Path planning method and device and vehicle

Abstract

The invention discloses a path planning method and device and a vehicle. The method belongs to the technical field of vehicle engineering and navigation, and comprises the following steps: acquiring satellite remote sensing data and road surface monitoring data of a road where a vehicle is located at the current moment; based on the satellite remote sensing data and the road surface monitoring data, the initial driving map is updated to obtain a dynamic driving map, and the initial driving map is used for representing a map used by the vehicle at the last moment; determining the path state of at least one driving path corresponding to the vehicle based on the map information of the dynamic driving map; and based on the path state, selecting a target driving path from the at least one driving path. According to the invention, the technical problem of low path planning efficiency in a complex traffic environment in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the fields of vehicle engineering and navigation technology, and in particular to a path planning method, device and vehicle. Background Art

[0002] Today, intelligent transportation systems (ITS) have become a major driving force for global transportation efficiency, safety, and sustainability. As a crucial component of these systems, intelligent vehicle routing technology is undergoing a transition from theoretical research to large-scale application. In recent years, with the rapid development of sensing, communication, and artificial intelligence technologies, vehicle routing technology has also undergone a transformation from rule-driven to data-driven.

[0003] Current path planning technologies rely heavily on vehicle-side sensor data and pre-loaded electronic maps, with onboard computing units performing real-time processing and decision-making. However, this path planning method is less efficient when dealing with complex traffic environments.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] Embodiments of the present invention provide a path planning method, device, and vehicle to at least solve the technical problem of low efficiency of path planning in complex traffic environments in related technologies.

[0006] According to one aspect of an embodiment of the present invention, a path planning method is provided, comprising: obtaining satellite remote sensing data and road surface monitoring data of a road on which a vehicle is currently located; updating an initial driving map based on the satellite remote sensing data and the road surface monitoring data to obtain a dynamic driving map, wherein the initial driving map is used to represent the map used by the vehicle at the previous moment; determining a path state of at least one driving path corresponding to the vehicle based on map information of the dynamic driving map, wherein the at least one driving path is used to represent a path that the vehicle can travel at the current moment, and the path state is used to represent the traffic condition of the at least one driving path when the vehicle is traveling on the at least one driving path; and selecting a target driving path from the at least one driving path based on the path state.

[0007] Furthermore, the map information includes: remote sensing map information corresponding to satellite remote sensing data, and radar map information corresponding to road surface monitoring data. Based on the map information of the dynamic driving map, the path status of at least one driving path corresponding to the vehicle is determined, including: based on the remote sensing map information, detecting events occurring in multiple map locations contained in the remote sensing map information to obtain event detection results, wherein the event detection results are used to characterize whether the events will affect the normal driving of the vehicle; based on the event detection results, determining a target map location from multiple map locations, wherein the events occurring in the target map location will affect the normal driving of the vehicle; performing correlation detection on the target map location and at least one driving path to obtain a correlation detection result, wherein the correlation detection result is used to characterize the degree of influence of the events occurring in the target map location on at least one driving path; determining the path status of at least one driving path based on the correlation detection result and the radar map information.

[0008] Furthermore, based on the correlation detection result and the radar map information, the path state of at least one driving path is determined, including: determining a first environmental score of the at least one driving path based on the correlation detection result, wherein the environmental score is used to characterize the safety level of the vehicle when driving on the at least one driving path; determining a second environmental score of the at least one driving path based on the radar map information; weighting the first environmental score and the second environmental score to obtain a target state score; and performing a state evaluation on the at least one driving path based on the target state score to obtain a path state.

[0009] Furthermore, based on the remote sensing map information, events occurring in multiple map locations contained in the remote sensing map information are detected to obtain event detection results, including: based on the multiple map locations, determining multiple target map information from the remote sensing map information, wherein the multiple map locations correspond one-to-one to the multiple target map information; based on the multiple target map information, feature extraction is performed on events occurring in the multiple map locations to obtain event features of the events; the event features are input into an event detection model, and the event detection results are determined using the event detection model.

[0010] Furthermore, based on the satellite remote sensing data and the road surface monitoring data, the initial driving map is updated to obtain a dynamic driving map, including: based on the satellite time calibration system, the satellite remote sensing data and the road surface monitoring data are time synchronized to obtain a first synchronized data set, wherein the data in the first synchronized data set are in the same time dimension; based on the satellite positioning system, the data in the first synchronized data set are spatially synchronized to obtain a second synchronized data set, wherein the data in the second synchronized data set are in the same geographic coordinate system; data fusion is performed on the data in the second synchronized data set to obtain target fusion data; based on the target fusion data, the initial driving map is updated to obtain a dynamic driving map.

[0011] Furthermore, based on the target fusion data, the initial driving map is updated to obtain a dynamic driving map, including: constructing at least one driving path based on the target fusion data; analyzing the target fusion data to determine environmental data and road condition data of the road on which the vehicle is currently located; determining environmental information of at least one path based on the environmental data, and determining road condition information of at least one path based on the road condition data; and updating at least one path to the initial driving map based on the environmental information and road condition information to obtain a dynamic driving map.

[0012] Furthermore, based on the target fusion data, at least one driving path is constructed, including: obtaining an initial path state of at least one initial path in the initial driving map; in response to the initial path state being a preset state, obtaining vehicle network information of the vehicle, wherein the vehicle network information is used to characterize communication information between the vehicle and other vehicles, wherein the preset state is used to characterize that the traffic conditions of at least one initial path are abnormal; based on the vehicle network information and the target fusion data, at least one driving path is constructed.

[0013] Furthermore, the method further includes: in response to the initial path state not being a preset state, updating at least one initial path based on the target fusion data to obtain at least one driving path.

[0014] Furthermore, based on the path status, a target driving path is selected from at least one driving path, including: based on the path status, evaluating at least one driving path from multiple evaluation dimensions to obtain a path evaluation score, wherein the path evaluation score is used to characterize the probability of at least one driving path being selected; based on the path evaluation score, selecting a target driving path from at least one driving path, the path evaluation score of the target driving path being greater than the path evaluation scores of other driving paths in the at least one driving path.

