Vehicle control method and device, vehicle storage medium and program product
By caching and updating crowdsourced maps in vehicles, the problem of inaccurate planning and control caused by errors in high-precision maps and communication anomalies is solved, achieving higher real-time performance and accuracy, and reducing dependence on the cloud and bandwidth consumption.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2026-03-24
AI Technical Summary
In vehicle autonomous driving assistance, high-precision maps may contain errors, affecting the decision-making of autonomous driving assistance. Furthermore, when the vehicle's communication with the cloud is abnormal, it may be unable to obtain and use cloud maps, resulting in inaccurate planning and control.
By caching crowdsourced maps collected by multiple devices in the vehicle, a local crowdsourced map is generated. Control is implemented based on the local map in case of communication failure, while the local map is updated to maintain consistency when communication is normal. The map data is stored in an SQLite database to support frequent queries and updates.
It improved the real-time performance and accuracy of the map, reduced the vehicle's reliance on the cloud, lowered bandwidth consumption, and ensured the normal operation of planning and control in the event of communication failures.
Smart Images
Figure CN121721997A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of planning and control, and in particular to vehicle control methods, devices, vehicle storage media, and program products. Background Technology
[0002] In autonomous driving assistance systems, vehicles need the ability to acquire information about their surroundings. For example, vehicles can use high-definition maps to perceive their surroundings and expand the boundaries of their perception. High-definition maps can include detailed information such as the topological relationships between roads, road components, and road attributes, providing assurance for autonomous driving assistance. However, in some scenarios, high-definition maps may contain errors, potentially affecting the decisions made by autonomous driving assistance systems. Summary of the Invention
[0003] To overcome the problems existing in related technologies, this disclosure provides a vehicle control method, device, vehicle storage medium, and program product.
[0004] According to a first aspect of the present disclosure, a vehicle control method is provided, comprising: A crowdsourced map is obtained from the cloud, and the crowdsourced map is generated from map data collected from multiple devices; The crowdsourced map is stored in the vehicle to obtain a local crowdsourced map; In the event of an abnormal communication between the vehicle and the cloud, the vehicle is controlled according to the local crowdsourced map.
[0005] Optionally, the method includes: If the vehicle is communicating normally with the cloud and the local crowdsourced map is inconsistent with the cloud crowdsourced map, the updated data of the local crowdsourced map is obtained from the cloud. The local crowdsourcing map is updated using the updated data; The vehicle is controlled based on the updated local crowdsourced map.
[0006] Optionally, the method includes: Obtain the version identifier of the cloud-based crowdsourced map to obtain the first identifier; Obtain the version identifier of the local crowdsourced map; If the first identifier is inconsistent with the version identifier of the local crowdsourcing map, it is determined that the local crowdsourcing map is inconsistent with the cloud crowdsourcing map.
[0007] Optionally, the local crowdsourcing map includes multiple sub-maps, and obtaining the updated data of the local crowdsourcing map from the cloud includes: For each sub-map, obtain the version identifier of the sub-map to obtain the second identifier; If the first identifier and the second identifier are inconsistent, the sub-map corresponding to the second identifier will be identified as the map to be updated. The update data of the map to be updated is obtained from the cloud.
[0008] Optionally, the method includes: The vehicle is communicating normally with the cloud, and the local crowdsourced map is connected to the cloud crowdsourced map. Figure 1 In the event of a conflict, the vehicle is controlled according to the local crowdsourced map.
[0009] Optionally, controlling the vehicle based on the local crowdsourced map includes: If the sub-maps of the local crowdsourcing map are not stored in memory, calculate the distance between the area corresponding to each sub-map of the local crowdsourcing map and the current position of the vehicle. The first sub-map is obtained by identifying sub-maps whose distance is less than or equal to the threshold. Save the first sub-map in the queue; The vehicle is controlled according to the sub-map in the queue; Determine the sub-maps whose distance is greater than the threshold to obtain the second sub-map; The second sub-map is stored in the memory.
[0010] Optionally, the method includes: If a sub-map of the local crowdsourced map is stored in the memory, calculate the distance between the area corresponding to the sub-map in the memory and the current position of the vehicle. Determine the sub-maps whose distance is less than or equal to the threshold, and obtain a new first sub-map; The new first sub-map is saved in the queue.
