WO2023035519A1 - 行驶路径确定 - Google Patents

行驶路径确定 Download PDF

Info

Publication number
WO2023035519A1
WO2023035519A1 PCT/CN2022/070525 CN2022070525W WO2023035519A1 WO 2023035519 A1 WO2023035519 A1 WO 2023035519A1 CN 2022070525 W CN2022070525 W CN 2022070525W WO 2023035519 A1 WO2023035519 A1 WO 2023035519A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
coordinate system
self
driving
driving vehicle
Prior art date
Application number
PCT/CN2022/070525
Other languages
English (en)
French (fr)
Inventor
黄超
朱再聪
Original Assignee
上海仙途智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海仙途智能科技有限公司 filed Critical 上海仙途智能科技有限公司
Publication of WO2023035519A1 publication Critical patent/WO2023035519A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles

Definitions

  • This specification relates to the technical field of automatic driving, and in particular to a method, device, terminal and medium for determining a driving route.
  • the self-driving vehicle determines a fast, safe and feasible driving path by integrating various information such as perception, positioning, map, and vehicle, and then drives according to the determined driving path, so as to realize Automated driving of vehicles. Therefore, how to determine the driving path more accurately has become an important topic in the automatic driving technology.
  • this specification provides the following driving route determination methods, devices, terminals and media.
  • a driving route determination method comprising: constructing a coordinate system based on the position of the self-driving vehicle and the position of the center line of the road where the self-driving vehicle is located, the coordinate system
  • the longitudinal direction of the coordinate system indicates the direction of the centerline of the road
  • the transverse direction of the coordinate system indicates the direction perpendicular to the centerline of the road
  • the Obstacle information, the position of the self-driving vehicle and the boundary of the road determine the drivable area
  • the driving route determination method comprising: constructing a coordinate system based on the position of the self-driving vehicle and the position of the center line of the road where the self-driving vehicle is located, the coordinate system
  • the longitudinal direction of the coordinate system indicates the direction of the centerline of the road
  • the transverse direction of the coordinate system indicates the direction perpendicular to the centerline of the road
  • the Obstacle information, the position of the self-driving vehicle and the boundary of the road determine the drivable area
  • the method further includes: sampling obstacle information on the road in the longitudinal direction of the coordinate system.
  • the obstacles in the road are mapped to polygons; in the longitudinal direction of the coordinate system, sampling the obstacle information in the road includes: in the polygon and in the longitudinal direction of the coordinate system On the side with the same direction, the obstacle information of the obstacle corresponding to the polygon is sampled.
  • the coordinate system is constructed based on the location of the self-driving vehicle and the road information of the road where the self-driving vehicle is located, including: taking the location of the self-driving vehicle as the coordinate origin of the coordinate system, taking the center of the road The tangent direction of the line is taken as the longitudinal direction of the coordinate system, and the normal direction of the centerline of the road is taken as the transverse direction of the coordinate system.
  • the drivable Area including: based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the boundary of the road, obtain the distance between obstacles in the driving direction of the autonomous vehicle And the width of the passable gap between the obstacle and the road boundary; take the position of the self-driving vehicle as the root node, and obtain multiple passable gaps to obtain the first search tree; according to the order of the widths corresponding to the multiple nodes in the first search tree from large to small, retain a preset number of nodes that are sorted at the top; based on the reserved nodes corresponding to Width, to determine the drivable area.
  • the drivable Area including: based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the boundary of the road, obtain the distance between obstacles in the driving direction of the autonomous vehicle And the width of the passable gap between the obstacle and the road boundary; take the position of the self-driving vehicle as the root node, and traverse multiple
  • the passable gap is obtained by obtaining a plurality of target nodes included in the second search tree, and the target node is the node corresponding to the passable gap with the largest width among the passable gaps corresponding to the obstacles at the same position as the distance from the self-driving vehicle; based on The target node determines the drivable area.
  • the travel data includes at least one of the distance between the self-driving vehicle and the obstacle, the distance between the self-driving vehicle and the centerline of the road, the lateral displacement of the self-driving vehicle, the lateral velocity of the self-driving vehicle, and the lateral acceleration of the self-driving vehicle. one item.
  • the driving path of the autonomous vehicle is determined based on the drivable area and the set conditions satisfied by the driving data of the autonomous vehicle during driving, including any of the following: The path formed by the position where the distance between the driving vehicle and the obstacle is the largest is determined as the driving path; the path formed by the position where the distance between the self-driving vehicle and the centerline of the road is the smallest in the drivable area is determined as the driving path; In the driving area, the path formed by the position of the minimum lateral displacement of the autonomous vehicle is determined as the driving path; the path formed by the position of the minimum lateral velocity change of the autonomous vehicle in the drivable area is determined as the driving path; In the drivable area, the path formed by the position where the lateral acceleration of the autonomous driving vehicle is the smallest is determined as the driving path.
  • a driving route determining device including: a construction unit, configured to construct an A coordinate system, the longitudinal direction of the coordinate system indicates the direction of the centerline of the road, and the transverse direction of the coordinate system indicates a direction perpendicular to the centerline of the road; the area determination unit is used for obstacle information based on the road in the transverse direction of the coordinate system, Obstacle information sampled in the longitudinal direction of the road coordinate system, the location of the autonomous vehicle, and the boundary of the road to determine the drivable area; the path determination unit is used to determine the drivable area based on the drivable area and the driving process of the autonomous vehicle According to the set conditions satisfied by the driving data, the driving route of the self-driving vehicle is determined.
  • the device further includes: a sampling unit, configured to sample obstacle information on the road in the longitudinal direction of the coordinate system.
  • obstacles in the road are mapped to polygons; when the sampling unit is used to sample information about obstacles in the road in the longitudinal direction of the coordinate system, specifically It is used for: sampling the obstacle information of the obstacle corresponding to the polygon on the side in the same direction as the longitudinal direction of the coordinate system in the polygon.
  • the construction unit when used to construct the coordinate system based on the location of the self-driving vehicle and the road information of the road where the self-driving vehicle is located, it is specifically configured to: use the location of the self-driving vehicle As the coordinate origin of the coordinate system, the tangent direction of the centerline of the road is taken as the longitudinal direction of the coordinate system, and the normal direction of the centerline of the road is taken as the transverse direction of the coordinate system.
  • the area determining unit is used to determine the obstacle information based on the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the location where the autonomous vehicle is located.
  • the position and the boundary of the road when determining the drivable area, are specifically used for: based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information sampled in the longitudinal direction of the coordinate system, and the boundary of the road, to obtain Width of the traversable gap between obstacles in the driving direction of the autonomous vehicle and between obstacles and the road boundary; taking the position of the autonomous vehicle as the root node, according to the distance between the obstacle and the position of the autonomous vehicle In the order of distance from small to large, expand the obtained multiple passable gaps layer by layer to obtain the first search tree; according to the order of widths corresponding to multiple nodes in the first search tree from large to small, keep the pre-ordered gaps that are ranked first. Set the number of nodes; determine the drivable
  • the area determining unit is used to determine the obstacle information based on the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the location where the autonomous vehicle is located.
  • the position and the boundary of the road when determining the drivable area, are specifically used for: based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information sampled in the longitudinal direction of the coordinate system, and the boundary of the road, to obtain Width of the passable gap between obstacles in the driving direction of the autonomous vehicle and between obstacles and the road boundary; taking the position of the autonomous vehicle as the root node, according to the distance between the obstacle and the autonomous vehicle The distance of the position is in ascending order, traversing multiple passable gaps, and obtaining multiple target nodes included in the second search tree, the target nodes are in the passable gaps corresponding to the obstacles at the same distance from the position of the self-driving vehicle , the node corresponding to the traversable gap with the largest width;
  • the travel data includes at least one of the distance between the self-driving vehicle and the obstacle, the distance between the self-driving vehicle and the centerline of the road, the lateral displacement of the self-driving vehicle, the lateral velocity of the self-driving vehicle, and the lateral acceleration of the self-driving vehicle. one item.
  • the path determining unit when used to determine the driving path of the self-driving vehicle based on the set conditions satisfied by the drivable area and the driving data of the self-driving vehicle during driving, it is specifically used for the following: Any of the above: determine the path formed by the position with the largest distance between the self-driving vehicle and the obstacle in the drivable area as the driving path; determine the position with the smallest distance between the self-driving vehicle and the road centerline The path formed is determined as the driving path; the path formed by the position where the lateral displacement of the self-driving vehicle is the smallest in the drivable area is determined as the driving path; The path formed by the positions is determined as the driving path; the path formed by the position where the lateral acceleration of the self-driving vehicle is the smallest in the drivable area is determined as the driving path.
  • a terminal including a memory, a processor, and a computer program stored in the memory and operable on the processor, wherein the above-mentioned driving route determination method is implemented when the processor executes the computer program The action performed.
  • a computer-readable storage medium is provided, and a program is stored on the computer-readable storage medium, and the program is used by a processor to execute the operations performed by the above-mentioned driving route determination method.
  • a computer program product including a computer program, and when the program is executed by a processor, the operations performed by the above driving route determination method are implemented.
  • the technical solutions provided by the embodiments of this specification may include the following beneficial effects:
  • the embodiments of this specification by using the sampled obstacle information in the longitudinal direction and using the unsampled obstacle information in the horizontal direction, the reduction in While the amount of calculation needs to be processed, the accuracy of obstacle information in the lateral direction is improved, thereby improving the accuracy of the determined driving path.
  • Fig. 1 is a flowchart of a method shown in this specification according to an exemplary embodiment.
  • Fig. 2A and Fig. 2B are schematic diagrams showing a coordinate system conversion result of an obstacle according to an exemplary embodiment in this specification.
  • Fig. 3 is a schematic diagram of a road shown in this specification according to an exemplary embodiment.
  • Fig. 4 is a schematic diagram of a first search tree shown in this specification according to an exemplary embodiment.
  • Fig. 5 is a schematic diagram of a first search tree shown in this specification according to an exemplary embodiment.
  • Fig. 6 is a block diagram of a device for determining a driving route according to an exemplary embodiment in this specification.
  • Fig. 7 is a schematic structural diagram of a terminal shown in this specification according to an exemplary embodiment.
  • first, second, third, etc. may be used in this specification to describe various information, the information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be called second information, and similarly, second information may also be called first information. Depending on the context, the word “if” as used herein may be interpreted as “at” or “when” or “in response to a determination.”
