Controlled access route determination

Abstract

Embodiments of the present disclosure relate to controlled access highway exit route determination. The invention relates to a method for determining an exit route of a vehicle to a target exit ramp of a road, and to a corresponding vehicle control unit and to a vehicle. To determine an exit route, an exit route map is generated based on map data arranged in a link. The exit route map includes a plurality of exit route nodes and a plurality of exit route edges including a lane direction edge based on lane information included in at least some of the links, and a lane change edge. A confidence value and a cost value are assigned to each exit route edge. Based on the correspondingly determined exit map, an exit route is determined that corresponds to a path through the exit map to the target exit ramp, the path having an optimized total confidence value and an optimized total cost value.

Description

Technical Field

[0001] The present invention generally relates to determining an exit route for an at least partially automated vehicle from an at least partially controlled-access highway, and more particularly, to generating an exit route map that is then used to determine the exit route. Background Art

[0002] At least partially automated vehicles (i.e., vehicles that are capable of autonomous longitudinal and lateral control if the driver removes his hands from the steering wheel on certain types of roads) typically rely on map data to determine the path of the at least partially automated vehicle. On a multi-lane highway with at least partially controlled access (i.e., a road with multiple lanes for each direction, each direction is physically separated from the other direction, and entry and exit of at least some sections are limited to on-ramps and off-ramps, respectively), the map data may include information about the number of lanes at any given point on the at least partially controlled access multi-lane highway, and information about how the lanes connect to each other where lanes end or begin. However, for some sections of the at least partially controlled access highway, such information may be incomplete or completely missing. As a result, the at least partially automated vehicle may be unable to determine longitudinal and lateral control when traveling on a section of the at least partially controlled access highway for which map data is incomplete or missing. This may be particularly a problem if the at least partially automated vehicle is approaching a target off-ramp, i.e., when the vehicle is about to leave the at least partially controlled access multi-lane highway. As a result, in these situations, the driver will need to take over control of the at least partially automated vehicle.

[0003] It is therefore an object of the present disclosure to enable an at least partially automated vehicle to determine an exit route when traveling on an at least partially controlled-access, multi-lane highway where map data is incomplete by road segment. Summary of the invention

[0004] To achieve this objective, the present disclosure provides a method for determining an exit route of a vehicle to a target exit ramp of a multi-lane highway with at least partially controlled access. The method includes obtaining map data about the multi-lane highway with at least partially controlled access. The map data is arranged in a plurality of links. Each link defines a geographic location for a corresponding section of the multi-lane highway with at least partially controlled access. At least a subset of the plurality of links includes at least one of the number of lanes and lane relationship information. The method also includes generating an exit route map based on the map data and the target exit ramp. The exit route map includes a plurality of exit route nodes and a plurality of exit route edges. The plurality of exit route edges include lane direction edges based on the number of lanes and lane relationship information of the plurality of links, and lane change edges corresponding to lane changes between lanes of the multi-lane highway with at least partially controlled access. Each of the plurality of exit route nodes defines the start and end of the lane direction edge based on the geographic location of the plurality of links. The method also includes assigning a confidence value and a cost value to each exit route edge, the confidence value indicating the probability of existence of each exit route edge, and the cost value indicating the cost of traversing each exit route edge. The method also includes determining the exit route. The exit route corresponds to a path to the target exit ramp through the exit route map, the path having an optimized total confidence value and an optimized total cost value.

[0005] The present disclosure also provides an automobile control unit. The automobile control unit includes at least one processing unit and a memory coupled to the at least one processing unit and configured to store machine-readable instructions. The machine-readable instructions cause the at least one processing unit to obtain map data about a multi-lane highway with at least partially controlled access. The map data is arranged in a plurality of links. Each link defines a geographic location for a corresponding section of the multi-lane highway with at least partially controlled access. At least a subset of the plurality of links includes at least one of the number of lanes and lane relationship information. The machine-readable instructions also cause the at least one processing unit to generate an exit route map based on the map data and a target exit ramp. The exit route map includes a plurality of exit route nodes and a plurality of exit route edges. The plurality of exit route edges include lane direction edges based on the number of lanes and lane relationship information of the plurality of links, and lane change edges corresponding to lane changes between lanes of the multi-lane highway with at least partially controlled access. Each of the plurality of exit route nodes defines the start and end of the lane direction edge based on the geographic location of the plurality of links. The machine-readable instructions also cause the at least one processing unit to allocate a confidence value and a cost value to each exit route edge, the confidence value indicating the probability of existence of each exit route edge, and the cost value indicating the cost of crossing each exit route edge. The machine-readable instructions further cause the at least one processing unit to determine an exit route. The exit route corresponds to a path through the exit route map to the target exit ramp, the path having an optimized total confidence value and an optimized total cost value.

[0006] The present disclosure also provides a vehicle including the vehicle control unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Examples of the present disclosure will be described with reference to the following drawings, wherein like reference numerals represent like elements.

[0008] Figure 1A illustrates a vehicle on a multi-lane highway with at least partial controlled access according to an example of the present disclosure;

[0009] Figure 1B The example according to the present disclosure is shown in FIG. Figure 1A map data corresponding to at least a portion of a multi-lane highway with controlled access;

[0010] Figure 1C The example according to the present disclosure is shown in FIG. Figure 1A A multi-lane highway of at least partial controlled access corresponding to a Figure 1B The export route map generated by the map data;

[0011] Figure 2 The concept of generating an exit route map based on partially incomplete map data according to an example of the present disclosure is illustrated;

[0012] Figure 3 A flow chart illustrating a method for determining an exit route for a vehicle to a target exit ramp of an at least partially controlled-access multi-lane highway according to an example of the present disclosure;

[0013] Figure 4 A vehicle according to an example of the present disclosure is illustrated; and

[0014] Figure 5 An automotive control unit according to an example of the present disclosure is illustrated.

[0015] It should be understood that the above-mentioned drawings are by no means intended to limit the present disclosure. On the contrary, these drawings are provided to aid in understanding the present disclosure. It will be readily understood by those skilled in the art that the various aspects of the present invention shown in one figure may be combined with the various aspects of another figure, or may be omitted, without departing from the scope of the present disclosure. DETAILED DESCRIPTION

[0016] The present disclosure generally provides a method for determining an exit route of a vehicle to a target exit ramp of a multi-lane highway with at least partial controlled access, and an automobile control unit configured to execute instructions implementing the method for determining an exit route, and a vehicle including the automobile control unit.

