sends the perceived road information back to the current traffic equipment. Similarly, road information on the opposite side of the intersection area that is outside the perception range of the current traffic equipment can also be perceived by traffic equipment located on the opposite side of the intersection area and uploaded to the processing equipment, which then sends the perceived road information back to the current traffic equipment.

[0106] Secondly, when traffic equipment uploads the road model, it uploads the road model of the intersection area instead of the entire road segment, which reduces the amount of data uploaded. Similarly, it also reduces the amount of data processed by the processing equipment and the amount of data sent back from the processing equipment to the traffic equipment.

[0107] Thirdly, the processing equipment can update the first road map in real time based on the road model uploaded by the traffic equipment to ensure the real-time nature and freshness of the first road map. Therefore, the road information of the intersection area obtained by the traffic equipment based on the more recent first road map will also be more recent, and the planned driving route will be more accurate.

[0108] Figure 6 This is an exemplary embodiment of the present disclosure, which is used to interpret an exemplary scheme for determining whether a traffic device passes through an intersection area and obtaining a road model after determining that the traffic device has passed through the intersection area, including the following steps.

[0109] (1) Obtain the road topology around the intersection area.

[0110] The road topology includes road information around the intersection area, which includes at least one of the following: road, lanes included in the road, lane centerline, road sign, lane sign, and lane centerline sign.

[0111] A road topology includes road topologies that include at least two roads traversed by traffic equipment. For example, to illustrate a road topology constructed using traffic equipment that consists of two roads, please refer to [link to relevant documentation]. Figure 6 As shown, assuming the intersection area is a cross-shaped intersection area, traffic device A travels from road 1 to road 2 in the cross-shaped intersection area. At this time, the road topology structure constructed by the traffic device can be obtained. This road topology structure records the road 1 that the traffic device passes through, the three lanes included in road 1, the road identifier of road 1 is 1, and the lane identifiers of the three lanes included in road 1 are 11, 12, and 13 respectively. Of course, it also records the road 2 that the traffic device passes through, the three lanes included in road 2, the road identifier of road 2 is 2, and the lane identifiers of the three lanes included in road 2 are 21, 22, and 23 respectively.

[0112] As traffic equipment passes through an intersection area, vehicles can use onboard sensors to perceive road information and then use this information to construct a road topology. This topology describes the connections and hierarchical structure between roads. Furthermore, it assigns identifiers to each road, lane, and lane centerline within the road topology to distinguish them. Road identifiers uniquely identify a road, lane identifiers uniquely identify a lane, and lane centerline identifiers uniquely identify a lane centerline.

[0113] (2) If different road signs are detected in the road topology, it is determined that the traffic equipment has passed through the intersection area.

[0114] Since intersection areas exist in the road topology of at least two roads constructed by the same traffic equipment, and the road signs of different roads are different, it can be determined that the traffic equipment has passed through the intersection area when a road with different road signs is detected in the road topology.

[0115] Please see Figure 7 As shown, taking a straight-ahead intersection area as an example, this area includes two intersection areas, one on the left and one on the right. Each intersection area has two roads, resulting in four roads in this straight-ahead intersection area. Each road can be assigned a road identifier, such as 1 to 4. Each road has two lanes, resulting in eight lanes in this straight-ahead intersection area. Each lane can be assigned a lane identifier, such as 11, 12, 21, 22, 31, 32, 41, and 42. Road 1 includes lanes 11 and 12, Road 2 includes lanes 21 and 22, Road 3 includes lanes 31 and 32, and Road 4 includes lanes 41 and 42. After a traffic device travels from Road 1 to Road 3, the constructed road topology is the road topology of both Road 1 and Road 3. Further detection of differences in road identifiers within the constructed road topology shows that the road identifiers for Road 1 and Road 2 are different, indicating that the vehicle has passed through the straight-ahead intersection area.

[0116] Of course, if no different road signs are detected in the road topology, it means that the traffic equipment has not yet passed through the intersection area and is still traveling on the same road. In this case, it is not necessary to build a road model based on the road topology, nor is it necessary to upload the road model.

[0117] Optionally, if an interruption is detected in the road markings and / or lane markings in the road topology, and the interruption duration reaches a preset duration, it can be determined that the traffic equipment has passed through the intersection area.