  • the present application provides a method for determining a driving route.
  • the method for determining a driving route can be executed by a terminal, and the terminal can be a vehicle-mounted terminal installed on an automatic driving vehicle, or the terminal can be a terminal of the automatic driving vehicle.
  • the self-driving vehicle is equipped with various types of sensors, such as camera sensors, radar sensors, etc.
  • the self-driving vehicle collects road condition information on the road through the sensors, and then transmits the collected road condition information to the terminal, and the terminal Process based on the received road condition information to determine the driving path of the self-driving vehicle, so that the self-driving vehicle can drive based on the determined driving path, so that the self-driving vehicle can realize the driving process safely and without collision, reducing the number of self-driving vehicles The occurrence of a collision with an obstacle on the road.
  • the road condition information includes the position of the center line of the road where the self-driving vehicle is located, the boundary of the road where the self-driving vehicle is located, and obstacle information on the road where the self-driving vehicle is located, etc.
  • the road condition information includes other content, which is not limited in this application.
  • Fig. 1 is a flowchart of a method according to an exemplary embodiment of this specification, including the following steps: In step 101, based on the location of the self-driving vehicle and the road where the self-driving vehicle is The position of the centerline of the coordinate system is used to construct a coordinate system.
  • the longitudinal direction of the coordinate system indicates the direction of the centerline of the road, and the horizontal direction of the coordinate system indicates the direction perpendicular to the centerline of the road.
  • the Cartesian coordinate system (that is, the latitude and longitude coordinate system) is usually used to represent the road condition information of the road where the self-driving vehicle is located, but the Cartesian coordinate system cannot fully reflect the structure of the road, so that the Cartesian coordinate system The ability to express traffic information is poor.
  • This application adopts a coordinate system conversion method to convert the Cartesian coordinate system into a coordinate system that can more fully reflect the structure of the road, so that the converted coordinate system can represent the road condition information of the road where the autonomous driving vehicle is located.
  • the position of the self-driving vehicle is used as the coordinate origin of the coordinate system
  • the tangent direction of the centerline of the road is used as the longitudinal direction of the coordinate system
  • the normal direction of the centerline of the road is used as the coordinate
  • the Frenet coordinate system (or S-L coordinate system) that can more fully reflect the structure of the road is obtained.
  • the coordinates (x, y) are used to represent the position of the point in the coordinate system, while in the Frenet coordinate system, (s, l) is used to represent the position of the point in the coordinate system, so in the coordinate system construction After completion, the position of each point in the Frenet coordinate system is determined based on the position of each point in the Cartesian coordinate system.
  • the s value at this reference point is the s value of (xi, yi) in the Frenet coordinate system.
  • the l value of the point (xi, yi) in the Frenet coordinate system can be determined by the following formula (1):
  • ⁇ xr is a vector direction angle
  • ⁇ r is the vector direction angle
  • the smoother the center line of the road where the vehicle is located the better the construction effect of the coordinate system. Therefore, when constructing the coordinate system, it can be based on the map processed by the map editing function. The construction of the coordinate system, thereby improving the construction effect of the coordinate system.
  • the road centerline in the map used to construct the coordinate system is not smooth, the road centerline can be processed by cubic spline difference, so as to improve the smoothness of the road centerline.
  • step 102 the drivable area is determined based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, the position of the self-driving vehicle, and the boundary of the road .
  • the output will not occur when the self-driving vehicle is driving
  • the coordinate value of the area boundary of the collision area and then based on the output coordinate value, the corresponding area boundary is determined, so as to obtain the drivable area.
  • s 0 , s 1 , s 2 ,..., s n is the ordinate
  • d min 0 , d min 1 , d min 2 ,..., d min n is the left boundary of the drivable area
  • d max 0 , d max 1 , d max 2 , ..., d max n are the right boundary of the drivable area.
  • step 103 the driving route of the automatic driving vehicle is determined based on the set conditions satisfied by the driving area and the driving data of the automatic driving vehicle during driving.
  • the objective function is constructed based on the set conditions that the autonomous driving vehicle satisfies during the driving process, so as to determine a path that minimizes the value of the objective function from the drivable area as the automatic driving vehicle. The vehicle's travel path.
  • the process of constructing the coordinate system in the above step 101 can be performed in real time.
  • the determination of the drivable area and the determination of the driving route can be performed in real time subsequently based on the coordinate system constructed at the current moment.
  • a coordinate system can be constructed in real time based on the current position of the self-driving vehicle and the position of the centerline of the road where the self-driving vehicle is currently located, so that the constructed coordinate system can It conforms to the driving conditions of the self-driving vehicle at various times, so that the application can accurately represent the road condition information of the road where the self-driving vehicle is at different times.
  • the drivable area and the driving route are determined based on the coordinate system constructed at the current moment, so as to realize the real-time update of the drivable area and the real-time update of the driving route .
  • the drivable area and driving route determined at the current moment are the same as the drivable area and driving route determined at the previous moment, the drivable area and driving route are not carried out, but continue to be determined at the previous moment
  • the drivable area and driving route are used as the current drivable area and driving route, and the number of updates is reduced, thereby reducing the processing pressure of the terminal, thereby increasing the speed of determining the drivable area and driving route.
  • this application can use the discretized result to represent the obstacle information of the road in the longitudinal direction, and use continuous values to represent the road in the transverse direction.
  • Obstacle information on the road in order to reduce the amount of calculation that needs to be processed while improving the accuracy of obstacle information in the lateral direction, and then combine the position of the self-driving vehicle and the boundary of the road to determine the drivable area.
  • the determination speed of the drivable area is increased, and the accuracy of the determined drivable area is higher, thereby reducing the possibility of collisions when the self-driving vehicle is driving in the drivable area; further, based on higher accuracy
  • the driving route is determined based on the drivable area of the vehicle, thereby reducing the possibility of a collision in the determined driving route, thereby improving the safety of automatic driving.
  • the acquisition process of the obstacle information after the road is sampled in the longitudinal direction of the coordinate system includes: sampling the obstacle information in the road in the longitudinal direction of the coordinate system.
  • the calculation amount in the subsequent determination of the drivable area and the driving route can be reduced, thereby increasing the speed of determining the drivable area and the driving route.
  • the process of sampling the obstacle information in the road includes: On the side of the polygon in the same direction as the longitudinal direction of the coordinate system, the obstacle information of the obstacle corresponding to the polygon is sampled.
  • FIG. 2A and FIG. 2B it is a schematic diagram of a coordinate system conversion result of an obstacle according to an exemplary embodiment of this specification.
  • the obstacle is a rectangle ABCD
  • the obstacle is mapped to a polygon A'B'C'D'
  • sampling is performed on the side of the polygon in the same direction as the longitudinal direction that is, sampling is performed on the side A'D' and the side B'C', so as to realize the sampling of obstacle information in the longitudinal direction.
  • Figure 2B after sampling on side A'D', three points located between point A' and point D' are obtained, and after sampling on side B'C', three points located between point B' and point C' are obtained. between three points.
  • the shape of the obstacle will be deformed during the coordinate system conversion, if a polygon is used to represent the obstacle in the Cartesian coordinate system, after the coordinate system conversion, the obstacle in the Frenet coordinate system can still be expressed as a Polygon, and then by sampling the sides of the polygon to a certain extent, the sampling of obstacle information can be realized without sampling each point included in the obstacle, which reduces the amount of data that needs to be processed in the sampling process and improves the sampling efficiency. The speed improves the sampling efficiency, thereby reducing the time consumption of the sampling process.
  • the sampling interval uses a fixed step size, or the sampling interval uses a non-fixed step size, which is not limited in the present application.
  • the obstacle information of the road in the transverse direction of the coordinate system based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, the position of the self-driving vehicle, and the boundary of the road, it can be determined that When driving the area, various ways can be adopted, and the process of determining the drivable area will be described below based on two exemplary ways.
  • the driving direction of the autonomous vehicle is obtained.
  • the width of the passable gap between the obstacles and the boundary between the obstacle and the road taking the position of the self-driving vehicle as the root node, according to the order of the distance between the obstacle and the position of the self-driving vehicle, from small to large, Expanding the obtained multiple passable gaps layer by layer to obtain the first search tree; according to the order of the widths corresponding to the multiple nodes in the first search tree from large to small, retain a preset number of nodes that are ranked first; based on The width corresponding to the reserved nodes determines the drivable area.
  • Fig. 3 is a schematic diagram of a road shown in this specification according to an exemplary embodiment.
  • four obstacles 301, 302, 303, and 304 are included, wherein the obstacles
  • the width of the passable gap between 301 and the left border of the road is w1
  • the width of the passable gap between obstacle 301 and obstacle 302 is w2
  • the width of the passable gap between obstacle 302 and the right border of the road is w3
  • the width of the passable gap between obstacle 303 and the right boundary of the road is w4
  • the width of the passable gap between obstacle 303 and obstacle 304 is w5
  • the width of the gap is w6.
  • the application Based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the boundary of the road, the application obtains the above six parameters from w1 to w6.
  • the width of a traversable gap take the position of the self-driving vehicle (that is, the position of the coordinate origin in Figure 3) as the root node, and use the traversable gaps with widths of w1, w2, and w3 as children of the root node node, using the passable gaps with widths of w4, w5, and w6 as the child nodes of the above-mentioned child nodes, so as to obtain the first search tree as shown in Figure 4, see Figure 4, Figure 4, Figure 4 is an exemplary A schematic diagram of a first search tree shown in the embodiment.
  • the score of each passable path is determined based on the width of each passable gap in the passable path, or the score of each passable path is determined based on other phonemes, which is not limited in the present application.
  • the multiple passable paths obtained after pruning the first search tree shown in Figure 4 include w1 ⁇ w4, w1 ⁇ w5, w2 ⁇ w4, and w2 ⁇ w5, and the width of each passable gap in the passable path w2 ⁇ w5 is the largest, that is, the passable path w2 ⁇ w5 has the highest score, so w2 ⁇ w5
  • the area corresponding to this passable route that is, the area corresponding to the part between the drivable left boundary and the drivable right boundary in FIG. 3 , is determined as the drivable area.
  • the driving direction of the autonomous vehicle is obtained based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the boundary of the road
  • the width of the traversable gap between obstacles on the road and between obstacles and the road boundary taking the position of the self-driving vehicle as the root node, according to the distance between the obstacle and the position of the self-driving vehicle from small to large
  • multiple target nodes included in the second search tree are obtained.
  • the target node is the passable gap with the largest width among the passable gaps corresponding to the obstacles at the same distance from the self-driving vehicle.
  • the node corresponding to the gap based on the target node, the drivable area is determined.
