Passable area analysis method based on high-precision map and fusion perception

Abstract

The invention relates to the technical field of driving environment perception, in particular to a passable area analysis method based on a high-precision map and fusion perception, and the method comprises the steps: obtaining an associated road node corresponding to a road node to which the current position of a target vehicle belongs; and the traffic jam risk area of the road node to which the current position of the target vehicle belongs is predicted by combining the traffic state of the associated road node in the road monitoring image at the current time. According to the invention, perception and identification of the position of the target vehicle in the high-precision map are realized, and the calibration of the high-precision map to which the target vehicle belongs is realized by combining multiple sensors to perceive obstacle information around the vehicle, so that the accuracy of the generated passable area is ensured; meanwhile, the flowability of vehicles in the roads and the influence of congestion risks of different roads in different time periods on the passable area are also considered, and the accuracy of the constructed passable area is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of driving environment perception, and specifically to a method for analyzing passable areas based on high-precision maps and fusion perception. Background Art

[0002] As an indispensable and important part of autonomous driving vehicles, high-precision maps provide favorable support for vehicle positioning, safe driving, path planning, vehicle energy conservation, etc. However, in the real scenario of autonomous driving, in order to ensure the safety of autonomous driving as much as possible, it is inevitable to perceive the environment under the fusion of multi-source data. Therefore, obtaining the passable areas of vehicles based on high-precision maps and fusion perception technology has gradually become a key research direction in the industry.

[0003] Existing methods for analyzing passable areas based on high-precision maps and fusion perception only realize the perception and recognition of the position of the target vehicle in the high-precision map, and combine multi-sensor to perceive the obstacle information around the vehicle to extract the passable area of the target vehicle. However, this method has great drawbacks and does not consider the fluidity of vehicles on the road and the congestion risks of different roads at different time periods. Therefore, there are large deviations in the accuracy of the passable areas extracted by the existing technology. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for analyzing passable areas based on high-precision maps and fusion perception to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solution: A method for analyzing passable areas based on high-precision maps and fusion perception, the method comprising the following steps:

[0006] S1. Obtain the task planning map of the target vehicle; when the position of the target vehicle is in the task planning map, obtain the on-vehicle monitoring information corresponding to each position point of the target vehicle and the on-vehicle monitoring information of the associated vehicle of the target vehicle in real time through fusion perception technology;

[0007] S2. Combine the on-vehicle monitoring information of the target vehicle and its associated vehicle to optimize the task planning map of the target vehicle and lock the passable area within a preset first radius area around the current target vehicle;

[0008] S3. Combine the historical road traffic information within a preset second radius area around the current position of the target vehicle, analyze the congestion status corresponding to each road node within the preset second radius area around the current position of the target vehicle at different time points, and the congestion correlation impact between different road nodes;

[0009] S4. Obtain the associated road nodes corresponding to the road node where the current position of the target vehicle is located; and combine the traffic states of the obtained associated road nodes in the road monitoring images at the current time to predict the traffic congestion risk areas of the road node where the current position of the target vehicle is located.

[0010] S5. Generate the passable area corresponding to the target vehicle at the current time based on the passable area within the preset first radius area around the current target vehicle and the traffic congestion risk areas of the road node where the current position of the target vehicle is located.

[0011] Furthermore, the task planning map of the target vehicle is the planned path map between the initial point corresponding to the target vehicle and the destination;

[0012] The vehicle-mounted monitoring information includes obstacle information, path boundary information, and road surface flatness information other than vehicles around, identified based on image recognition technology;

[0013] The obstacle information includes the obstacle contour and the position vector of the corresponding obstacle relative to the vehicle based on the vehicle-mounted monitoring information; the path boundary information includes the position vectors of the identified path boundary points relative to the vehicle based on the vehicle-mounted monitoring information; the road surface flatness information includes the road surface position points where the corresponding flatness does not belong to the preset interval and the position vectors of the corresponding road surface position points relative to the vehicle based on the vehicle-mounted monitoring information;

[0014] The associated vehicle of the target vehicle is the same as the vehicle networking to which the target vehicle is connected, and the distance between the vehicle positions uploaded by the target vehicle and its associated vehicle within the preset upload time deviation is less than the preset distance;

[0015] The preset upload time deviation represents the maximum interval duration between the preset data upload times of the target vehicle and its associated vehicle in the database.