[0015] According to another aspect of an embodiment of the present invention, a path planning device is also provided, including: a data acquisition module for acquiring satellite remote sensing data and road surface monitoring data of the road on which the vehicle is currently located; a map update module for updating the initial driving map based on the satellite remote sensing data and road surface monitoring data to obtain a dynamic driving map, wherein the initial driving map is used to represent the map used by the vehicle at the previous moment; a state determination module for determining the path state of at least one driving path corresponding to the vehicle based on map information of the dynamic driving map, wherein the at least one driving path is used to represent the path that the vehicle can travel at the current moment, and the path state is used to represent the traffic condition of at least one driving path when the vehicle is traveling on the at least one driving path; and a path selection module for selecting a target driving path from the at least one driving path based on the path state.

[0016] According to another aspect of an embodiment of the present invention, a vehicle is provided, including: a memory storing an executable program; and a processor for running the program, wherein the method of each embodiment of the present invention is executed when the program is run.

[0017] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0018] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0019] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0020] According to another aspect of the embodiments of the present invention, a computer program is provided. When the computer program is executed by a processor, the methods in various embodiments of the present invention are implemented.

[0021] In an embodiment of the present invention, satellite remote sensing data and road surface monitoring data of the road on which the vehicle is currently located are obtained: based on the satellite remote sensing data and road surface monitoring data, an initial driving map is updated to obtain a dynamic driving map; based on the map information of the dynamic driving map, the path status of at least one driving path corresponding to the vehicle is determined; based on the path status, a target driving path is selected from at least one driving path. A wide range of vision is obtained through satellite remote sensing data to detect factors affecting road conditions from a macro perspective, and close-range road condition information is obtained through road surface monitoring data to detect factors affecting road conditions from a micro perspective. By obtaining satellite remote sensing data and road surface monitoring data, the planning system can obtain multi-scale and multi-angle environmental information, thereby enhancing the perception of complex traffic environments. Subsequently, the planning system dynamically updates the content of the initial driving map by integrating the satellite remote sensing data and road surface monitoring data at the current moment to obtain a dynamic driving map. The map can reflect the current road condition information in real time, ensuring the real-time and accuracy of path planning. Based on this, through the analysis of the above-mentioned dynamic driving map, the planning system can identify the path status of different paths, and based on the path status, screen out the driving path that is more in line with the current driving needs, thereby achieving the purpose of accurate path planning in complex traffic environments, thereby achieving the technical effect of improving the accuracy of path planning in complex traffic environments, and thus solving the technical problem of poor path planning effect in related technologies when facing complex traffic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 is a flow chart of a path planning method according to an embodiment of the present invention;

[0024] Figure 2 is a flow chart of an optional path planning method implementation scheme according to an embodiment of the present invention;

[0025] Figure 3 2 is a schematic diagram of a path planning device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] According to an embodiment of the present invention, an embodiment of a path planning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 1 is a flow chart of a path planning method according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0030] Step S102: Acquire satellite remote sensing data and road surface monitoring data of the road where the vehicle is currently located.

[0031] The above-mentioned satellite remote sensing data may refer to information about the earth's surface acquired by sensors or high-definition cameras carried by satellites. This information can cover a wide geographical area. For example, the above-mentioned satellite remote sensing data may include at least one or more of the following: high-resolution images of surface features such as roads, buildings, vegetation, and water bodies; thermal infrared images for monitoring road temperature and road conditions; and meteorological data, etc., but are not limited thereto. The above-mentioned road surface monitoring data may be collected in real time by the above-mentioned vehicles themselves or various devices deployed on both sides of the road, as well as road condition information stored in real time in the cloud. For example, the above-mentioned road surface monitoring data may include at least one or more of the following: road sensor data for monitoring changes in road load, temperature, and humidity; roadside monitoring data for identifying information such as vehicles, pedestrians, obstacles, and traffic signs; and point cloud data collected by vehicle-mounted or roadside lidar, etc., but are not limited thereto.

[0032] In an optional embodiment, considering that intelligent driving vehicles rely on accurate perception of the external environment to make reasonable driving decisions, and traditional path planning is often based on static map information, lacking real-time performance and flexibility, the path planning effect is poor when facing complex road conditions such as heavy rain and snow or sudden road disasters. Further considering that satellite remote sensing data provides large-scale, macro-environmental information, such as road conditions, weather changes, traffic flow, building layout, etc., while road surface monitoring data provides real-time monitoring information of the local, micro-environment, such as the slipperiness of the road surface, the presence of obstacles, and the status of traffic signals, the real-time acquisition of satellite remote sensing and road surface monitoring data can enable the path planning system (hereinafter referred to as the planning system) to have more comprehensive environmental perception capabilities, so that it can perform dynamic planning based on the actual current road conditions, avoid paths subject to unfavorable conditions such as congestion and construction disasters, and select safer routes with better driving experience. Therefore, the planning system can use wireless communication technology to send real-time location information to the satellite data platform, requesting satellite remote sensing data of the road where the vehicle is currently located. After receiving the request from the planning system, the satellite data platform can transmit the real-time captured remote sensing data to the planning system. After receiving the data from the satellite, the planning system can decode and analyze the data to extract remote sensing information related to the road. At the same time, the planning system can also use the vehicle's V2X (Vehicle-to-Everything) communication technology to obtain monitoring data from roadside sensors and road condition data stored in real time in the cloud, thereby realizing the coordinated use of data.

[0033] In another optional embodiment, the above-mentioned satellite can also store the remote sensing data captured in real time in the cloud server, and the planning system can also directly send data requests to the cloud server. The cloud server can retrieve remote sensing data matching the real-time position of the above-mentioned vehicle from multiple satellite databases based on the real-time position of the above-mentioned vehicle to ensure the timeliness of the data. At the same time, the cloud server can also extract road surface monitoring data from the roadside sensor network. The planning system can combine the satellite remote sensing data and road surface monitoring data sent by the cloud server, as well as the data captured by the sensor equipment deployed by the above-mentioned vehicle itself, so as to realize the full-area data sharing of vehicle, road, cloud and satellite.

[0034] Step S104 : Based on the satellite remote sensing data and the road surface monitoring data, the initial driving map is updated to obtain a dynamic driving map, wherein the initial driving map is used to represent the map used by the vehicle at the last moment.

[0035] The initial driving map may be the map used by the vehicle at the moment before the current moment, and the initial driving map may include satellite remote sensing data and road surface monitoring data from the previous moment. The dynamic driving map may be a map generated by the planning system by real-time updating the initial driving map based on the initial driving map and combining it with satellite remote sensing data and road surface monitoring data at the current moment. The dynamic driving map may reflect changes in the environment and traffic conditions at the current moment compared to the previous moment.