[0011] According to a second aspect of the present disclosure, a vehicle control device is provided, comprising: The first module is configured to retrieve a crowdsourced map from the cloud, which is generated from map data collected from multiple devices; The second module is configured to store the crowdsourced map in the vehicle to obtain a local crowdsourced map; The third module is configured to control the vehicle based on the local crowdsourced map in the event of an abnormal communication between the vehicle and the cloud.
[0012] Optionally, the vehicle control device includes: The fourth module is configured to obtain updated data of the local crowdsourced map from the cloud when the vehicle is communicating normally with the cloud and the local crowdsourced map is inconsistent with the cloud crowdsourced map. The fifth module is configured to update the local crowdsourced map using the updated data; The sixth module is configured to control the vehicle based on an updated local crowdsourced map.
[0013] Optionally, the vehicle control device includes: The seventh module is configured to obtain the version identifier of the cloud-based crowdsourced map and obtain the first identifier; The eighth module is configured to obtain the version identifier of the local crowdsourced map; The ninth module is configured to determine that the local crowdsourcing map is inconsistent with the cloud crowdsourcing map if the first identifier is inconsistent with the version identifier of the local crowdsourcing map.
[0014] Optionally, the local crowdsourced map includes multiple sub-maps, and the fourth module includes: The first submodule is configured to obtain the version identifier of each submap and obtain the second identifier. The second submodule is configured to determine the submap corresponding to the second identifier as the map to be updated when the first identifier and the second identifier are inconsistent. The third submodule is configured to obtain update data for the map to be updated from the cloud.
[0015] Optionally, the vehicle control device includes: The tenth module is configured to ensure that communication between the vehicle and the cloud is normal, and that the local crowdsourced map and the cloud crowdsourced map are connected. Figure 1 In the event of a conflict, the vehicle is controlled according to the local crowdsourced map.
[0016] Optionally, the third module includes: The fourth submodule is configured to calculate the distance between the area corresponding to each submap of the local crowdsourcing map and the current position of the vehicle, when the submaps of the local crowdsourcing map are not saved in memory. The fifth submodule is configured to determine the submaps whose distance is less than or equal to a threshold, thereby obtaining the first submap; The sixth submodule is configured to store the first submap in a queue; The seventh submodule is configured to control the vehicle based on a submap in the queue; The eighth submodule is configured to determine submaps whose distance is greater than the threshold, and obtain a second submap; The ninth submodule is configured to store the second submap in the memory.
[0017] Optionally, the vehicle control device includes: The eleventh module is configured to, when the local crowdsourced map sub-map is stored in memory, calculate the distance between the area corresponding to the sub-map in memory and the current position of the vehicle. The twelfth module is configured to determine sub-maps whose distance is less than or equal to the threshold, and obtain a new first sub-map. The thirteenth module is configured to store the new first sub-map in the queue.
[0018] According to a third aspect of the present disclosure, a vehicle is provided, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to perform the steps of the method described in any of the first aspects.
[0019] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.
[0020] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0021] In the above solution, a crowdsourced map can be obtained from the cloud, generated from map data collected by multiple devices. This allows the crowdsourced map to be stored in the vehicle, creating a local crowdsourced map. Thus, in the event of a communication failure between the vehicle and the cloud, the vehicle can be controlled based on the local crowdsourced map.
[0022] The above solution allows for caching of crowdsourced maps within the vehicle. Since crowdsourced maps are generated by fusing map data collected from multiple devices, they offer higher real-time performance compared to high-precision maps. Therefore, using crowdsourced maps helps reduce map errors, thereby ensuring the accuracy of vehicle planning and control. Furthermore, storing the crowdsourced map in the vehicle reduces its reliance on the cloud, thus lowering bandwidth consumption between the vehicle and the cloud. Moreover, storing the crowdsourced map allows for vehicle control based on the local crowdsourced map even in the event of communication failures between the vehicle and the cloud, ensuring the normal operation of vehicle planning and control.
[0023] 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
[0024] 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.
[0025] Figure 1 This is a flowchart illustrating a vehicle control method according to an exemplary embodiment.
[0026] Figure 2 This is a flowchart illustrating an implementation of step S13 according to an exemplary embodiment.
[0027] Figure 3 This is a flowchart illustrating a vehicle control method according to an exemplary embodiment.
[0028] Figure 4 This is a flowchart illustrating a vehicle control method according to an exemplary embodiment.
[0029] Figure 5 This is a block diagram illustrating a vehicle control device according to an exemplary embodiment.
[0030] Figure 6 This is a block diagram illustrating a vehicle according to an exemplary embodiment. Detailed Implementation
[0031] 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.