[0016] In the present invention, the task planning map of the target vehicle is obtained based on the preset high-precision map, that is, the task route of the target vehicle is planned on the preset high-precision map, and the planning result of the task route of the target vehicle is intercepted in the area where the corresponding high-precision map is located as the task planning map of the target vehicle;

[0017] Furthermore, when optimizing the task planning map of the target vehicle, obtain the mapped position points of the current position of the target vehicle and the position of its associated vehicle at the current time in the task planning map of the target vehicle;

[0018] Based on the mapped position points in the task planning map of the target vehicle, generate a corresponding boundary position mapping area for the path boundary information in the on-vehicle monitoring information corresponding to each mapped position point in the task planning map of the target vehicle, extract the boundary feature information in the obtained boundary position mapping area, and obtain the associated boundary feature information of the boundary feature information in the target vehicle's task planning map in the obtained boundary position mapping area; according to the boundary feature information and its corresponding associated boundary feature information, obtain the forward mapping calibration coefficient and the bias mapping calibration coefficient corresponding to the on-vehicle monitoring information corresponding to the position of the target vehicle and its associated vehicle position at the current time respectively;

[0019] Take the straight line where the respective traveling directions of the target vehicle and its associated vehicle are located as the first reference pointing line of the corresponding vehicle; take the straight line perpendicular to the traveling direction of the target vehicle and its associated vehicle respectively as the second reference pointing line of the corresponding vehicle;

[0020] Calculate the calibration results of the on-vehicle monitoring information corresponding to the target vehicle and its associated vehicle at the current time respectively. The calibration result corresponding to the position vector in each element of the on-vehicle monitoring information calibration result is equal to the vector sum of the first calibration sub-vector and the second calibration sub-vector corresponding to the corresponding position vector; the first calibration sub-vector corresponding to the corresponding position vector in the on-vehicle monitoring information calibration result is equal to the product vector of the sub-vector of the corresponding position vector on the first reference pointing line and the forward mapping calibration coefficient corresponding to the corresponding on-vehicle monitoring information; the second calibration sub-vector corresponding to the corresponding position vector in the on-vehicle monitoring information calibration result is equal to the product vector of the sub-vector of the corresponding position vector on the second reference pointing line and the bias mapping calibration coefficient corresponding to the corresponding on-vehicle monitoring information;

[0021] According to the calibration results of the on-vehicle monitoring information corresponding to the position of the target vehicle and its associated vehicle at the current time respectively; based on the mapped position points in the task planning map of the target vehicle, generate and mark the position mapping areas corresponding to the obstacle information, path boundary information, and road surface flatness information in the calibration result of the on-vehicle monitoring information corresponding to each mapped position point in the task planning map of the target vehicle, and obtain the optimization result of the task planning map of the target vehicle;

[0022] The passable area within the preset first radius around the currently locked target vehicle represents the area within the preset first radius around the current target vehicle in the optimization result of the task planning map of the target vehicle that is not marked and belongs to the road area; mark the area within the preset first radius around the current target vehicle that does not belong to the road area.

[0023] In the present invention, the passable area within a preset first radius around the current target vehicle is obtained based on the analysis of high-precision maps and sensor perception data, which belongs to the analysis result of the passable area at the perception level. During this process, the high-precision map and the sensor perception result complement each other. The high-precision map can dynamically screen the accurate map model around the target vehicle according to the position of the target vehicle, while the sensor perception technology can perceive and obtain the obstacle information, path boundary information, and road surface flatness information around the vehicle, and can also calibrate the position of the target vehicle in the extracted high-precision map.

[0024] Further, the boundary feature information includes the positions of each guardrail post in the road boundary and the curvature of the road corresponding to the position of the corresponding guardrail post. When obtaining the associated boundary feature information corresponding to the boundary feature information of the vehicle in the task planning map of the target vehicle, it is obtained by querying the boundary feature information in the task planning map of the target vehicle that is closest to the mapped position point of the corresponding vehicle and has the same boundary feature information as the corresponding vehicle.

[0025] The forward mapping calibration coefficient represents the mapping calibration coefficient corresponding to the component vector of the position vector corresponding to each element in the obtained on-vehicle monitoring information on the first reference direction line corresponding to the corresponding vehicle.

[0026] The forward mapping calibration coefficients corresponding to the target vehicle and its associated vehicles are equal to the average of the mapping calibration coefficients corresponding to the component vectors of each position vector in the path boundary information of the corresponding vehicle on the first reference direction line. The mapping calibration coefficient corresponding to the component vector of each position vector in the path boundary information of the vehicle on the first reference direction line is equal to the quotient of the scalar of the component vector of each position vector in the path boundary information of the vehicle on the first reference direction line and the scalar of the component vector of the corresponding position vector in the associated boundary feature information on the first reference direction line. And when the scalar of the component vector of the corresponding position vector in the associated boundary feature information on the first reference direction line is 0, it is determined that the mapping calibration coefficient corresponding to the component vector of the corresponding position vector in the path boundary information on the first reference direction line is 1.

[0027] The deviation mapping calibration coefficient represents the mapping calibration coefficient corresponding to the component vector of the position vector corresponding to each element in the obtained on-vehicle monitoring information on the second reference direction line corresponding to the corresponding vehicle.