[0036] In an optional embodiment, considering that the road and traffic environment are constantly changing, such as changes in weather conditions, road construction, traffic accidents, temporary closures, changes in traffic light status, etc., the above-mentioned initial driving map may not be able to reflect the changes at the current moment. However, the above-mentioned initial driving map is updated in real time through satellite remote sensing data and road surface monitoring data, and the resulting dynamic driving map can quickly reflect these changes, allowing the planning system to immediately adjust the driving strategy of the above-mentioned vehicle to avoid potential risks and delays. For example, the planning system can analyze the satellite remote sensing data and road surface monitoring data obtained at the current moment to obtain the status of at least one path at the current moment, and compare this status with the status of the corresponding path at the previous moment in the above-mentioned initial driving map. If the planning system detects that the above-mentioned two states are inconsistent, the status of at least one path at the current moment can be updated to the above-mentioned initial driving map, thereby obtaining the above-mentioned dynamic driving map.

[0037] In another optional embodiment, considering that the above-mentioned satellite remote sensing data and road surface monitoring data may be heterogeneous, in order to accurately extract data that can reflect the driving path status at the current moment from the above-mentioned satellite remote sensing data and road surface monitoring data, the planning system can also perform data fusion on the above-mentioned satellite remote sensing data and road surface monitoring data. The fused data can be used as a basis for adjusting the above-mentioned initial driving map. For example, if the fused data indicates that at least one driving path is not included in the above-mentioned initial driving map, the planning system communicates with other vehicles through the vehicle network environment of the above-mentioned vehicle to obtain the basic information of the above-mentioned at least one driving path. Subsequently, the planning system can construct the above-mentioned at least one driving path based on the fused data and the basic information of the above-mentioned at least one driving path. Finally, the planning system can add the constructed at least one driving path to the above-mentioned initial driving map to obtain the above-mentioned dynamic driving map.

[0038] Step S106: Based on the map information of the dynamic driving map, determine the path status of at least one driving path corresponding to the vehicle, wherein the at least one driving path is used to represent the path that the vehicle can travel at the current moment, and the path status is used to represent the traffic condition of the at least one driving path when the vehicle is traveling on the at least one driving path.

[0039] The map information may refer to information related to route planning contained in the dynamic driving map. For example, the map information may include, but is not limited to, remote sensing map information corresponding to satellite remote sensing data and radar map information corresponding to road surface monitoring data. The route status may be a comprehensive description of the traffic conditions of at least one route currently traversable by the vehicle, used to guide the planning system in planning the vehicle's route.

[0040] In an optional embodiment, considering that the map information of the dynamic driving map can instantly reflect road driving conditions such as traffic congestion, road maintenance, accident scenes, weather changes, etc., based on this information, the planning system can analyze the current traffic conditions of each possible driving path, that is, the above-mentioned path status, so as to make a more reasonable path selection. The calculation of the above-mentioned path status allows the planning system to evaluate the risks of different driving paths, thereby ensuring that the planning system can avoid those sections with potential dangers or low traffic efficiency during the path planning process. Therefore, the planning system can first obtain at least one driving path that the above-mentioned vehicle can travel at the current moment, and then the planning system can analyze the map information in the dynamic driving map, and then determine the traffic conditions of the above-mentioned at least one driving path based on the analysis results, that is, the path status of the above-mentioned at least one driving path.

[0041] For example, the planning system can extract risk factors such as traffic congestion, weather conditions, road construction, accident reports, dynamic obstacles, etc. from the map information of the dynamic driving map and pre-set a risk threshold. Subsequently, the planning system can assign a weight to each risk factor, the size of the weight depends on the impact of the risk factor on driving safety and efficiency. Then, for each possible driving path, the planning system can use edge computing devices to calculate the comprehensive risk score of each driving path based on the risk factors and weights contained in each driving path, as the above-mentioned path status. If the risk score is lower than the above-mentioned risk factor, the traffic condition of the path can be considered normal. If the risk score is higher than the above-mentioned risk factor, the traffic condition of the path can be considered abnormal.

[0042] For another example, the planning system can pre-train a machine learning model based on historical map information and traffic data. This model can establish a correlation between map information and the path status of a driving route. The planning system can input the map information and at least one driving route from the dynamic driving map into the model, and the model can output the path status of the at least one driving route based on the correlation.

[0043] Step S108: Select a target driving path from at least one driving path based on the path status.

[0044] The target driving path may be a preferred driving path selected from at least one currently drivable path by the planning system after evaluating the path status. The target driving path may be selected based on a comprehensive consideration of multiple factors, such as, but not limited to, at least one or more of the following: safety, driving efficiency, comfort, and economy.

[0045] In an optional embodiment, considering that the planning system faces a constantly changing external environment, including but not limited to road conditions, traffic flow, weather conditions, emergencies (such as accidents, construction), etc., based on the above-mentioned path status, the planning system can timely understand these changes, thereby screening out a target driving path that is more suitable under current conditions from at least one driving path, thereby helping the above-mentioned vehicle to dynamically adapt to the environment and avoid traffic delays or risks.

[0046] For example, safety may be the primary consideration for the above-mentioned vehicles during driving, and the path status includes safety hazards on the driving path, such as slippery roads, obstacles ahead, and areas with poor visibility. At this time, the planning system can analyze this information and eliminate unsafe options from at least one driving path, select a safer path as the target driving path, and recommend it to the above-mentioned vehicles for execution, thereby significantly improving the safety factor of vehicle driving and reducing the risk of accidents.

[0047] For another example, the above-mentioned vehicles may consider driving efficiency more. The planning system can analyze the path status to predict or immediately detect traffic congestion, so as to select a target driving path with less traffic flow and shorter expected driving time from at least one of the above-mentioned driving paths.