[0032] Before introducing the vehicle control method, device, vehicle storage medium and program product of this disclosure, the relevant scenarios of the embodiments of this disclosure will be introduced first.
[0033] Automated driving assistance systems utilize technologies such as sensors, cameras, and radar to provide drivers with some automated functions during driving. They can assist in functions such as lane keeping, speed control, and maintaining a safe following distance, thus improving driving safety and convenience.
[0034] In autonomous driving assistance systems, vehicles need the ability to acquire information about their surroundings. For example, high-definition maps can be used to obtain this information. High-definition maps can include information such as the topological relationships between roads, road components, and road attributes, serving as the basis for the vehicle to perceive its surroundings and expand its perception boundaries. In some scenarios, the topological relationships and geometric attributes of roads provided by high-definition maps can also be used to continuously predict the vehicle's possible driving states.
[0035] It's worth noting that high-definition maps are complex to create and updated infrequently. In some road construction areas, insufficient updates may lead to errors in the high-definition map information. Incorrect high-definition maps can cause errors in vehicle positioning or planning and control, potentially affecting the reliability of automated driving assistance systems.
[0036] Therefore, this disclosure provides a vehicle control method, which can be executed by a vehicle, related components in the vehicle, or related devices that are independently configured with respect to the vehicle. Figure 1 This is a flowchart illustrating a vehicle control method according to an exemplary embodiment of this disclosure, with reference to... Figure 1 The vehicle control method includes: In step S11, a crowdsourced map is obtained from the cloud. The crowdsourced map is generated by collecting map data from multiple devices.
[0037] In one implementation, the plurality of devices may include vehicles, terminals (mobile phones, tablets), drones, etc. Taking a vehicle as an example, the vehicle can be equipped with relevant sensors, such as lidar and cameras. In this way, the vehicle can collect road environment information (such as location data, lane lines, signs, obstacles, road conditions, etc.) during its operation, thereby constructing and generating map data corresponding to the vehicle.
[0038] However, map data from a single vehicle may not cover a large geographical area. Furthermore, due to processing power limitations, the accuracy of map data from a single vehicle may also be relatively low. Therefore, the vehicle can also upload its collected map data to the cloud in real time or periodically. As an example, the cloud may include the cloud server of the vehicle's manufacturer. In possible implementations, the cloud may also include relevant cloud servers configured based on demand.
[0039] After receiving map data uploaded from multiple devices, the cloud can merge the received map data, removing noise or erroneous data in the process. By merging the map data from various devices, a high-precision cloud-based crowdsourced map can be generated, covering a larger geographical area.
[0040] It should be noted that vehicles may sometimes travel in areas such as tunnels and elevated roads. In these areas, vehicles may be unable to successfully send requests to the cloud, and thus may be unable to access and use the crowdsourced map in the cloud. Therefore, the crowdsourced map can be stored in the vehicle.
[0041] Reference Figure 1 In step S11, a crowdsourced map is obtained from the cloud.
[0042] For example, in one implementation, the method can be performed by a vehicle, so that the vehicle can obtain a cloud-based crowdsourced map (cloud-based crowdsourced map) by sending a request to the cloud.
[0043] In step S12, the crowdsourced map is stored in the vehicle to obtain the local crowdsourced map.
[0044] In one implementation, the crowdsourced map can be stored in a vehicle-related database to obtain a local crowdsourced map.
[0045] As an example, the crowdsourced map can be stored using an SQLite database. This allows for fast querying and updating of the crowdsourced map. It also supports frequent query and update requests from vehicles and helps reduce the disk space occupied by the crowdsourced map.
[0046] Reference Figure 1 In step S13, if the vehicle communication with the cloud is abnormal, the vehicle is controlled according to the local crowdsourced map.
[0047] In one implementation, an abnormality in the vehicle-cloud communication can be determined if a lag is detected in the vehicle-cloud communication.
[0048] In one implementation, an abnormality in vehicle-to-cloud communication can be determined if a failure to communicate between the vehicle and the cloud is detected.
[0049] Figure 2 This is a flowchart illustrating an implementation of step S13 as shown in an exemplary embodiment of this disclosure, with reference to... Figure 2 The method of controlling the vehicle based on a local crowdsourced map includes: In step S21, if the sub-maps of the local crowdsourcing map are not saved in memory, the distance between the area corresponding to each sub-map of the local crowdsourcing map and the current position of the vehicle is calculated.