[0028] The respective deviation mapping calibration coefficients corresponding to the target vehicle and its associated vehicles are equal to the average of the mapping calibration coefficients corresponding to the component vectors of each position vector in the path boundary information of the corresponding vehicle on the second reference direction line. The mapping calibration coefficient corresponding to the component vector of each position vector in the path boundary information of a vehicle on the second reference direction line is equal to the quotient of the scalar of the component vector of each position vector in the path boundary information of the vehicle on the second reference direction line and the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the second reference direction line. And when the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the second reference direction line is 0, it is determined that the mapping calibration coefficient corresponding to the component vector of the corresponding position vector in the path boundary information on the second reference direction line is 1.

[0029] In addition to the basic guarantee of having a high-precision map (HDMAP), the present invention also gives full play to the respective advantages of sensors to improve the reliability of environmental perception information. The construction of the mapping calibration coefficient can calibrate the on-vehicle monitoring information collected by each vehicle and update the obtained high-precision map through the calibration results of the on-vehicle monitoring information, thereby laying a data foundation for accurately obtaining the passable area subsequently.

[0030] Further, when analyzing the congestion states corresponding to each road node in a preset second radius area around the current position of the target vehicle within different preset time intervals,

[0031] obtain the historical road traffic information in a preset second radius area around the current position of the target vehicle, and construct a set composed of each road node in the preset second radius area around the current position of the target vehicle, denoted as the road node set;

[0032] The historical road traffic information includes the traffic characteristic information corresponding to different preset time intervals in a day for each road node in the corresponding area. The traffic characteristic information includes the traffic states corresponding to each preset position area in the corresponding road node, and the traffic states include the normal traffic state and the traffic congestion state; the states of the construction areas or the obstacle occupation areas existing in the road nodes are also recorded as the traffic congestion state;

[0033] The road node corresponds to a preset road area in the database. Different road nodes correspond to different preset road areas and the areas corresponding to each road area are equal; there are multiple preset time intervals in a day and the interval durations corresponding to different preset time intervals are all equal;

[0034] Obtain the traffic characteristic information corresponding to different preset time intervals in a day in the historical road traffic information corresponding to the k-th element in the road node set,

[0035] Statistically analyze the set of traffic characteristic information corresponding to the j-th preset time interval within different dates in the historical road traffic information corresponding to the k-th element in the set of road nodes, and denote it as the congestion status analysis set YDF of the k-th element in the set of road nodes within the j-th preset time interval. (k，j) ;

[0036] For each preset position area in the k-th element of the set of road nodes in YDF (k，j) among the elements, count the frequency of the traffic status being in a traffic jam state, and mark all preset position areas where the ratio of the obtained frequency to the total number of elements in YDF (k，j) is greater than the preset frequency; all position points within the marked preset position areas are marked.

[0037] Based on the congestion status corresponding to the k-th element of the set of road nodes during the j-th preset time interval of a day, for all marked preset position areas, the traffic status is in a traffic jam state, and for all unmarked preset position areas, the traffic status is in a normal traffic state.

[0038] Furthermore, when analyzing the congestion correlation impact between different road nodes,

[0039] Obtain the historical road traffic information within a preset second radius area around the current position of the target vehicle, and denote any element corresponding to a road node in the set of road nodes as a reference node;

[0040] Obtain the congestion time interval corresponding to each occurrence of the congestion status of the reference node in the obtained historical road traffic information, denote it as the first time interval, and obtain the set of all non-reference node road nodes whose corresponding congestion time interval has a non-empty intersection with the first time interval, and denote it as a congestion correlation subset corresponding to the congestion status of the reference node;

[0041] The set of road nodes in the set of road nodes that have a congestion correlation impact with the reference node is the union of the respective congestion correlation subsets corresponding to the congestion status of the reference node.

[0042] Furthermore, the associated road nodes corresponding to the road node where the current position of the target vehicle is located are all road nodes that have a congestion correlation impact with the road node where the current position of the target vehicle is located;

[0043] When predicting the traffic congestion risk area of the road node where the current position of the target vehicle is located, obtain the traffic status of the obtained associated road nodes in the current time in the road monitoring image.

[0044] If the traffic status of any one of the obtained associated road nodes is a traffic jam status, it is determined that all the obtained associated road nodes are congestion risk nodes; if the traffic status of all the obtained associated road nodes is a normal traffic status, it is determined that none of the obtained associated road nodes are congestion risk nodes;

[0045] Denote the time interval to which the current time belongs as T;

[0046] Obtain the congestion status analysis sets respectively corresponding to each congestion risk node within the time interval T, and use the set composed of the respective preset position areas marked in the obtained congestion status analysis sets as the traffic congestion risk area of the road node where the current position of the target vehicle is located.

[0047] Furthermore, when generating the passable area corresponding to the target vehicle at the current time,

[0048] Obtain the passable area within the preset first radius area around the current target vehicle, and denote it as the first passable area;

[0049] Obtain the traffic congestion risk area of the road node where the current position of the target vehicle is located, and denote it as the second passable area;

[0050] The passable area corresponding to the target vehicle at the current time is the set of position points that are not marked in both the first passable area and the second passable area within the union area of the first passable area and the second passable area.

