Navigation method and device based on high-precision map and vehicle

Abstract

The embodiment of the application discloses a kind of navigation method, device and vehicle based on high-precision map, it is related to automatic driving technical field.By obtaining the real-time position of vehicle, then based on real-time position and navigation routing map determines the sequence of road point around vehicle, then attribute assignment is carried out to the sequence of road point around vehicle, obtains the sequence of driving road point, finally, according to the sequence of driving road point, driving route planning is carried out.Therefore, by real-time output the sequence of driving road point around vehicle, so that vehicle can always according to the sequence of driving road point, driving route planning is not present in navigation route planning period, cannot drive due to no effective navigation result Condition, ensure the driving safety of vehicle in various situations, improve the use experience of user, further improve the safety of vehicle in automatic driving process.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and more specifically, to a navigation method, device, and vehicle based on high-precision maps. Background Technology

[0002] In recent years, with the emergence of the concept of autonomous driving, cars capable of autonomous driving have become increasingly popular among users. The most crucial aspect of achieving autonomous driving is ensuring that vehicles can operate safely in complex and ever-changing road environments.

[0003] However, during the research and practice of related technologies, the inventors of this application discovered that existing vehicles rely on navigation routes to drive in the process of autonomous driving, but it takes time for the vehicle to plan the navigation route. Therefore, during the period when the vehicle is planning the navigation route, there is no effective navigation path to support the vehicle to drive, which makes it impossible for the vehicle to use the autonomous driving function. Summary of the Invention

[0004] In view of the above problems, this application proposes a navigation method, device and vehicle based on high-precision maps, which can ensure that the vehicle always has a drivable path and will not stop driving during the autonomous driving process based on the real-time output of drivable roads around the vehicle.

[0005] To address the aforementioned technical problems, the embodiments of this application provide the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a navigation method based on a high-precision map. The method includes: obtaining the real-time location of a vehicle; determining a sequence of waypoints around the vehicle based on the real-time location and a navigation route map; wherein the navigation route map includes the connectivity of all lane units in the high-precision map, and the sequence of waypoints around the vehicle is a sequence of waypoints composed of trajectory points of lane units associated with the real-time location in the navigation route map; assigning attribute values ​​to the sequence of waypoints around the vehicle to obtain a driving waypoint sequence; and planning a driving route based on the driving waypoint sequence.

[0007] Secondly, embodiments of this application provide a navigation device based on a high-precision map. The device includes: an acquisition module for acquiring the real-time location of a vehicle; a determination module for determining a sequence of waypoints around the vehicle based on the real-time location and a navigation route map; wherein the navigation route map includes the connectivity of all lane units in the high-precision map, and the sequence of waypoints around the vehicle is a sequence of waypoints composed of trajectory points of lane units associated with the real-time location in the navigation route map; an assignment module for assigning attribute values ​​to the sequence of waypoints around the vehicle to obtain a driving waypoint sequence; and a planning module for planning a driving route based on the driving waypoint sequence.

[0008] Thirdly, embodiments of this application provide a vehicle comprising: one or more processors, a memory, and one or more application programs. The one or more application programs are stored in the memory and configured to be executed by the one or more processors, and are configured to perform the aforementioned navigation method based on high-precision maps.

[0009] Fourthly, embodiments of this application also provide a computer-readable storage medium storing program code, wherein the program code is executed by a processor to perform the above-described method.

[0010] The technical solution provided in this application obtains the vehicle's real-time location, then determines the road point sequence around the vehicle based on the real-time location and navigation route map, assigns attribute values ​​to the road point sequence to obtain the driving road point sequence, and finally plans the driving route based on the driving road point sequence. Therefore, by outputting the driving road point sequence around the vehicle in real time, the vehicle can always plan its route according to the driving road point sequence, avoiding situations where it cannot drive due to the lack of effective navigation results during navigation route planning. This ensures vehicle driving safety in various situations, improves the user experience, and further enhances the safety of the vehicle during autonomous driving. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating a navigation method based on a high-precision map provided in an embodiment of this application.

[0013] Figure 2 This is a flowchart illustrating another navigation method based on high-precision maps provided in this application embodiment.

[0014] Figure 3 This is a flowchart illustrating another navigation method based on a high-precision map provided in the embodiments of this application.

[0015] Figure 4 This is a schematic diagram of the structure of a navigation device based on a high-precision map provided in an embodiment of this application.

[0016] Figure 5 This is a schematic diagram of the vehicle structure provided in the embodiments of this application.

[0017] Figure 6This is a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Please see Figure 1 , Figure 1 This is a flowchart illustrating a navigation method based on a high-precision map provided in an embodiment of this application. The navigation method based on the high-precision map includes steps 110 to 140.

[0020] In step 110, the real-time location of the vehicle is obtained.

[0021] In this embodiment, the vehicle may include a positioning module for acquiring the vehicle's real-time location. The positioning module can acquire the vehicle's real-time location in various ways, such as LiDAR positioning, GPS (Global Positioning System), BeiDou Navigation Satellite System, or RTK (Real-time kinematic) positioning. Optionally, the positioning module can also acquire the vehicle's real-time location using a combination of these methods. For example, RTK and LiDAR can be used together to determine the vehicle's real-time location, achieving better positioning results and thus more accurately determining the vehicle's real-time location.

[0022] Optionally, if the real-time location is obtained via lidar, then the real-time location is the coordinate in the lidar coordinate system. Optionally, if the real-time location is obtained via GPS, BeiDou satellite navigation system, RTK, or other methods, then the real-time location is the coordinate in the Earth coordinate system. Understandably, if the real-time location is obtained via other methods, then the real-time location can also be the coordinate in other coordinate systems (e.g., geographic coordinate system).