[0017] The method generates an exit route map based on map data. More specifically, the map data of the at least partially controlled access multi-lane highway is arranged in a link including lane information. The lane information can, for example, specify at least the number of lanes for some sections of the at least partially controlled access multi-lane highway, and how the lanes are connected when the lanes end or begin. The method obtains the link and the included lane information, and generates an exit route map based on the link and the included lane information. If the lane information of a section of the at least partially controlled access multi-lane highway is incomplete or missing, the method estimates the exit route nodes and exit route edges of the exit route map corresponding to the section of the at least partially controlled access multi-lane highway with incomplete lane information. In order to consider the estimation of the exit route edges and exit route nodes of the exit route map, the method assigns a confidence value to each exit route edge of the exit route map, the confidence value indicating the confidence of the method regarding the existence of a given exit route edge. The method also assigns a cost value to each exit route edge, the cost value indicating the cost of crossing the corresponding exit route edge when the vehicle executes the method. Based on the exit route map and the assigned confidence values ​​and the assigned cost values, the method determines an exit route toward a target exit ramp by determining a path through the exit route map that minimizes the total cost and maximizes the total confidence associated with reaching the target exit ramp.

[0018] As the vehicle travels along the exit route, the method may also update the exit route map based on the vehicle's sensor data, and may update the exit route accordingly to take into account the impact of surrounding traffic on the cost values ​​of the exit route edges, and changes in confidence values ​​of the exit route edges, such as based on surrounding traffic or environmental features detected by the vehicle.

[0019] This general concept will be explained with reference to the accompanying drawings, in which Figure 3 A flow chart of a method 300 for determining an exit route for a vehicle to a target exit ramp of at least a partial access controlled multi-lane highway is provided, and Figures 1A to 2 Various aspects of method 300 are illustrated. In addition, Figure 4 A vehicle according to the present disclosure is illustrated, and Figure 5 An automobile controller configured to perform method 300 is illustrated.

[0020] Understandably, Figure 3 The dashed boxes in illustrative examples illustrate optional steps of method 300 .

[0021] The method 300 is configured to determine a vehicle, such as Figure 4 The vehicle 100 is driven onto a multi-lane highway with at least partial controlled access, such as FIG. 1 or Figure 2 An exit route of a target exit ramp of at least a portion of the controlled-access multi-lane highway 200 .

[0022] In the context of the present disclosure, vehicle 100 refers to any type of motor vehicle configured to transport people and / or goods. The motor of vehicle 100 may be any type of motor, such as an electric motor or an internal combustion engine. Vehicle 100 may be, for example, Figure 4 100 is a passenger vehicle shown. However, it should be understood that the vehicle 100 may also be a bus, a truck, or any other kind of vehicle, including one or more sensors 110 and a vehicle control unit 400 that enables the vehicle 100 to be driven in a partially automated manner. In other words, the vehicle control unit 400 and the one or more sensors 110 are configured to implement at least partial driving automation, i.e., Level 2 as defined in SAE International Standard J3016. Thus, the method 300 provides an exit route for functions within the vehicle control unit 400 that control longitudinal and lateral movement under the supervision of the driver of the vehicle 100 to guide the vehicle 100 to a target exit ramp. It should be understood that the vehicle control unit 400 and the one or more sensors 110 may implement a higher level of automation, i.e., the exit route may be used as an input to the lateral and longitudinal control of the vehicle 100, with limited or no supervision by the driver, or even without the presence of a driver.

[0023] The one or more sensors 110 may be configured to capture sensor data indicative of the environment of the vehicle 100, which may provide environmental awareness to enable at least partial driving automation. For example, the one or more sensors 110 may provide information to the vehicle 100 regarding the environment of the vehicle 100. Figure 2The information of the position and size of other vehicles 101 and trucks 102. To this end, one or more sensors 110 may be radar sensors, which may be configured to emit radio waves so as to determine the distance, angle and speed of objects around the vehicle based on the reflected radio waves. One or more sensors 110 may be light detection and ranging (LIDAR) sensors, which are configured to emit laser beams so as to determine the distance, angle and speed of objects around the vehicle 100 based on the reflected laser beams. One or more sensors 110 may be cameras that capture environmental images of the vehicle. One or more sensors 110 may be thermal imaging cameras that capture environmental images of the vehicle 100 based on infrared radiation. It should be understood that LIDAR sensors, radar sensors or cameras are provided only as examples of sensor types of one or more sensors 110. For example, one or more sensors 110 may also be ultrasonic sensors. More generally, one or more sensors 110 may be any type of sensor capable of capturing sensor data indicating the environment of the vehicle 100. It will also be understood that one or more sensors 110 may include multiple sensors of various types of sensors. In addition, one or more sensors 110 of the same type may exhibit different properties, such as by being configured to capture sensor data at different ranges, such as short range, medium range, and long range. For example, the vehicle 100 may include three short-range radar sensors located at the front and rear of the vehicle 100, respectively, a medium- and long-range radar sensor located at the rear of the vehicle 100, a LIDAR sensor located at the front of the vehicle 100, a rear-facing camera located at the rear of the vehicle 100, a front-facing camera located at the front of the vehicle, a front-facing camera located at the rearview mirror, and a rear-facing short- to medium-range radar sensor in each exterior mirror mounted on the vehicle door. It should be understood that the vehicle 100 may include more than one short-range radar sensor. Figure 4 More or fewer automotive sensors may be shown and discussed in the examples above.

[0024] The following will be combined Figure 5 The vehicle control unit 400 is discussed in more detail.

[0025] The at least partially access controlled multi-lane highway 200, hereinafter referred to as highway 200, can be any kind of road that has multiple lanes for each direction, the directions being separated from each other, such as by a piece of land, a median, or a combination of the two. In addition, entry and exit to the highway 200 is at least partially controlled, that is, entry and exit to the highway 200 are limited to entry ramps and exit ramps at least in some sections of the highway 200. For example, entry and exit to the highway 200 can be fully controlled, in which case the highway 200 can be referred to as an access controlled highway, such as an expressway, an interstate, or a freeway. In another example, some sections of the highway 200 can include at-grade intersections, in which case the highway 200 can also be referred to as a limited access highway, a two-lane road, or a freeway. Figure 1A and Figure 2 An example of one direction including an exit ramp of highway 200 is shown in FIG.

[0026] In step 310 , method 300 acquires map data, such as map data 210 , regarding at least a portion of the controlled-access multi-lane highway 200 .

