Route generation device, parking assistance system, and route generation method

Abstract

To provide a route generation device capable of reducing a processing load in generation of a parking route.SOLUTION: A route generation device 100 comprises: a surrounding environment information acquisition unit 101 that acquires a surrounding environment of an own vehicle 10; an own vehicle position estimation unit 102 that estimates an own vehicle position; a geometrical route generation unit 103 that generates a geometrical route AL using an expression representing a geometrical shape of a route; a graph search route generation unit 104 that generates a graph search route GL using a graph search algorithm for searching for the route using a plurality of nodes and a plurality of edges for connecting the nodes; and a route combination unit 105 that generates a parking route from a parking start position SP to a parking target position EP by combining the geometrical route AL and the graph search route GL.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present application relates to a route generation device, a parking assistance system, and a route generation method. [Background technology]

[0002] With the development of autonomous driving technology for vehicles, various parking assistance devices and parking assistance systems that assist in parking a vehicle have been proposed or put into practical use. For example, the parking assistance system described in Patent Document 1 generates a route from an initial position to a target position using a graph search algorithm that utilizes graph theory, and parks the vehicle. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6749480 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the parking assistance system described in Patent Document 1 had a problem in that when parking in a situation where the vehicle must repeatedly turn around within a parking space over a short distance, such as parallel parking, there were many redundant calculations, resulting in a high processing load.

[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a route generation device, a parking assistance system, and a route generation method that can reduce the processing load in generating parking routes. [Means for solving the problem]

[0006] The route generation device according to the present disclosure comprises: a surrounding environment information acquisition unit that acquires information about the surrounding environment of the vehicle; a vehicle position estimation unit that estimates a vehicle position; a geometric route generation unit that generates a geometric route using an equation that represents a geometric shape of the route; a graph search path generator that generates a graph search path using a graph search algorithm that searches for a path using a plurality of nodes and a plurality of edges connecting the nodes; and a route combination unit that generates a parking route from the parking start position to the parking target position within the parking space by combining the geometric route and the graph search route.

[0007] The parking assistance system according to the present disclosure comprises: The above-mentioned route generation device; and a vehicle control device that parks the vehicle based on the parking path generated by the path generation device.

[0008] The route generation method according to the present disclosure includes: A vehicle control method in which the following steps are executed by a processing circuit: generating a geometric path using an equation representing a geometric shape of the path, and an end of the geometric path as a connection point; generating a graph search path based on a graph search algorithm using the nodes and edges connecting the nodes; generating a parking path from a parking start position to a parking target position by combining the geometric path and the graph search path through the connection points; Equipped with. [Effects of the Invention]

[0009] The route generation device, parking assistance system, and route generation method disclosed herein have the advantage of reducing the processing load in generating a parking route by generating a route from the parking start position to a connection point using a graph search algorithm, and generating a route from the connection point to the parking target position as a geometric route. [Brief explanation of the drawings]