[0118] Since an intersection area is where at least two roads meet, and there are no roads and / or lanes within the intersection area, there will be no road markings in the blank areas within the intersection area. Therefore, road markings and / or lane markings can be continuously detected, and if an interruption in road markings and / or lane markings is detected, it can be determined that a vehicle has passed through the intersection area.

[0119] Of course, if the road signs and / or lane signs in the road topology are detected to be continuous, it can be determined that the traffic equipment has not yet passed through the intersection area and is still traveling on the same road. In this case, it is not necessary to build a road model based on the road topology, nor is it necessary to upload the road model.

[0120] In this exemplary solution, outdoor roads may be affected by severe weather conditions, causing the painted lines representing road lines or lanes to disappear. They may also be affected by human damage, resulting in the loss of fences representing road lines or lanes, leading to road or lane interruptions. Therefore, in the event of interruptions in road signs and / or lane signs, it can be determined whether the interruption duration has reached a preset duration. If the preset duration has been reached, it indicates that the traffic equipment has passed through the intersection area; if the preset duration has not been reached, it indicates that the road or lane where the traffic equipment is located is interrupted, and it has not yet passed through the intersection area, thereby avoiding the misclassification of accidentally damaged road sections as intersection areas.

[0121] Optionally, it can also be determined that the traffic equipment has passed through the intersection area if the lane sign in the road topology is detected to belong to a set of lane signs associated with different road signs.

[0122] Each road includes at least two lanes, so each road sign is associated with at least two lane signs, meaning each road sign is associated with a set of lane signs.

[0123] If a lane sign belonging to at least two lane sign sets is detected in the road topology, it indicates that the traffic device has passed through the intersection area; if a lane sign belonging to the same lane sign set is detected in the road topology, it indicates that the traffic device is traveling in a different lane within the road, and the traffic device has not yet passed through the intersection area.

[0124] For example, taking a straight-ahead intersection area as an example, this area includes four intersection zones, each with two roads, resulting in four roads in the straight-ahead intersection area. Each road can be assigned a road identifier, such as 1 to 4. Each road has two lanes, resulting in eight lanes in the straight-ahead intersection area. Each lane can be assigned a lane identifier, such as 11, 12, 21, 22, 31, 32, 41, and 42. Therefore, road identifier 1 is associated with lane identifiers 11 and 12, road identifier 2 with lane identifiers 21 and 22, road identifier 3 with lane identifiers 31 and 32, and road identifier 4 with lane identifiers 41 and 42. When lane sign 11 and lane sign 21 exist in the road topology region, these two lane signs belong to different lane sign sets, indicating that the traffic equipment has passed through the straight intersection area; when lane sign 11 and lane sign 12 exist in the road topology region, these two lane signs belong to the same lane sign set of road 1, indicating that the traffic equipment has traveled from the lane marked by lane sign 11 to the lane marked by lane sign 12, and it is still traveling within the same road, not from one road to another. In this case, it means that the traffic equipment has not yet passed through the intersection area.

[0125] (3) The road model is obtained based on the location information of the traffic equipment and the road topology around the intersection area.

[0126] A mapping relationship can be established between the location information of traffic equipment and the road topology around the intersection area traversed by the traffic equipment, thereby obtaining a road model. The location information of the traffic equipment can be used to locate the intersection area, thus distinguishing it from other intersection areas.

[0127] The location information of traffic equipment refers to its real-time location. This location information can be obtained by fusing the relative and absolute positions of the traffic equipment.

[0128] Relative position is the change in position of a traffic device relative to a specified reference position. It relies on position sensing devices inside the vehicle, such as wheel encoders and gyroscopes, to calculate the current position of the traffic device relative to the reference position by measuring changes in the speed, direction, and acceleration of the traffic device. This current position is the relative position of the traffic device.

[0129] Absolute position is the location of a transportation device in a world coordinate system, obtained by receiving external signals or markers. For example, the latitude, longitude, and altitude of the transportation device can be determined by receiving satellite signals from the Global Navigation Satellite System (GNSS); real-time motion positioning (RTK) can also be used to assist and correct errors in satellite signals, updating the satellite signals and obtaining a more accurate absolute position for the transportation device.

[0130] After obtaining the relative and absolute positions, the relative and absolute positions can be fused to obtain the location information of the transportation equipment.

[0131] Understandably, in the above scheme, traffic equipment will pass through different intersection areas, and each intersection area will also pass through multiple traffic equipment. Therefore, different road models can be built for different intersection areas, and then the road models of different intersection areas can be uploaded to the processing equipment to build the first road map of different intersection areas.