[0027] like Figure 1B and Figure 2 As shown, the map data 210 is configured to provide location information about the highway 200. To this end, the map data 210 is arranged in a plurality of links, such as Figure 2 Link l1 to l 10 Each link defines the geographic location of a corresponding segment of highway 200, for example, defining the start and end of the segment according to a geographic coordinate system (GCS) defined in the European Petroleum Survey Group (EPSG) geodetic parameter dataset or any other geographic location representation. Figure 1B and Figure 2 In both, the start and end of a road segment and the start and end of a link are shown as nodes, indicating the corresponding start position of the link and the corresponding end position of the link. Figure 2 Based on the vertical dashed line illustration, the starting position of the link and the ending position of the link correspond to the beginning and the end of the section of the highway 200, respectively. Therefore, it can be understood that in the context of the present disclosure, a link refers to a representation of a geographical location and the length of the section of the highway 200. Figure 1B and Figure 2 As shown, the lengths of the links can be different or equal. In addition, these links can represent straight sections and curved sections of the highway 200.

[0028] In addition to providing a representation of the geographic location of the segment of highway 200, at least a subset of the plurality of links also each include lane information, the lane information including at least one of a lane number and lane relationship information. The lane number is a number indicating how many lanes a given segment of highway 200 includes. The lane relationship information defines how the lanes of a given segment connect to lanes of adjacent segments, i.e., a segment before the given segment and a segment after the given segment.

[0029] Although each link defines the geographic location of each road segment, not every link may include lane information separately. In addition, not every link may include both the number of lanes and lane relationship information. Therefore, there may be four types of links: a link that only defines the geographic location of a given road segment, a link that defines the number of lanes of a given road segment in addition to the geographic location, a link that defines the lane relationship information of a given road segment in addition to the geographic location, and a link that includes the number of lanes and lane relationship information in addition to defining the geographic location.

[0030] Figure 2 The links l2 and l4 and their corresponding road sections of the highway 200 (indicated by dashed lines and question marks) in the map data 210 that do not include lane information illustrate the fact that not all links may include lane information. That is, the map data 210 indicates the start and end of the road section of the highway 200 corresponding to the links l2 and l4, but does not indicate whether the lanes of the preceding road section continue through the road sections corresponding to the links l2 and l4 or end within these road sections, and how they connect to the next road section of 200 corresponding to the link including the number of lanes. In other words, the lane information of the map data 210 may be partially incomplete. The incompleteness of the lane information may extend to the entrance ramp and the exit ramp, that is, the map data 210 may indicate the existence of the ramp, but does not indicate on which side of the highway 200 the corresponding ramp is located.

[0031] The lane information included in each link of the map data 210 may also include lane change information indicating permitted changes between lanes. The lane change information may be based on road markings or traffic regulations, for example. For example, the map data 210 may indicate the presence of a shoulder, onto which a lane change is not permitted except in the case of an emergency or breakdown. Therefore, the lane change information may not indicate a lane change onto a shoulder. However, in countries where the use of shoulders is permitted during rush hour or similar situations, the lane change information may indicate such a temporarily permitted lane change.

[0032] It should be appreciated that the multiple links of the map data 210 may include additional information, or may include additional data inconsistencies as described above. For the sake of brevity, the above discussion of the map data 210 focuses only on aspects of the map data 210 that are relevant to the present disclosure.

[0033] In step 320 , the method 300 generates an exit route map based on the map data 210 and the target exit ramp, such as Figure 1C More specifically, based on the map data 210, the exit route map 220 provides a representation of all conceivable paths between the position of the vehicle 100 on the highway 200 and a target exit ramp, i.e., the exit ramp of the highway 200 that the vehicle 100 should exit, e.g., as determined by the navigation function of the automobile controller 400. Since the vehicle 100 is typically located on a link of the map data 210 when the exit route map 220 is generated, the exit route map 220 may start from a position behind the vehicle 100 so as to include the entire link that the vehicle 100 is currently traversing.

[0034] The exit route graph 220 includes a plurality of exit route nodes and a plurality of exit route edges. Therefore, the exit route graph 220 can be defined as shown in equation (1).

[0035] G 220 =(V, E) (1)

[0036] In equation (1), G 220 represents the exit route graph 220, V represents the vertices of the exit route graph 220, that is, multiple exit route nodes, and E represents the edges of the exit route graph 220, that is, the exit route edges.

[0037] The multiple exit route edges include lane direction edges and lane change edges. Therefore, the multiple exit route edges can be defined as shown in equation (2).

[0038] E={e ld1 ,…,e ldn , e lc1 ,…,e lcm} (2)

[0039] In equation (2), e ld1 To e ldn represents the lane direction edge, e lc1 To e lcm Therefore, as defined in equation (2), the exit roadmap 220 may include n lane direction edges and m lane change edges.

[0040] The lane-direction edges correspond to lanes of the road segment of highway 200. In other words, each lane-direction edge represents a lane of highway 200, and the direction of each lane-direction edge indicates the driving direction of the corresponding lane. Therefore, the number of lane-direction edges is based on the above-mentioned number of lanes. If the number of lanes of the link of highway 200 and the number of lanes of the road segment are missing, the number of lane-direction edges is determined based on the nearest preceding link including the number of lanes and the nearest following link including the number of lanes. More specifically, the number of lane-direction edges corresponds to all conceivable connections between the lanes of the nearest preceding link including the number of lanes and the lanes of the nearest following link including the number of lanes. In the context of connections, conceivable refers to connections that are typically present on multi-lane highways with at least partially controlled access. For example, if the nearest following link including the number of lanes indicates one less lane than the nearest preceding link including the number of lanes, one of the two rightmost lanes or one of the two leftmost lanes of the nearest preceding link can be terminated and can be connected to the leftmost lane or the rightmost lane of the nearest following link including the number of lanes, respectively.

[0041] Based on the lane relationship information of multiple links, the lane direction edges are connected to each other. That is, each lane direction edge is connected to the adjacent lane direction edge based on the connection indicated by the corresponding lane relationship information. In the context of the present disclosure, the expression "adjacent lane direction edges" should be understood to refer to the lane direction edges before and after the given lane direction edge in the driving direction of the lane of Highway 200, which is determined based on the geographical location of multiple links. If the lane relationship information of a given link is missing, the connection can be determined based on a lane relationship assumption. The lane relationship assumption can be a set of connection rules, which can be specific to the type of Highway 200 or can be country-specific. The lane relationship assumption can be based on a method of connecting all lane direction edges between two adjacent road sections. It should be understood that, as described above, the lane relationship assumption can be any kind of determination of lane direction edge connections based on conceivable connections of lane direction edge connections.