[0010] [Figure 1]1 is a block diagram of a path generating device according to a first embodiment. [Figure 2] FIG. 2 is a schematic diagram illustrating the operation of the path generation device in Example 1 of Embodiment 1. [Figure 3] FIG. 2 is a schematic diagram illustrating the operation of the path generation device in Example 1 of Embodiment 1. [Figure 4] FIG. 2 is a schematic diagram illustrating the operation of the path generation device in Example 1 of Embodiment 1. [Figure 5] FIG. 2 is a schematic diagram illustrating the operation of the path generation device in Example 1 of Embodiment 1. [Figure 6] FIG. 2 is a flowchart illustrating a processing flow of the path generating device in Example 1 of Embodiment 1. [Figure 7] FIG. 10 is a flowchart illustrating the processing flow of a graph search route generation unit of the route generation device in Example 1 of Embodiment 1. [Figure 8] FIG. 10 is a flowchart illustrating a processing flow of a route combination unit of the route generation device according to the first example of the first embodiment. [Figure 9] FIG. 10 is a schematic diagram illustrating the operation of the path generation device in Example 2 of Embodiment 1. [Figure 10] FIG. 10 is a flowchart illustrating the processing flow of a graph search path generation unit in the path generation device according to the second example of the first embodiment. [Figure 11] FIG. 10 is a schematic diagram illustrating the operation of the path generation device in Example 3 of Embodiment 1. [Figure 12] FIG. 10 is a schematic diagram illustrating the operation of the path generation device in Example 3 of Embodiment 1. [Figure 13] FIG. 10 is a schematic diagram illustrating the operation of the path generation device in Example 3 of Embodiment 1. [Figure 14] FIG. 10 is a block diagram of a route generation system according to a second embodiment. [Figure 15] FIG. 10 is a schematic diagram of a vehicle equipped with a route generation system according to a second embodiment. [Figure 16]1 is a diagram showing a hardware configuration for realizing a route generation device according to a first embodiment and a parking assistance system according to a second embodiment. [Figure 17] 1 is a diagram showing a hardware configuration for realizing a route generation device according to a first embodiment and a parking assistance system according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Embodiment 1 <Configuration of the path generation device according to the first embodiment> 1 is a block diagram of a route generation device 100 according to the embodiment 1. The route generation device 100 is mounted on, for example, a vehicle.

[0012] The route generation device 100 includes a surrounding environment information acquisition unit 101, a vehicle position estimation unit 102, a geometric route generation unit 103, a graph search route generation unit 104, and a route combination unit 105. Each component of the route generation device 100 will be described below.

[0013] <Surrounding Environment Information Acquisition Department> The surrounding environment information acquisition unit 101 acquires surrounding environment information of the vehicle 10 from various sensors mounted on the vehicle 10 or from an external source such as a traffic control center. The surrounding environment information acquisition unit 101 outputs the acquired surrounding environment information to the geometric route generation unit 103 and the graph search route generation unit 104.

[0014] The surrounding environment information is a series of information used in route generation, such as parking space 30, obstacle information regarding obstacles 40 around the host vehicle 10 including aisle width, and parking target position EP. Methods for acquiring the surrounding environment information include, for example, a method of detecting the obstacle 40 by measuring the distance between the host vehicle 10 and the obstacle 40 using a sonar sensor, a method of detecting the obstacle 40 around the host vehicle 10 using a high-precision sensor such as LiDAR (Light Detection and Ranging), which is a type of radar sensor, or an image sensor such as a camera, and a method of acquiring the surrounding environment information through communication with an outside of the host vehicle 10, such as a traffic control center. Additionally, the surrounding environment information may be acquired from one or a combination of two or more of a vehicle-to-vehicle communication device and a road-to-vehicle communication device.

[0015] <Vehicle position estimation unit> The vehicle position estimation unit 102 estimates the current vehicle position. The vehicle position estimation unit 102 outputs the estimated vehicle position to the geometric route generation unit 103 and the graph search route generation unit 104. One example of a means for estimating the vehicle position by the vehicle position estimation unit 102 is a GNSS receiver that receives signals transmitted from a GNSS (Global Navigation Satellite System) such as a GPS (Global Positioning System) to acquire information on absolute position (latitude, longitude). Alternatively, the vehicle position may be detected by a speed sensor, a direction sensor, or the like.

[0016] <Geometric path generation section> The geometric path generation unit 103 generates a path using a geometric formulation, that is, a combination of curves. The curves are formulated using equations that represent geometric shapes. The path generated by the geometric path generation unit 103 is referred to as a geometric path AL in the following description. The geometric path generation unit 103 generates a path from the parking target position EP to within or near the parking space 30, that is, the geometric path AL, based on the surrounding environment information around the host vehicle and the parking target position EP.

[0017] When generating a route, the geometric route generating unit 103 provisionally sets a terminal target point at a position within or near the parking space 30 where exit is possible, and generates a geometric route AL from the parking target position EP to the terminal target point by combining curves. The terminal end of the geometric route AL generated in this manner, within or near the parking space 30, does not strictly coincide with the terminal target point. Along with the generation of the geometric route AL, a connection point CP, which is the terminal end of the geometric route AL within or near the parking space 30, is generated.