  • FIG. 5 is a schematic diagram of a second search tree according to an exemplary embodiment in this specification. Based on the second search tree shown in Figure 5, the area corresponding to the target nodes w2 and w5 can be determined, that is, the area corresponding to the part between the drivable left boundary and the drivable right boundary in Figure 3, that is, the drivable driving area.
  • the driving data involved in determining the driving path of the self-driving vehicle includes the distance between the self-driving vehicle and obstacles, the distance between the self-driving vehicle and the centerline of the road, the lateral displacement of the self-driving vehicle, the At least one of the lateral velocity of the vehicle and the lateral acceleration of the self-driving vehicle.
  • the driving data further includes other types of data, which is not limited in the present application.
  • the objective functions involved in determining the driving path of the self-driving vehicle include the function corresponding to the distance between the self-driving vehicle and obstacles, the function corresponding to the distance between the self-driving vehicle and the road centerline, and the lateral direction of the self-driving vehicle. At least one of the function corresponding to the displacement, the function corresponding to the lateral velocity of the autonomous vehicle, and the function corresponding to the lateral acceleration of the autonomous vehicle, or other functions corresponding to the driving data type.
  • the process of determining the driving route based on different types of data will be described below.
  • the driving route As the distance between the automatic driving vehicle and the obstacle as an example, the path formed by the position where the distance between the automatic driving vehicle and the obstacle is the largest in the drivable area is determined as the driving route.
  • the driving path formed by the position where the distance between the self-driving vehicle and the road centerline is the smallest in the drivable area is determined as the driving path.
  • the path formed by the position where the lateral displacement of the self-driving vehicle is the smallest in the drivable area is determined as the driving path.
  • the path formed by the position where the lateral speed of the autonomous vehicle changes the least in the drivable area is determined as the driving route.
  • the path formed by the position where the lateral acceleration of the automatic driving vehicle is the smallest in the drivable area is determined as the driving route.
  • the determined driving route can be more in line with the driving requirements of the vehicle, thereby improving the driving effect of the automatic driving vehicle.
  • the driving route may also be determined based on other types of data.
  • various types of data can also be integrated to determine the driving path. For example, in the drivable area, determine a path formed by a position whose distance from obstacles is greater than the distance threshold and where the lateral displacement of the self-driving vehicle is the smallest. paths, as travel paths, etc.
  • the distance threshold value is any positive value, and the application does not limit the value of the distance threshold value.
  • this specification also provides embodiments of a device and a terminal to which it is applied.
  • FIG. 6 is a block diagram of a device for determining a driving route according to an exemplary embodiment of the present specification.
  • the device for determining a driving route includes: a construction unit 601 for The position of the centerline of the road where the coordinate system is constructed, the longitudinal direction of the coordinate system indicates the direction of the centerline of the road, and the horizontal direction of the coordinate system indicates a direction perpendicular to the centerline of the road; the area determination unit 602 is used to The obstacle information in the horizontal direction of the coordinate system, the obstacle information sampled on the longitudinal direction of the coordinate system, the position of the self-driving vehicle and the boundary of the road, determine the drivable area; the path determination unit 603 is used to Based on the drivable area and the setting conditions satisfied by the driving data of the self-driving vehicle during driving, the driving path of the self-driving vehicle is determined.
  • the device for determining the driving route further includes: a sampling unit, configured to sample information about obstacles in the road in the longitudinal direction of the coordinate system.
  • obstacles in the road are mapped to polygons; when the sampling unit is used to sample information about obstacles in the road in the longitudinal direction of the coordinate system, specifically Used for:
  • the obstacle information of the obstacle corresponding to the polygon is sampled.
  • the construction unit 601 when used to construct the coordinate system based on the location of the self-driving vehicle and the road information of the road where the self-driving vehicle is located, it is specifically configured to: take the location of the self-driving vehicle as The coordinate origin of the coordinate system takes the tangent direction of the centerline of the road as the longitudinal direction of the coordinate system, and takes the normal direction of the centerline of the road as the transverse direction of the coordinate system.
  • the area determining unit 602 is used to determine the obstacle information of the road in the horizontal direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the position of the self-driving vehicle.
  • the boundary of the road when determining the drivable area, it is specifically used to: based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information sampled in the longitudinal direction of the coordinate system and the boundary of the road, to obtain automatic The width of the passable gap between obstacles in the driving direction of the driving vehicle and between obstacles and the road boundary; the position of the self-driving vehicle is used as the root node, according to the distance between the obstacle and the position of the self-driving vehicle From small to large, expand the obtained multiple passable gaps layer by layer to obtain the first search tree; according to the order of the widths corresponding to multiple nodes in the first search tree from large to small, keep the presets that are sorted first The number of nodes; based on the width corresponding
  • the area determining unit 602 is used to determine the obstacle information of the road in the horizontal direction of the coordinate system, the obstacle information of the road sampled in the longitudinal direction of the coordinate system, and the position of the self-driving vehicle.
  • the boundary of the road when determining the drivable area, it is specifically used to: based on the obstacle information of the road in the transverse direction of the coordinate system, the obstacle information sampled in the longitudinal direction of the coordinate system and the boundary of the road, to obtain automatic The width of the passable gap between obstacles in the driving direction of the driving vehicle and between obstacles and the road boundary; taking the position of the self-driving vehicle as the root node, according to the position of the obstacle and the self-driving vehicle The order of the distance from small to large is to traverse multiple passable gaps to obtain multiple target nodes included in the second search tree.
  • the target nodes are in the passable gaps corresponding to the obstacles at the same distance from the position of the self-driving vehicle.
  • the travel data includes at least one of the distance between the self-driving vehicle and the obstacle, the distance between the self-driving vehicle and the centerline of the road, the lateral displacement of the self-driving vehicle, the lateral velocity of the self-driving vehicle, and the lateral acceleration of the self-driving vehicle. one item.
  • the path determination unit 603 when used to determine the driving path of the autonomous vehicle based on the drivable area and the set conditions satisfied by the driving data of the autonomous vehicle during driving, it is specifically used for the following Either: determine the path formed by the position with the largest distance between the self-driving vehicle and the obstacle in the drivable area; The path formed is determined as the driving path; the path formed by the position where the lateral displacement of the autonomous vehicle is the smallest in the drivable area is determined as the driving path; the position where the lateral velocity change of the autonomous vehicle is the smallest in the drivable area The formed path is determined as the driving path; the path formed by the position where the lateral acceleration of the self-driving vehicle is the smallest in the drivable area is determined as the driving path.
  • the device embodiment since it basically corresponds to the method embodiment, for related parts, please refer to the part description of the method embodiment.
  • the device embodiments described above are only illustrative, and the modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in One place, or it can be distributed to multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution in this specification. It can be understood and implemented by those skilled in the art without creative effort.
  • FIG. 7 is a schematic structural diagram of a terminal shown in this specification according to an exemplary embodiment.
  • the terminal includes a processor 710, a memory 720, and a network interface 730.
  • the memory 720 is used to store computer instructions that can be run on the processor 710.
  • the processor 710 is used to implement the present application when executing the computer instructions.
  • the network interface 730 is used to implement input and output functions.
  • the terminal may further include other hardware, which is not limited in this application.
  • the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium can be in various forms.
  • the computer-readable storage medium can be: RAM (Radom Access Memory, Random Access Memory) access memory), volatile memory, non-volatile memory, flash memory, storage drives (such as hard disk drives), solid-state drives, storage disks of any type (such as compact discs, DVDs, etc.), or similar storage media, or combinations thereof .
  • the computer-readable medium may also be paper or other suitable medium capable of printing programs.
  • a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the method for determining the driving route provided in any embodiment of the present application is implemented.
  • the present application also provides a computer program product, including a computer program.
  • the computer program is executed by a processor, the driving route determination method provided in any embodiment of the present application is implemented.
  • one or more embodiments of this specification may be provided as a method, device, terminal, computer-readable storage medium, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may employ a computer program embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein. The form of the product.
  • each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments.
  • the description is relatively simple, and for relevant parts, refer to part of the description of the method embodiment.
  • Embodiments of the subject matter and functional operations described in this specification can be implemented in digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or in A combination of one or more of .
  • Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or more of computer program instructions encoded on a tangible, non-transitory program carrier for execution by or to control the operation of data processing apparatus. Multiple modules.
  • the program instructions may be encoded on an artificially generated propagated signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode and transmit information to a suitable receiver device for transmission by the data
  • the processing means executes.
  • a computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
  • the processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output.
  • the processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • Computers suitable for the execution of a computer program include, for example, general and/or special purpose microprocessors, or any other type of central processing unit.
  • a central processing unit will receive instructions and data from a read only memory and/or a random access memory.
  • the essential components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data.
  • a computer will also include, or be operatively coupled to, one or more mass storage devices for storing data, such as magnetic or magneto-optical disks, or optical disks, to receive data therefrom or to It transmits data, or both.
  • mass storage devices for storing data, such as magnetic or magneto-optical disks, or optical disks, to receive data therefrom or to It transmits data, or both.
  • a computer is not required to have such a device.
  • a computer may be embedded in another device such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a device such as a Universal Serial Bus (USB) ) portable storage devices like flash drives, to name a few.
  • PDA personal digital assistant
  • GPS Global Positioning System
  • USB Universal Serial Bus
  • Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices), magnetic disks (such as internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks.
  • semiconductor memory devices such as EPROM, EEPROM, and flash memory devices
  • magnetic disks such as internal hard disks or removable disks
  • magneto-optical disks and CD ROM and DVD-ROM disks.
  • the processor and memory can be supplemented by, or incorporated in, special purpose logic circuitry.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种行驶路径确定方法、装置、终端及介质，行驶路径确定方法包括：基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的中心线的位置，构建坐标系；基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域；基于可行驶区域和自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定自动驾驶车辆的行驶路径。行驶路径确定方法通过在纵向方向上使用采样后的障碍物信息，而在横向方向上使用未经采样的障碍物信息，在减少需要处理的计算量的同时，提高横向方向上障碍物信息的准确性，从而提高确定出的行驶路径的准确性。