[0051] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention not only realizes the sensing and recognition of the position of the target vehicle in the high-precision map, but also combines multi-sensor to sense the obstacle information around the vehicle, realizes the calibration of the high-precision map to which the target vehicle belongs, and ensures the accuracy of the generated passable area; at the same time, it also takes into account the fluidity of vehicles on the road and the influence of the congestion risk of different roads at different time periods on the passable area, and ensures the accuracy of the constructed passable area. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0053] Figure 1 is a flowchart of the passable area analysis method based on high-precision map and fusion perception of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] Please refer to Figure 1 , the present invention provides a technical solution: a passable area analysis method based on high-precision maps and fusion perception. The method includes the following steps:

[0056] S1. Obtain the task planning map of the target vehicle; when the position of the target vehicle is on the task planning map, obtain the on-vehicle monitoring information corresponding to the target vehicle at each position point in real time through the fusion perception technology and the on-vehicle monitoring information of the associated vehicle corresponding to the target vehicle.

[0057] The task planning map of the target vehicle is the planned path map between the corresponding initial point and the destination of the target vehicle.

[0058] The on-vehicle monitoring information includes obstacle information other than vehicles around, path boundary information, and road surface flatness information identified based on image recognition technology.

[0059] The obstacle information includes the obstacle contour and the position vector of the corresponding obstacle based on the vehicle in the on-vehicle monitoring information; the path boundary information includes the position vectors of each identified path boundary point based on the vehicle in the on-vehicle monitoring information; the road surface flatness information includes each road surface position point where the corresponding flatness does not belong to the preset interval and the position vector of the corresponding road surface position point based on the vehicle in the on-vehicle monitoring information.

[0060] The associated vehicle of the target vehicle is the same as the vehicle network connected to the target vehicle, and the distance between the vehicle positions uploaded by the target vehicle and its associated vehicle within the preset upload time deviation is less than the preset distance.

[0061] The preset upload time deviation represents the maximum interval duration between the preset data upload times of the target vehicle and its associated vehicle in the database.

[0062] S2. Combine the on-vehicle monitoring information of the target vehicle and its associated vehicle to optimize the task planning map of the target vehicle, and lock the passable area within a preset first radius area around the current target vehicle.

[0063] When optimizing the task planning map of the target vehicle, obtain the mapped position points of the position of the target vehicle and its associated vehicle at the current time in the task planning map of the target vehicle respectively.

[0064] Based on the mapped position points in the mission planning map of the target vehicle, generate the corresponding boundary position mapping regions of the path boundary information in the on-vehicle monitoring information for each mapped position point in the mission planning map of the target vehicle, extract the boundary feature information in the obtained boundary position mapping regions, and obtain the associated boundary feature information of the boundary feature information in the obtained boundary position mapping regions in the mission planning map of the target vehicle; according to the boundary feature information and its corresponding associated boundary feature information, obtain the forward mapping calibration coefficients and deviation mapping calibration coefficients respectively corresponding to the on-vehicle monitoring information corresponding to the current time's target vehicle position and its associated vehicle position;

[0065] Take the straight lines where the traveling directions of the target vehicle and its associated vehicle are respectively located as the first reference pointing lines of the corresponding vehicles; take the straight lines perpendicular to the traveling directions of the target vehicle and its associated vehicle as the second reference pointing lines of the corresponding vehicles;

[0066] Calculate the calibration results of the on-vehicle monitoring information corresponding to the target vehicle and its associated vehicle at the current time. The calibration result of the position vector in each element of the on-vehicle monitoring information calibration result is equal to the vector sum of the first calibration sub-vector and the second calibration sub-vector corresponding to the corresponding position vector; the first calibration sub-vector corresponding to the corresponding position vector in the on-vehicle monitoring information calibration result is equal to the product vector of the sub-vector of the corresponding position vector on the first reference pointing line and the forward mapping calibration coefficient corresponding to the corresponding on-vehicle monitoring information; the second calibration sub-vector corresponding to the corresponding position vector in the on-vehicle monitoring information calibration result is equal to the product vector of the sub-vector of the corresponding position vector on the second reference pointing line and the deviation mapping calibration coefficient corresponding to the corresponding on-vehicle monitoring information;

[0067] In this embodiment, since there may be differences in the vehicle pointing directions of the target vehicle and its associated vehicle, the first reference pointing lines and the second reference pointing lines corresponding to different vehicles in the target vehicle and its associated vehicle will also be different; and the first reference pointing lines and the second reference pointing lines corresponding to the same vehicle at different times will also be different, so the forward mapping calibration coefficients and deviation mapping calibration coefficients corresponding to the same vehicle at different times may change.