[0018] The terminal target point may be set at a point where the vehicle 10 is expected to be able to leave the parking space 30, for example, based on the vehicle width or length from the boundary between the parking space 30 and the aisle. For example, in the case of parallel parking, the vehicle width of the vehicle 10 is LW, and the terminal target point may be set within a range of 0.2LW to 0.5LW from the center of the boundary between the parking space 30 and the aisle, based on the vehicle width LW. In the case of perpendicular parking, the vehicle length of the vehicle 10 is LL, and the terminal target point may be set within a range of 0.5LL to 1.5LL from the center of the boundary between the parking space 30 and the aisle, based on the vehicle length LL. Furthermore, a tentative geometric route AL may be generated from the parking start position SP to the parking target position EP, and a point on the tentative geometric route AL within or near the parking space 30 may be set as the terminal target point.

[0019] The geometric path AL is composed of a combination of any curves. Here, examples of curves include straight lines, clothoid curves, circular arc curves, and polynomial curves. For example, a geometric path AL consisting of a travel distance S and a curvature ρ can be generated using a path generation method such as that disclosed in International Publication No. 2020-217315. Other examples of methods for generating the geometric path AL include the well-known state lattice method, potential method, and spline interpolation function method.

[0020] An evaluation function is applied to the route generated by the geometric route generation unit 103 to generate an evaluation function minimization route that minimizes the evaluation function J. The evaluation function J can be expressed as in the following equation (1) by using a weighting coefficient ω.

[0021]

number

[0022] In equation (1), the weighting coefficient ω ρ,i (s) is the weighting coefficient ω for each i-th turn, expressed as the variable s of the travel distance S. ρ,i (s) is ω ρ,1 (s), ω ρ,2 (s), ω ρ,3 As shown in (s), it is possible to set a function for the variable s of the travel distance S for each turn.

[0023] Examples of means for minimizing the evaluation function J include the sequential quadratic programming method and the interior point method. Alternatively, the ACADO (Automatic Control And Dynamic Optimization) method and the C / GMRES (Continuation / Generalized Minimum Residual) method may be used. In other words, when minimizing the evaluation function J, any known method including the above-mentioned methods may be applied.

[0024] The geometric route generation unit 103 outputs the geometric route AL, which is the route that minimizes the evaluation function, and information on whether the geometric route AL can be generated to the route combination unit 105. It also outputs the information on whether generation is possible and the final position of the route that minimizes the evaluation function to the graph search route generation unit 104. Here, the final position of the route that minimizes the evaluation function is called a connection point CP. The information on whether the geometric route AL can be generated refers to information on whether the geometric route AL can be generated by the geometric route generation unit 103. This is because there are cases in which the geometric route generation unit 103 cannot generate the geometric route AL depending on the surrounding environment information around the host vehicle and the contents of the parking target position EP.

[0025] <Graph search path generation unit> The graph search path generation unit 104 generates a path, i.e., a graph search path GL, using a graph search algorithm. The graph search path generation unit 104 generates the graph search path GL using a graph search algorithm that utilizes graph theory, such as the A* (A-star) search algorithm. For example, the graph search algorithm described in Patent Document 1 may be applied as the graph search algorithm.

[0026] The graph search algorithm described in Patent Document 1 is a route search method that finds the shortest route that is composed of nodes (nodes or vertices) and edges (branches or sides) that connect the nodes, and that minimizes the inter-node cost (evaluation index) between two nodes connected by the edges, for example, the total cost represented by the travel distance. Although an example of applying the graph search algorithm described in Patent Document 1 has been given as the graph search algorithm used in the route generation device and route generation method according to the first embodiment, other known graph search algorithms may also be applied.

[0027] <Route combination section> The route combination unit 105 combines the geometric route AL generated by the geometric route generation unit 103 and the graph search route GL generated by the graph search route generation unit 104, and outputs a parking route from the parking start position SP to the parking target position EP. This concludes the description of each component of the path generating device 100 according to the first embodiment.