Description

行驶路径确定 技术领域
本说明书涉及自动驾驶技术领域，尤其涉及用于确定行驶路径的方法、装置、终端及介质。
背景技术
自动驾驶技术作为一种能够提升道路交通智能化水平、推动交通运输行业转型升级的重要途径，逐渐成为一个重要的研究方向。
在自动驾驶技术中，自动驾驶车辆通过整合感知、定位、地图、车辆等多方面的信息，以确定出一条快速、安全、可行的行驶路径，进而依据所确定出的行驶路径进行行驶，从而实现车辆的自动驾驶。因此，如何更为准确地确定出行驶路径，成为自动驾驶技术中的一个重要课题。
发明内容
为更加准确地为自动驾驶车辆规划行驶路径，本说明书提供了如下的行驶路径确定方法、装置、终端及介质。
根据本说明书实施例的第一方面，提供一种行驶路径确定方法，所述方法包括：基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的中心线的位置，构建坐标系，坐标系的纵向方向指示道路的中心线方向，坐标系的横向方向指示与道路的中心线垂直的方向；基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域；基于可行驶区域和自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定自动驾驶车辆的行驶路径。
在一些实施例中，所述方法还包括：在坐标系的纵向方向上，对道路中的障碍物信息进行采样。
在一些实施例中，在构建坐标系时，道路中的障碍物被映射为多边形；在坐标系的纵向方向上，对道路中的障碍物信息进行采样，包括：在多边形中与坐标系的纵向方向同向的边上，对多边形对应的障碍物的障碍物信息进行采样。
在一些实施例中，基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的道路信息，构建坐标系，包括：以自动驾驶车辆所处的位置作为坐标系的坐标原点，以道路的中心线的切线方向作为坐标系的纵向方向，以道路的中心线的法线方向作为坐标系的横向方向。
在一些实施例中，基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的 纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域，包括：基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆的位置的距离从小到大的顺序，逐层展开获取到的多个可通行间隙，得到第一搜索树；按照第一搜索树中多个节点对应的宽度从大到小的顺序，保留排序靠前的预设数量的节点；基于所保留的节点对应的宽度，确定可行驶区域。
在一些实施例中，基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域，包括：基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆所处的位置的距离从小到大的顺序，遍历多个可通行间隙，得到第二搜索树所包括的多个目标节点，目标节点为距离自动驾驶车辆所处的位置相同的障碍物对应的可通行间隙中，宽度最大的可通行间隙对应的节点；基于目标节点，确定可行驶区域。
在一些实施例中，行驶数据包括自动驾驶车辆与障碍物的距离、自动驾驶车辆与道路中心线的距离、自动驾驶车辆的横向位移、自动驾驶车辆的横向速度以及自动驾驶车辆的横向加速度中至少一项。
在一些实施例中，基于可行驶区域和自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定自动驾驶车辆的行驶路径，包括下述任一项：将可行驶区域中，自动驾驶车辆与障碍物的距离最大的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆与道路中心线的距离最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向位移最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向速度变化最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向加速度最小的位置所构成的路径，确定为行驶路径。
根据本说明书实施例的第二方面，提供一种行驶路径确定装置，所述装置包括：构建单元，用于基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的中心线的位置，构建坐标系，坐标系的纵向方向指示道路的中心线方向，坐标系的横向方向指示与道路的中心线垂直的方向；区域确定单元，用于基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域；路径确定单元，用于基于可行驶区域和自动驾驶车辆在行 驶过程中的行驶数据所满足的设定条件，确定自动驾驶车辆的行驶路径。
在一些实施例中，所述装置还包括：采样单元，用于在坐标系的纵向方向上，对道路中的障碍物信息进行采样。
在一些实施例中，在构建坐标系时，道路中的障碍物被映射为多边形；所述采样单元，在用于在坐标系的纵向方向上，对道路中的障碍物信息进行采样时，具体用于：在多边形中与坐标系的纵向方向同向的边上，对多边形对应的障碍物的障碍物信息进行采样。
在一些实施例中，所述构建单元，在用于基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的道路信息，构建坐标系时，具体用于：以自动驾驶车辆所处的位置作为坐标系的坐标原点，以道路的中心线的切线方向作为坐标系的纵向方向，以道路的中心线的法线方向作为坐标系的横向方向。
在一些实施例中，所述区域确定单元，在用于基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域时，具体用于：基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆的位置的距离从小到大的顺序，逐层展开获取到的多个可通行间隙，得到第一搜索树；按照第一搜索树中多个节点对应的宽度从大到小的顺序，保留排序靠前的预设数量的节点；基于所保留的节点对应的宽度，确定可行驶区域。
在一些实施例中，所述区域确定单元，在用于基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域时，具体用于：基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆所处的位置的距离从小到大的顺序，遍历多个可通行间隙，得到第二搜索树所包括的多个目标节点，目标节点为距离自动驾驶车辆所处的位置相同的障碍物对应的可通行间隙中，宽度最大的可通行间隙对应的节点；基于目标节点，确定可行驶区域。
在一些实施例中，行驶数据包括自动驾驶车辆与障碍物的距离、自动驾驶车辆与道路中心线的距离、自动驾驶车辆的横向位移、自动驾驶车辆的横向速度以及自动驾驶车辆的横向加速度中至少一项。
在一些实施例中，所述路径确定单元，在用于基于可行驶区域和自动驾驶车辆在行 驶过程中的行驶数据所满足的设定条件，确定自动驾驶车辆的行驶路径时，具体用于下述任一项：将可行驶区域中，自动驾驶车辆与障碍物的距离最大的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆与道路中心线的距离最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向位移最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向速度变化最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向加速度最小的位置所构成的路径，确定为行驶路径。
根据本说明书实施例的第三方面，提供一种终端，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，处理器执行计算机程序时实现上述行驶路径确定方法所执行的操作。
根据本说明书实施例的第四方面，提供一种计算机可读存储介质，计算机可读存储介质上存储有程序，程序被处理器执行上述行驶路径确定方法所执行的操作。
根据本说明书实施例的第五方面，提供一种计算机程序产品，包括计算机程序，所述程序被处理器执行时实现上述行驶路径确定方法所执行的操作。
本说明书的实施例提供的技术方案可以包括以下有益效果：本说明书实施例中，通过在纵向方向上使用采样后的障碍物信息，而在横向方向上使用未经采样的障碍物信息，在减少需要处理的计算量的同时，提高横向方向上障碍物信息的准确性，从而提高确定出的行驶路径的准确性。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本说明书。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本说明书的实施例，并与说明书一起用于解释本说明书的原理。
图1是本说明书根据一示例性实施例示出的一种方法的流程图。
图2A和图2B是本说明书根据一示例性实施例示出的一种障碍物的坐标系转换结果示意图。