[0023] Furthermore, the vehicle may also include a vehicle perimeter modeling module, used to construct a driving environment model around the vehicle based on its real-time location. Specifically, after obtaining the vehicle's real-time location, the positioning module sends the real-time location to the vehicle perimeter modeling module, so that the vehicle perimeter modeling module, upon receiving the real-time location sent by the positioning module, constructs a driving environment model of the vehicle's surrounding real-time location, ensuring that the vehicle can find drivable paths around its real-time location under various conditions.

[0024] In step 120, the sequence of waypoints around the vehicle is determined based on the real-time location and navigation route map.

[0025] In this embodiment, the navigation routing map includes the connectivity between all lane units in the high-precision map. A lane unit is a reference unit used to represent the position of a lane; for example, the longitudinal beam unit (referring to the longitudinal skeleton that makes up the lane) closest to the lane centerline can be used as the reference unit. The navigation routing map stores the relative coordinates of each lane unit and the connectivity cost between lane units.

[0026] In some implementations, the type of connectivity cost may include time cost, mileage cost, lane change cost, etc., which will be explained in detail in the following embodiments. It is understood that the type of connectivity cost can be set according to actual needs, and this application does not impose any restrictions on it.

[0027] In this embodiment, the road point sequence around the vehicle is a sequence of road points composed of the trajectory points of lane units associated with the real-time location of the vehicle in the navigation routing map. Specifically, it can be a sequence of road points composed of the trajectory points of lane units associated with the lane unit where the real-time location of the vehicle is located in the navigation routing map.

[0028] In some implementations, the lane unit associated with the lane unit where the vehicle's real-time location is located can be used as the vehicle-around associated lane unit. Therefore, the vehicle-around waypoint sequence can be a waypoint sequence composed of trajectory points of the vehicle-around associated lane units in the navigation routing map.

[0029] Optionally, the vehicle-around associated lane unit can be another lane unit in the navigation routing map that is directly connected to the lane unit where the vehicle's real-time location is located. Optionally, the vehicle-around associated lane unit may also include the lane unit where the vehicle's real-time location is located, as well as other lane units in the navigation routing map that are directly connected to that lane unit.

[0030] Specifically, after receiving the real-time location sent by the positioning module, the vehicle perimeter modeling module searches the navigation routing map based on the real-time location to determine the lane unit where the vehicle is located at the current moment. Then, it searches the navigation routing map with the lane unit where the vehicle is located as the center to determine the associated lane units around the vehicle. Finally, it extracts the trajectory points of the associated lane units around the vehicle to obtain the vehicle perimeter road point sequence.

[0031] In some implementations, the trajectory point of the vehicle-around lane unit can be the trajectory point of the center line of the vehicle-around lane unit, or it can be the trajectory point at other locations (such as the trajectory point corresponding to the lane line of the lane unit). This application does not limit this.

[0032] In some implementations, the number of lane units to be searched laterally from the lane unit where the vehicle is located can be preset. The lateral search can search for adjacent lane units on the left and right sides of the lane unit where the vehicle is located; alternatively, it can search for the lane unit where the vehicle is located, as well as the lane units on the left and right sides adjacent to that lane unit.

[0033] For example, if the search quantity is set to 1, then the search will take the lane cell where the vehicle is located as the center and search for lane cells that are directly adjacent to that lane cell in the left and right directions (i.e., one lane cell is searched in each direction). The searched lane cells will be output as the lane cells associated with the vehicle.

[0034] In some implementations, the longitudinal search distance of the lane cell where the vehicle is located can be preset. For example, if the forward search distance is set to 50m, then the lane cell in front of the vehicle will be determined by searching forward 50m.

[0035] Furthermore, if the lane units covered by the set search distance include intersections, the search direction is determined based on the global navigation results. If no valid navigation results are found, the nearest intersection is selected to continue the search forward. For example, if the forward search distance is set to 50m, but there is an intersection at 35m where you can travel in both directions, the global navigation results indicate that you need to continue to the left, so the search continues towards the left intersection.

[0036] Since the coordinates of lane units in the navigation route map are relative coordinates, the coordinates corresponding to the real-time location in the geographic coordinate system are needed to find the lane unit where the vehicle is located in the navigation route map based on the real-time location.

[0037] In some implementations, if the real-time location obtained by the positioning module is not in a geographic coordinate system (i.e., relative coordinates), the vehicle perimeter modeling module needs to perform coordinate transformation on the received real-time location, converting the non-geographic coordinate system to a geographic coordinate system to obtain the real-time location expressed in relative coordinates. For example, the real-time location is in a geocentric coordinate system (i.e., latitude and longitude) obtained through GPS. In order to determine the lane unit where the vehicle is located based on the real-time location, it is necessary to convert the geocentric coordinate system to a geographic coordinate system, that is, to convert the latitude and longitude representing the real-time location to relative coordinates.

[0038] In step 130, attribute values ​​are assigned to the vehicle surrounding road point sequence to obtain the driving road point sequence.

[0039] In this embodiment of the application, the driving waypoint sequence refers to the vehicle perimeter waypoint sequence after attribute assignment. Specifically, after determining the vehicle perimeter waypoint sequence, the vehicle perimeter modeling module assigns attribute values ​​to it to obtain the attribute-assigned vehicle perimeter waypoint sequence, i.e., the driving waypoint sequence.

[0040] In some implementations, the assigned attribute can be, for example, a speed limit attribute (e.g., 50 km / h) or an intersection direction attribute (e.g., straight, right turn, left turn, etc.). The specific setting can be determined according to actual needs, and this application does not impose any restrictions on it.

[0041] Furthermore, the vehicle may also include a decision-making and planning module, which is used to plan the vehicle's route, direction, and speed based on the waypoint sequence. Therefore, after determining the waypoint sequence, the vehicle perimeter modeling module sends the obtained waypoint sequence to the decision-making and planning module.

[0042] In step 140, a driving route is planned based on the driving waypoint sequence.