[0068] According to the calibration results of the on-vehicle monitoring information corresponding to the target vehicle position and its associated vehicle position at the current time; based on the mapped position points in the mission planning map of the target vehicle, generate and mark the position mapping regions corresponding to the obstacle information, path boundary information, and road surface flatness information in the calibration results of the on-vehicle monitoring information for each mapped position point in the mission planning map of the target vehicle, and obtain the optimized result of the mission planning map of the target vehicle;

[0069] The passable area within the preset first radius around the locked current target vehicle represents the area within the preset first radius around the current target vehicle in the optimized result of the task planning map of the target vehicle that is not marked and belongs to the road area; mark the areas within the preset first radius around the current target vehicle that do not belong to the road area as well.

[0070] The boundary feature information includes the positions of each guardrail post in the road boundary and the curvature of the road corresponding to the position of the corresponding guardrail post; when obtaining the associated boundary feature information corresponding to the boundary feature information of the vehicle in the task planning map of the target vehicle, it is obtained by querying the boundary feature information in the task planning map of the target vehicle that is closest to the mapped position point of the corresponding vehicle and has the same boundary feature information as the corresponding vehicle.

[0071] The forward mapping calibration coefficient represents the mapping calibration coefficient corresponding to the component vector of the position vector corresponding to each element in the obtained vehicle-mounted monitoring information on the first reference direction line corresponding to the corresponding vehicle.

[0072] The forward mapping calibration coefficients corresponding to the target vehicle and its associated vehicles are equal to the average of the mapping calibration coefficients corresponding to the component vectors of each position vector in the path boundary information of the corresponding vehicle on the first reference direction line. The mapping calibration coefficient corresponding to the component vector of each position vector in the path boundary information of the vehicle on the first reference direction line is equal to the quotient of the scalar of the component vector of each position vector in the path boundary information of the vehicle on the first reference direction line and the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the first reference direction line. And when the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the first reference direction line is 0, it is determined that the mapping calibration coefficient corresponding to the component vector of the corresponding position vector in the path boundary information on the first reference direction line is 1.

[0073] The deviation mapping calibration coefficient represents the mapping calibration coefficient corresponding to the component vector of the position vector corresponding to each element in the obtained vehicle-mounted monitoring information on the second reference direction line corresponding to the corresponding vehicle.

[0074] The deviation mapping calibration coefficients corresponding to the target vehicle and its associated vehicle respectively are equal to the average value of the mapping calibration coefficients corresponding to the component vectors of each position vector in the path boundary information of the corresponding vehicle on the second reference pointing line. The mapping calibration coefficient corresponding to the component vector of each position vector in the path boundary information of the vehicle on the second reference pointing line is equal to the quotient of the scalar of the component vector of each position vector in the path boundary information of the vehicle on the second reference pointing line and the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the second reference pointing line. And when the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the second reference pointing line is 0, it is determined that the mapping calibration coefficient corresponding to the component vector of the corresponding position vector in the path boundary information on the second reference pointing line is 1.

[0075] S3. Combine the historical road traffic information in the preset second radius area around the current position of the target vehicle, analyze the congestion status corresponding to each road node in the preset second radius area around the current position of the target vehicle at different time points, and the congestion correlation effect between different road nodes;

[0076] When analyzing the congestion status corresponding to each road node in the preset second radius area around the current position of the target vehicle within different preset time intervals,

[0077] Obtain the historical road traffic information in the preset second radius area around the current position of the target vehicle, construct a set composed of each road node in the preset second radius area around the current position of the target vehicle, and denote it as the road node set;

[0078] The historical road traffic information includes the traffic characteristic information corresponding to each road node in the corresponding area at different preset time intervals in a day. The traffic characteristic information includes the traffic status corresponding to each preset position area in the corresponding road node, and the traffic status includes the normal traffic status and the traffic jam status; the status of the construction area or the obstacle occupation area existing in the road node is also recorded as the traffic jam status;

[0079] The road node corresponds to a preset road area in the database. Different road nodes correspond to different preset road areas and the areas corresponding to each road area are equal; there are multiple preset time intervals in a day and the interval durations corresponding to different preset time intervals are all equal;

[0080] In this embodiment, a day is evenly divided into 24 consecutive and equal-length preset time intervals, and the duration corresponding to each preset time interval is one hour; the number of divisions of the preset time interval is preset manually and can be adjusted according to human needs;

[0081] Obtain the traffic characteristic information corresponding to different preset time intervals for each day in the historical road traffic information corresponding to the k-th element in the set of road nodes.

[0082] Statistically analyze the set of traffic characteristic information corresponding to the j-th preset time interval within different dates in the historical road traffic information corresponding to the k-th element in the set of road nodes, and denote it as the congestion status analysis set YDF of the k-th element in the set of road nodes within the j-th preset time interval. (k，j) ;

[0083] Statistically analyze the frequency of the traffic status being in a traffic jam state for each preset position area in the k-th element in the set of road nodes among the elements in YDF (k，j) and mark all preset position areas where the ratio of the obtained frequency to the total number of elements in YDF (k，j) is greater than the preset frequency; all position points within the marked preset position areas are marked.