[0048] In an embodiment of the present invention, satellite remote sensing data and road surface monitoring data of the road on which the vehicle is currently located are obtained: based on the satellite remote sensing data and road surface monitoring data, the initial driving map is updated to obtain a dynamic driving map; based on the map information of the dynamic driving map, the path status of at least one driving path corresponding to the vehicle is determined; based on the path status, a target driving path is selected from at least one driving path. A wide range of vision is obtained through satellite remote sensing data to detect factors affecting road conditions from a macro perspective, and close-range road condition information is obtained through road surface monitoring data to detect factors affecting road conditions from a micro perspective. By obtaining satellite remote sensing data and road surface monitoring data, the above-mentioned planning system can obtain multi-scale and multi-angle environmental information, thereby enhancing the perception of complex traffic environments. Subsequently, the planning system dynamically updates the content of the initial driving map by integrating the satellite remote sensing data and road surface monitoring data at the current moment to obtain a dynamic driving map. The map can reflect the current road condition information in real time, ensuring the real-time and accuracy of path planning. Based on this, through the analysis of the above-mentioned dynamic driving map, the planning system can identify the path status of different paths, and based on the path status, screen out the driving path that is more in line with the current driving needs, thereby achieving the purpose of accurate path planning in complex traffic environments, thereby achieving the technical effect of improving the effectiveness and accuracy of path planning in complex traffic environments, and thus solving the technical problem of poor path planning effect in related technologies when facing complex traffic environments.

[0049] Furthermore, the map information includes: remote sensing map information corresponding to satellite remote sensing data, and radar map information corresponding to road surface monitoring data. Based on the map information of the dynamic driving map, the path status of at least one driving path corresponding to the vehicle is determined, including: based on the remote sensing map information, detecting events occurring in multiple map locations contained in the remote sensing map information to obtain event detection results, wherein the event detection results are used to characterize whether the events will affect the normal driving of the vehicle; based on the event detection results, determining a target map location from multiple map locations, wherein the events occurring in the target map location will affect the normal driving of the vehicle; performing correlation detection on the target map location and at least one driving path to obtain a correlation detection result, wherein the correlation detection result is used to characterize the degree of influence of the events occurring in the target map location on at least one driving path; determining the path status of at least one driving path based on the correlation detection result and the radar map information.

[0050] The above-mentioned remote sensing map information can be used for macro-level road and environmental monitoring, and can provide map information on real-time road conditions and environmental changes over a wide range. For example, the above-mentioned remote sensing map information can include at least one or more of the following: high-resolution terrain images, road conditions observed by satellites, weather conditions (such as rainfall, snow accumulation, etc.), vegetation coverage, building density, traffic flow, etc., but is not limited to these.

[0051] The radar map information can be used for microscopic environmental perception, providing accurate information about the vehicle's surroundings. For example, the radar map information can include at least one or more of the following: road surface conditions (such as wetness), the location and form of obstacles (such as pedestrians, other vehicles, roadblocks, etc.), traffic light status, and road marking clarity, among others, but is not limited thereto. It should be noted that the radar map information can also complement the remote sensing map information. For example, when the vehicle enters a tunnel, the remote sensing map information may be unable to obtain the vehicle's map information within the tunnel. In this case, the radar map information can supplement the vehicle's map information within the tunnel.

[0052] The events occurring at the aforementioned multiple map locations may be events that affect road traffic or vehicle driving safety. For example, the aforementioned events may include at least one or more of the following: traffic accidents, road construction, natural disasters (such as floods, landslides, etc.), traffic congestion, sudden environmental changes (such as rain or snow), etc., but are not limited thereto. The aforementioned event detection results may be information such as the presence of the aforementioned events identified through analysis of the remote sensing map information, as well as information such as the type, location, scope, and severity of the events.

[0053] The target map location may refer to the location on the map of an event that is determined, after event detection, to have a negative impact on vehicle driving.

[0054] The correlation test results described above can be used as an indicator to assess the impact of events at the target map location on the vehicle's pre-set driving path. By calculating the correlation between events and the driving path, the planning system can determine which events have the greatest impact on the current driving path and prioritize routes that avoid those locations.

[0055] In an optional embodiment, given that the planning system relies on accurate perception of the surrounding environment to make safe and efficient routing decisions, the planning system can obtain a wide range of real-time road condition information, including road conditions, weather conditions, and traffic flow changes, through the remote sensing map information corresponding to the satellite remote sensing data. This information is crucial for detecting events that may affect vehicle travel. For example, based on the remote sensing map information, the planning system can identify possible landslides or road construction, which are potential threats that the planning system needs to avoid when planning routes. Therefore, the planning system can first detect events occurring in the remote sensing map information to identify those events that may affect the normal operation of the vehicle, thereby constructing the event detection results. Subsequently, based on the event detection results, the planning system can determine the locations of the events that may affect the normal operation of the vehicle. Then, to determine whether the location of the event will affect the at least one driving route and the extent of the impact on the at least one driving route, the planning system can perform a correlation test based on the target map location and the at least one driving route to obtain a correlation test result. Furthermore, considering that the decision-making of the intelligent driving system should not rely solely on a single data source, by combining the above-mentioned correlation detection results and radar map information, the planning system can comprehensively evaluate road conditions and environmental changes from both macro and micro levels, and thus can more accurately determine the path status of at least one of the above-mentioned driving paths.

[0056] Furthermore, based on the correlation detection result and the radar map information, the path state of at least one driving path is determined, including: determining a first environmental score of the at least one driving path based on the correlation detection result, wherein the environmental score is used to characterize the safety level of the vehicle when driving on the at least one driving path; determining a second environmental score of the at least one driving path based on the radar map information; weighting the first environmental score and the second environmental score to obtain a target state score; and performing a state evaluation on the at least one driving path based on the target state score to obtain a path state.

[0057] The above-mentioned first environmental score can be a score obtained based on the above-mentioned correlation detection result. The above-mentioned first environmental score reflects the degree of impact of the event detected in the above-mentioned remote sensing map information on the safety of at least one driving path. The above-mentioned first environmental score can help the planning system evaluate the impact of macro-environmental factors (such as weather conditions, traffic flow, road construction, etc.) on the safety of the driving path, and provide a basis for path selection.

[0058] The above-mentioned second environmental score can be a score calculated based on the above-mentioned radar map information. The second environmental score provides real-time feedback on the close environment around the vehicle, focusing on reflecting the impact of micro-level environmental factors on the safety of the above-mentioned at least one driving path. For example, the above-mentioned micro-level environmental factors may include at least one or more of the following: actual road capacity, obstacle detection, traffic signal status, road surface conditions (such as wet, potholes, etc.), etc., but not limited to these.

[0059] The target state score may be a score obtained by weighting the first environment score and the second environment score. The score comprehensively considers macro and micro environmental factors and is an evaluation indicator of the safety of the at least one driving path at the current moment.