[0043] In this embodiment of the application, the vehicle perimeter modeling module sends the obtained waypoint sequence to the decision planning module. Upon receiving the waypoint sequence, the decision planning module obtains the attributes contained in the waypoint sequence and determines how to plan the driving route based on the attributes contained in the waypoint sequence, so as to determine the driving route of the vehicle.

[0044] In some implementations, the vehicle perimeter modeling module can assign a corresponding sequence ID to the waypoint sequence corresponding to each lane unit in the driving waypoint sequence obtained after attribute assignment, and extract the boundary point sequence in each lane unit. Then, according to a preset order, the sequence ID, boundary point sequence, and boundary line type are encapsulated into a message and sent to the decision planning module so that the decision planning module can plan the driving route based on the received message.

[0045] Furthermore, if the waypoint sequence includes the waypoint sequence corresponding to the lane unit where the vehicle's real-time location is located, the preset order can be, for example, front-back-left-right-center, front-left-rear-right-center, front-right-rear-left-center, etc. If the waypoint sequence does not include the waypoint sequence corresponding to the lane unit where the vehicle's real-time location is located, the preset order can be, for example, front-back-left-right, front-left-rear-right, front-right-rear-left, etc. Understandably, the preset order can be set according to actual needs, and this application does not impose any restrictions on it.

[0046] As described above, this embodiment of the application obtains the real-time location of the vehicle, then determines the sequence of waypoints around the vehicle based on the real-time location and the navigation route map, assigns attribute values ​​to the sequence of waypoints around the vehicle to obtain the driving waypoint sequence, and finally plans the driving route based on the driving waypoint sequence. Therefore, by outputting the driving waypoint sequence around the vehicle in real time, the vehicle can always plan its driving route according to the driving waypoint sequence, avoiding situations where it cannot drive due to the lack of effective navigation results during navigation route planning. This ensures the vehicle's driving safety in various situations, improves the user experience, and further enhances the safety of the vehicle during autonomous driving.

[0047] Please see Figure 2 , Figure 2 This is a flowchart illustrating another navigation method based on a high-precision map provided in this application embodiment. The navigation method based on the high-precision map includes steps 210 to 290.

[0048] In step 210, the real-time location of the vehicle is obtained.

[0049] In step 220, the sequence of waypoints around the vehicle is determined based on the real-time location and navigation route map.

[0050] For a detailed description of steps 210 to 220, please refer to steps 110 to 120 above, which will not be repeated here.

[0051] In step 230, the traffic rule attributes of the vehicle perimeter road point sequence are set to obtain the first assignment sequence.

[0052] In this embodiment, the traffic regulation attribute refers to the vehicle perimeter modeling module setting the corresponding attribute for the lane unit based on the traffic regulation information after determining the traffic regulation information corresponding to each trigger function contained in the lane unit.

[0053] For example, if the road point sequence around a vehicle includes a trigger function A, and the traffic regulation information corresponding to trigger function A is a speed limit sign, then when trigger function A is triggered, the speed limit parameter in the road point sequence around the vehicle will be updated, thereby setting the updated speed limit parameter as a traffic regulation attribute for the road point sequence around the vehicle, so that the vehicle's driving speed does not exceed the corresponding speed limit parameter in the traffic regulation attribute.

[0054] For example, if the road point sequence around a vehicle includes a trigger function B, and the traffic regulation information corresponding to trigger function B is a traffic light, then when trigger function B is triggered, it means that a traffic light has been identified, thereby obtaining the real-time position of the vehicle. Based on the real-time position of the vehicle, the intersection stage in which the vehicle is located can be determined (e.g., not approaching the intersection, approaching the intersection, entering the intersection). Thus, the traffic regulation attributes corresponding to the intersection stage in which the vehicle is located can be set for the road point sequence around the vehicle (e.g., the deceleration attribute corresponding to the approaching intersection stage), so that the vehicle's driving complies with the traffic regulation attribute.

[0055] In some implementations, traffic regulation information may include, for example, traffic lights, pedestrian crossings, traffic signs (e.g., speed limit signs, height limit signs), right-of-way signs, etc.

[0056] In some implementations, trigger functions can enable the vehicle perimeter modeling module to set traffic regulation attributes corresponding to the trigger function for the vehicle perimeter roadpoint sequence. Specifically, after obtaining the vehicle perimeter roadpoint sequence, the trigger function contained in each lane unit of the vehicle perimeter roadpoint sequence is triggered. Based on the trigger function, the corresponding traffic regulation information can be determined, and thus, based on the traffic regulation information, the traffic regulation attributes that need to be set for the vehicle perimeter roadpoint sequence can be determined. In other words, different trigger functions correspond to different traffic regulation information, and therefore correspond to different traffic regulation attributes.

[0057] In this embodiment, the first assignment sequence refers to the sequence of road points around the vehicle after assigning traffic regulation attributes. After setting traffic regulation attributes on the road point sequence around the vehicle, the decision planning module controls the vehicle to perform driving planning based on the traffic regulation attributes in the first assignment sequence.

[0058] Specifically, after determining the road point sequence around the vehicle, the vehicle perimeter modeling module assigns traffic rule attributes to it, that is, sets the traffic rule attributes of the road point sequence around the vehicle to obtain the first assignment sequence, so that the vehicle always complies with traffic rules during the autonomous driving process.

[0059] In some implementations, traffic regulation attributes may include, for example, intersection attributes, stop attributes, speed limit attributes, intersection direction attributes, etc. It is understood that, depending on actual needs, traffic regulation attributes may also include other content, and this application does not impose any limitations on this.

[0060] In some implementations, the mapping relationship between each lane unit and traffic regulation information can be pre-set. Specifically, after determining the road point sequence around the vehicle, the traffic regulation information corresponding to each lane unit in the road point sequence can be determined according to the mapping relationship between the lane unit and the traffic regulation information, thereby setting the traffic regulation attributes corresponding to the traffic regulation information for the road point sequence around the vehicle, and obtaining the first assignment sequence.