[0084] Based on the traffic status corresponding to the k-th element in the set of road nodes during the j-th preset time interval in a day, the traffic status of all marked preset position areas is in a traffic jam state, and the traffic status of all unmarked preset position areas is in a normal traffic state.

[0085] When analyzing the congestion correlation impact between different road nodes,

[0086] Obtain the historical road traffic information within a preset second radius area around the current position of the target vehicle, and denote the road node corresponding to any element in the set of road nodes as the reference node;

[0087] Obtain the congestion time interval corresponding to each occurrence of the reference node in a congestion state in the obtained historical road traffic information, denote it as the first time interval, and obtain the set of all road nodes of non-reference nodes whose corresponding congestion time intervals have a non-empty intersection with the first time interval, and denote it as a congestion correlation subset corresponding to the congestion state of the reference node;

[0088] The set of road nodes in the set of road nodes that have a congestion correlation impact with the reference node is the union of the respective congestion correlation subsets corresponding to the congestion state of the reference node.

[0089] S4. Obtain the associated road nodes corresponding to the road node where the current position of the target vehicle is located; and combine the traffic status of the obtained associated road nodes at the current time in the road monitoring image to predict the traffic congestion risk area of the road node where the current position of the target vehicle is located.

[0090] The associated road nodes corresponding to the road node where the current position of the target vehicle is located are all road nodes that have a congestion-related impact on the road node where the current position of the target vehicle is located;

[0091] When predicting the traffic congestion risk area of the road node where the current position of the target vehicle is located, obtain the traffic states of the associated road nodes obtained from the road monitoring images at the current time.

[0092] If the traffic state of any one of the obtained associated road nodes is a traffic jam state, it is determined that all the obtained associated road nodes are congestion risk nodes; if the traffic states of the obtained associated road nodes are all normal traffic states, it is determined that none of the obtained associated road nodes are congestion risk nodes.

[0093] Record the time interval to which the current time belongs as T.

[0094] Obtain the congestion state analysis sets corresponding to each congestion risk node within the time interval T, and use the set composed of the preset position areas marked in each of the obtained congestion state analysis sets as the traffic congestion risk area of the road node where the current position of the target vehicle is located.

[0095] S5. Generate the passable area corresponding to the target vehicle at the current time based on the passable area within the preset first radius area around the current target vehicle and the traffic congestion risk area of the road node where the current position of the target vehicle is located.

[0096] When generating the passable area corresponding to the target vehicle at the current time,

[0097] Obtain the passable area within the preset first radius area around the current target vehicle, and record it as the first passable area;

[0098] Obtain the traffic congestion risk area of the road node where the current position of the target vehicle is located, and record it as the second passable area;

[0099] The passable area corresponding to the target vehicle at the current time is the set of position points that are not marked in both the first passable area and the second passable area within the union area of the first passable area and the second passable area.

[0100] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0101] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A passable area analysis method based on high-precision maps and fusion perception, characterized in that, The method includes the following steps: S1. Obtain the task planning map of the target vehicle; when the position of the target vehicle is on the task planning map, obtain the in-vehicle monitoring information corresponding to each position point of the target vehicle and the in-vehicle monitoring information of the associated vehicle of the target vehicle in real time through the fusion perception technology; S2. Combine the in-vehicle monitoring information of the target vehicle and its associated vehicle to optimize the task planning map of the target vehicle, and lock the passable area within a preset first radius area around the current target vehicle; S3. Combine the historical road traffic information within a preset second radius area around the current position of the target vehicle, analyze the congestion status corresponding to each road node within the preset second radius area around the current position of the target vehicle at different time points, and the congestion correlation effect between different road nodes; S4. Obtain the associated road nodes corresponding to the road node where the current position of the target vehicle is located; and combine the traffic status of the obtained associated road nodes in the road monitoring image at the current time to predict the traffic congestion risk area of the road node where the current position of the target vehicle is located; S5. Generate the passable area corresponding to the target vehicle at the current time based on the passable area within a preset first radius area around the current target vehicle and the traffic congestion risk area of the road node where the current position of the target vehicle is located.

2. The passable area analysis method based on high-precision map and fusion perception according to claim 1, wherein: The task planning map of the target vehicle is the planning path map between the corresponding initial point and the destination of the target vehicle; The in-vehicle monitoring information includes obstacle information other than vehicles, path boundary information, and road surface flatness information recognized based on image recognition technology; The obstacle information includes the obstacle contour and the position vector of the corresponding obstacle based on the vehicle to which the in-vehicle monitoring information belongs; the path boundary information includes the position vectors of each recognized path boundary point based on the vehicle to which the in-vehicle monitoring information belongs; the road surface flatness information includes each road surface position point whose corresponding flatness does not belong to the preset interval and the position vector of the corresponding road surface position point based on the vehicle to which the in-vehicle monitoring information belongs; The associated vehicle of the target vehicle has the same vehicle networking as the target vehicle, and the distance between the vehicle positions uploaded by the target vehicle and its associated vehicle within a preset upload time deviation is less than a preset distance; The preset upload time deviation represents the maximum interval duration between the preset data upload times of the target vehicle and its associated vehicle in the database.