[0060] In an optional embodiment, considering that the above-mentioned correlation detection results provide the strength of association between events detected in satellite remote sensing data and driving paths, these events may be natural phenomena (such as rain, snow, fog, dust, etc.), human activities (such as construction, traffic accidents, etc.), or any other factors that may affect the safe driving of the vehicle. Therefore, the planning system can analyze the above-mentioned correlation detection results to obtain factors such as the severity and duration of the above-mentioned events, as well as the geographical proximity of the above-mentioned events to the paths. Subsequently, the planning system calculates a first environmental score for each driving path based on the above-mentioned factors, reflecting the safety status of each driving path at a macro level. The determination of the above-mentioned first environmental score can quantify the potential impact of the above-mentioned events on vehicle driving safety, and is the basis for the planning system to make intelligent path decisions. Furthermore, considering that the radar map information provides instant feedback on the vehicle's immediate surroundings, including the location of obstacles, the actual road capacity, and traffic signal status, this information is crucial for assessing the vehicle's immediate safety during travel. The planning system analyzes this radar map information to identify changes in the vehicle's immediate surroundings, such as the sudden appearance of pedestrians, bicycles, and slippery roads. Based on this real-time data, the planning system can then calculate a secondary environmental score for each driving path, reflecting each path's safety and traffic conditions at a microscopic level. This secondary environmental score effectively complements the primary environmental score, ensuring the real-time and accuracy of path planning. Since the above-mentioned first environmental score and second environmental score respectively reflect the impact of the macro and micro environment on the driving path, but their importance may vary from scenario to scenario, the planning system can assign different weight values ​​to the above-mentioned first environmental score and second environmental score based on the current driving conditions and goals, and weight the two scores based on the above-mentioned weight values ​​to calculate the target state score of each driving path. This score integrates macro and micro environmental factors and comprehensively reflects the safety and suitability of the path. Finally, the planning system can perform a state evaluation on at least one driving path based on the above-mentioned target state score to obtain the path state. The path with a higher target state score means better safety and stronger traffic capacity under current conditions.

[0061] Furthermore, based on the remote sensing map information, events occurring in multiple map locations contained in the remote sensing map information are detected to obtain event detection results, including: based on the multiple map locations, determining multiple target map information from the remote sensing map information, wherein the multiple map locations correspond one-to-one to the multiple target map information; based on the multiple target map information, performing feature extraction on events occurring in the multiple map locations to obtain event features of the events; inputting the event features into an event detection model, and using the event detection model to determine event detection results.

[0062] The target map information may be the map information corresponding to the map location of the event within the remote sensing map information. The event features may be characteristic parameters associated with a possible event extracted from multiple target map information. The event detection model may be a machine learning or deep learning model trained to identify and classify event features extracted from remote sensing map information. The model may be trained based on a large amount of annotated remote sensing data to identify characteristic patterns of different event types.

[0063] In an optional embodiment, considering that remote sensing map information usually covers a wide geographical area and contains a large amount of data, performing the same depth of analysis on all data will consume a large amount of unnecessary computing resources. Therefore, the planning system can focus the analysis on those map information related to the above-mentioned events. Specifically, the planning system can determine the map information corresponding to the above-mentioned multiple map locations from the above-mentioned remote sensing map information based on the map location where the above-mentioned event occurred, that is, the above-mentioned target map information. By determining the target map information, the planning system can concentrate resources and more finely analyze those map location data that have a direct impact on driving safety and path planning. After determining the above-mentioned target map information, the planning system can determine the event characteristics of the above-mentioned event through feature extraction. Finally, the planning system can input the above-mentioned event characteristics into the above-mentioned event detection model, which can identify whether the above-mentioned event will affect the vehicle driving, thereby generating the above-mentioned event detection results.

[0064] Furthermore, based on the satellite remote sensing data and the road surface monitoring data, the initial driving map is updated to obtain a dynamic driving map, including: based on the satellite time calibration system, the satellite remote sensing data and the road surface monitoring data are time synchronized to obtain a first synchronized data set, wherein the data in the first synchronized data set are in the same time dimension; based on the satellite positioning system, the data in the first synchronized data set are spatially synchronized to obtain a second synchronized data set, wherein the data in the second synchronized data set are in the same geographic coordinate system; data fusion is performed on the data in the second synchronized data set to obtain target fusion data; based on the target fusion data, the initial driving map is updated to obtain a dynamic driving map.

[0065] The above-mentioned satellite timing system can be a time synchronization system based on satellite signals, which is used to ensure the time consistency of satellite remote sensing data and road surface monitoring data. The above-mentioned first synchronized data set can be a set of satellite remote sensing data and road surface monitoring data that have been synchronized in the time dimension. The above-mentioned satellite positioning system can be a system for positioning based on satellite signals, which is used to map the remote sensing data and road surface monitoring data in the first synchronized data set to the same geographic coordinate system, thereby eliminating position deviation and ensuring the accuracy of subsequent data fusion. The above-mentioned second synchronized data set can be the first synchronized data set after completing spatial synchronization in the geographic coordinate system. The above-mentioned target fusion data can be a set of more complete, accurate and real-time traffic environment information obtained by fusing the remote sensing data and road surface monitoring data in the second synchronized data set and combining the advantages of both.

[0066] In an optional embodiment, considering that satellite remote sensing data and road surface monitoring data are collected by different devices at different locations, there may be differences in the clocks between the devices, which will lead to inconsistent timestamps of satellite remote sensing data and road surface monitoring data, affecting the timeliness and accuracy of the data. In order to ensure the consistency of satellite remote sensing data and road surface monitoring data in the time dimension, thereby avoiding data fusion errors caused by time deviation, the planning system can first synchronize the satellite remote sensing data and road surface monitoring data based on the above-mentioned satellite time calibration system, thereby obtaining the above-mentioned first synchronized data set, creating conditions for subsequent spatial synchronization and data fusion. Further considering that satellite remote sensing data has a wide coverage area, while road surface monitoring data usually has fixed geographic coordinates, spatial synchronization can align the data in the first synchronized data set in the geographic coordinate system, eliminating spatial deviations caused by differences in device location or coordinate system. Therefore, the planning system can also convert the data in the first synchronized data set into a unified geographic coordinate system through the satellite positioning system, thereby obtaining the above-mentioned second synchronized data set, so that the geographic features in the remote sensing data and the location information in the road surface monitoring data can be accurately matched. After completing the aforementioned temporal and spatial synchronization, the planning system can also use a data fusion algorithm to merge the remote sensing data and road surface monitoring data from the second synchronized dataset to generate the target fused data. This eliminates redundant information, fills data gaps, and achieves complementarity between satellite remote sensing data and road surface monitoring data. This target fused data incorporates the macroscopic perspective of satellite remote sensing and the microscopic details of road surface monitoring, more accurately reflecting real-time information such as road conditions, obstacles, and traffic flow. Based on this target fused data, the planning system can then update the initial driving map, resulting in a dynamic driving map that accurately reflects the current path status.