[0132] The above technical solution can determine that when there are different road signs in the road topology structure constructed by the traffic equipment, it can be determined that the traffic equipment has passed through the intersection area. This clarifies that the road model around the intersection area will only be uploaded to the processing equipment for processing when the traffic equipment has passed through the intersection area, rather than uploading invalid non-intersection area data to the processing equipment for processing.

[0133] Figure 8 This is a data processing method proposed according to an exemplary embodiment, which is applied in a processing device and includes the following steps.

[0134] The processing device can be a cloud server or other electronic devices capable of creating road maps; this disclosure does not limit the scope of the embodiments.

[0135] In step S40, multiple road models sent by multiple traffic devices are received; the road models are determined when the traffic devices have passed through the intersection area, and the road models indicate the road information around the intersection area.

[0136] The processing equipment can receive multiple road models sent by multiple traffic devices, and the multiple road models come from different intersection areas.

[0137] In step S50, a first road map around the intersection area is obtained based on the plurality of road models.

[0138] The processing device can first cluster multiple road models uploaded by multiple traffic devices in different intersection areas to obtain multiple road models in different intersection areas. Then, for each of the multiple road models in the multiple road models of different intersection areas, the first road map around that intersection area is obtained. In this way, the first road map of different intersection areas is obtained.

[0139] In step S60, the first road map is sent to the plurality of traffic devices.

[0140] Before a traffic device has passed through an intersection area, it can send a request to the processing device. This request requests a first road map of the intersection area. After receiving the request, the processing device returns the first road map of the intersection area to the traffic device so that the traffic device can plan its travel route.

[0141] Through the above technical solution, firstly, the processing device can obtain complete first road maps for each intersection area based on the road models of each intersection area uploaded by multiple traffic devices, and send these first road maps back to the traffic devices so that the traffic devices can plan driving routes based on the complete first road maps.

[0142] Secondly, when the processing device creates the first road map, it creates a first road map of the intersection area, rather than a road map of the entire road segment the processing device is traveling on. Therefore, the amount of data of the first road map sent back to the processing device is relatively small, which not only reduces the amount of computation of the processing device, but also reduces the amount of data sent back by the processing device.

[0143] Thirdly, the processing equipment can also update the first road map based on the fresh road models uploaded by the traffic equipment, thereby ensuring the freshness of the first road map in the intersection area.

[0144] Figures 9 to 14 This is an exemplary scheme for obtaining a first road map around the same intersection area according to an exemplary embodiment, which includes the following steps.

[0145] (1) Cluster the multiple road models and classify the multiple first road models belonging to the same intersection area into the same category.

[0146] Since multiple road models include road models uploaded by traffic equipment located in different intersection areas, cluster analysis can be performed on these road models to classify multiple first road models belonging to the same intersection area into the same category, and first road models belonging to different intersection areas into different categories.

[0147] This clustering method involves repeatedly performing the following screening sub-steps if the stopping condition is not met:

[0148] Sub-step A1: Select a second road model from the plurality of road models that is less than a preset distance from the target road model and whose connection with the target road model does not pass through the road model.

[0149] For example, from multiple road models, a second road model is selected that is less than a preset distance from the target road model and whose connection to the target road model does not pass through any of the road models.

[0150] This distance refers to Euclidean distance; the closer the distance, the greater the likelihood that they belong to the same category.

[0151] Sub-step A2: If the stopping condition is met, the target road model and the second road model are treated as multiple first road models under the same category.

[0152] The target road model is a designated road model from the plurality of road models or a second road model selected in the previous screening. For example, the designated model can be a designated road model randomly selected from the plurality of road models, or it can be the first road model among the plurality of road models after sorting the plurality of road models.

[0153] Please see Figure 9 As shown, a specified road model can be selected from multiple road models. It is then determined whether the specified road model has been clustered. If the specified road model is not clustered, it is used as the cluster center of a cluster of a certain category and marked as clustered. If the stopping condition is not met, a second road model is selected from the multiple road models whose distance to the specified road model is less than a preset distance and whose connecting line does not pass through the specified road model. The stopping condition is then checked again. If the stopping condition is not met, a second road model is selected from the multiple road models whose distance to the previously selected second road model is less than a preset distance and whose connecting line does not pass through the previously selected second road model. This process is repeated until the stopping condition is met. The second road model selected when the stopping condition is met, along with the specified road model, can then be considered as multiple first road models for the same intersection area.