[0061] In some implementations, a mapping relationship between each lane unit, trigger function, and traffic regulation information can be pre-set, i.e., a preset mapping relationship. Specifically, after determining the road point sequence around the vehicle, the trigger function contained in each lane unit in the road point sequence is determined according to the preset mapping relationship, and then the traffic regulation information corresponding to the trigger function is determined according to the preset mapping relationship, thereby setting the traffic regulation attributes corresponding to the traffic regulation information for the road point sequence around the vehicle, and obtaining the first assignment sequence.

[0062] Furthermore, in some implementations, a unique lane ID can be assigned to each lane unit in the navigation routing map, and a mapping relationship between the lane ID, trigger function, and traffic information can be established. Thus, after determining the vehicle perimeter road point sequence, the trigger function contained in each lane unit can be searched in the mapping relationship between the lane ID, trigger function, and traffic information based on the lane ID of each lane unit in the vehicle perimeter road point sequence. Then, the vehicle perimeter modeling module can obtain the corresponding traffic regulation information based on the trigger function, and set the corresponding traffic regulation attributes for the vehicle perimeter road point sequence based on the obtained traffic regulation information.

[0063] In some implementations, the above mapping relationship can be stored in the form of a file or a data table; the mapping relationship can be stored locally (i.e., in the storage area of ​​the vehicle) or stored on a server connected to the vehicle.

[0064] In step 240, it is determined whether a valid global navigation result exists.

[0065] In this embodiment, the vehicle may further include a global planning module, which can be used to determine the global navigation result. The global navigation result refers to the optimal navigation route obtained by the global planning module based on the vehicle's starting point and destination.

[0066] During the autonomous driving process, the vehicle perimeter modeling module and the global planning module are executed in parallel. After obtaining the global navigation results, the global planning module sends them to the vehicle perimeter modeling module.

[0067] Specifically, the vehicle perimeter modeling module determines whether a valid global navigation result exists at this moment. A valid global navigation result means that the vehicle perimeter modeling module currently has a global navigation result sent by the global planning module, and the destination has not yet been reached.

[0068] In some implementations, the destination of the vehicle's journey can be input by the user. For example, if the user inputs "Tiananmen," the global planning module can determine that the vehicle's destination is Tiananmen.

[0069] Optionally, when the user is in the vehicle, the user can input the destination location through the in-vehicle display screen; alternatively, when the vehicle is in an autonomous driving state, the user can input the destination location remotely by connecting to the in-vehicle display screen.

[0070] In some implementations, the input can be entered manually or by voice.

[0071] In some implementations, the navigation method based on high-precision maps further includes:

[0072] (1) Determine the real-time status of the vehicle.

[0073] (2) If the real-time status meets the global planning triggering conditions, global planning is performed based on the vehicle's real-time location and destination location to determine the global navigation link information.

[0074] (3) Update the global navigation results based on the global navigation link information.

[0075] In this embodiment, the real-time status of the vehicle can refer to the vehicle's current driving information. This driving information can include the vehicle's current lane cell, the existence of a valid global planning result, and whether the destination location has changed.

[0076] In this embodiment of the application, global navigation link information refers to the link relationship of lane units that make up the optimal navigation route.

[0077] In this embodiment, the global planning module first determines the vehicle's real-time state, and then determines whether the vehicle's real-time state meets the global planning trigger conditions. If it is determined that the global planning trigger conditions are met, global planning is performed based on the vehicle's real-time location and destination location to determine global navigation link information. Specifically, the vehicle's real-time location and destination location are obtained, and then the starting lane unit and ending lane unit of the lane are determined in the navigation routing map based on the relative coordinates of the real-time location and the destination location. Then, based on the navigation routing map, the starting lane unit and ending lane unit are determined, and then, based on the connectivity cost of each lane unit in the navigation routing map, a navigation algorithm is used to finally determine the connection method with the minimum connectivity cost between the starting lane unit and the ending lane unit, thus obtaining the global navigation link information. Finally, the global planning module sends the obtained global navigation link information to the vehicle perimeter modeling module to update the global navigation results of the vehicle perimeter modeling module.

[0078] In some implementations, the navigation algorithm may be, for example, Dijkstra's algorithm, D* algorithm, A* algorithm, FLOYD path smoothing algorithm, etc. Understandably, different navigation algorithms have different characteristics and can be selected according to actual needs; this application does not impose any limitations on the comparison.

[0079] In some implementations, if a road segment contains multiple lane units that travel in the same direction and can change lanes between each other, these lane units can be output together in the global navigation link information. These lane units are divided into three types: optimal lanes, ordinary lanes, and special lanes. An optimal lane is the lane unit with the lowest connectivity cost; an ordinary lane is a lane unit where vehicles can change lanes to enter the optimal lane in both the current and next lane units; a special lane is a lane unit where lane changes are not allowed in the next lane unit and can only be made in the current lane unit to enter the optimal lane.

[0080] For example, the global navigation link information includes three lane units (left, center, and right) on the same road segment, all with the same direction and capable of changing lanes between each other. If a left turn is required to reach the destination, the left lane unit has the lowest cost for turning left to reach the destination, thus determining it as the optimal lane. The other two lane units are either ordinary lanes or special lanes. If, after entering the next lane unit along the remaining two lane units, the vehicle can still change lanes across the dashed line to enter the optimal lane, then the lane unit that can change lanes in these two lane units is an ordinary lane. If there is a lane unit in these two lane units that cannot change lanes to enter the optimal lane, then it means that the current lane unit is the last chance to change lanes to the optimal lane, and this lane unit will be marked as a special lane to provide special reminders to the user.