[0067] Furthermore, based on the target fusion data, the initial driving map is updated to obtain a dynamic driving map, including: constructing at least one driving path based on the target fusion data; analyzing the target fusion data to determine environmental data and road condition data of the road on which the vehicle is currently located; determining environmental information of at least one path based on the environmental data, and determining road condition information of at least one path based on the road condition data; and updating at least one path to the initial driving map based on the environmental information and road condition information to obtain a dynamic driving map.

[0068] The environmental data may be data extracted from satellite remote sensing data and road surface monitoring data, describing the state of the road's surrounding environment. The road condition data may be data describing the actual current traffic conditions of the road. The environmental information may be analyzed and processed environmental data used to describe current road environmental changes and the potential impact of such changes. The road condition information may be analyzed road condition data used to describe current road traffic conditions.

[0069] In an optional embodiment, considering that the above-mentioned target fusion data already contains comprehensive information of satellite remote sensing data and road surface monitoring data, the planning system can construct at least one feasible path from the starting point to the end point of the above-mentioned vehicle by analyzing the road network structure, obstacle distribution, traffic flow and other information in the target fusion data. This path not only takes into account the physical distance, but also integrates the road conditions and environmental factors. Subsequently, the planning system can use the timestamp and geographic location information in the target fusion data to analyze the environmental conditions and road conditions of the current position of the vehicle, thereby determining the overall environmental data and road condition data of the road and the surrounding area of ​​the above-mentioned vehicle. Then, the planning system can further analyze and process the above-mentioned environmental data and road condition data, and accurately map the above-mentioned environmental data and road condition data to the at least one feasible path constructed in the above steps. Finally, the planning system can combine the above-mentioned environmental data and road condition data with the at least one newly constructed feasible path, and update the combined overall path information to the above-mentioned initial driving map.

[0070] Furthermore, based on the target fusion data, at least one driving path is constructed, including: obtaining an initial path state of at least one initial path in the initial driving map; in response to the initial path state being a preset state, obtaining vehicle network information of the vehicle, wherein the vehicle network information is used to characterize communication information between the vehicle and other vehicles, wherein the preset state is used to characterize that the traffic conditions of at least one initial path are abnormal; based on the vehicle network information and the target fusion data, at least one driving path is constructed.

[0071] The above-mentioned initial path state may refer to the state information of the driving path obtained by the planning system from the initial driving map before real-time updating. The above-mentioned preset state may be a state used to characterize the abnormal traffic conditions of at least one initial path. The above-mentioned abnormality may refer to an event that hinders normal traffic. For example, the above-mentioned abnormality may include at least one or more of the following: traffic jams, road closures, construction areas, accident scenes, etc., but not limited to these. The triggering of the above-mentioned preset state means that the planning system needs to take immediate action to replan the path to avoid or mitigate the impact of these abnormal conditions on driving. The above-mentioned Internet of Vehicles information may refer to information collected through wireless communication networks between vehicles and communication networks between vehicles and infrastructure, and this information may include the driving paths of other vehicles.

[0072] In an optional embodiment, considering that the current path of the above-mentioned vehicle may encounter an emergency during driving, resulting in inaccessibility, at this time, the planning system needs to construct a new path in a timely manner. Based on this, the planning system can obtain at least one initial path in the initial driving map, and monitor the path status of the above-mentioned initial path based on the target fusion data at the current moment. Once it is identified that the above-mentioned initial path is no longer suitable for the passage of the above-mentioned vehicle, the planning system can obtain the vehicle network information of the vehicle in a timely manner. By analyzing the information, the planning system can quickly identify the driving paths of other vehicles, thereby screening out paths that are consistent with the destination of the above-mentioned vehicle. Subsequently, the planning system can combine the target fusion data and the screened paths to construct at least one path suitable for the passage of the above-mentioned vehicle.

[0073] Furthermore, the method further includes: in response to the initial path state not being a preset state, updating at least one initial path based on the target fusion data to obtain at least one driving path.

[0074] In an optional embodiment, considering that the target fusion data of the path traveled by the above-mentioned vehicle at the current moment has changed compared with the previous moment, but this change does not affect the continued driving of the vehicle, at this time, in order to ensure the accuracy of subsequent path planning, the planning system still needs to update the target fusion data at the current moment to the current path. Therefore, the planning system can update the above-mentioned at least one initial path based on the above-mentioned target fusion data to obtain the above-mentioned at least one driving path. Subsequently, the planning system can replace the above-mentioned driving path with the initial driving map.

[0075] Furthermore, based on the path status, a target driving path is selected from at least one driving path, including: based on the path status, evaluating at least one driving path from multiple evaluation dimensions to obtain a path evaluation score, wherein the path evaluation score is used to characterize the probability of at least one driving path being selected; based on the path evaluation score, selecting a target driving path from at least one driving path, the path evaluation score of the target driving path being greater than the path evaluation scores of other driving paths in the at least one driving path.

[0076] The multiple evaluation dimensions may be factors that need to be considered to ensure that the target driving route is more aligned with the driving requirements of the vehicle. For example, the multiple evaluation dimensions may include at least one or more of the following: safety, comfort, vehicle customization requirements, and economy, but are not limited thereto. The path evaluation score may be a score used to comprehensively evaluate each of the above dimensions to determine the priority of the driving route.

[0077] In an optional embodiment, the planning system can first determine at least one drivable road based on the path status. Subsequently, the planning system can comprehensively evaluate each path from multiple dimensions, such as safety, efficiency, comfort, energy consumption, legal and regulatory compliance, and customization requirements, and calculate a score for each dimension. The planning system can then perform a weighted summation of the scores for each dimension to obtain the path evaluation score. Finally, based on the path evaluation score, the planning system can select the path with the higher score from the at least one driving path as the target driving path, i.e., the path recommended for the vehicle. In these steps, the multi-dimensional evaluation ensures that the planning system not only focuses on a single factor (such as faster arrival time), but also comprehensively considers other factors such as safety and comfort, thereby making more reasonable path selections. Furthermore, to leverage the computing power of the satellite platform to improve the efficiency of path planning, the planning system can also distribute the computational tasks of the entire path planning process. For example, some computationally intensive tasks can be assigned to the satellite platform, while less computationally intensive tasks can be assigned to the cloud, thereby shortening the overall response time of path planning.