图3是本说明书根据一示例性实施例示出的一种道路的示意图。
图4是本说明书根据一示例性实施例示出的一种第一搜索树的示意图。
图5是本说明书根据一示例性实施例示出的一种第一搜索树的示意图。
图6是本说明书根据一示例性实施例示出的一种行驶路径确定装置的框图。
图7是本说明书根据一示例性实施例示出的一种终端的结构示意图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本说明书相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本说明书的一些方面相一致的装置和方法的例子。
在本说明书使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本说明书。在本说明书和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本说明书可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本说明书范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
本申请提供了一种行驶路径的确定方法，所述行驶路径的确定方法可以由终端执行，所述终端可以是安装在自动驾驶车辆上的车载终端，或者，所述终端可以是自动驾驶车辆的乘客随身携带的移动终端，例如，手机、平板电脑、游戏机、便携式计算机等等，本申请对终端的具体类型不加以限定。
在本申请中，自动驾驶车辆上安装有多种类型的传感器，如摄像头传感器、雷达传感器等，自动驾驶车辆通过传感器采集道路中的路况信息，进而将采集到的路况信息传输给终端，由终端基于接收到的路况信息进行处理，以确定自动驾驶车辆的行驶路径，以便自动驾驶车辆基于所确定出的行驶路径进行行驶，使得自动驾驶车辆能够安全、无碰撞地实现行驶过程，减少自动驾驶车辆与道路上的障碍物发生碰撞的情况的出现。
其中，路况信息包括自动驾驶车辆所处道路的中心线的位置、自动驾驶车辆所处道路的边界以及自动驾驶车辆所处道路上的障碍物信息，等等，在更多可能的实现方式中，路况信息包括其他内容，本申请对此不加以限定。
上述仅为关于本申请的应用场景的相关介绍，接下来结合本说明书实施例，对本申请所提供的行驶路径确定方法进行详细说明。
如图1所示，图1是本说明书根据一示例性实施例示出的一种方法的流程图，包括以下步骤：在步骤101中，基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的中心线的位置，构建坐标系，坐标系的纵向方向指示道路的中心线方向，坐标系的横向方向指示与道路的中心线垂直的方向。
在自动驾驶领域，通常采用笛卡尔坐标系(也即是经纬度坐标系)，来表示自动驾驶车辆所处道路的路况信息，但笛卡尔坐标系无法充分体现道路的结构，从而使得笛卡尔坐标系对路况信息的表示能力较差。本申请采用坐标系转换的方式，将笛卡尔坐标系转换为能够更加充分地体现道路的结构的坐标系，从而通过所转换得到的坐标系，来表示自动驾驶车辆所处道路的路况信息。
在一种可能的实现方式中，以自动驾驶车辆所处的位置作为坐标系的坐标原点，以道路的中心线的切线方向作为坐标系的纵向方向，以道路的中心线的法线方向作为坐标系的横向方向，从而完成坐标系的构建，得到能够更加充分地体现道路的结构的Frenet坐标系(或称S-L坐标系)。
在笛卡尔坐标系中，采用坐标(x,y)表示坐标系中的点的位置，而在Frenet坐标系中，采用(s,l)表示坐标系中的点的位置，因而在坐标系构建完成后，基于笛卡尔坐标系中各个点的位置，确定Frenet坐标系中各个点的位置。
在一种可能的实现方式中，对于笛卡尔坐标系中的待进行坐标转换的点(xi,yi)，在确定道路中心线(也即是参考线)上距离(xi,yi)最近的参考点，该参考点处的s值即为(xi,yi)在Frenet坐标系下的s值。
而点(xi,yi)在Frenet坐标系下的l值，可以通过如下公式(1)确定：
Figure PCTCN2022070525-appb-000001
其中，
Figure PCTCN2022070525-appb-000002
为参考点在笛卡尔坐标系下的向量，
Figure PCTCN2022070525-appb-000003
为点(xi,yi)在笛卡尔坐标系下的向量，
Figure PCTCN2022070525-appb-000004
为
Figure PCTCN2022070525-appb-000005
的单位向量，θ x-r为向量
Figure PCTCN2022070525-appb-000006
的方向角度，
Figure PCTCN2022070525-appb-000007
为单位向量
Figure PCTCN2022070525-appb-000008
的方向角度，θ r为向量
Figure PCTCN2022070525-appb-000009
的方向角度。
可选地，在构建坐标系时，车辆所处道路的中心线越平滑，则坐标系的构建效果越好，因而，在构建坐标系时，可以基于通过地图编辑功能处理过的地图，来进行坐标系的构建，从而提高坐标系的构建效果。
在更多可能的实现方式中，若用于构建坐标系的地图中道路中心线不平滑，则可以通过三次样条差值，来对道路中心线进行处理，从而提高道路中心线的平滑程度。
在步骤102中，基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵 向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域。
其中，可行驶区域中不存在障碍物，自动驾驶车辆在该可行驶区域中的各个位置处行驶时，均不会发生碰撞。
基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，输出自动驾驶车辆行驶时不会发生碰撞的区域的区域边界的坐标值，进而基于所输出的坐标值，确定出对应的区域边界，从而得到可行驶区域。
其中，可行驶区域的边界可以采用如式(2)所示的形式表示：
Figure PCTCN2022070525-appb-000010
其中，s 0，s 1，s 2，...，s n为纵坐标，d min 0，d min 1， d min 2，...， d min n为可行驶区域的左边界，d max 0，d max 1，d max 2，...，d max n为可行驶区域的右边界。
由于道路在横向方向上的距离较小，此时再进行采样，会导致道路横向方向上的障碍物信息严重丢失，通过仅在纵向方向上的障碍物信息使用采样后的结果，而横向方向上的障碍物信息使用未经采样的结果，从而在能够保证降低需要处理的数据量的基础上，保证横向方向上障碍物信息的准确性，而提高确定出的可行驶区域的准确性。
在步骤103中，基于所述可行驶区域和所述自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定所述自动驾驶车辆的行驶路径。
在一种可能的实现方式中，基于自动驾驶车辆在行驶过程中所满足的设定条件，构建目标函数，从而从可行驶区域中，确定出一条使目标函数取值最小的路径，作为自动驾驶车辆的行驶路径。
上述步骤101中构建坐标系的过程可以实时进行，相应地，后续可以基于当前时刻所构建的坐标系，实时进行可行驶区域的确定以及行驶路径的确定。
也即是，在自动驾驶车辆的行驶过程中，可以基于自动驾驶车辆当前所处的位置以及自动驾驶车辆当前所处道路的中心线的位置，实时构建坐标系，从而使得所构建的坐标系能够符合自动驾驶车辆在各个时刻的行驶情况，从而使得本申请能够准确地表示自动驾驶车辆在不同时刻所处道路的路况信息。相应地，在自动驾驶车辆行驶到任一位置时，基于当前时刻所构建的坐标系，来进行可行驶区域的确定以及行驶路径的确定，以 实现可行驶区域的实时更新以及行驶路径的实时更新。
可选地，在当前时刻确定出的可行驶区域和行驶路径，与上一时刻所确定出的可行驶区域和行驶路径相同时，不进行可行驶区域和行驶路径，而继续以上一时刻所确定出的可行驶区域和行驶路径，作为当前时刻的可行驶区域和行驶路径，减少更新次数，从而减少终端的处理压力，进而提高可行驶区域和行驶路径的确定速度。
在本申请中，通过不对道路在横向方向上的障碍物信息进行采样，从而使得本申请能够采用离散化的结果来表示道路在纵向方向上的障碍物信息，采用连续值来表示道路在横向方向上的障碍物信息，以在减少需要处理的计算量的同时，提高横向方向上障碍物信息的准确性，进而结合自动驾驶车辆所处的位置以及道路的边界，来进行可行驶区域的确定，从而提高可行驶区域的确定速度，并使得所确定出的可行驶区域的准确性更高，进而降低自动驾驶车辆在可行驶区域中行驶时发生碰撞的可能性；进一步地，基于准确性更高的可行驶区域来进行行驶路径的确定，从而能够降低所确定出的行驶路径发生碰撞的可能性，进而提高自动驾驶的安全性。
在介绍了本申请的基本实现过程之后，下面具体介绍本申请的各种非限制性实施方式。
在一些实施例中，道路在坐标系的纵向方向上采样后的障碍物信息的获取过程包括：在坐标系的纵向方向上，对道路中的障碍物信息进行采样。
通过在道路中纵向方向上的障碍物信息进行采样，能够减少后续进行可行驶区域和行驶路径的确定过程中的计算量，从而提高可行驶区域和行驶路径的确定速度。