[0042] Figure 2, the concept of generating lane direction edges based on links that do not include lane information and conceivably connected is illustrated for links l2 and l4. For links l2 and l4 that do not include lane information, four lane direction edges are generated. In the case of link l2, the four lane direction edges connect the three lanes of the preceding section corresponding to link l1 and the two lanes of the following section corresponding to link l3. In the case of link l4, the four lane direction edges connect the two lanes of the preceding section corresponding to link l3 and the three lanes of the following section corresponding to link l5. Therefore, in both cases, the number of lane direction edges generated for each link is based on the number of lanes of multiple links. In the case of links that include the number of lanes, the number of lane direction edges generated for each such link corresponds to the number of lanes. If the link does not include the number of lanes, the number of lane direction edges generated for each link is derived from the number of lanes of the preceding link and the following link. In addition, the connection of the lane direction edges with the adjacent lane direction edges in this example is based on the lane relationship assumption, which is based on the assumption that the outermost lane usually ends or the new lane usually starts on the left or right side of the highway 200 in this example.

[0043] It can be understood that the lane direction edge corresponding to the 200 lanes of the highway is unidirectional, such as Figure 1A and Figure 2 However, in some cases, the lane direction edge indicating the lane at the grade intersection may be bidirectional, indicating a combined exit and access lane in the example where the highway 200 is a limited access highway.

[0044] The lane change edge corresponds to a lane change between lanes of the highway 200. That is, the lane change edge indicates that a lane change between lanes of a given segment of the highway 200 is legally permitted, for example, in view of road surface markings or traffic regulations, which may be indicated in the lane change information included in the plurality of links, or may be provided to the method 300 via a lane change rule set. In some examples, the method 300 may also generate lane changes between all lane direction edges and take this approach into account, as discussed in detail below with respect to step 330. Although the lane change edge connects vertices of the exit roadmap 220 corresponding to lanes of the highway 200, as Figure 1C and Figure 2 , but the lane-changing edge does not indicate that the lane change can only be performed at the location corresponding to the corresponding vertex. The lane change can also be performed along two lanes represented by two parallel one-way edges of the exit route map 220 starting from the corresponding vertex. For example, for at least a portion of the one-way edge starting at the corresponding vertex or for the entire lane direction edge mentioned above, until a subsequent vertex in the driving direction is reached, a lane change is possible. The subsequent vertex may or may not be connected to the two-way edge, thereby indicating a potential change in the permissibility of the lane change. For example, this concept can be used in Figure 2 Seen in Figure 2 The sections of the highway 200 corresponding to the links 16 and 17 are shown in which lane changes between the first lane and the second lane are not permitted, but in the section of the highway 200 corresponding to the link 18, such lane changes are permitted.

[0045] It can be understood that the lane change edge can be bidirectional, such as Figure 1C and Figure 2 As shown, it can also be unidirectional, if lane changes are allowed from one lane to another, but not the other way around.

[0046] Each of the plurality of exit route nodes defines the beginning and end of a lane direction edge based on the geographic locations of the plurality of links. In other words, the exit route node includes the geographic locations of the beginning and end of a segment of the highway 200 defined in the links of the map data 210. More specifically, each exit route node corresponds to a connection of two lane direction edges and includes the geographic locations of the connection. It should be understood that each exit route node therefore corresponds to the beginning of one segment of the highway 200 and the end of a corresponding subsequent segment.

[0047] Based on the above definition of the exit roadmap 220 and the elements of the exit roadmap 220 , step 320 may include steps 321 to 324 .

[0048] In step 321, method 300 may generate a number of lane-direction edges for each link that includes a number of lanes, wherein the number of lane-direction edges generated for each link corresponds to the number of lanes. For each link that also includes lane relationship information, each lane-direction edge is connected to two adjacent lane-direction edges based on the lane relationship information. For each link that does not include lane relationship information, each lane-direction edge is connected to two adjacent lane-direction edges based on the lane relationship assumption, as described above.

[0049] In step 322, method 300 may generate, for each link that does not include a lane number, a number of lane-direction edges based on the lane numbers of adjacent links that each include a lane number. That is, method 322 may generate, for each link that does not include a lane number, a number of lane-direction edges that are connected to adjacent lane-direction edges based on conceivable connections between lane-direction edges as described above.

[0050] In step 323, method 300 may generate an exit route node for each connection of two lane direction edges. Each exit route node includes a geographic location based on the link corresponding to the corresponding two lane direction edges. More precisely, the geographic location included in each exit route node corresponds to the end of the link and the beginning of the subsequent link. It should be understood that as part of step 323, method 300 may not generate more than one exit route node for each geographic location.

[0051] In step 324, the method 300 may generate lane change edges indicating lane changes between at least a subset of the plurality of exit route nodes. The generation of the lane change edges may be based on lane change information included in the plurality of links, or may be based on known traffic regulations governing lane changes or any other type of information indicating that lane changes are permitted.

[0052] It should be understood that steps 321 to 324 merely represent examples of how to generate the exit route map 220 based on the principles discussed above with respect to step 320. In step 320, the method 300 may generate the exit route map 220 in any suitable manner based on the above principles.

[0053] In step 330, the method 300 assigns a confidence value and a cost value to each exit route edge. In other words, the method 300 may assign two weights to each exit route in step 330. Therefore, the exit route graph 220 is a weighted graph.

[0054] The confidence value indicates the probability of existence of each exit route edge. That is, the confidence value can indicate the possibility of existence of each exit route. For example, in the case of a lane direction edge based on a link including lane number and lane relationship information, it can be assumed that the corresponding lane of highway 200 and the lane direction edge do exist. In this case, the confidence value can indicate a high probability of existence, such as the maximum probability of existence. If any one or both of the number of lanes and lane relationship information are not included in a given link, the corresponding lane direction edge may or may not exist, provided that the corresponding lane direction edge can be based on an assumption about the adjacent lane direction or about the connection between the lane direction edge and the adjacent lane direction edge. In this case, the confidence value assigned to the corresponding lane direction edge by method 300 can reflect at least some degree of uncertainty about the existence of such a lane direction edge. The same principle applies to a lane change edge. If the lane change edge is based on the lane change information of a link of map data 210, the confidence value can indicate a high probability of existence, such as the maximum probability of existence. If a lane change edge is generated in step 320 based on a lane change rule set or based on a method of generating lane change edges between all lane direction edges, the confidence value assigned by the method 300 can reflect at least some degree of uncertainty regarding the existence of such a lane change edge. In summary, the confidence value can also be understood as indicating the confidence that the method 300 has regarding the existence of a given exit route edge.