[0078] For ease of understanding, Figure 2 is a flow chart of an optional path planning method implementation scheme according to an embodiment of the present invention, such as Figure 2As shown, after the process begins, it proceeds sequentially through infrastructure construction, data collection and processing, intelligent algorithm application, system integration and operation and maintenance, and continuous improvement of implementation results. The process concludes after the continuous improvement of implementation results is completed. Specifically, infrastructure construction includes vehicle-side equipment installation, road infrastructure deployment, and cloud platform establishment. Vehicle-side equipment installation can include sensor installation, communication equipment installation, and onboard computer configuration. Road infrastructure deployment can include sensing device deployment, edge computing device deployment, traffic signal and intelligent control equipment upgrades, and cloud platform establishment can include the construction of a data storage and processing center and the development of an intelligent dispatching system. Data collection and processing includes real-time data collection, data preprocessing, and data fusion. Real-time data collection can include vehicle driving data, road condition data, and traffic signal status data. Data preprocessing can include data cleaning, data format conversion, and data compression. Data fusion can include multivariate data integration and post-integration data analysis and mining. Algorithms used in intelligent algorithm applications include path planning algorithms and prediction and warning algorithms. The execution of the path planning algorithm can be divided into three steps: inputting real-time traffic data, running the path planning algorithm, and outputting the optimal driving route. The prediction and warning algorithm can implement traffic flow prediction, congestion prediction, and safety hazard warning. System integration and operation and maintenance include system architecture design, device access and data interaction, and system operation and maintenance management. System architecture design can include layered architecture design and the determination of each layer's functions and interaction methods. Device access and data interaction can include the development of device access standards and the implementation of data exchange mechanisms. System operation and maintenance management can include daily system maintenance, troubleshooting, performance enhancement, and the establishment of emergency response mechanisms. Continuous improvement of implementation results includes implementation evaluation, user feedback collection, and continuous improvement and upgrades. Implementation evaluation can include traffic efficiency and road safety improvement assessments. User feedback collection can include collecting user opinions and suggestions. Continuous improvement and upgrades can include improving system performance based on the evaluation results and introducing new technologies and methods to adjust the original path planning algorithm to further enhance system performance.

[0079] According to an embodiment of the present invention, an embodiment of a path planning device is provided. It should be noted that the device can be used to execute the above-mentioned path planning method. The specific implementation and application scenarios are the same as those of the above-mentioned embodiment and will not be described in detail here. Figure 3 is a schematic diagram of a path planning device according to an embodiment of the present invention. Figure 3 As shown, the device includes:

[0080] The data acquisition module 302 is used to acquire satellite remote sensing data and road surface monitoring data of the road where the vehicle is currently located.

[0081] The map updating module 304 is configured to update the initial driving map based on satellite remote sensing data and road surface monitoring data to obtain a dynamic driving map, wherein the initial driving map is used to represent the map used by the vehicle at the last moment.

[0082] The state determination module 306 is used to determine the path state of at least one driving path corresponding to the vehicle based on the map information of the dynamic driving map, wherein the at least one driving path is used to represent the path that the vehicle can travel at the current moment, and the path state is used to represent the traffic condition of the at least one driving path when the vehicle is traveling on the at least one driving path.

[0083] The path selection module 308 is configured to select a target driving path from at least one driving path based on the path status.

[0084] Furthermore, the map information includes: remote sensing map information corresponding to satellite remote sensing data, and radar map information corresponding to road surface monitoring data. The state determination module is also used to: based on the remote sensing map information, detect events occurring in multiple map locations contained in the remote sensing map information to obtain event detection results, wherein the event detection results are used to characterize whether the events will affect the normal driving of the vehicle; based on the event detection results, determine a target map location from multiple map locations, wherein the events occurring in the target map location will affect the normal driving of the vehicle; perform correlation detection on the target map location and at least one driving path to obtain a correlation detection result, wherein the correlation detection result is used to characterize the degree of influence of the events occurring in the target map location on at least one driving path; determine the path state of at least one driving path based on the correlation detection result and the radar map information.

[0085] Furthermore, the state determination module is also used to: determine a first environmental score of at least one driving path based on the correlation detection result, wherein the environmental score is used to characterize the safety level of the vehicle when driving on at least one driving path; determine a second environmental score of at least one driving path based on radar map information; perform weighted processing on the first environmental score and the second environmental score to obtain a target state score; and perform a state evaluation on at least one driving path based on the target state score to obtain a path state.

[0086] Furthermore, the state determination module is also used to: determine multiple target map information from the remote sensing map information based on multiple map locations, wherein the multiple map locations correspond one-to-one to the multiple target map information; based on the multiple target map information, perform feature extraction on events occurring in the multiple map locations to obtain event features of the events; input the event features into the event detection model, and use the event detection model to determine the event detection results.

[0087] Furthermore, the map update module is also used to: based on the satellite timing system, synchronize the satellite remote sensing data and the road surface monitoring data in time to obtain a first synchronized data set, wherein the data in the first synchronized data set are in the same time dimension; based on the satellite positioning system, synchronize the data in the first synchronized data set in space to obtain a second synchronized data set, wherein the data in the second synchronized data set are in the same geographic coordinate system; perform data fusion on the data in the second synchronized data set to obtain target fusion data; based on the target fusion data, update the initial driving map to obtain a dynamic driving map.

[0088] Furthermore, the map update module is also used to: construct at least one driving path based on the target fusion data; analyze the target fusion data to determine the environmental data and road condition data of the road on which the vehicle is currently located; determine the environmental information of at least one path based on the environmental data, and determine the road condition information of at least one path based on the road condition data; and update at least one path to the initial driving map based on the environmental information and road condition information to obtain a dynamic driving map.

[0089] Furthermore, the map update module is also used to: obtain the initial path state of at least one initial path in the initial driving map; in response to the initial path state being a preset state, obtain the vehicle network information of the vehicle, wherein the vehicle network information is used to characterize the communication information between the vehicle and other vehicles, wherein the preset state is used to characterize that the traffic conditions of at least one initial path are abnormal; and construct at least one driving path based on the vehicle network information and target fusion data.