在一种可能的实现方式中，在构建坐标系时，道路中的障碍物被映射为多边形，相应地，在坐标系的纵向方向上，对道路中的障碍物信息进行采样的过程包括：在多边形中与坐标系的纵向方向同向的边上，对多边形对应的障碍物的障碍物信息进行采样。
参见图2A和图2B，是本说明书根据一示例性实施例示出的一种障碍物的坐标系转换结果示意图，在如图2A所示的笛卡尔坐标系中，障碍物为一个矩形ABCD，而在将笛卡尔坐标系转换为Frenet坐标系后，障碍物被映射为一个多边形A’B’C’D’，则在对纵向方向上的障碍物信息进行采样时，可以按照预设的采样间隔，在多边形与纵向方向同向的边上进行采样，也即是，在边A’D’和边B’C’上进行采样，从而实现对纵向方向上的障碍物信息的采样。如图2B所示，在边A’D’上采样后得到位于点A’和点D’之间的三个点，在边B’C’上采样后得到位于点B’和点C’之间的三个点。
虽然在进行坐标系转化时，障碍物的形状会发生变形，但如果在笛卡尔坐标系中使用多边形来表示障碍物，在经过坐标系转换后，Frenet坐标系中的障碍物仍然可以表示为一个多边形，进而通过对多边形的边进行一定程度的采样，即可实现对障碍物信息的采样，无需对障碍物内部所包括的各个点进行采样，减少了采样过程需要处理的数据量， 提高了采样速度，提高了采样效率，从而减少了采样过程的耗时。
可选地，在采样过程中，采样间隔使用固定步长，或者，采样间隔使用不固定步长，本申请对此不加以限定。
在一些实施例中，在基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域时，可以采用多种方式，下面基于两种示例性的方式，对可行驶区域的确定过程进行说明。
在一种可能的实现方式中，基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆的位置的距离从小到大的顺序，逐层展开获取到的多个可通行间隙，得到第一搜索树；按照述第一搜索树中多个节点对应的宽度从大到小的顺序，保留排序靠前的预设数量的节点；基于所保留的节点对应的宽度，确定可行驶区域。
参见图3，图3是本说明书根据一示例性实施例示出的一种道路的示意图，在如图3所示的道路中，包括301、302、303、304四个障碍物，其中，障碍物301与道路左边界之间的可通行间隙的宽度为w1，障碍物301与障碍物302之间的可通行间隙的宽度为w2，障碍物302与道路右边界之间的可通行间隙的宽度为w3，障碍物303与道路右边界之间的可通行间隙的宽度为w4，障碍物303与障碍物304之间的可通行间隙的宽度为w5，障碍物304与道路左边界之间的可通行间隙的宽度为w6，本申请在基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取到上述w1至w6这六个可通行间隙的宽度后，以自动驾驶车辆所处的位置(也即是图3中坐标原点的位置)作为根节点，将宽度为w1、w2、w3的可通行间隙，作为根节点的子节点，将宽度为w4、w5、w6的可通行间隙，作为上述各个子节点的子节点，从而得到如图4所示的第一搜索树，参见图4，图4是本说明书根据一示例性实施例示出的一种第一搜索树的示意图。
以预设数量为2，w1＝30，w2＝60，w3＝25，w4＝20，w5＝80，w6＝15为例，从作为根节点的子节点的w1、w2、w3中，删除宽度最小的w3及对应的子树，保留宽度较大的w1、w2以及对应的子树，进而在w1、w2的子节点中，分别删除宽度最小的w6，保留宽度较大的w4和w5，从而得到剪枝后的第一搜索树，进而基于剪枝后的第一搜索树，确定多条可选的通行路径，进而基于各条通行路径对应的分值，进而基于各条通行路径的分值，确定可行驶区域。其中，分值表示车辆在通行路径上行驶不会发生碰撞的可能性。
可选地，各条可通行路径的分值基于可通行路径中各个可通行间隙的宽度确定，或者，各条可通行路径的分值基于其他音素确定，本申请对此不加以限定。以每条可通行路径的分值基于可通行路径中各个可通行间隙的宽度确定为例，图4所示的第一搜索树剪枝后得到的多条可通行路径包括w1→w4、w1→w5、w2→w4以及w2→w5，而w2→w5这条可通行路径中各个可通行间隙的宽度最大，也即是，w2→w5这条可通行路径的分值最高，从而将w2→w5这条可通行路径对应的区域，也即是，图3中可行驶左边界与可行驶右边界之间的部分对应的区域，确定为可行驶区域。
在另一种可能的实现方式中，基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆所处的位置的距离从小到大的顺序，遍历多个可通行间隙，得到第二搜索树所包括的多个目标节点，目标节点为距离自动驾驶车辆所处的位置相同的障碍物对应的可通行间隙中，宽度最大的可通行间隙对应的节点；基于目标节点，确定可行驶区域。
仍以如图3所示的道路以及道路中各个可通行间隙的取值为例，本申请在基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取到图3中w1至w6这六个可通行间隙的宽度后，将自动驾驶车辆所处的位置作为根节点，并遍历能够作为根节点的子节点的w1、w2、w3，从中确定出对应的可通行间隙的宽度最大的w2，进而遍历能够作为w2的子节点的w4、w5、w6，从中确定出对应的可通行间隙的宽度最大的w5，将w2和w5作为目标节点，从而得到第二搜索树，参见5，图5是本说明书根据一示例性实施例示出的一种第二搜索树的示意图。基于如图5所示的第二搜索树，即可确定目标节点w2和w5对应的区域，也即是图3中可行驶左边界与可行驶右边界之间的部分对应的区域，即为可行驶区域。
需要说明的是，上述仅为确定可行驶区域的两种示例性方式，在另一些实施例中，还可以采用其他的方式来进行可行驶区域的确定，本申请对此不加以限定。
在一些实施例中，在确定自动驾驶车辆的行驶路径时所涉及到的行驶数据包括自动驾驶车辆与障碍物的距离、自动驾驶车辆与道路中心线的距离、自动驾驶车辆的横向位移、自动驾驶车辆的横向速度以及自动驾驶车辆的横向加速度中至少一项，可选地，行驶数据还包括其他类型的数据，本申请对此不加以限定。
相应地，在确定自动驾驶车辆的行驶路径时所涉及到的目标函数，包括自动驾驶车辆与障碍物的距离对应的函数、自动驾驶车辆与道路中心线的距离对应的函数、自动驾驶车辆的横向位移对应的函数、自动驾驶车辆的横向速度对应的函数以及自动驾驶车辆的横向加速度对应的函数中至少一项，或者，其他与行驶数据类型对应的函数。
以行驶数据包括上述几种类型的数据为例，下面分别对基于不同类型的数据进行行驶路径的确定的过程进行说明。
以行驶数据为自动驾驶车辆与障碍物的距离为例，将可行驶区域中，自动驾驶车辆与障碍物的距离最大的位置所构成的路径，确定为行驶路径。
以行驶数据为自动驾驶车辆与道路中心线的距离为例，将可行驶区域中，自动驾驶车辆与道路中心线的距离最小的位置所构成的路径，确定为行驶路径。
以行驶数据为自动驾驶车辆的横向位移为例，将可行驶区域中，自动驾驶车辆的横向位移最小的位置所构成的路径，确定为行驶路径。
以行驶数据为自动驾驶车辆的横向速度为例，将可行驶区域中，自动驾驶车辆的横向速度变化最小的位置所构成的路径，确定为行驶路径。
以行驶数据为自动驾驶车辆的横向加速度为例，将可行驶区域中，自动驾驶车辆的横向加速度最小的位置所构成的路径，确定为行驶路径。
通过基于行驶数据来进行行驶路径的确定，能够使得所确定出的行驶路径更加符合车辆的行驶要求，从而提高自动驾驶车辆的行驶效果。
上述仅为几种确定行驶路径时涉及到的示例性数据，在另一些实施例中，还可以基于其他类型的数据，来进行行驶路径的确定。
此外，还可以综合多种类型的数据，来进行行驶路径的确定，例如，在可行驶区域中，确定一条与障碍物的距离大于距离阈值、且自动驾驶车辆的横向位移最小的位置所构成的路径，作为行驶路径，等等。其中，该距离阈值为任意正数值，本申请对距离阈值的取值不加以限定，通过综合多种类型的数据，从而使得所确定出的行驶路径，在能够保证驾驶安全性的基础上，更加符合车辆的运动学规律，从而提高确定出来的行驶路径的准确性和可行性。
与前述方法的实施例相对应，本说明书还提供了装置及其所应用的终端的实施例。
参见图6，图6是本说明书根据一示例性实施例示出的一种行驶路径确定装置的框图，行驶路径确定装置包括：构建单元601，用于基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的中心线的位置，构建坐标系，坐标系的纵向方向指示道路的中心线方向，坐标系的横向方向指示与道路的中心线垂直的方向；区域确定单元602，用于基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域；路径确定单元603，用于基于可行驶区域和自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定自动驾驶车辆的行驶路径。
在一些实施例中，行驶路径确定装置还包括：采样单元，用于在坐标系的纵向方向上，对道路中的障碍物信息进行采样。
在一些实施例中，在构建坐标系时，道路中的障碍物被映射为多边形；所述采样单元，在用于在坐标系的纵向方向上，对道路中的障碍物信息进行采样时，具体用于：
在多边形中与坐标系的纵向方向同向的边上，对多边形对应的障碍物的障碍物信息进行采样。