[0154] For example, if the processing device receives 100 road models, it can first select road model 1 as the designated road model and use it as the cluster center of a category. If the stopping condition is not met, it can filter out road models 2 and 3 from the multiple road models that are less than a preset distance from road model 1 and whose connecting lines do not pass through road model 1. After this filtering, the resulting multiple first road models include road models 1 to 3. Then, it is determined whether the stopping condition is met. If the stopping condition is not met, it can filter out road models 2 and 3 that are less than a preset distance from road model 1 and whose connecting lines do not pass through road model 1. Road models 4-10, where the distance between road models 2 is less than a preset distance and the line connecting them to road models 2 does not pass through the road models, are selected from multiple road models. Road models 11-20, where the distance between them and road models 3 is less than a preset distance and the line connecting them to road models 3 does not pass through the road models, are then selected. After this selection, multiple first road models are obtained, including road models 1-40. The above steps are repeated until the stopping condition is met. At this point, the initially specified road model 1 and the subsequent road models 2-50 selected multiple times are considered as multiple first road models belonging to the same category.

[0155] After obtaining multiple first road models under one category, multiple first road models under the next category are then aggregated. For example, road model 51 is selected as the specified road model, and road 51 is selected as the cluster center of another category. If the stopping condition is not met, road models 57, 100, etc., which are less than the preset distance from road model 51 and whose connection with road model 51 does not pass through the road model are selected from the remaining road models 52 to 100. This process is repeated until the stopping condition is met. Then, the initially specified road model 51 and the selected road models are used as multiple first road models under another category.

[0156] For a fourth road model other than the target road model among multiple road models, it is necessary to calculate whether the distance between it and the target road model is less than a preset distance, and whether the line connecting it to the target road model passes through the road model. If the distance between it and the target road model is less than the preset distance, and the line connecting it to the target road model does not pass through the road model, then the fourth road model is treated as a second road model and assigned to the same cluster as the target road model. If the distance between it and the target road model reaches the preset distance, and / or the line connecting it to the target road model passes through the road model, then the fourth road model participates in the clustering of road models under other categories.

[0157] For example, if the processing device receives 100 road models, and the target road model is road model 2, it will determine whether the distance between road model 2 and the remaining 99 fourth road models is less than a preset distance, and whether the line connecting road model 2 and road model 2 passes through the road model. The road model is any one of the 100 road models.

[0158] The stopping conditions include any one of the following:

[0159] The first condition is that the distance between multiple first road models and the third road model in the same category is greater than or equal to a preset distance and / or the line connecting them to the third road model passes through the road model, wherein the third road model is a road model other than the multiple first road models in the same category among the multiple road models.

[0160] For example, if the processing device receives 100 road models, and the selected first road models in the same category are road models 1 to 20, then the remaining road models 21 to 100 are third road models. For each road model in road models 1 to 20, it is determined whether the distance between it and road models 21 to 100 reaches a preset distance, and whether the connecting line passes through any road model. If the distance reaches the preset distance and / or the connecting line passes through any road area, the stopping condition is met, indicating that road models 1 to 20 belong to the same category.

[0161] The second condition is that the number of multiple first road models under the same category no longer changes.

[0162] After multiple rounds of filtering, the number of multiple first road models in the same category will eventually stop changing. The distance between any two first road models in the same category is less than a preset distance, and the line connecting any two first road models does not pass through the road model. Therefore, these first road models with similar characteristics will be clustered into the same category. After clustering the first road models with similar characteristics into the same category, the number of multiple first road models in the same category will tend to stabilize and no longer change.

[0163] Conversely, if a road model located outside the same category is at a predetermined distance from multiple first road models within the same category, and / or the line connecting it to multiple first road models passes through the road model, then this part of the road model will be clustered into other clusters to form a second road model under another category.

[0164] When calculating the connection between the target road model and a fourth road model (excluding the target road model) among multiple road models, the calculation involves connecting the first center point between two intersection road models in the target road model and the second center point between two intersection road models in the fourth road model. The first center point between two intersection road models in the target road model represents the position of the target road model; the second center point between two intersection road models in the fourth road model represents the position of the fourth road model.