[0050] For example, the local crowdsourced map may include multiple tile maps, which can then be used as sub-maps. Furthermore, during processing, the vehicle can read memory to determine if the sub-map is stored in memory. If the sub-map is stored in memory, it can be loaded for processing, thereby improving processing speed. Referring to step S21, if no sub-maps of the local crowdsourced map are stored in memory, the vehicle can load the local crowdsourced map and calculate the distance between the area corresponding to each sub-map and the vehicle's current location.
[0051] As an example, a vehicle can determine the center point of the sub-map and the position of that center point in the world coordinate system, obtaining a first position. The vehicle can also determine its current position in the world coordinate system, obtaining a second position. Thus, the vehicle can calculate the distance between the first position and the second position, and use this distance as the distance between the region corresponding to the sub-map and the vehicle's current position.
[0052] Depending on the requirements, other points in the sub-map can also be selected to calculate the distance, such as determining the point in the sub-map closest to the vehicle and using that point to calculate the distance. This disclosure does not limit this approach.
[0053] Reference Figure 2 In step S22, sub-maps with distances less than or equal to a threshold are determined to obtain the first sub-map.
[0054] The threshold can be set based on requirements. For example, the threshold can be set to 20, 25, etc., in meters. Taking a threshold of 20 as an example, a vehicle can identify sub-maps within 20 meters of its current location as the first sub-map. It should be understood that the first sub-map may include one or more sub-maps.
[0055] In step S23, the first sub-map is saved in the queue.
[0056] In step S24, the vehicle is controlled according to the sub-map in the queue.
[0057] In one implementation, each first sub-map can be added to a queue based on the distance between the area corresponding to the first sub-map and the vehicle's current position. For example, sub-maps can be added to the queue in ascending order of distance. This way, sub-maps with shorter distances are at the front of the queue and can be used by the vehicle more quickly.
[0058] In one implementation, the vehicle can send the sub-maps in the queue to downstream modules in the autonomous driving assistance process.
[0059] As an example, the downstream module may include a map module for autonomous driving assistance functions. For instance, the map module may match environmental information collected by the vehicle (or map data generated based on the environmental information) with the sub-map, thereby mapping the vehicle's location onto the sub-map.
[0060] As an example, the downstream module may include a planning and control module for automated driving assistance functions. In this way, the planning and control module can perform vehicle planning and control based on the sub-map. For example, the planning and control module can plan vehicle control based on the vehicle's position in the sub-map and the information included in the sub-map.
[0061] Reference Figure 2 In step S25, sub-maps with distances greater than a threshold are determined to obtain a second sub-map.
[0062] In step S26, the second sub-map is saved in memory.
[0063] Using the example with a threshold of 20, the vehicle can identify sub-maps with a distance greater than 20 as the second sub-map. Since the distance is greater than the threshold, the second sub-map is likely to be used by the vehicle later, so it can be stored in memory for later retrieval.
[0064] For example, in one implementation, it is possible to: If a sub-map of the local crowdsourced map is stored in the memory, calculate the distance between the area corresponding to the sub-map in the memory and the current position of the vehicle. Determine the sub-maps whose distance is less than or equal to the threshold, and obtain a new first sub-map; The new first sub-map is saved in the queue.
[0065] In other words, if the sub-maps of the local crowdsourced map are stored in memory, the vehicle can quickly retrieve the sub-maps from memory and then calculate the distance. Sub-maps with distances less than or equal to the threshold can then be stored as new first sub-maps in the queue, facilitating vehicle control based on the sub-maps in the queue.
[0066] The above scheme calculates the distance between the area corresponding to the sub-map and the vehicle's current location, thereby loading the sub-map based on the distance. Specifically, the first sub-map with a distance less than or equal to a threshold is stored in a queue for later use, while the second sub-map with a distance greater than the threshold is stored in memory for later use. Thus, compared to loading the entire crowdsourced map, this scheme reduces the amount of map data cached and transmitted. This helps reduce bandwidth usage on the vehicle side and also helps avoid data congestion.
[0067] Furthermore, the above solution allows for caching of crowdsourced maps within the vehicle. Since crowdsourced maps are generated by fusing map data collected from multiple devices, they offer higher real-time performance compared to high-precision maps. Therefore, using crowdsourced maps helps reduce map errors, thereby ensuring the accuracy of vehicle planning and control. Moreover, storing the crowdsourced map in the vehicle reduces its reliance on the cloud, thus lowering bandwidth consumption between the vehicle and the cloud. Additionally, storing the crowdsourced map allows for vehicle control based on the local crowdsourced map even in the event of communication failures between the vehicle and the cloud, ensuring the normal operation of vehicle planning and control.