[0055] To provide an example of the above concepts, the method 300 may assign a confidence value ranging from 0 to 1 to each exit route edge, where 0 indicates that a given exit route edge does not exist and 1 indicates that a given entry route edge does exist, i.e., a value of 1 may indicate the maximum probability of existence. If the exit route edge is based on lane information or lane change information included in a link of the map data 210, the method 300 may assign a confidence value of 1, i.e., the maximum probability value. If the map data 210 is not considered completely accurate, the method 300 may also take into account the quality of the map data 210 by assigning a value less than 1, such as 0.95, 0.9, or 0.85 in these cases. If the exit route edge is based on a lane relationship assumption, a lane change rule set, or a method of generating a lane change edge between all lane direction edges, the method 300 may assign a confidence value of 0.5 to reflect the above uncertainty of existence. If the method 300 is more or less confident in the existence of the exit route edge, the method 300 may also assign a value higher or lower than 0.5, such as 0.6 or 0.4, respectively.

[0056] It should be understood that the value range of 0 to 1 is provided only as an example. The method 300 may assign confidence values ​​based on any kind of value range or based on any other metric indicating a range from “exit route edge is likely not present” to “exit route edge is likely present”.

[0057] According to the above principles regarding confidence values, step 330 may include steps 331 and 332. In step 332, method 300 may assign a confidence value indicating a maximum existence probability to each exit route edge corresponding to a link including at least one of the number of lanes and the lane relationship information. In step 332, method 300 may assign a confidence value indicating an existence probability of the corresponding exit route edge to each exit route edge that does not correspond to a link including at least one of the number of lanes and the lane relationship information.

[0058] The cost value indicates the cost of traversing each exit route edge. That is, the cost value reflects whether there are any additional costs in addition to the costs already incurred for traveling along highway 200 toward the target exit ramp. Therefore, traveling along the lane direction edge will not incur additional costs, while changing lanes may incur additional costs, for example due to necessary speed reduction. In addition, the closer the exit route edge is to the target exit ramp, the greater the urgency of navigating toward the target exit ramp, which can also be included in the cost value assigned to the exit route edge closer to the target exit ramp in exit route map 220. Therefore, the cost of traversing each exit route edge can take into account various cost factors, such as the above-mentioned cost factors or additional costs indicating the cost of reaching the target exit ramp.

[0059] Again using the value range of 0 to 1 as an example, a value of 0 may indicate no additional cost associated with traversing a given exit-route edge, while a value of 1 may indicate a maximum additional cost associated with traversing a given exit-route edge. To reflect the increasing urgency as the target exit ramp is approached, method 300 may assign a cost value that gradually approaches 1 as the target on-ramp is approached. For example, a lane-wise edge corresponding to the leftmost lane of highway 200 at the same location on highway 200 as the target exit ramp may be assigned a lane-wise edge (see Figure 2 Link 17 in can be assigned a cost value of 1. Therefore, the lane direction edge at the beginning of the exit route edge can have a cost value of 0. For the lane farthest from the target exit ramp, e.g. Figure 1A and Figure 2 For the leftmost lane in , the cost value can approach 1 as the proximity to the target exit ramp increases. For the lane closest to the target exit ramp, for example Figure 1A and Figure 2 For the rightmost lane in highway 200, the cost value may remain close to or remain at 0 as the proximity to the target exit ramp increases. With respect to the lane change edge, the cost value may reflect a basic lane change cost, such as 0.25 or 0.4. As the proximity to the target exit ramp increases, the cost value assigned by method 300 may increase dramatically for the lane change edge connected to the lane direction edge corresponding to the leftmost lane of highway 200. In contrast, the cost value assigned by method 300 for the lane change edge connected to the rightmost lane of highway 200 only increases slowly.

[0060] Furthermore, a given exit route edge that is assigned a confidence value indicating that the given exit route edge is likely not present may be assigned a cost value of 1 or infinity to reflect in the cost value the likelihood that the given exit route edge also does not exist.

[0061] It should be understood that the value range of 0 to 1 is provided only as an example. The method 300 may assign cost values ​​based on any kind of value range or based on any other metric indicating a range from "no additional cost" to "maximum additional cost."

[0062] According to the above principle regarding cost value, step 330 may include steps 333 to 335 .

[0063] In step 333, method 300 may assign a lane cost to each lane direction edge based on the drivable speed during the lane direction edge crossing. For example, if a given lane direction edge can be driven at a national speed limit or a speed set by the driver of vehicle 100 or a speed set by an autonomous driving function of vehicle 100, the lane cost based on the drivable speed may be zero. If the drivable speed is below such a speed limit or set speed, the lane cost based on the drivable speed may increase as the speed decreases. The lane cost based on the drivable speed may also take into account sensor data from one or more sensors 110 that may indicate the drivable speed.

[0064] In step 334, the method 300 may assign a lane change cost to each lane change edge. The lane change cost may be based on at least one of the probability of lane change success, the traffic density in the target lane corresponding to the lane change, and the lane change direction cost. The lane change direction cost may account for the fact that the lane change from a faster lane, such as a Figure 1A and Figure 2 Switching from the leftmost lane in the lane change to a slower lane may be easier to perform than switching from a slower lane to a faster lane. The lane change success probability, the traffic density in the target lane corresponding to the lane change, and the lane change direction cost may also take into account the sensor data of the one or more sensors 110 .

[0065] In step 335, method 300 may assign an urgency cost to each exit-route edge, the urgency cost indicating the remaining distance to the target exit ramp. As described above, the farther away the lane of the exit-route edge is when approaching the target exit ramp, the greater the urgency to drive to the exit ramp. This urgency may be reflected by the urgency, so the shorter the remaining distance, the greater the urgency, especially in the case of the exit-route edge associated with the lane farthest from the target exit ramp, such as Figure 1A and Figure 2 The leftmost lane.

[0066] In step 340, method 300 determines an exit route. The exit route corresponds to a path through the exit route map 220 to reach the target exit ramp, the path having an optimized total confidence value and an optimized total cost value. In other words, method 300 may apply an algorithm in step 340 for determining the shortest path through the exit route map 220 based on the cost value and confidence value assigned to the exit route map edge in step 330. Examples of algorithms for determining the shortest path through the exit route map 220 may include, but are not limited to, a Dijkstra algorithm, an A* algorithm, a Bellman-Ford algorithm, or a Floyd-Warshall algorithm. To this end, step 340 may include step 341, in which method 300 may determine the shortest path through the exit route map having the lowest associated total cost value and the largest associated total confidence value.