[0165] Please see Figure 10 As shown, if the target road model includes intersection road model 1 and intersection road model 2, and the fourth road model includes intersection road model 3 and intersection road model 4, the line connecting the target road model and the fourth road model is the line connecting the first position center point between intersection road model 1 and intersection road model 2, and the second position center point between intersection road model 3 and intersection road model 4.

[0166] Understandably, while multiple road models can be clustered into the same category by calculating the distance between them, there may be two road models that are close to each other but belong to different intersection areas within the same category cluster. If they are clustered into the same category and assigned to the same intersection area, there will be errors.

[0167] In this embodiment of the disclosure, in addition to calculating the distance between the target road model and the fourth road model excluding the target road model, the connection between the target road model and the fourth road model is also calculated. If the connection passes through any of the multiple road models, it means that the fourth road model and the target road model do not belong to the same category; if it does not pass through any road model, it means that the fourth road model and the target road model belong to the same category, and the fourth road model will be used as the second road model.

[0168] Among them, the road model that the line does not cross includes the intersection road model in the road model that the line does not cross.

[0169] Please see Figure 11 As shown, taking a cross-shaped intersection area as an example, within this cross-shaped intersection area, the lines connecting any two road models (1 to 4) are within the blank areas of the cross-shaped intersection area and do not cross any other road models surrounding the cross-shaped intersection area. For example, the line connecting road model 1 and road model 2 is within the blank areas of the cross-shaped intersection area and does not cross any intersection road model among road models 1 to 4.

[0170] Please see Figure 12The two types of intersection areas shown are a cross-shaped intersection area and a straight-ahead intersection area. Taking them as examples, if the cross-shaped intersection area and the straight-ahead intersection area are adjacent, the line connecting road model 1 in the cross-shaped intersection area and road model 30 in the straight-ahead intersection area passes through the road model above road model 30 and the intersection road model below road model 2. This indicates that road 1 and road model 30 belong to different intersection areas.

[0171] In this embodiment of the disclosure, a second road model is selected from multiple road models. The distance between the second road model and the target road model is less than a preset distance, and the line connecting the second road model and the target road model does not pass through the road model. This can further ensure that the selected second road model belongs to the same intersection area and the same category as the target road model. This avoids classifying road models in other intersection areas into intersection areas under the same target road model. This achieves accurate classification of multiple first road models in different intersection areas, and the first road map around the intersection area constructed based on multiple first road models in the same intersection area will be more accurate.

[0172] (2) Based on multiple first road models around the intersection area, obtain the first road map around the intersection area.

[0173] Multiple first road models belonging to the same intersection area can be merged and stitched together to obtain a second road map of the intersection area. Then, based on the stop lines at the ends of each road in the second road map, a first road map can be obtained.

[0174] If multiple first road models are road models associated with two identical intersection road models, then the multiple first road models are merged to obtain the first road model associated with the two intersection road models.

[0175] In the case where multiple first road models are road models associated with different intersection road models, the multiple first road models are spliced ​​together according to their positions to obtain first road models in different directions around the intersection area.

[0176] A stop line is a type of traffic marking used to indicate the location where traffic equipment must stop under special circumstances, such as when the traffic light is red or when there are pedestrians crossing the zebra crossing in front of the stop line. In these special circumstances, traffic equipment must stop within the stop line.

[0177] In this second road map, some roads may have stop lines at their ends, while others may not.

[0178] If there is no stop line at the end of the road, the stop line can be fitted based on the endpoints of the road. If there is a stop line at the end of the road, there is no need to fit the stop line; the existing stop line can be used directly.

[0179] For example, if there is no stop line at the end of the road in the second road map, a fitting line is fitted to the end of the road based on the endpoint of the road end. The fitting line is a straight line without endpoints. Then, the outermost line of the outermost lane in the second road map is taken as the end point of the fitting line to obtain the stop line at the end of the road. The outermost line of the road is usually the position where it connects with the pedestrian walkway.

[0180] Please see Figure 13 As shown, the fitting line at the end of the road can be fitted based on the endpoints 1 and 2 of the end of road 1 and the adjacent road 2 in the second road map; then the intersection of the outermost lane 11 and lane 22 of the road with the fitting line is used as the starting point and ending point of the fitting line, thereby fitting the stop line at the end of the road.

[0181] After obtaining the stop lines at the ends of each road in the second road map, the ends of adjacent stop lines can be connected to form the boundaries of the blank areas in the intersection area, resulting in, as shown below. Figure 14 The first road map shown.