[0068] Figure 3 This is a flowchart illustrating a vehicle control method according to an exemplary embodiment of this disclosure, with reference to... Figure 3 The method is in Figure 1 In addition to: In step S14, if the vehicle is communicating normally with the cloud and the local crowdsourced map is inconsistent with the cloud crowdsourced map, the updated data of the local crowdsourced map is obtained from the cloud.
[0069] Here, we will first provide an example of how to determine whether the local crowdsourcing map and the cloud-based crowdsourcing map are consistent.
[0070] In one possible implementation, a hash value can be calculated on the cloud-based crowdsourcing map to obtain a first hash value. Additionally, a hash value can be calculated on the local crowdsourcing map to obtain a second hash value. Thus, if the first hash value and the second hash value are inconsistent, it can be determined that the local crowdsourcing map and the cloud-based crowdsourcing map are inconsistent. Furthermore, if the first hash value and the second hash value are consistent, it can be determined that the local crowdsourcing map and the cloud-based crowdsourcing map are consistent. Figure 1 To.
[0071] In one possible implementation, the consistency between the local crowdsourcing map and the cloud-based crowdsourcing map can also be determined based on the version identifier of the crowdsourcing map.
[0072] For example, the version identifier of the cloud-based crowdsourcing map can be obtained to obtain a first identifier. Additionally, the version identifier of the local crowdsourcing map can be obtained. Thus, if the first identifier and the version identifier of the local crowdsourcing map are inconsistent, it can be determined that the local crowdsourcing map is inconsistent with the cloud-based crowdsourcing map. If the first identifier and the version identifier of the local crowdsourcing map are consistent, it can be determined that the local crowdsourcing map is inconsistent with the cloud-based crowdsourcing map. Figure 1 To. The version identifier can be set based on requirements; as an example, the version identifier can be the version number of the crowdsourced map.
[0073] Reference Figure 3 In step S15, the local crowdsourcing map is updated by updating the data.
[0074] In one possible implementation, the complete crowdsourced map can be requested from the cloud and then replaced with the local crowdsourced map to achieve the update.
[0075] In one possible implementation, in order to reduce data transmission volume and reduce bandwidth usage on the link, the local crowdsourced map can be updated by requesting the cloud to update it through partial updates.
[0076] For example, in one implementation, the local crowdsourcing map includes multiple sub-maps. Obtaining updated data of the local crowdsourcing map from the cloud includes: For each sub-map, a version identifier is obtained to generate a second identifier. If the first identifier and the second identifier are inconsistent, the sub-map corresponding to the second identifier is identified as the map to be updated. In this way, update data for the map to be updated can be obtained from the cloud.
[0077] For example, if the tile map includes sub-land Figure 1-1 0, where sub-land Figure 1 The version identifier -8 (second identifier) matches the version identifier (first identifier) of the cloud-based crowdsourced map, while the version identifiers of sub-maps 9 and 10 do not match the version identifier of the cloud-based crowdsourced map. Therefore, it can be determined that sub-maps 9 and 10 are maps awaiting updates.
[0078] Furthermore, when retrieving updated data from the cloud, the vehicle can send an update request to the cloud, including the sub-maps numbered 9-10 of the map to be updated. Upon receiving the update request, the cloud can send the sub-maps numbered 9-10 from the cloud-sourced map to the vehicle, and the updated data includes these sub-maps.
[0079] In this way, the vehicle can obtain the updated data and replace the local sub-maps numbered 9-10 with the sub-maps numbered 9-10, thereby completing the update.
[0080] In this way, the sub-map to be updated can be determined based on the version identifier, and the update data for the sub-map can be requested. This method enables partial updates, helps reduce the order of magnitude of the update data, and reduces bandwidth consumption.
[0081] Reference Figure 3 In step S16, the vehicle is controlled according to the updated local crowdsourced map.
[0082] The implementation method for controlling the vehicle based on the local crowdsourced map has been described in detail in the implementation method of step S13, and will not be repeated here for the sake of brevity.
[0083] By employing the above solution, under normal vehicle-cloud communication conditions, the consistency between the cloud-based crowdsourced map and the local crowdsourced map can be detected. If a discrepancy occurs, the local crowdsourced map is updated. This ensures the accuracy of the local crowdsourced map, thereby guaranteeing the reliability of vehicle planning and control using it.