[0090] Furthermore, the device further includes: a path updating module for updating at least one initial path based on the target fusion data in response to the initial path state not being a preset state to obtain at least one driving path.

[0091] Furthermore, the path selection module is also used to: based on the path status, evaluate at least one driving path from multiple evaluation dimensions to obtain a path evaluation score, wherein the path evaluation score is used to characterize the probability of at least one driving path being selected; based on the path evaluation score, select a target driving path from at least one driving path, wherein the path evaluation score of the target driving path is greater than the path evaluation scores of other driving paths in at least one driving path.

[0092] An embodiment of the present application further provides a vehicle, comprising: a memory storing an executable program; and a processor for running the program, wherein the method of each embodiment of the present invention is executed when the program is running.

[0093] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0094] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0095] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0096] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0097] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0098] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0100] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0101] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0103] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A path planning method, characterized in that: include: Obtain satellite remote sensing data and road surface monitoring data of the road where the vehicle is currently located; Based on the satellite remote sensing data and the road surface monitoring data, an initial driving map is updated to obtain a dynamic driving map, wherein the initial driving map is used to represent a map used by the vehicle at a previous moment; Determining, based on map information of the dynamic driving map, a path state of at least one driving path corresponding to the vehicle, wherein the at least one driving path is used to represent a path that the vehicle can currently travel, and the path state is used to represent a traffic condition of the at least one driving path when the vehicle travels on the at least one driving path; A target driving path is selected from the at least one driving path based on the path status.

2. The path planning method according to claim 1, characterized in that: The map information includes: remote sensing map information corresponding to the satellite remote sensing data, and radar map information corresponding to the road surface monitoring data. Based on the map information of the dynamic driving map, determining the path state of at least one driving path corresponding to the vehicle includes: Based on the remote sensing map information, detecting events occurring in a plurality of map locations included in the remote sensing map information to obtain event detection results, wherein the event detection results are used to indicate whether the events will affect normal driving of the vehicle; determining a target map location from the plurality of map locations based on the event detection result, wherein an event occurring at the target map location may affect normal driving of the vehicle; performing a correlation test on the target map location and the at least one driving path to obtain a correlation test result, wherein the correlation test result is used to represent the degree of influence of an event occurring at the target map location on the at least one driving path; Based on the correlation detection result and the radar map information, a path status of the at least one driving path is determined.

3. The path planning method according to claim 2, characterized in that: Determining a path state of the at least one driving path based on the correlation detection result and the radar map information includes: Determining a first environment score of the at least one driving path based on the correlation detection result, wherein the environment score is used to represent a safety level of the vehicle when driving on the at least one driving path; determining a second environment score for the at least one driving path based on the radar map information; Performing weighted processing on the first environment score and the second environment score to obtain a target state score; A state evaluation is performed on the at least one driving path based on the target state score to obtain the path state.

4. The path planning method according to claim 2, characterized in that: Based on the remote sensing map information, events occurring in a plurality of map locations included in the remote sensing map information are detected to obtain event detection results, including: determining, from the remote sensing map information, a plurality of target map information based on the plurality of map locations, wherein the plurality of map locations correspond one-to-one to the plurality of target map information; Based on the multiple target map information, feature extraction is performed on events occurring in the multiple map locations to obtain event features of the events; The event features are input into an event detection model, and the event detection result is determined using the event detection model.

5. The path planning method according to claim 1, wherein: Based on the satellite remote sensing data and the road surface monitoring data, the initial driving map is updated to obtain a dynamic driving map, including: Based on a satellite timing system, time-synchronize the satellite remote sensing data and the road surface monitoring data to obtain a first synchronized data set, wherein the data in the first synchronized data set are in the same time dimension; performing spatial synchronization on the data in the first synchronized dataset based on a satellite positioning system to obtain a second synchronized dataset, wherein the data in the second synchronized dataset are in the same geographic coordinate system; Performing data fusion on the data in the second synchronized data set to obtain target fused data; Based on the target fusion data, the initial driving map is updated to obtain the dynamic driving map.

6. The path planning method according to claim 5, characterized in that: Based on the target fusion data, the initial driving map is updated to obtain the dynamic driving map, including: constructing the at least one driving path based on the target fusion data; Analyzing the target fusion data to determine environmental data and road condition data of the road currently located by the vehicle; Determining environmental information of the at least one path based on the environmental data, and determining road condition information of the at least one path based on the road condition data; Based on the environmental information and the road condition information, the at least one path is updated to the initial driving map to obtain the dynamic driving map.

7. The path planning method according to claim 6, characterized in that: Constructing the at least one driving path based on the target fusion data includes: Acquiring an initial path state of at least one initial path in the initial driving map; In response to the initial path state being a preset state, obtaining vehicle network information of the vehicle, wherein the vehicle network information is used to represent communication information between the vehicle and other vehicles, and the preset state is used to represent that the traffic conditions of the at least one initial path are abnormal; Based on the Internet of Vehicles information and the target fusion data, the at least one driving path is constructed.

8. The path planning method according to claim 7, characterized in that: The method further comprises: In response to the initial path state not being a preset state, the at least one initial path is updated based on the target fusion data to obtain the at least one driving path.

9. The path planning method according to any one of claims 1 to 8, characterized in that: Selecting a target driving path from the at least one driving path based on the path state includes: Based on the path state, evaluating the at least one driving path from multiple evaluation dimensions to obtain a path evaluation score, wherein the path evaluation score is used to represent the probability of the at least one driving path being selected; Based on the path evaluation score, the target driving path is selected from the at least one driving path, wherein the path evaluation score of the target driving path is greater than the path evaluation scores of other driving paths in the at least one driving path.

10. A path planning device, characterized in that: include: A data acquisition module is used to obtain satellite remote sensing data and road surface monitoring data of the road where the vehicle is currently located; a map updating module, configured to update an initial driving map based on the satellite remote sensing data and the road surface monitoring data to obtain a dynamic driving map, wherein the initial driving map is used to represent the map used by the vehicle at a previous moment; a state determination module, configured to determine, based on map information of the dynamic driving map, a path state of at least one driving path corresponding to the vehicle, wherein the at least one driving path is used to represent a path that the vehicle can currently travel, and the path state is used to represent a traffic condition of the at least one driving path when the vehicle travels on the at least one driving path; A path selection module is used to select a target driving path from the at least one driving path based on the path state.

11. A vehicle, characterized in that: include: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors execute the path planning method according to any one of claims 1 to 9.

Images