[0182] In the process of fitting the line by using the endpoints at the end of the road, the least squares method can be used. The least squares method uses at least two endpoints at the end of the road to fit the line.

[0183] If there is no stop line at the end of the road in the second road map, a fitting line can be fitted by the endpoints of the road and the adjacent roads. Then, the intersection point between the outermost lane and the fitting line is taken as the start and end points of the fitting line, thereby fitting the stop line at the end of the road and obtaining the first road map. Only then can the traffic equipment plan the stopping position according to the stop lines of each road intersection area in the first road map.

[0184] Figure 16 This is a data processing system proposed according to an exemplary embodiment, the data processing system including traffic equipment and processing equipment.

[0185] The traffic equipment uploads the constructed road model to the processing equipment. The traffic equipment obtains its fused location information based on its absolute and relative positions. Then, based on the perceived road information, the traffic equipment constructs a road topology. After determining that the traffic equipment has passed through an intersection area based on the road topology, a road model is generated using the perceived road topology and the traffic equipment's location information.

[0186] The processing device receives road models uploaded by various processing devices, such as road model 1 to road model N.

[0187] The processing equipment clusters the various road models, dividing them into road models of different intersection regions, such as road models of intersection region 1 to intersection region M.

[0188] For each intersection area, the processing device performs fusion matching on the road model of each intersection area to obtain a second road map after fusion for each intersection area, such as the second road map of intersection area 1 to intersection area M.

[0189] The processing device calculates the stop lines of the road model after the intersection area is merged, obtains the stop lines of each intersection area, and then constructs the first road map of the intersection area, such as the first road map of intersection area 1 to intersection area M.

[0190] Figure 17 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment. (Refer to...) Figure 17 The data processing device 1700 includes: a sensing module 1710, a first transmitting module 1720 and a first receiving module 1730.

[0191] The perception module 1710 is configured to determine a road model around the intersection area when it detects that a traffic device has passed through the intersection area; the road model indicates road information around the intersection area.

[0192] The first sending module 1720 is configured to send the road model to the processing device; the processing device is used to obtain a first road map of the intersection area based on multiple road models sent by multiple traffic devices.

[0193] The first receiving module 1730 is configured to receive a first road map returned by the processing device.

[0194] Optionally, the data processing device 1700 further includes:

[0195] The road topology construction module is configured to acquire the road topology structure around the intersection area; the road topology structure includes road markings of the roads traversed by the traffic equipment.

[0196] The intersection area perception module is configured to determine that the traffic equipment has passed through the intersection area when different road signs are detected in the road topology.

[0197] Optionally, the sensing module 1710 is further configured to obtain the road model based on the location information of the traffic equipment and the road topology around the intersection area.

[0198] Figure 18 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment. (Refer to...) Figure 18 The data processing device 1800 includes a second receiving module 1810, a production module 1820, and a second transmitting module 1830.

[0199] The second receiving module 1810 is configured to receive multiple road models sent by multiple traffic devices; the road models are determined when the traffic devices have passed through an intersection area, and the road models indicate road information around the intersection area;

[0200] The production module 1820 is configured to obtain a first road map around the intersection area based on the plurality of road models;

[0201] The second sending module 1830 is configured to send the first road map to the plurality of traffic devices.

[0202] Optionally, module 1820 includes:

[0203] The clustering submodule is configured to cluster the multiple road models, classifying multiple first road models belonging to the same intersection area into the same category.

[0204] The calculation submodule is configured to obtain a first road map around the intersection area based on multiple first road models around the intersection area.

[0205] Optionally, the clustering submodule is also configured to repeatedly perform the following filtering steps if the stopping condition is not met:

[0206] From the plurality of road models, a second road model is selected that is less than a preset distance from the target road model and whose connecting line to the target road model does not pass through the road model; the target road model is a specified road model from the plurality of road models or the second road model selected in the previous screening.

[0207] If the stopping condition is met, the target road model and the second road model are classified as the plurality of first road models under the same category.

[0208] Optionally, the stopping condition includes any one of the following:

[0209] The distance between multiple first road models and third road models in the same category is greater than or equal to a preset distance and / or the line connecting them to the third road model passes through the road model, wherein the third road model is a road model other than the multiple first road models in the same category among the multiple road models;

[0210] The number of multiple first road models under the same category no longer changes.