在一些实施例中，构建单元601，在用于基于自动驾驶车辆所处的位置以及自动驾驶车辆所处道路的道路信息，构建坐标系时，具体用于：以自动驾驶车辆所处的位置作为坐标系的坐标原点，以道路的中心线的切线方向作为坐标系的纵向方向，以道路的中心线的法线方向作为坐标系的横向方向。
在一些实施例中，区域确定单元602，在用于基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域时，具体用于：基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆的位置的距离从小到大的顺序，逐层展开获取到的多个可通行间隙，得到第一搜索树；按照第一搜索树中多个节点对应的宽度从大到小的顺序，保留排序靠前的预设数量的节点；基于所保留的节点对应的宽度，确定可行驶区域。
在一些实施例中，区域确定单元602，在用于基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息、自动驾驶车辆所处的位置以及道路的边界，确定可行驶区域时，具体用于：基于道路在坐标系的横向方向上的障碍物信息、道路在坐标系的纵向方向上采样后的障碍物信息和道路的边界，获取自动驾驶车辆的行驶方向上的障碍物之间以及障碍物与道路的边界之间的可通行间隙的宽度；将自动驾驶车辆所处的位置作为根节点，按照障碍物与自动驾驶车辆所处的位置的距离从小到大的顺序，遍历多个可通行间隙，得到第二搜索树所包括的多个目标节点，目标节点为距离自动驾驶车辆所处的位置相同的障碍物对应的可通行间隙中，宽度最大的可通行间隙对应的节点；基于目标节点，确定可行驶区域。
在一些实施例中，行驶数据包括自动驾驶车辆与障碍物的距离、自动驾驶车辆与道路中心线的距离、自动驾驶车辆的横向位移、自动驾驶车辆的横向速度以及自动驾驶车辆的横向加速度中至少一项。
在一些实施例中，路径确定单元603，在用于基于可行驶区域和自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定自动驾驶车辆的行驶路径时，具体用于下述任一项：将可行驶区域中，自动驾驶车辆与障碍物的距离最大的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆与道路中心线的距离最小的位置所构 成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向位移最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向速度变化最小的位置所构成的路径，确定为行驶路径；将可行驶区域中，自动驾驶车辆的横向加速度最小的位置所构成的路径，确定为行驶路径。
上述装置中各个单元的功能和作用的实现过程具体详见上述方法中对应步骤的实现过程，在此不再赘述。
对于装置实施例而言，由于其基本对应于方法实施例，所以相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本说明书方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
本申请还提供了一种终端，参见图7，图7是本说明书根据一示例性实施例示出的一种终端的结构示意图。如图7所示，终端包括处理器710、存储器720和网络接口730，存储器720用于存储可在处理器710上运行的计算机指令，处理器710用于在执行所述计算机指令时实现本申请任一实施例所提供的行驶路径确定方法，网络接口730用于实现输入输出功能。在更多可能的实现方式中，终端还可以包括其他硬件，本申请对此不做限定。
本申请还提供了一种计算机可读存储介质，计算机可读存储介质可以是多种形式，比如，在不同的例子中，所述计算机可读存储介质可以是：RAM(Radom Access Memory，随机存取存储器)、易失存储器、非易失性存储器、闪存、存储驱动器(如硬盘驱动器)、固态硬盘、任何类型的存储盘(如光盘、DVD等)，或者类似的存储介质，或者它们的组合。特殊的，所述的计算机可读介质还可以是纸张或者其他合适的能够打印程序的介质。计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时实现本申请任一实施例所提供的行驶路径确定方法。
本申请还提供了一种计算机程序产品，包括计算机程序，计算机程序被处理器执行时实现本申请任一实施例所提供的行驶路径确定方法。
本领域技术人员应明白，本说明书一个或多个实施例可提供为方法、装置、终端、计算机可读存储介质或计算机程序产品。因此，本说明书一个或多个实施例可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本说明书一个或多个实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于终端所对应的实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
本说明书中描述的主题及功能操作的实施例可以在以下中实现：数字电子电路、有形体现的计算机软件或固件、包括本说明书中公开的结构及其结构性等同物的计算机硬件、或者它们中的一个或多个的组合。本说明书中描述的主题的实施例可以实现为一个或多个计算机程序，即编码在有形非暂时性程序载体上以被数据处理装置执行或控制数据处理装置的操作的计算机程序指令中的一个或多个模块。可替代地或附加地，程序指令可以被编码在人工生成的传播信号上，例如机器生成的电、光或电磁信号，该信号被生成以将信息编码并传输到合适的接收机装置以由数据处理装置执行。计算机存储介质可以是机器可读存储设备、机器可读存储基板、随机或串行存取存储器设备、或它们中的一个或多个的组合。
本说明书中描述的处理及逻辑流程可以由执行一个或多个计算机程序的一个或多个可编程计算机执行，以通过根据输入数据进行操作并生成输出来执行相应的功能。所述处理及逻辑流程还可以由专用逻辑电路—例如FPGA(现场可编程门阵列)或ASIC(专用集成电路)来执行，并且装置也可以实现为专用逻辑电路。
适合用于执行计算机程序的计算机包括，例如通用和/或专用微处理器，或任何其他类型的中央处理单元。通常，中央处理单元将从只读存储器和/或随机存取存储器接收指令和数据。计算机的基本组件包括用于实施或执行指令的中央处理单元以及用于存储指令和数据的一个或多个存储器设备。通常，计算机还将包括用于存储数据的一个或多个大容量存储设备，例如磁盘、磁光盘或光盘等，或者计算机将可操作地与此大容量存储设备耦接以从其接收数据或向其传送数据，抑或两种情况兼而有之。然而，计算机不是必须具有这样的设备。此外，计算机可以嵌入在另一设备中，例如移动电话、个人数字助理(PDA)、移动音频或视频播放器、游戏操纵台、全球定位系统(GPS)接收机、或例如通用串行总线(USB)闪存驱动器的便携式存储设备，仅举几例。
适合于存储计算机程序指令和数据的计算机可读介质包括所有形式的非易失性存储器、媒介和存储器设备，例如包括半导体存储器设备(例如EPROM、EEPROM和闪 存设备)、磁盘(例如内部硬盘或可移动盘)、磁光盘以及CD ROM和DVD-ROM盘。处理器和存储器可由专用逻辑电路补充或并入专用逻辑电路中。
虽然本说明书包含许多具体实施细节，但是这些不应被解释为限制任何发明的范围或所要求保护的范围，而是主要用于描述特定发明的具体实施例的特征。本说明书内在多个实施例中描述的某些特征也可以在单个实施例中被组合实施。另一方面，在单个实施例中描述的各种特征也可以在多个实施例中分开实施或以任何合适的子组合来实施。此外，虽然特征可以如上所述在某些组合中起作用并且甚至最初如此要求保护，但是来自所要求保护的组合中的一个或多个特征在一些情况下可以从该组合中去除，并且所要求保护的组合可以指向子组合或子组合的变型。
类似地，虽然在附图中以特定顺序描绘了操作，但是这不应被理解为要求这些操作以所示的特定顺序执行或顺次执行、或者要求所有例示的操作被执行，以实现期望的结果。在某些情况下，多任务和并行处理可能是有利的。此外，上述实施例中的各种系统模块和组件的分离不应被理解为在所有实施例中均需要这样的分离，并且应当理解，所描述的程序组件和系统通常可以一起集成在单个软件产品中，或者封装成多个软件产品。
由此，主题的特定实施例已被描述。其他实施例在所附权利要求书的范围以内。在某些情况下，权利要求书中记载的动作可以以不同的顺序执行并且仍实现期望的结果。此外，附图中描绘的处理并非必需所示的特定顺序或顺次顺序，以实现期望的结果。在某些实现中，多任务和并行处理可能是有利的。
本领域技术人员在考虑说明书及实践这里申请的发明后，将容易想到本说明书的其它实施方案。本说明书旨在涵盖本说明书的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本说明书的一般性原理并包括本说明书未申请的本技术领域中的公知常识或惯用技术手段。也即是，本说明书并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。
以上所述仅为本说明书的可选实施例而已，并不用以限制本说明书，凡在本说明书的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本说明书保护的范围之内。