[0067] It should be understood that the exit route may not include the exit route edge having a confidence value indicating the lowest probability of existence. Likewise, the exit route edge having a cost value indicating the highest additional traversal cost may be excluded from the exit route.

[0068] The method 300 may include step 350, wherein the method 300 updates the exit route map based on sensor data captured by one or more sensors 110 of the vehicle 100. As described above, the sensor data may indicate at least one of the traffic conditions on each lane of the highway 200, such as Figure 2 As shown. Figure 2 In FIG. 1 , based on sensor data from one or more sensors 110 , vehicle 100 may sense other vehicles 101 and trucks 102 . The sensor data may also indicate road markings, such as Figure 2 200. The sensor data may also indicate the end of a lane of the highway 200. Based on the sensor data of the one or more sensors, the method 300 may update the exit route map 220 and more accurately update the weights of the exit route edges. To this end, step 350 may include step 351, in which the method 300 may update the probability value and cost value of each of the plurality of exit route edges based on the sensor data of the one or more sensors 110.

[0069] To provide an example of updating probability values ​​based on sensor data, if the sensor data indicates the presence of a lane, the probability values ​​of exit route edges that were initially set to values ​​indicating a lower probability of existence may be increased, for example even to a maximum probability of existence, due to links corresponding to map data 210 without lane information or lane change information. Conversely, if the sensor data indicates that there are no exit route edges generated based on links without lane information or lane change information, the probability values ​​may be updated to indicate a minimum probability of existence. In the context of lane change edges, the probability values ​​of these edges may be updated based on detected road surface markings that may indicate that a lane change may not be permitted. If such road markings are detected, the corresponding probability values ​​may be set to the minimum probability value.

[0070] To provide an example of updating a cost value based on sensor data, the cost value associated with an exit route edge may be increased or decreased based on the traffic density detected by one or more sensors, respectively. Similarly, if the drivable speed is determined by the sensor data to be increased or decreased, the cost value of the corresponding exit route edge may be decreased or increased, respectively.

[0071] When the vehicle 100 is traveling toward the target exit ramp, steps 340 and 350 may be performed continuously. That is, the method 300 initially assigns probability values ​​and confidence values ​​to the exit route edges in step 330, and the method 300 determines the initial exit route based on the probability values ​​and confidence values ​​in step 340. Thereafter, the method 300 may update the probability values ​​and confidence values ​​in step 350, and re-determine the exit route in step 340, and repeat these steps until the target exit ramp is reached. This concept is described in detail in FIG. Figure 3 340 and 350. Thus, by repeatedly performing steps 340 and 350, the exit route determined in step 340 may continually take into account the current location of the vehicle 100 and the sensor data captured by the one or more sensors 110.

[0072] It is understood that although steps 340 and 350 may be performed continuously, the exit route may be determined only once without updating the exit route map, for example, if the highway 200 is reserved only for autonomous driving vehicles, in which case the vehicle 100 may broadcast its route intention to other vehicles on the highway 200. In this case, re-destination planning of the exit route and updating of the exit route map 220 may not be required.

[0073] Figure 5 An automotive control unit 400 is shown configured to perform the method 300. The automotive control unit 400 may include a processor 410, a graphics processing unit (GPU) 320, an automotive processing system 430, a memory 440, a removable storage device 450, a storage device 460, a cellular interface 470, a global navigation satellite system (GNSS) interface 480, and a communication interface 490.

[0074] Processor 410 may be any type of single-core or multi-core processing unit that employs a reduced instruction set (RISC) or complex instruction set (CISC). Exemplary RISC processing units include ARM-based cores or RISC V-based cores. Exemplary CISC processing units include x86-based cores or x86-64-based cores. Processor 410 may execute instructions to cause automotive control unit 400 to perform method 300. Processor 410 may be directly coupled to any component of computing device 400, or may be directly coupled to memory 430, GPU 420, and device bus.

[0075] GPU 420 can be any kind of processing unit optimized for processing graphics-related instructions or more generally for parallel processing of instructions. Thus, GPU 420 can be configured to generate information, such as ADAS information or telemetry data, for a driver of a vehicle, for example via a head-up display (HUD) or a display arranged within the driver's field of view. GPU 420 can be coupled to the HUD and / or display via connection 420C. GPU 420 can also execute at least a portion of method 300 to achieve fast parallel processing of instructions related to method 300. It should be noted that in some embodiments, processor 410 can determine that GPU 420 does not need to execute instructions related to method 300. GPU 420 can be directly coupled to any component of the automotive control unit 400, or can be directly coupled to processor 410 and memory 430. In some embodiments, GPU 320 can also be coupled to a device bus.

[0076] The vehicle processing system 430 can be any kind of system on a chip that is configured to provide trillions of operations per second (TOPS) to enable the vehicle control unit 400 to implement one or more ADAS while driving. The vehicle processing system 430 can interface only with the processor 410, or can interface with other devices via a system bus. For example, the vehicle processing system 430 can execute instructions related to updating the exit route map 220 and redetermining the exit route map based on the updated exit route map 220. The vehicle processing system 430 can also determine the lateral and longitudinal control of the vehicle 100 toward the target exit ramp of the highway 200.

[0077] The memory 440 may be any kind of fast storage device that enables the processor 410, GPU 420, and vehicle processing system 430 to store instructions for fast retrieval during instruction processing, as well as cache and buffer data. The memory 440 may be a unified memory that is coupled to the processor 410 and GPU 420 and vehicle processing system 330 so that the memory 340 can be allocated to the processor 310, GPU 320, and vehicle processing system 430 as needed. Alternatively, the processor 410, GPU 320, and vehicle processing system 430 may be coupled to separate processor memories 440a, GPU memories 440b, and vehicle processing system memories 440c.

[0078] The removable storage device 450 may be a storage device that is detachably coupled to the vehicle control unit 400. Examples include a digital versatile disc (DVD), a compact disc (CD), a universal serial bus (USB) storage device, such as an external SSD or a magnetic tape. It should be noted that the removable storage device 450 may store data, such as instructions of the method 300 and / or the map data 210, or may be omitted.