[0211] Optionally, the computation submodule includes:

[0212] The fusion submodule is configured to fuse multiple first road models around the intersection area to obtain a second road map of the intersection area;

[0213] The stop line submodule is configured to obtain the first road map based on the stop lines at the ends of each road in the second road map.

[0214] Optionally, the stop line submodule includes:

[0215] The first fitting submodule is configured to fit a stop line at the end of a road based on the endpoint of the road when there is no stop line at the end of the road in the second road map.

[0216] The second fitting submodule is configured to obtain the first road map based on the stop lines at the ends of each road in the second road map.

[0217] Optionally, the first fitting submodule includes:

[0218] The third fitting submodule is configured to fit a fitting line to the end of the road based on the endpoint of the road when there is no stop line at the end of the road in the second road map.

[0219] The fourth fitting submodule is configured to take the outermost line of the outermost lane in the second road map as the end point of the fitting line to obtain the stop line at the end of the road.

[0220] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0221] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the data processing method provided in this disclosure.

[0222] Figure 19 This is a block diagram illustrating a transportation device 1900 according to an exemplary embodiment. For example, the transportation device 1900 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. The transportation device 1900 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0223] Reference Figure 19 The transportation device 1900 may include various subsystems, such as an infotainment system 1910, a sensing system 1920, a decision control system 1930, a drive system 1940, and a computing platform 1950. The transportation device 1900 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the transportation device 1900 can be interconnected via wired or wireless means.

[0224] In some embodiments, the infotainment system 1910 may include a communication system, an entertainment system, and a navigation system, etc.

[0225] The sensing system 1920 may include several types of sensors for sensing information about the environment surrounding the transportation equipment 1900. For example, the sensing system 1920 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0226] The decision control system 1930 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0227] The drive system 1940 may include components that provide powered motion to the vehicle 1900. In one embodiment, the drive system 1940 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0228] Some or all of the functions of the transportation equipment 1900 are controlled by a computing platform 1950. The computing platform 1950 may include at least one processor 1951 and a memory 1952, the processor 1951 being able to execute instructions 1953 stored in the memory 1952.

[0229] The processor 1951 can be any conventional processor, such as a commercially available CPU. The processor can also include, for example, a Graphics Processing Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0230] The memory 1952 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0231] In addition to instruction 1953, memory 1952 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 1952 can be used by computing platform 1950.

[0232] In this embodiment of the disclosure, processor 1951 may execute instruction 1953 to complete all or part of the steps of the above-described data processing method.

[0233] In one exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the data processing method described above when executed by the programmable device.

[0234] Some embodiments of this disclosure also provide a chip system, such as Figure 20 As shown, the chip system includes at least one processor 2001 and at least one interface circuit 2002. The processor 2001 and the interface circuit 2002 are interconnected via lines. For example, the interface circuit 2002 can be used to receive signals from other devices (e.g., the memory of an electronic device). As another example, the interface circuit 2002 can be used to send signals to other devices (e.g., the processor 2001). Exemplarily, the interface circuit 2002 can read instructions stored in memory and send those instructions to the processor 2001. When the instructions are executed by the processor 2001, the data processing device can perform the steps in the above embodiments. Of course, the chip system may also include other discrete devices, and some embodiments of this disclosure do not specifically limit this.

[0235] In some embodiments of this disclosure, the interface circuit 2002 can acquire data, program instructions, and / or information from the internal storage area of ​​the chip system; it can also acquire data, program instructions, and / or information from outside the chip system.

[0236] Figure 21 This is a block diagram illustrating a processing apparatus 2100 for data processing according to an exemplary embodiment. For example, the processing apparatus 2100 may be provided as a server, such as a cloud server. (Refer to...) Figure 21 The processing device 2100 includes a processing component 2122, which further includes one or more processors, and memory resources represented by memory 2132 for storing instructions, such as application programs, that can be executed by the processing component 2122. The application programs stored in memory 2132 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 2122 is configured to execute instructions to perform the aforementioned data processing methods.

[0237] The processing device 2100 may also include a power supply component 2126 configured to perform power management of the processing device 2100, a wired or wireless network interface 2150 configured to connect the processing device 2100 to a network, and an input / output interface 2158. The processing device 2100 can operate on an operating system stored in memory 2132.