3. The method for analyzing passable areas based on high-precision maps and fusion perception according to claim 2, wherein: When optimizing the task planning map of the target vehicle, obtain the mapped position points of the current position of the target vehicle and the position of its associated vehicle in the task planning map of the target vehicle at the current time; Based on the mapped position points in the mission planning map of the target vehicle, generate a corresponding boundary position mapping area in the mission planning map of the target vehicle for the path boundary information in the vehicle-mounted monitoring information corresponding to each mapped position point, extract the boundary feature information in the obtained boundary position mapping area, and obtain the associated boundary feature information of the boundary feature information in the mission planning map of the target vehicle; according to the boundary feature information and its corresponding associated boundary feature information, obtain the forward mapping calibration coefficient and the bias mapping calibration coefficient corresponding to the vehicle-mounted monitoring information corresponding to the position of the target vehicle and its associated vehicle position at the current time; Take the straight line where the respective traveling directions of the target vehicle and its associated vehicle are located as the first reference pointing line of the corresponding vehicle; take the straight line perpendicular to the traveling direction of the target vehicle and its associated vehicle as the second reference pointing line of the corresponding vehicle; Calculate the calibration results of the vehicle-mounted monitoring information corresponding to the target vehicle and its associated vehicle at the current time. The calibration result corresponding to the position vector in each element of the vehicle-mounted monitoring information calibration result is equal to the vector sum of the first calibration sub-vector and the second calibration sub-vector corresponding to the corresponding position vector; the first calibration sub-vector corresponding to the corresponding position vector in the vehicle-mounted monitoring information calibration result is equal to the product vector of the sub-vector of the corresponding position vector on the first reference pointing line and the forward mapping calibration coefficient corresponding to the corresponding vehicle-mounted monitoring information; the second calibration sub-vector corresponding to the corresponding position vector in the vehicle-mounted monitoring information calibration result is equal to the product vector of the sub-vector of the corresponding position vector on the second reference pointing line and the bias mapping calibration coefficient corresponding to the corresponding vehicle-mounted monitoring information; According to the calibration results of the vehicle-mounted monitoring information corresponding to the position of the target vehicle and its associated vehicle at the current time; based on the mapped position points in the mission planning map of the target vehicle, generate and mark the position mapping areas corresponding to the obstacle information, path boundary information, and road surface flatness information in the calibration results of the vehicle-mounted monitoring information corresponding to each mapped position point in the mission planning map of the target vehicle, and obtain the optimization result of the mission planning map of the target vehicle; The passable area within the preset first radius around the currently locked target vehicle represents the area within the preset first radius around the current target vehicle in the optimization result of the mission planning map of the target vehicle that is not marked and belongs to the road area; Mark the areas within the preset first radius around the current target vehicle that do not belong to the road area.

4. The passable area analysis method based on high-precision maps and fusion perception according to claim 3, wherein: The boundary feature information includes the positions of each guardrail post in the road boundary and the curvature of the road corresponding to the position of the corresponding guardrail post; when obtaining the associated boundary feature information corresponding to the boundary feature information of the vehicle in the mission planning map of the target vehicle, it is obtained by querying the boundary feature information in the mission planning map of the target vehicle that is the closest to the mapped position point of the corresponding vehicle and is the same as the boundary feature information corresponding to the corresponding vehicle; The forward mapping calibration coefficient represents the mapping calibration coefficient corresponding to the sub-vector of the position vector corresponding to each element in the obtained vehicle-mounted monitoring information on the first reference pointing line corresponding to the corresponding vehicle; The respective forward mapping calibration coefficients corresponding to the target vehicle and its associated vehicles are equal to the average values of the mapping calibration coefficients corresponding to the component vectors of each position vector in the path boundary information of the corresponding vehicle on the first reference pointing line. The mapping calibration coefficient corresponding to the component vector of each position vector in the path boundary information of the vehicle on the first reference pointing line is equal to the quotient of the scalar of the component vector of each position vector in the path boundary information of the vehicle on the first reference pointing line and the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the first reference pointing line. And when the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the first reference pointing line is 0, it is determined that the mapping calibration coefficient corresponding to the component vector of the corresponding position vector in the path boundary information on the first reference pointing line is 1; The bias mapping calibration coefficient represents the mapping calibration coefficient corresponding to the component vector of the position vector corresponding to each element in the obtained vehicle-mounted monitoring information on the second reference pointing line corresponding to the corresponding vehicle; The respective bias mapping calibration coefficients corresponding to the target vehicle and its associated vehicles are equal to the average values of the mapping calibration coefficients corresponding to the component vectors of each position vector in the path boundary information of the corresponding vehicle on the second reference pointing line. The mapping calibration coefficient corresponding to the component vector of each position vector in the path boundary information of the vehicle on the second reference pointing line is equal to the quotient of the scalar of the component vector of each position vector in the path boundary information of the vehicle on the second reference pointing line and the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the second reference pointing line. And when the scalar of the component vector of the corresponding position vector in the corresponding associated boundary feature information on the second reference pointing line is 0, it is determined that the mapping calibration coefficient corresponding to the component vector of the corresponding position vector in the path boundary information on the second reference pointing line is 1.