[0084] Furthermore, the vehicle communicates normally with the cloud, and the local crowdsourced map and the cloud crowdsourced map are in good working order. Figure 1 In some cases, the vehicle can also be controlled based on the local crowdsourced map.
[0085] Figure 4 This is a flowchart illustrating a vehicle control method according to an exemplary embodiment of this disclosure, with reference to... Figure 4 The method includes: The vehicle checks its own network for lag. If the network is stable, the vehicle retrieves the version number of the crowdsourced map from its local crowdsourcing database and the version number of the cloud-based crowdsourcing map. The local crowdsourcing map may include multiple tile maps, each with a version number. The vehicle compares the version numbers of each tile map with those of the cloud-based crowdsourcing map. If the version numbers of all tile maps match those of the cloud-based crowdsourcing map, the vehicle can confirm that the local and cloud-based crowdsourcing maps are compatible. Figure 1Therefore, a local crowdsourced map can be loaded for vehicle planning and control. It should be noted that even in cases of network lag, the vehicle can still load the local crowdsourced map for planning and control.
[0086] Furthermore, if the version number of any tile map is inconsistent with the version number of the cloud-based crowdsourced map, the vehicle can identify the tile map as the map to be updated and request update data for the map to be updated from the cloud. The cloud can respond to the request and send the update data, which can be used, for example, to replace the map to be updated. In this way, the vehicle can update its local crowdsourced map based on the update data. Afterward, the vehicle can load the updated local crowdsourced map for planning and vehicle control.
[0087] When loading a local crowdsourced map for vehicle planning and control, the vehicle can calculate the distance between the center point of each tile map and its current position. If the distance is greater than a threshold, the tile map can be stored in memory for later retrieval. The tile map in memory does not need to be sent to downstream modules temporarily. If the distance is less than or equal to the threshold, the tile map can be stored in a queue and sent to downstream modules sequentially. Downstream modules may include a planning and control module, a map module, etc.
[0088] As an example, the downstream module may include a map module for autonomous driving assistance functions. The map module can match environmental information collected by the vehicle (or map data generated based on the environmental information) with the tile map, thereby mapping the vehicle's location onto the tile map.
[0089] As an example, the downstream module may include a planning and control module for automated driving assistance functions. In this way, the planning and control module can perform vehicle planning and control based on the tile map. For example, the planning and control module can plan vehicle control based on the vehicle's position in the tile map and the information included in the tile map.
[0090] The above solution allows for caching of crowdsourced maps within the vehicle. Since crowdsourced maps are generated by fusing map data collected from multiple devices, they offer higher real-time performance compared to high-precision maps. Therefore, using crowdsourced maps helps reduce map errors, thereby ensuring the accuracy of vehicle planning and control. Furthermore, storing the crowdsourced map in the vehicle reduces its reliance on the cloud, thus lowering bandwidth consumption between the vehicle and the cloud. Moreover, storing the crowdsourced map allows for vehicle control based on the local crowdsourced map even in the event of communication failures between the vehicle and the cloud, ensuring the normal operation of vehicle planning and control.
[0091] Furthermore, assuming normal communication between the vehicle and the cloud, the system can detect whether the cloud-based crowdsourced map and the local crowdsourced map are consistent. If they are inconsistent, the local crowdsourced map can be partially updated. This reduces the magnitude of the data update and lowers the risk of network congestion. Simultaneously, updating the local crowdsourced map ensures its real-time performance and accuracy, thereby guaranteeing the reliability of vehicle planning and control using the local crowdsourced map.
[0092] During vehicle control, the above scheme calculates the distance between the center point of the tile map and the vehicle's current position, thereby loading the tile map based on this distance. Specifically, tile maps with a distance less than or equal to a threshold are stored in a queue for later use, while those with a distance greater than the threshold are stored in memory for later use. Thus, compared to loading the entire crowdsourced map, this scheme reduces the amount of map data cached and transmitted. This helps reduce bandwidth usage on the vehicle side and also helps avoid data congestion.