[0081] Optionally, the global planning trigger condition can refer to a situation where a valid global navigation result exists at the current moment, but the global planning module determines, based on the vehicle's real-time location, that the vehicle is not currently included in the global navigation result. For example, according to the current navigation calculation result, the vehicle has missed the last opportunity to change lanes into the optimal lane, resulting in the inability to continue driving to the destination based on the currently valid navigation calculation result.

[0082] Optionally, the global planning trigger condition can also refer to the situation where the global planning module determines, based on the vehicle's real-time location, that the vehicle is not in the optimal lane corresponding to the global navigation result. For example, the vehicle changes lanes from the optimal lane to a regular lane or a special lane.

[0083] Optionally, the global planning trigger condition can also refer to the global planning module receiving an update instruction for the destination location, i.e., the user has re-entered the destination location. For example, the original global navigation result shows the destination location as A, but now the destination location has changed to B. According to the original global navigation result, it is impossible to reach the destination location B. Therefore, the global planning module needs to re-perform global planning and update the global navigation result.

[0084] Optionally, the global planning trigger condition can also refer to the absence of a valid global navigation result at the current moment, i.e., the absence of an optimal navigation route at the current moment. For example, the vehicle may have already reached the destination position in the previous global navigation result, but the destination position has not yet been re-determined.

[0085] In step 250, if a valid global navigation result exists, the navigation attribute of the first assignment sequence is set according to the global navigation result to obtain the second assignment sequence.

[0086] In this embodiment, the second assignment sequence refers to a vehicle-around road point sequence that, in addition to setting traffic regulation attributes, also has navigation attributes. In other words, the second assignment sequence contains both traffic regulation attributes and navigation attributes.

[0087] Specifically, the first assignment sequence already includes the speed limit attribute as a traffic regulation attribute. After receiving the global navigation result sent by the global planning module, the navigation attribute is assigned to the vehicle surrounding road point sequence according to the lane type in the global navigation result. That is, the lane unit in the vehicle surrounding road point sequence that corresponds to the global navigation result is set to the corresponding lane type as the navigation attribute, thereby obtaining the second assignment sequence.

[0088] For example, in the global navigation results, lane unit A is the optimal lane and lane unit B is the special lane. The lane unit corresponding to lane unit A in the vehicle perimeter road point sequence with traffic regulation attributes is set as the optimal lane, and the lane unit corresponding to lane unit B is set as the special lane.

[0089] In some implementations, in addition to assigning navigation attributes to the first assignment sequence based on the global navigation results, the navigation attributes and preset attributes of the first assignment sequence can also be set based on the global navigation results.

[0090] Optionally, if the number of lane units corresponding to the road point sequence around the vehicle is less than or equal to the number of lane units corresponding to the global navigation result, the navigation attributes of the first assignment sequence can be set according to the global navigation result.

[0091] Optionally, if the number of lane units corresponding to the road point sequence is greater than the number of lane units corresponding to the global navigation result, navigation attributes can be set for the lane units corresponding to the global navigation result, and preset attributes can be set for the excess lane units. The preset attributes are used to indicate that the lane units corresponding to the road point sequence are not within the global navigation result, so that after receiving the first assignment sequence with preset attributes, the decision-making and planning module can drive normally according to the traffic rule attributes set in the first assignment sequence. Understandably, the preset attributes serve an identifying function; therefore, the decision-making and planning module does not consider the preset attributes when planning the driving route.

[0092] In step 260, the second assignment sequence is used as the waypoint sequence.

[0093] Specifically, after the vehicle perimeter modeling module sets traffic rule attributes on the vehicle perimeter waypoint sequence to obtain the first assignment sequence, it further sets navigation attributes on the first assignment sequence according to the global navigation results sent by the global planning module to obtain the second assignment sequence. Then, the second assignment sequence is used as the driving waypoint sequence, so that the decision planning module can plan the driving route according to the driving waypoint sequence.

[0094] In step 270, if there is no valid global navigation result, the preset attributes of the first assignment sequence are set to obtain the third assignment sequence.

[0095] For a detailed description of the preset attributes, please refer to the previous content, which will not be repeated here.

[0096] Specifically, if the vehicle perimeter modeling module does not contain the global navigation result sent by the global planning module, the vehicle perimeter modeling module actively sets preset attributes for the first assignment sequence to obtain the third assignment sequence. In other words, the vehicle perimeter waypoint sequence in the third assignment sequence includes both traffic rule attributes and preset attributes.

[0097] In step 280, the third assignment sequence is used as the waypoint sequence.

[0098] Specifically, the vehicle perimeter modeling module takes the third assignment sequence as the driving waypoint sequence and sends it to the decision planning module. The decision planning module obtains the attributes contained in the driving waypoint sequence. If a preset attribute exists, it determines that the lane unit corresponding to the waypoint sequence with the preset attribute does not belong to the navigation calculation result, that is, it does not belong to the navigation route.

[0099] As can be seen from the above description, in this embodiment of the application, if there is a valid navigation calculation result, the waypoint sequence contains at least traffic regulation attributes and navigation attributes; if there is no valid navigation calculation result, the waypoint sequence contains traffic regulation attributes and preset attributes.

[0100] Upon receiving a waypoint sequence, the decision-making and planning module first determines whether a waypoint sequence with navigation attributes exists. If so, the module plans a route based on these navigation attributes. If no waypoint sequence with navigation attributes exists, it indicates that no valid navigation calculation result exists, and the waypoint sequence only includes traffic regulation attributes and preset attributes. Therefore, the module can randomly select drivable lane units from the waypoint sequence for route planning. Furthermore, during the journey, the module guides the vehicle to drive in accordance with traffic rules based on the traffic regulation attributes in the waypoint sequence.

[0101] In step 290, a driving route is planned based on the driving waypoint sequence.

[0102] For a detailed description of step 290, please refer to step 140 above, which will not be repeated here.