[0238] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0239] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0240] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0241] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

[0242] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0243] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Rather, these terms are used only to distinguish one component, part, region, layer, or section from another. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section. Furthermore, the terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “a plurality” means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A data processing method, characterized in that, include: Upon detecting that traffic equipment has passed through an intersection area, a road model surrounding the intersection area is determined; the road model includes road information surrounding the intersection area. The road model is sent to a processing device; the processing device is used to obtain a first road map of the intersection area based on multiple road models sent by multiple traffic devices. Receive the first road map returned by the processing device.

2. The method according to claim 1, characterized in that, Before determining the road model around the intersection area, the method further includes: Obtain the road topology around the intersection area; the road topology includes road markings on the roads traversed by the traffic equipment; If different road signs are detected in the road topology, it is determined that the traffic equipment has passed through the intersection area.

3. The method according to claim 1, characterized in that, Determining the road model around the intersection area includes: The road model is obtained based on the location information of the traffic equipment and the road topology around the intersection area.

4. A data processing method, characterized in that, include: Receive multiple road models sent by multiple traffic devices; The road model is determined after the traffic equipment has passed through the intersection area, and the road model indicates the road information around the intersection area; Based on the multiple road models, a first road map is obtained around the intersection area; The first road map is sent to the plurality of transportation devices.

5. The method according to claim 4, characterized in that, The process of obtaining a first road map around the intersection area based on the multiple road models includes: Cluster the multiple road models and group multiple first road models belonging to the same intersection area into the same category; Based on multiple first road models surrounding the intersection area, a first road map surrounding the intersection area is obtained.

6. The method according to claim 5, characterized in that, The clustering of the multiple road models, classifying multiple first road models belonging to the same intersection area into the same category, includes repeatedly performing the following filtering steps if the stopping condition is not met: From the plurality of road models, a second road model is selected that is less than a preset distance from the target road model and whose connecting line to the target road model does not pass through the road model; the target road model is a specified road model from the plurality of road models or the second road model selected in the previous screening. If the stopping condition is met, the target road model and the second road model are classified as the plurality of first road models under the same category.

7. The method according to claim 6, characterized in that, The stopping condition includes any one of the following: The distance between multiple first road models and third road models in the same category is greater than or equal to a preset distance, and / or the line connecting them to the third road model passes through the road model, wherein the third road model is a road model other than the multiple first road models in the same category among the multiple road models; The number of multiple first road models under the same category no longer changes.

8. The method according to claim 5, characterized in that, The step of obtaining a first road map around the intersection area based on multiple first road models around the intersection area includes: Multiple first road models around the intersection area are fused to obtain a second road map of the intersection area; The first road map is obtained based on the stop lines at the ends of each road in the second road map.

9. The method according to claim 8, characterized in that, The step of obtaining the first road map based on the stop lines at the ends of each road in the second road map includes: If there is no stop line at the end of the road in the second road map, the stop line at the end of the road is fitted based on the endpoint of the road end; The first road map is obtained based on the stop lines at the ends of each road in the second road map.

10. The method according to claim 9, characterized in that, In the case where there is no stop line at the end of the road in the second road map, the stop line at the end of the road is fitted based on the endpoint of the road end, including: In the case that there is no stop line at the end of the road in the second road map, a fitting line for the end of the road is fitted based on the endpoint of the end of the road; The outermost line of the outermost lane in the second road map is used as the end point of the fitted line to obtain the stop line at the end of the road.

11. A data processing apparatus, characterized in that, include: The perception module is configured to determine a road model around the intersection area when it detects that a traffic device has passed through the intersection area; the road model indicates road information around the intersection area. A first sending module is configured to send the road model to a processing device; the processing device is used to obtain a first road map of the intersection area based on multiple road models sent by multiple traffic devices. The first receiving module is configured to receive a first road map returned by the processing device.

12. A data processing apparatus, characterized in that, include: The second receiving module is configured to receive multiple road models sent by multiple traffic devices; The road model is determined after the traffic equipment has passed through the intersection area, and the road model indicates the road information around the intersection area; The creation module is configured to obtain a first road map around the intersection area based on the multiple road models; The second sending module is configured to send the first road map to the plurality of traffic devices.

13. A transportation device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured as follows: The steps of performing the method according to any one of claims 1 to 3.

14. A processing apparatus, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured as follows: Perform the steps of the method described in any one of claims 4 to 10.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1 to 3 or 4 to 10.

Images