[0093] Based on the same inventive concept, this disclosure provides a vehicle control device. Figure 5 This is a block diagram of a vehicle control device shown in an exemplary embodiment of the present disclosure, with reference to... Figure 5 The vehicle control device includes: The first module 501 is configured to obtain a crowdsourced map from the cloud, the crowdsourced map being generated from map data collected from multiple devices; The second module 502 is configured to store the crowdsourced map in the vehicle to obtain a local crowdsourced map; The third module 503 is configured to control the vehicle based on the local crowdsourced map in the event of an abnormal communication between the vehicle and the cloud.
[0094] The aforementioned vehicle control device allows for the caching of crowdsourced maps within the vehicle. Since crowdsourced maps are generated by fusing map data collected from multiple devices, they offer higher real-time performance compared to high-precision maps. Therefore, using crowdsourced maps helps reduce map errors, thereby ensuring the accuracy of vehicle planning and control. Furthermore, storing the crowdsourced map in the vehicle reduces its reliance on the cloud, thus lowering bandwidth consumption between the vehicle and the cloud. Moreover, storing the crowdsourced map also allows for vehicle control based on the local crowdsourced map even in the event of communication failures between the vehicle and the cloud, ensuring the normal operation of vehicle planning and control.
[0095] Optionally, the vehicle control device includes: The fourth module is configured to obtain updated data of the local crowdsourced map from the cloud when the vehicle is communicating normally with the cloud and the local crowdsourced map is inconsistent with the cloud crowdsourced map. The fifth module is configured to update the local crowdsourced map using the updated data; The sixth module is configured to control the vehicle based on an updated local crowdsourced map.
[0096] Optionally, the vehicle control device includes: The seventh module is configured to obtain the version identifier of the cloud-based crowdsourced map and obtain the first identifier; The eighth module is configured to obtain the version identifier of the local crowdsourced map; The ninth module is configured to determine that the local crowdsourcing map is inconsistent with the cloud crowdsourcing map if the first identifier is inconsistent with the version identifier of the local crowdsourcing map.
[0097] Optionally, the local crowdsourced map includes multiple sub-maps, and the fourth module includes: The first submodule is configured to obtain the version identifier of each submap and obtain the second identifier. The second submodule is configured to determine the submap corresponding to the second identifier as the map to be updated when the first identifier and the second identifier are inconsistent. The third submodule is configured to obtain update data for the map to be updated from the cloud.
[0098] Optionally, the vehicle control device includes: The tenth module is configured to ensure that communication between the vehicle and the cloud is normal, and that the local crowdsourced map and the cloud crowdsourced map are connected. Figure 1 In the event of a conflict, the vehicle is controlled according to the local crowdsourced map.
[0099] Optionally, the third module 503 includes: The fourth submodule is configured to calculate the distance between the area corresponding to each submap of the local crowdsourcing map and the current position of the vehicle, when the submaps of the local crowdsourcing map are not saved in memory. The fifth submodule is configured to determine the submaps whose distance is less than or equal to a threshold, thereby obtaining the first submap; The sixth submodule is configured to store the first submap in a queue; The seventh submodule is configured to control the vehicle based on a submap in the queue; The eighth submodule is configured to determine submaps whose distance is greater than the threshold, and obtain a second submap; The ninth submodule is configured to store the second submap in the memory.
[0100] Optionally, the vehicle control device includes: The eleventh module is configured to, when the local crowdsourced map sub-map is stored in memory, calculate the distance between the area corresponding to the sub-map in memory and the current position of the vehicle. The twelfth module is configured to determine sub-maps whose distance is less than or equal to the threshold, and obtain a new first sub-map. The thirteenth module is configured to store the new first sub-map in the queue.
[0101] This disclosure provides a vehicle, including: processor; Memory used to store processor-executable instructions; The processor is configured to perform steps of the vehicle control method provided in any embodiment of this disclosure.
[0102] This disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle control method provided in any embodiment of this disclosure.
[0103] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle control method provided in any embodiment of this disclosure.
[0104] Regarding the vehicle control device in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the relevant vehicle control method, and will not be elaborated here.
[0105] Figure 6 This is a block diagram illustrating a vehicle 600 according to an exemplary embodiment. For example, vehicle 600 can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 600 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.
[0106] Reference Figure 6The vehicle 600 may include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. The vehicle 600 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 600 can be interconnected via wired or wireless means.
[0107] In some embodiments, the infotainment system 610 may include a communication system, an entertainment system, and a navigation system, etc.
[0108] The perception system 620 may include several sensors for sensing information about the environment surrounding the vehicle 600. For example, the perception system 620 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.
[0109] The decision control system 630 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.