[0103] As described above, this embodiment of the application obtains the real-time location of the vehicle, then determines the road point sequence around the vehicle based on the real-time location and the navigation route map, sets the traffic rule attributes of the road point sequence to obtain a first assigned sequence, and then determines whether there is a valid global navigation result. If there is a valid global navigation result, the navigation attribute of the first assigned sequence is set according to the global navigation result to obtain a second assigned sequence, which is then used as the driving road point sequence. If there is no valid global navigation result, the preset attribute of the first assigned sequence is set to obtain a third assigned sequence, which is then used as the driving road point sequence. Finally, driving route planning is performed based on the driving road point sequence. Therefore, by assigning attribute values ​​to the driving road point sequence around the vehicle in real time, the vehicle can always plan its driving route according to the assigned road point sequence, ensuring that the vehicle can drive normally according to the set attributes regardless of whether there is a global navigation result. This improves the user experience and further enhances the safety of the vehicle during autonomous driving.

[0104] Please see Figure 3 , Figure 3 This is a flowchart illustrating another navigation method based on a high-precision map provided in this application. The navigation method based on the high-precision map includes steps 310 to 390.

[0105] In step 310, a high-precision map is loaded, and lane units in the high-precision map are determined.

[0106] In this embodiment of the application, after the vehicle starts autonomous driving, it loads the content of the high-precision map and determines all lane units contained in the high-precision map.

[0107] In some implementations, the loaded high-definition map may be collected by the company's dedicated road information collection vehicle; or it may be collected by other companies, and the vehicle can load the high-definition map through the API of the high-definition map it needs to use.

[0108] In step 320, the relative coordinates of the lane units are determined.

[0109] In this embodiment of the application, after determining the lane unit, the relative coordinates corresponding to the lane unit are determined, thereby establishing a mapping relationship between the lane unit and the relative coordinates.

[0110] In some implementations, if the loaded high-precision map stores the relative coordinates of lane units, then the mapping relationship between the lane units and the high-precision map is established directly based on the relative coordinates of the lane units in the high-precision map.

[0111] In some implementations, if the coordinates of lane units in the loaded high-precision map are non-relative coordinates (e.g., latitude and longitude), a geographic coordinate system needs to be configured, and projection techniques are used to convert the non-relative coordinates into relative coordinates. The projection techniques can be, for example, UTM (Universal Transverse Mercator) projection, Gauss-Kruger projection, Mercator projection, etc., and this application does not limit the specific methods used.

[0112] In step 330, a navigation route map is determined based on the relative coordinates and the connectivity cost between lane units.

[0113] Connectivity cost refers to the resources required to travel from one lane unit to another.

[0114] In some implementations, connectivity costs can be of the following types: time cost, mileage cost, lane change cost, etc. Time cost refers to the time required to connect two lane units; mileage cost refers to the distance traveled to connect two lanes; and lane change cost refers to the ease or difficulty of changing lanes between two lanes.

[0115] Specifically, after determining the mapping relationship between lane units and relative coordinates, the connectivity relationships between lane units are determined. Then, the type of cost to be calculated (i.e., time cost, mileage cost, lane change cost) is determined, and the parameters required to calculate this type of cost are configured. Finally, the cost required for connectivity between lane units is calculated, resulting in the navigation routing map. Understandably, the navigation routing map includes the connectivity relationships between lane units and the connectivity costs between each lane unit.

[0116] In some implementations, if the cost type is mileage cost, the parameter to be configured is the mileage cost coefficient, so the mileage cost required for lane unit connectivity = mileage required for lane unit connectivity × mileage cost coefficient; if the cost type is time cost, the parameter to be configured is the time cost coefficient, so the time cost required for lane unit connectivity = mileage required for lane unit connectivity / lane unit speed limit × coefficient; if the cost type is lane change cost, the parameter to be configured is the lane change cost coefficient, so as to determine the lane change cost across dashed lines, lane change cost across solid lines, and lane change cost across opposite lane boundary lines (i.e., borrowing lanes).

[0117] In some implementations, the connectivity between lane units can be determined based on lane boundary lines. Specifically, the connectivity between a lane unit and its adjacent lane units is determined by the left and right lane boundary lines (i.e., adjacent lane boundary lines); the connectivity between a lane unit and the lanes in front and behind it is determined by the front and rear boundary lines; and the direction of all lane units is determined by the directional arrows within the lane units. For example, if the left and right boundary lines of lane unit A are both white dashed lines, it indicates that lane unit A can connect with the lane units to its left and right; if there is a lateral boundary line in front of lane unit A, it indicates that lane unit A cannot connect with the lane units in front of it; if there is a forward-pointing white arrow in lane unit A, it indicates that the vehicle's direction of travel in that lane unit is straight forward.

[0118] In step 340, the traffic regulations information corresponding to the high-precision map is loaded.

[0119] In some implementations, traffic regulation information corresponding to each lane unit can be loaded separately. Specifically, after determining the navigation route map, the traffic regulation information corresponding to each lane unit in the high-precision map can be directly saved to the lane unit, that is, the traffic regulation information is saved to the navigation route map. Thus, when the lane unit belongs to the vehicle surrounding road point sequence, the traffic regulation information contained in the vehicle surrounding road point sequence can be directly obtained.

[0120] In some implementations, traffic regulation information in high-precision maps can be loaded as a whole, and a unique identifier (e.g., traffic regulation ID) can be assigned to each traffic regulation information so that lane units can directly obtain the corresponding traffic regulation information based on the identifier.

[0121] Furthermore, in some implementations, the traffic regulations information loaded as a whole can be, for example, a linked list structure, a stack structure, a tuple structure, etc.

[0122] In step 350, the preset mapping relationship between lane units and traffic regulations is determined based on the navigation route map and traffic regulations information.