[0079] Storage device 460 may be a storage device that enables storage of program instructions and other data. For example, storage device 460 may be a hard disk drive (HDD), a solid state disk (SSD), or some other type of non-volatile memory. Storage device 460 may, for example, store instructions of method 300.

[0080] Removable storage device 450 and storage device 460 may be coupled to processor 410 via a system bus. The system bus may be any kind of bus system that enables processor 410 and optional GPU 420 and vehicle processing system 430 to communicate with other devices of vehicle control unit 400. Bus 440 may be, for example, a Peripheral Component Interconnect Express (PCIe) bus or a Serial AT Attachment (SA-TA) bus.

[0081] The cellular interface 470 may be any kind of interface that enables the vehicle control unit 400 to communicate via a cellular network, such as a 4G network or a 5G network.

[0082] The GNSS interface 480 may be any type of interface that enables the vehicle control unit 400 to receive position data provided by a satellite network, such as the Global Positioning System (GPS), the Global Navigation Satellite System (GLONASS), or Galileo. This position data may be used when generating and updating the exit route map 320 and when determining and re-determining exit routes.

[0083] The communication interface 490 may enable the computing device 400 to interface with external devices, either directly or via a network, via connection 480C. The communication interface 380 may, for example, enable the computing device 400 to couple to a wired or wireless network, such as Ethernet, Wifi, a controller area network (CAN) bus, or any bus system suitable for a vehicle. For example, the vehicle control unit 400 may be coupled to one or more sensors 110 to receive information about the environment of the vehicle 100 to update the exit route map 210. The communication interface 490 may also include a USB port or a serial port to enable direct communication with external devices.

[0084] The automotive control unit 400 may be integrated with the vehicle, for example under the cab, under the dashboard, or in the trunk of the vehicle 400 .

[0085] The present invention can also be explained by the following examples.

[0086] In one example, a method for determining an exit route for a vehicle to a target exit ramp of a multi-lane highway with at least partially controlled access includes: obtaining map data about the at least partially controlled access multi-lane highway, the map data being arranged in a plurality of links, each link defining a geographic location for a corresponding section of the at least partially controlled access multi-lane highway, wherein at least a subset of the plurality of links includes at least one of a number of lanes and lane relationship information; generating an exit route map based on the map data and the target exit ramp, the exit route map including a plurality of exit route nodes and a plurality of exit route edges, wherein: the plurality of exit route edges include the plurality of links based on the plurality of links. The invention relates to a method for controlling a plurality of exit route nodes, comprising: providing a plurality of exit route nodes for determining a lane direction edge of the plurality of lanes and the lane relationship information, and a lane change edge corresponding to a lane change between lanes of the at least partially controlled-access multi-lane highway, and each of the plurality of exit route nodes defines a start and an end of the lane direction edge based on the geographic location of the plurality of links; assigning a confidence value and a cost value to each exit route edge, the confidence value indicating an existence probability of each exit route edge, and the cost value indicating a cost of traversing each exit route edge; and determining the exit route, the exit route corresponding to a path through the exit route map to the target exit ramp, the path having an optimized total confidence value and an optimized total cost value.

[0087] In the example method, assigning a confidence value to each exit route edge may include assigning a confidence value indicating a maximum existence probability to each exit route edge corresponding to a link including at least one of a lane number and lane relationship information.

[0088] In the example method, assigning a confidence value to each exit route edge may include assigning a confidence value indicating an existence probability of the corresponding exit route edge to each exit route edge that does not correspond to a link including at least one of a lane number and a lane relationship information.

[0089] In the example method, assigning a cost value to each exit route edge may include assigning a lane cost to each lane direction edge based on a drivable speed during traversal of the lane direction edge.

[0090] In the example method, assigning a cost value to each exit route edge may include assigning a lane change cost to each lane change edge, the lane change cost being based on at least one of a lane change success probability, a traffic density in a target lane corresponding to the lane change, and a lane change direction cost.

[0091] In the example method, assigning a cost value to each exit route edge may include assigning an emergency cost to each exit route edge, the emergency cost indicating a remaining distance to the target exit ramp.

[0092] The example method may also include at least one of: updating the exit route map based on sensor data captured by the vehicle, the sensor data indicating traffic conditions on each lane of the at least partially controlled-access multi-lane highway, one or more road surface markings, and the end of a lane of the at least partially controlled-access multi-lane highway.

[0093] In this example method, updating the exit route map based on the sensor data may include updating the probability value and the cost value of each exit route edge in the plurality of exit route edges.

[0094] In this example method, determining the exit route may include determining a shortest path through the exit route map having a lowest associated total cost value and a greatest associated total confidence value.

[0095] In this example method, generating the exit route map may include generating a number of lane-direction edges corresponding to the number of lanes for each link including a number of lanes, wherein for each link also including lane relationship information, each lane-direction edge may be connected to two adjacent lane-direction edges based on the lane relationship information, and wherein for each link not including lane relationship information, each lane-direction edge may be connected to two adjacent lane-direction edges based on a lane relationship assumption, and for each link not including a number of lanes, generating the number of lane-direction edges based on the number of lanes of adjacent links that respectively include a number of lanes; generating an exit route node at each connection of two lane-direction edges, each exit route node including a geographic location based on the link corresponding to the corresponding two lane-direction edges; and generating a lane change edge indicating a lane change between at least a subset of the multiple exit route nodes.

[0096] In one example, an automobile control unit includes at least one processing unit; and a memory coupled to the at least one processing unit and configured to store machine-readable instructions. The machine-readable instructions cause the at least one processing unit to: obtain map data about the at least partially controlled-access multi-lane highway, the map data being arranged in a plurality of links, each link defining a geographic location for a corresponding section of the at least partially controlled-access multi-lane highway, wherein at least a subset of the plurality of links includes at least one of a number of lanes and lane relationship information; generate an exit route map based on the map data and the target exit ramp, the exit route map including a plurality of exit route nodes and a plurality of exit route edges, wherein: the plurality of exit route edges include the number of lanes and the lane relationship information based on the plurality of links lane-direction edges, and lane-change edges corresponding to lane changes between lanes of the at least partially controlled-access multi-lane highway, and each of the plurality of exit route nodes defines the start and end of the lane-direction edges based on the geographic locations of the plurality of links; assigning a confidence value and a cost value to each exit route edge, the confidence value indicating the probability of existence of each exit route edge, and the cost value indicating the cost of traversing each exit route edge; and determining the exit route, the exit route corresponding to a path through the exit route map to the target exit ramp, the path having an optimized total confidence value and an optimized total cost value.