Claims (11)

  1. 一种行驶路径确定方法，包括：
    基于自动驾驶车辆所处的位置以及所述自动驾驶车辆所处道路的中心线的位置，构建坐标系，所述坐标系的纵向方向指示所述道路的中心线方向，所述坐标系的横向方向指示与所述道路的中心线垂直的方向；
    基于所述道路在所述坐标系的横向方向上的障碍物信息、所述道路在所述坐标系的纵向方向上采样后的障碍物信息、所述自动驾驶车辆所处的位置以及所述道路的边界，确定可行驶区域；
    基于所述可行驶区域和所述自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定所述自动驾驶车辆的行驶路径。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述坐标系的纵向方向上，对所述道路中的障碍物信息进行采样。
  3. 根据权利要求2所述的方法，其特征在于，在构建所述坐标系时，所述道路中的障碍物被映射为多边形；
    所述在所述坐标系的纵向方向上，对所述道路中的障碍物信息进行采样，包括：
    在所述多边形中与所述坐标系的纵向方向同向的边上，对所述多边形对应的障碍物的障碍物信息进行采样。
  4. 根据权利要求1所述的方法，其特征在于，所述基于自动驾驶车辆所处的位置以及所述自动驾驶车辆所处道路的道路信息，构建坐标系，包括：
    以所述自动驾驶车辆所处的位置作为所述坐标系的坐标原点，
    以所述道路的中心线的切线方向作为所述坐标系的纵向方向，
    以所述道路的中心线的法线方向作为所述坐标系的横向方向。
  5. 根据权利要求1所述的方法，其特征在于，所述基于所述道路在所述坐标系的横向方向上的障碍物信息、所述道路在所述坐标系的纵向方向上采样后的障碍物信息、所述自动驾驶车辆所处的位置以及所述道路的边界，确定可行驶区域，包括：
    基于所述道路在所述坐标系的横向方向上的障碍物信息、所述道路在所述坐标系的纵向方向上采样后的障碍物信息和所述道路的边界，获取所述自动驾驶车辆的行驶方向上的障碍物之间以及所述障碍物与所述道路的边界之间的可通行间隙的宽度；
    将所述自动驾驶车辆所处的位置作为根节点，按照所述障碍物与所述自动驾驶车辆的位置的距离从小到大的顺序，逐层展开获取到的多个可通行间隙，得到第一搜索树；
    按照所述第一搜索树中多个节点对应的宽度从大到小的顺序，保留排序靠前的预设数量的节点；
    基于所保留的节点对应的宽度，确定所述可行驶区域。
  6. 根据权利要求1所述的方法，其特征在于，所述基于所述道路在所述坐标系的横向方向上的障碍物信息、所述道路在所述坐标系的纵向方向上采样后的障碍物信息、所述自动驾驶车辆所处的位置以及所述道路的边界，确定可行驶区域，包括：
    基于所述道路在所述坐标系的横向方向上的障碍物信息、所述道路在所述坐标系的纵向方向上采样后的障碍物信息和所述道路的边界，获取所述自动驾驶车辆的行驶方向上的障碍物之间以及所述障碍物与所述道路的边界之间的可通行间隙的宽度；
    将所述自动驾驶车辆所处的位置作为根节点，按照所述障碍物与所述自动驾驶车辆所处的位置的距离从小到大的顺序，遍历多个可通行间隙，得到第二搜索树所包括的多个目标节点，所述目标节点为距离所述自动驾驶车辆所处的位置相同的障碍物对应的可通行间隙中，宽度最大的可通行间隙对应的节点；
    基于所述目标节点，确定所述可行驶区域。
  7. 根据权利要求1所述的方法，其特征在于，所述行驶数据包括所述自动驾驶车辆与障碍物的距离、所述自动驾驶车辆与道路中心线的距离、所述自动驾驶车辆的横向位移、所述自动驾驶车辆的横向速度以及所述自动驾驶车辆的横向加速度中至少一项。
  8. 根据权利要求7所述的方法，其特征在于，所述基于所述可行驶区域和所述自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定所述自动驾驶车辆的行驶路径，包括下述任一项：
    将所述可行驶区域中，所述自动驾驶车辆与障碍物的距离最大的位置所构成的路径，确定为所述行驶路径；
    将所述可行驶区域中，所述自动驾驶车辆与道路中心线的距离最小的位置所构成的路径，确定为所述行驶路径；
    将所述可行驶区域中，所述自动驾驶车辆的横向位移最小的位置所构成的路径，确定为所述行驶路径；
    将所述可行驶区域中，所述自动驾驶车辆的横向速度变化最小的位置所构成的路径，确定为所述行驶路径；
    将所述可行驶区域中，所述自动驾驶车辆的横向加速度最小的位置所构成的路径，确定为所述行驶路径。
  9. 一种行驶路径确定装置，其特征在于，所述装置包括：
    构建单元，用于基于自动驾驶车辆所处的位置以及所述自动驾驶车辆所处道路的中心线的位置，构建坐标系，所述坐标系的纵向方向指示所述道路的中心线方向，所述坐标系的横向方向指示与所述道路的中心线垂直的方向；
    区域确定单元，用于基于所述道路在所述坐标系的横向方向上的障碍物信息、所述道路在所述坐标系的纵向方向上采样后的障碍物信息、所述自动驾驶车辆所处的位置以 及所述道路的边界，确定可行驶区域；
    路径确定单元，用于基于所述可行驶区域和所述自动驾驶车辆在行驶过程中的行驶数据所满足的设定条件，确定所述自动驾驶车辆的行驶路径。
  10. 一种终端，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求1至8中任一项所述的行驶路径确定方法所执行的操作。
  11. 一种计算机可读存储介质，其上存储有程序，所述程序被处理器执行如权利要求1至8中任一项所述的行驶路径确定方法所执行的操作。
PCT/CN2022/070525 2021-09-13 2022-01-06 行驶路径确定 WO2023035519A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111070523.X 2021-09-13
CN202111070523.XA CN115230731A (zh) 2021-09-13 2021-09-13 行驶路径确定方法、装置、终端及介质

Publications (1)

Publication Number Publication Date
WO2023035519A1 true WO2023035519A1 (zh) 2023-03-16

Family

ID=83666864

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/070525 WO2023035519A1 (zh) 2021-09-13 2022-01-06 行驶路径确定

Country Status (2)

Country Link
CN (1) CN115230731A (zh)
WO (1) WO2023035519A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117068199A (zh) * 2023-08-08 2023-11-17 广州汽车集团股份有限公司 车辆可行驶空间的生成方法、装置、车辆及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116279596B (zh) * 2023-05-26 2023-08-04 禾多科技（北京）有限公司 车辆控制方法、装置、电子设备和计算机可读介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012233856A (ja) * 2011-05-09 2012-11-29 Fujitsu General Ltd 緊急車輌用経路案内装置
US20140200801A1 (en) * 2013-01-16 2014-07-17 Denso Corporation Vehicle travel path generating apparatus
CN109855636A (zh) * 2018-12-20 2019-06-07 江苏大学 一种基于智能驾驶的特种车辆路径规划系统和方法
CN110749333A (zh) * 2019-11-07 2020-02-04 中南大学 基于多目标优化的无人驾驶车辆运动规划方法
CN111679678A (zh) * 2020-06-30 2020-09-18 安徽海博智能科技有限责任公司 一种横纵向分离的轨迹规划方法、系统及计算机设备
CN112362074A (zh) * 2020-10-30 2021-02-12 重庆邮电大学 一种结构化环境下的智能车辆局部路径规划方法
CN112572472A (zh) * 2020-12-08 2021-03-30 重庆大学 一种基于Frenet坐标系的自动驾驶碰撞预测方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012233856A (ja) * 2011-05-09 2012-11-29 Fujitsu General Ltd 緊急車輌用経路案内装置
US20140200801A1 (en) * 2013-01-16 2014-07-17 Denso Corporation Vehicle travel path generating apparatus
CN109855636A (zh) * 2018-12-20 2019-06-07 江苏大学 一种基于智能驾驶的特种车辆路径规划系统和方法
CN110749333A (zh) * 2019-11-07 2020-02-04 中南大学 基于多目标优化的无人驾驶车辆运动规划方法
CN111679678A (zh) * 2020-06-30 2020-09-18 安徽海博智能科技有限责任公司 一种横纵向分离的轨迹规划方法、系统及计算机设备
CN112362074A (zh) * 2020-10-30 2021-02-12 重庆邮电大学 一种结构化环境下的智能车辆局部路径规划方法
CN112572472A (zh) * 2020-12-08 2021-03-30 重庆大学 一种基于Frenet坐标系的自动驾驶碰撞预测方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117068199A (zh) * 2023-08-08 2023-11-17 广州汽车集团股份有限公司 车辆可行驶空间的生成方法、装置、车辆及存储介质
CN117068199B (zh) * 2023-08-08 2024-05-24 广州汽车集团股份有限公司 车辆可行驶空间的生成方法、装置、车辆及存储介质

Also Published As

Publication number Publication date
CN115230731A (zh) 2022-10-25

Similar Documents

Publication Publication Date Title
WO2023035519A1 (zh) 行驶路径确定
US20200265710A1 (en) Travelling track prediction method and device for vehicle
WO2022001773A1 (zh) 轨迹预测方法及装置
US10800408B2 (en) Determining driving paths for autonomous driving that avoid moving obstacles
JP7086111B2 (ja) 自動運転車のｌｉｄａｒ測位に用いられるディープラーニングに基づく特徴抽出方法
US10137896B2 (en) Method and system for operating autonomous driving vehicles using graph-based lane change guide
US11112259B2 (en) Localization determination for vehicle operation
US10775801B2 (en) Determining speeds along a path for autonomous driving vehicles
EP3438953A1 (en) Information processing device
US7865277B1 (en) Obstacle avoidance system and method
WO2022056770A1 (zh) 一种路径规划方法和路径规划装置
WO2020237890A1 (zh) 一种速度规划方法、装置、电子设备及存储介质
JP2023514905A (ja) 自律型車両のためのビヘイビア・プランニング
CN112673234A (zh) 路径规划方法和路径规划装置
CN114212110B (zh) 障碍物轨迹预测方法、装置、电子设备及存储介质
CN113608531B (zh) 基于安全a*引导点的无人车实时全局路径规划方法
CN112577506B (zh) 一种自动驾驶局部路径规划方法和系统
CN111338360B (zh) 一种规划车辆行驶状态的方法及装置
WO2022052881A1 (zh) 一种构建地图的方法及计算设备
WO2022148441A1 (zh) 车辆泊车规划方法、装置、设备及计算机存储介质
CN114261404B (zh) 一种自动驾驶方法及相关装置
WO2022142839A1 (zh) 一种图像处理方法、装置以及智能汽车
CN115855095A (zh) 一种自主导航方法、装置及电子设备
Yan et al. RH-Map: Online Map Construction Framework of Dynamic Object Removal Based on 3D Region-wise Hash Map Structure
WO2021000787A1 (zh) 道路几何识别方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22865999

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22865999

Country of ref document: EP

Kind code of ref document: A1