[0123] Specifically, after loading the traffic regulations information, a mapping relationship between lane units and traffic regulations information is set according to the lane units in the navigation routing map. Thus, when a lane unit belongs to a vehicle-circle road point sequence, the traffic regulations information corresponding to each lane can be determined based on the mapping relationship. This reduces the complexity of the navigation routing map, and since multiple lane units can correspond to the same traffic regulations information, the storage space occupied by the traffic regulations information can be reduced.

[0124] In step 360, the real-time location of the vehicle is obtained.

[0125] In step 370, the sequence of waypoints around the vehicle is determined based on the real-time location and the navigation route map.

[0126] In step 380, attribute values ​​are assigned to the vehicle surrounding road point sequence to obtain the driving road point sequence.

[0127] In step 390, a driving route is planned based on the driving waypoint sequence.

[0128] For a detailed description of steps 360 to 390, please refer to steps 110 to 140 above, which will not be repeated here.

[0129] As described above, this embodiment of the application loads a high-precision map, determines the lane units within the high-precision map, then determines the relative coordinates of the lane units, and subsequently determines a navigation route map based on the relative coordinates and the connectivity cost between lane units. Then, it loads the traffic regulation information corresponding to the high-precision map and determines the preset mapping relationship between lane units and traffic regulation information based on the navigation route map and the traffic regulation information. Therefore, by pre-loading the high-precision map, determining the navigation route map, and establishing the mapping relationship between lane units and traffic regulation information, the connectivity cost between lane units and the traffic regulation information corresponding to each lane unit can be determined. This allows the vehicle perimeter modeling module and the global planning module to directly use this data, shortening processing time and improving the user experience.

[0130] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a high-precision map-based navigation device 400 provided in an embodiment of this application. The high-precision map-based navigation device 400 may include an acquisition module 410, a determination module 420, an assignment module 450, and a planning module 440. Specifically:

[0131] The acquisition module 410 is used to acquire the real-time location of the vehicle.

[0132] The determination module 420 is used to determine the road point sequence around the vehicle based on the real-time location and the navigation route map; wherein, the navigation route map includes the connectivity of all lane units in the high-precision map, and the road point sequence around the vehicle is a sequence of road points composed of the trajectory points of the lane units associated with the real-time location in the navigation route map.

[0133] The assignment module 450 is used to assign attribute values ​​to the road point sequence around the vehicle to obtain the driving road point sequence.

[0134] The planning module 440 is used to plan driving routes based on the sequence of waypoints.

[0135] In some embodiments, the assignment module 450 includes:

[0136] The first sequence unit is used to set the traffic regulation attributes of the vehicle perimeter road point sequence to obtain the first assignment sequence;

[0137] The judgment unit is used to determine whether a valid global navigation result exists.

[0138] The second sequence unit is used to set the navigation attributes of the first assignment sequence according to the global navigation result if a valid global navigation result exists, so as to obtain the second assignment sequence.

[0139] The first determining unit is used to take the second assignment sequence as the waypoint sequence.

[0140] In some embodiments, the assignment module 450 further includes:

[0141] The third sequence unit is used to set the preset properties of the first assignment sequence to obtain the third assignment sequence if no valid global navigation result exists.

[0142] The second determining unit is used to take the third assignment sequence as the waypoint sequence.

[0143] In some embodiments, the second sequence unit is further configured to set the navigation attributes and preset attributes of the first assignment sequence based on the global navigation result.

[0144] In some embodiments, the first sequence unit includes:

[0145] The traffic regulation determination sub-unit is used to determine the traffic regulation information corresponding to the vehicle perimeter road point sequence based on the preset mapping relationship between lane units and traffic regulation information;

[0146] The first sequence subunit is used to set the traffic regulation attributes of the vehicle perimeter road point sequence according to the traffic regulation information, and obtain the first assignment sequence.

[0147] In some embodiments, the navigation device 400 based on a high-precision map further includes:

[0148] The status determination module is used to determine the real-time status of the vehicle.

[0149] The global planning module is used to determine the global navigation link information based on the vehicle's real-time location and destination location if the real-time status meets the global planning trigger conditions.

[0150] The update module is used to update the global navigation results based on the global navigation link information.

[0151] In some embodiments, the global planning module includes:

[0152] The determining unit is used to determine the starting lane corresponding to the real-time location and the ending lane corresponding to the ending location based on the navigation routing map;

[0153] The global planning unit is used to determine global navigation link information based on the navigation routing map and the starting lane and ending lane.

[0154] In some embodiments, the navigation device 400 based on a high-precision map further includes:

[0155] The map loading module is used to load a high-precision map and determine the lane units in the high-precision map.

[0156] The relative coordinate determination module is used to determine the relative coordinates of lane units;

[0157] The navigation route determination module is used to determine the navigation route map based on relative coordinates and connectivity costs between lane units.

[0158] In some embodiments, the navigation device 400 based on a high-precision map further includes:

[0159] The traffic regulations loading module is used to load traffic regulations information corresponding to the high-precision map;

[0160] The mapping relationship determination module is used to determine the preset mapping relationship between lane units and traffic regulations based on the navigation routing map and traffic regulations information.

[0161] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0162] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0163] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0164] Please see Figure 5 , Figure 5 The present invention provides a schematic diagram of the structure of a vehicle 500. The vehicle 500 in this application may include one or more of the following components: a processor 510, a memory 520, and one or more application programs. The one or more application programs may be stored in the memory 520 and configured to be executed by one or more processors 510. The one or more programs are configured to execute the navigation method based on high-precision maps as described in the foregoing method embodiments.

[0165] The processor 510 may include one or more processing cores. The processor 510 connects to various parts within the vehicle 500 using various interfaces and lines, and performs various functions and processes data of the vehicle 500 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 520, and by calling data stored in the memory 520. Optionally, the processor 510 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 510 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 510 and may be implemented separately using a communication chip.