[0097] In the example automotive control unit, the machine-readable instructions may further cause the at least one processing unit to perform any one of the above-described example methods.

[0098] In one example, a vehicle includes any of the above example automotive control units.

[0099] The foregoing description is provided to illustrate the determination of an exit route on an access controlled highway. It should be understood that this description is by no means intended to limit the scope of the present disclosure to the precise embodiments discussed throughout the description. On the contrary, those skilled in the art will appreciate that the examples of the present disclosure may be combined, modified, or condensed without departing from the scope of the present disclosure as defined by the following claims.

[0100] Reference numerals list

[0101] 100: Car

[0102] 101: Other vehicles

[0103] 102: Truck

[0104] 110: Sensor

[0105] 120: Light

[0106] 200: At least partial access to controlled multi-lane highway 200

[0107] 210: Map Data

[0108] 220: Export Roadmap

[0109] L1-l10: Link

[0110] 300: Methods

[0111] 310-351: Methods and Steps

[0112] 400: Automotive control unit

[0113] 410: CPU

[0114] 420: GPU

[0115] 420c: Connect

[0116] 430: Automotive Processing Systems

[0117] 440: Memory

[0118] 450: Removable storage device

[0119] 460: Storage device

[0120] 470: Cellular interface

[0121] 480: GNSS interface

[0122] 490: Communication interface

Claims

1. A method for determining an exit route for a vehicle to a target exit ramp of a multi-lane highway with at least partial controlled access, comprising: obtaining map data regarding the at least partially controlled-access multi-lane highway, the map data being arranged in a plurality of links, each link defining a geographic location for a corresponding segment of the at least partially controlled-access multi-lane highway, wherein at least a subset of the plurality of links includes at least one of a number of lanes and lane relationship information; An exit route map is generated based on the map data and the target exit ramp, wherein the exit route map includes a plurality of exit route nodes and a plurality of exit route edges, wherein: The plurality of exit route edges include lane direction edges based on the number of lanes and the lane relationship information of the plurality of links, and lane change edges corresponding to lane changes between lanes of the at least partially controlled-access multi-lane highway, and each of the plurality of exit route nodes defining a start and an end of the lane-wise edge based on the geographic location of the plurality of links; Assigning a confidence value and a cost value to each exit route edge, wherein the confidence value indicates the existence probability of each exit route edge and the cost value indicates the cost of traversing each exit route edge; and The exit route is determined, the exit route corresponding to a path to the target exit ramp through the exit route map, the path having an optimized total confidence value and an optimized total cost value.

2. The method according to claim 1, wherein assigning a confidence value to each exit route edge comprises: A confidence value indicating a maximum existence probability is assigned to each exit route edge corresponding to a link including at least one of a lane number and lane relationship information.

3. The method according to any one of the preceding claims, wherein assigning a confidence value to each exit route edge comprises: A confidence value indicating an existence probability of the corresponding exit route edge is assigned to each exit route edge that does not correspond to a link including at least one of the number of lanes and the lane relationship information.

4. The method of any one of the preceding claims, wherein assigning a cost value to each exit route edge comprises: A lane cost is assigned to each lane-wise edge based on a drivable speed during traversal of that lane-wise edge.

5. The method of any one of the preceding claims, wherein assigning a cost value to each exit route edge comprises: A lane change cost is assigned to each lane change edge, the lane change cost being based on at least one of a probability of lane change success, a traffic density in a target lane corresponding to the lane change, and a lane change direction cost.

6. The method of any one of the preceding claims, wherein assigning a cost value to each exit route edge comprises: An emergency cost is assigned to each exit route edge, the emergency cost indicating a remaining distance to the target exit ramp.

7. The method according to any one of the preceding claims, further comprising: The exit route map is updated based on sensor data captured by the vehicle, the sensor data indicating at least one of: traffic conditions on each lane of the at least partially controlled-access multi-lane highway, one or more road surface markings, and the end of a lane of the at least partially controlled-access multi-lane highway.

8. The method of claim 7, wherein updating the exit route map based on the sensor data comprises: The probability value and the cost value of each of the plurality of exit route edges are updated.

9. The method according to any one of the preceding claims, wherein determining the exit route comprises: A shortest path through the exit roadmap having a lowest associated total cost value and a greatest associated total confidence value is determined.

10. The method according to any one of the preceding claims, wherein generating the exit route map comprises: generating, for each link including the number of lanes, the number of lane-direction edges corresponding to the number of lanes, wherein for each link that also includes lane relationship information, each lane direction edge is connected to two adjacent lane direction edges based on the lane relationship information, and Where for each link that does not include lane relationship information, each lane direction edge is assumed to be connected to two adjacent lane direction edges based on the lane relationship, For each link that does not include a lane number, generating a number of lane-direction edges based on the lane numbers of adjacent links that each include a lane number; generating an exit route node at each connection of two lane direction edges, each exit route node including a geographic location based on the link corresponding to the corresponding two lane direction edges; as well as A lane change edge is generated that indicates a lane change between at least a subset of the plurality of exit route nodes.

11. An automobile control unit, comprising: at least one processing unit; as well as a memory coupled to the at least one processing unit and configured to store machine-readable instructions, wherein the machine-readable instructions cause the at least one processing unit to: obtaining map data regarding the at least partially controlled-access multi-lane highway, the map data being arranged in a plurality of links, each link defining a geographic location for a corresponding segment of the at least partially controlled-access multi-lane highway, wherein at least a subset of the plurality of links includes at least one of a number of lanes and lane relationship information; An exit route map is generated based on the map data and the target exit ramp, wherein the exit route map includes a plurality of exit route nodes and a plurality of exit route edges, wherein: The plurality of exit route edges include lane direction edges based on the number of lanes and the lane relationship information of the plurality of links, and lane change edges corresponding to lane changes between lanes of the at least partially controlled-access multi-lane highway, and each of the plurality of exit route nodes defining a start and an end of the lane-wise edge based on the geographic location of the plurality of links; Assigning a confidence value and a cost value to each exit route edge, wherein the confidence value indicates the existence probability of each exit route edge and the cost value indicates the cost of traversing each exit route edge; and The exit route is determined, the exit route corresponding to a path to the target exit ramp through the exit route map, the path having an optimized total confidence value and an optimized total cost value.

12. The automotive control unit according to claim 11, wherein the machine-readable instructions further cause the at least one processing unit to perform the method according to any one of claims 2 to 10.

13. A vehicle comprising the vehicle control unit according to any one of claims 11 and 12.

Images