[0110] The drive system 640 may include components that provide powered motion to the vehicle 600. In one embodiment, the drive system 640 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.
[0111] Some or all of the functions of vehicle 600 are controlled by computing platform 650. Computing platform 650 may include at least one processor 651 and memory 652, processor 651 can execute instructions 653 stored in memory 652.
[0112] Processor 651 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.
[0113] The memory 652 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.
[0114] In addition to instruction 653, memory 652 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 652 can be used by computing platform 650.
[0115] In this embodiment of the disclosure, processor 651 may execute instructions 653 to complete all or part of the steps of the vehicle control method described above.
[0116] 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.”
[0117] 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 this specification and the accompanying 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 (e.g., modules) described above, 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.”
[0118] 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.
[0119] 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.
[0120] Furthermore, unless otherwise specified, features of various embodiments of this disclosure described herein may be combined with each other. As used herein, the term “and / or” includes any one of the relevant listed items and any combination of any two or more; similarly, “at least one of…” includes any one of the relevant listed items and any combination of any two or more.
[0121] Although terms such as “first,” “second,” and “third” may be used herein to describe various modules, these modules are not limited to these terms. Rather, these terms are used only to distinguish one module from another. Thus, without departing from the teachings of the examples described herein, the first module mentioned in the examples may also be referred to as the second module. 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. Therefore, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “multiple” means at least two, such as two, three, etc., unless otherwise explicitly specified.
Claims
1. A vehicle control method, characterized in that, include: A crowdsourced map is obtained from the cloud, and the crowdsourced map is generated from map data collected from multiple devices; The crowdsourced map is stored in the vehicle to obtain a local crowdsourced map; In the event of an abnormal communication between the vehicle and the cloud, the vehicle is controlled according to the local crowdsourced map.
2. The method according to claim 1, characterized in that, include: If the vehicle is communicating normally with the cloud and the local crowdsourced map is inconsistent with the cloud crowdsourced map, the updated data of the local crowdsourced map is obtained from the cloud. The local crowdsourcing map is updated using the updated data; The vehicle is controlled based on the updated local crowdsourced map.
3. The method according to claim 2, characterized in that, include: Obtain the version identifier of the cloud-based crowdsourced map to obtain the first identifier; Obtain the version identifier of the local crowdsourced map; If the first identifier is inconsistent with the version identifier of the local crowdsourcing map, it is determined that the local crowdsourcing map is inconsistent with the cloud crowdsourcing map.
4. The method according to claim 3, characterized in that, The local crowdsourcing map includes multiple sub-maps, and obtaining the updated data of the local crowdsourcing map from the cloud includes: For each sub-map, obtain the version identifier of the sub-map to obtain the second identifier; If the first identifier and the second identifier are inconsistent, the sub-map corresponding to the second identifier will be identified as the map to be updated. The update data of the map to be updated is obtained from the cloud.
5. The method according to claim 1, characterized in that, include: When the vehicle communicates normally with the cloud and the local crowdsourcing map is consistent with the cloud crowdsourcing map, the vehicle is controlled according to the local crowdsourcing map.
6. The method according to any one of claims 1 to 5, characterized in that, The step of controlling the vehicle based on the local crowdsourced map includes: If the sub-maps of the local crowdsourcing map are not stored in memory, calculate the distance between the area corresponding to each sub-map of the local crowdsourcing map and the current position of the vehicle. The first sub-map is obtained by identifying sub-maps whose distance is less than or equal to the threshold. Save the first sub-map in the queue; The vehicle is controlled according to the sub-map in the queue; Determine the sub-maps whose distance is greater than the threshold to obtain the second sub-map; The second sub-map is stored in the memory.
7. The method according to claim 6, characterized in that, include: If a sub-map of the local crowdsourced map is stored in the memory, calculate the distance between the area corresponding to the sub-map in the memory and the current position of the vehicle. Determine the sub-maps whose distance is less than or equal to the threshold, and obtain a new first sub-map; The new first sub-map is saved in the queue.
8. A vehicle control device, characterized in that, include: The first module is configured to retrieve a crowdsourced map from the cloud, which is generated from map data collected from multiple devices; The second module is configured to store the crowdsourced map in the vehicle to obtain a local crowdsourced map; The third module is configured to control the vehicle based on the local crowdsourced map in the event of an abnormal communication between the vehicle and the cloud.
9. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to perform the steps of the method according to any one of claims 1 to 7.
10. 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 according to any one of claims 1 to 7.
11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.