[0166] The memory 520 may include random access memory (RAM) or read-only memory (ROM). The memory 520 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 520 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as assignment functions, global planning functions, loading functions, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created by the vehicle 500 during use (such as lane units, vehicle-around road point sequences, driving road point sequences, global navigation results, traffic regulation information, etc.).

[0167] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of this application. The computer-readable medium 600 stores program code, which can be called by a processor to execute the navigation method based on a high-precision map described in the above method embodiments.

[0168] The computer-readable storage medium 600 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 600 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 600 has storage space for program code 610 that performs any of the method steps described above. This program code can be read from or written to one or more computer program devices. The program code 610 may be compressed, for example, in a suitable form.

[0169] This application also provides a computer program device or computer program that includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the high-precision map-based navigation method described in the various optional embodiments above.

[0170] The navigation method, device, and vehicle based on high-precision maps provided in this application acquire the vehicle's real-time location, then determine the road point sequence around the vehicle based on the real-time location and navigation route map, assign attribute values ​​to the road point sequence to obtain the driving road point sequence, and finally plan the driving route based on the driving road point sequence. Therefore, by outputting the driving road point sequence around the vehicle in real time, the vehicle can always plan its route according to the driving road point sequence, avoiding situations where it cannot drive due to the lack of effective navigation results during navigation route planning. This ensures driving safety in various situations, improves the user experience, and further enhances the safety of the vehicle during autonomous driving.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A navigation method based on high-precision maps, characterized in that, The method includes: Obtain the real-time location of the vehicle; The vehicle surrounding waypoint sequence is determined based on the real-time location and the navigation routing map; wherein, the navigation routing map includes the connectivity of all lane units in the high-precision map, and the vehicle surrounding waypoint sequence is a waypoint sequence composed of the trajectory points of the lane units associated with the real-time location in the navigation routing map; Assigning attribute values ​​to the vehicle surrounding road point sequence to obtain a driving road point sequence: setting the traffic regulation attribute of the vehicle surrounding road point sequence to obtain a first assignment sequence; determining whether there is a valid global navigation result; if there is a valid global navigation result, setting the navigation attribute of the first assignment sequence according to the global navigation result to obtain a second assignment sequence; using the second assignment sequence as the driving road point sequence, wherein the navigation attribute includes lane type; The driving route is planned based on the driving waypoint sequence.

2. The method according to claim 1, characterized in that, The method further includes: If no valid global navigation result exists, the preset attribute of the first assignment sequence is set to obtain the third assignment sequence. The preset attribute is used to indicate that the lane unit corresponding to the vehicle perimeter road point sequence is not in the global navigation result. The third assignment sequence is used as the waypoint sequence.

3. The method according to claim 1, characterized in that, Setting the navigation attributes of the first assignment sequence based on the global navigation result includes: Based on the global navigation results, set the navigation attributes and preset attributes of the first assignment sequence.

4. The method according to claim 1, characterized in that, The traffic regulation attributes of the vehicle perimeter road point sequence are set to obtain the first assignment sequence, including: Based on the preset mapping relationship between lane units and traffic regulation information, the traffic regulation information corresponding to the vehicle perimeter road point sequence is determined; Based on the traffic regulations information, the traffic regulations attributes of the vehicle perimeter road point sequence are set to obtain the first assignment sequence.

5. The method according to claim 1, characterized in that, The method further includes: Determine the real-time status of the vehicle; If the real-time status meets the global planning triggering conditions, then global planning is performed based on the vehicle's real-time location and destination location to determine the global navigation link information; The global navigation results are updated based on the global navigation link information.

6. The method according to claim 5, characterized in that, The global planning triggering conditions include: There is a valid global navigation result at the current moment, but the vehicle's real-time location is not included in the global navigation result; or The vehicle's real-time location is not in the optimal lane corresponding to the global navigation result; or Received an update instruction for the destination location; or There is no valid global navigation result at the current moment.

7. The method according to claim 5, characterized in that, The global planning based on the vehicle's real-time location and destination location includes: Based on the navigation routing map, determine the starting lane corresponding to the real-time location and the ending lane corresponding to the ending location; Based on the navigation route map, global navigation link information is determined through global planning according to the starting lane and the ending lane.

8. The method according to claim 1, characterized in that, Before obtaining the real-time location of the vehicle, the method further includes: Load the high-precision map and determine the lane units in the high-precision map; Determine the relative coordinates of the lane unit; A navigation route map is determined based on the relative coordinates and the connectivity cost between the lane units.

9. The method according to claim 8, characterized in that, After determining the navigation route map, the process also includes: Load the traffic regulations information corresponding to the high-precision map; The mapping relationship between preset lane units and traffic regulations is determined based on the navigation route map and the traffic regulations information.

10. A navigation device based on a high-precision map, characterized in that, The device includes: The acquisition module is used to acquire the real-time location of the vehicle; The determination module is used to determine the vehicle surrounding waypoint sequence based on the real-time location and the navigation routing map; wherein, the navigation routing map includes the connectivity of all lane units in the high-precision map, and the vehicle surrounding waypoint sequence is a waypoint sequence composed of the trajectory points of the lane units associated with the real-time location in the navigation routing map; The assignment module is used to assign attribute values ​​to the vehicle surrounding road point sequence to obtain a driving road point sequence: setting the traffic regulation attribute of the vehicle surrounding road point sequence to obtain a first assignment sequence; determining whether there is a valid global navigation result; if there is a valid global navigation result, setting the navigation attribute of the first assignment sequence according to the global navigation result to obtain a second assignment sequence; and using the second assignment sequence as the driving road point sequence, wherein the navigation attribute includes lane type; The planning module is used to plan the driving route based on the driving waypoint sequence.

11. A vehicle, characterized in that, include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the navigation method based on a high-precision map as described in any one of claims 1-9.

Images