5. The method for analyzing passable areas based on high-precision maps and fusion perception according to claim 1, wherein: When analyzing the congestion states corresponding to each road node in the preset second-radius area around the current position of the target vehicle within different preset time intervals, Obtain the historical road traffic information in the preset second-radius area around the current position of the target vehicle, and construct a set composed of each road node in the preset second-radius area around the current position of the target vehicle, denoted as the road node set; The historical road traffic information includes the traffic characteristic information corresponding to each road node in the corresponding area within different preset time intervals in a day. The traffic characteristic information includes the traffic states corresponding to each preset position area in the corresponding road node, and the traffic states include the normal traffic state and the traffic jam state; the states of the construction areas existing in the road nodes or the obstacle occupancy areas that appear are also recorded as the traffic jam state; The road nodes correspond to the preset road areas in the database. Different road nodes correspond to different preset road areas and the areas corresponding to each road area are equal; there are multiple preset time intervals in a day and the interval durations corresponding to different preset time intervals are equal; Obtain the traffic characteristic information corresponding to different preset time intervals in each day in the historical road traffic information corresponding to the k-th element in the road node set, Statistically analyze the set of traffic characteristic information corresponding to the j-th preset time interval on different dates in the historical road traffic information corresponding to the k-th element in the set of road nodes, and denote it as the congestion status analysis set YDF of the k-th element in the set of road nodes within the j-th preset time interval (k，j) ; Statistically analyze the frequency of each preset position area in the k-th element of the road node set where the corresponding traffic state is traffic congestion in YDF (k，j) Among the elements, mark all the preset position areas where the ratio of the obtained frequency to the total number of elements in YDF (k，j) is greater than the preset frequency; each position point within the marked preset position area is marked; When, based on the j-th preset time interval of a day, the traffic states of all the preset position areas marked in the traffic congestion state corresponding to the k-th element of the road node set are all traffic jams, and the traffic states of all the unmarked preset position areas are normal traffic states.

6. The method for analyzing passable areas based on high-precision maps and fusion perception according to claim 5, wherein: When analyzing the congestion correlation effects between different road nodes, obtain the historical road traffic information within a preset second radius area around the current position of the target vehicle, and denote any element corresponding road node in the road node set as the reference node; obtain the congestion time intervals corresponding to the congestion state of the reference node each time it appears in the obtained historical road traffic information, denoted as the first time interval, and obtain the set composed of each road node of all non-reference nodes whose corresponding congestion time interval and the first time interval have a non-empty intersection, denoted as a congestion correlation subset corresponding to the congestion state of the reference node; The set composed of the road nodes in the road node set that have congestion correlation effects with the reference node is the union of each congestion correlation subset corresponding to the congestion state of the reference node respectively.

7. The passable area analysis method based on high-precision maps and fusion perception according to claim 6, wherein: The associated road nodes corresponding to the road node where the current position of the target vehicle is located are all the road nodes that have congestion correlation effects with the road node where the current position of the target vehicle is located; When predicting the traffic congestion risk area of the road node where the current position of the target vehicle is located, obtain the traffic states of the obtained associated road nodes at the current time in the road monitoring images, if the traffic state of any one of the obtained associated road nodes is a traffic jam state, then determine that all the obtained associated road nodes are congestion risk nodes; if the traffic states of all the obtained associated road nodes are normal traffic states, then determine that all the obtained associated road nodes are not congestion risk nodes; Denote the time interval to which the current time belongs as T; Obtain the congestion state analysis sets corresponding to each congestion risk node within the time interval T respectively, and use the set composed of each preset position area marked in the obtained congestion state analysis sets as the traffic congestion risk area of the road node where the current position of the target vehicle is located.

8. The passable area analysis method based on high-precision map and fusion perception according to claim 1, wherein: When generating the passable area corresponding to the target vehicle at the current time, obtain the passable area within a preset first radius area around the current target vehicle, denoted as the first passable area; obtain the traffic congestion risk area of the road node where the current position of the target vehicle is located, denoted as the second passable area; The passable area corresponding to the target vehicle at the current time is the set of the position points that are not marked in both the first passable area and the second passable area in the union area of the first passable area and the second passable area.

Images