[0028] Example 1 of Embodiment 1 <Route Generation Device of First Embodiment> The route generation device 100 according to the first embodiment will be described below, but application examples of the route generation device 100 are not limited to the application examples of the following first to third embodiments.

[0029] 2, 3, 4, and 5 are schematic diagrams illustrating the operation of the route generation device 100 according to the first embodiment. The operation of the route generation device 100 according to the first embodiment will be described below with reference to FIGS. 2, 3, 4, and 5.

[0030] The parking route output from the route combination unit 105 is a route that combines a geometric route AL from the parking target position EP to a connection point CP within or near the parking space 30, which is generated by the geometric route generation unit 103, and a graph search route GL from the parking start position SP to the connection point CP, which is generated by the graph search route generation unit 104, which is shown in Figure 2. Note that in Figure 2, the parking space 30 refers to the space sandwiched between two adjacent vehicles 20.

[0031] 4, the graph search path generator 104 uses a graph search algorithm to generate the graph search path GL by connecting an initial tree ST consisting of multiple nodes and multiple edges that starts from the initial position of the vehicle 10, i.e., the initial node GND corresponding to the parking target position EP, and heads toward the connection point CP or the target node corresponding to the parking target position EP of the vehicle 10, with a target tree ET consisting of multiple nodes and multiple edges that starts from the target node and heads toward the initial node. As described above, for example, the graph search algorithm described in Patent Document 1 may be used.

[0032] As shown in FIG. 5, if the geometric path generation unit 103 is unable to generate the geometric path AL, the graph search path generation unit 104 may generate a path from the parking start position SP to the parking target position EP, i.e., the entire parking path.

[0033] If the graph search path generation unit 104 is unable to find a path from the parking start position SP to the connection point CP, i.e., the graph search path GL, it may use a method other than that described above, for example, by changing the parameters used in the graph search algorithm and re-searching, i.e., re-generating, the graph search path GL. When changing the parameters, the parameters used in the graph search algorithm may include, for example, the length of the edges connecting the nodes, the curvature of the edges, and the maximum number of iterations. Multiple parameters may also be used. Note that parameters other than those listed above may be used as long as they can be used in the graph search algorithm, and are not limited to the parameters described above.

[0034] The above is the basic operation of the route generation device 100 of the embodiment 1. The operation of the route generation device 100 of the embodiment 1 will be described in more detail below.

[0035] <Route generation method using the route generation device of the first embodiment> The process flow by the route generation device 100 of the first embodiment, that is, the route generation method, will be described below with reference to the flowcharts of Figures 6, 7, and 8. Steps S101 to S105 will be described below with reference to the flowchart shown in Figure 6, steps S111 to S117 with reference to the flowchart shown in Figure 7, and steps S131 to S135 with reference to the flowchart shown in Figure 8.

[0036] First, in step S101, the surrounding environment information acquisition unit 101 acquires surrounding environment information of the host vehicle 10 using various sensors mounted on the host vehicle 10. As another acquisition method, the surrounding environment information of the host vehicle 10 may be acquired from a traffic control center or the like outside the host vehicle 10. The surrounding environment information is a series of information used to generate a route, such as parking spaces 30, obstacle information around the host vehicle 10 including aisle width, and a parking target position EP.

[0037] In step S102, the vehicle position estimation unit 102 estimates the current vehicle position using, for example, various sensors mounted on the vehicle 10.

[0038] In step S103, the geometric route generation unit 103 generates a geometric route AL using the geometric formulation as described above. The geometric route generation unit 103 also generates a connection point CP, which is the end point of the geometric route AL.

[0039] In step S104, the graph search path generation unit 104 generates a graph search path GL from the parking start position SP to the connection point CP based on the surrounding environment information and the connection point CP relating to the periphery of the vehicle 10 using the graph search algorithm as described above. Furthermore, if the geometric path generation unit 103 cannot generate a geometric path AL, the graph search path generation unit 104 may generate the entire parking path from the parking start position SP to the parking target position EP as the graph search path GL, or may change the parameters used in the graph search algorithm and regenerate the graph search path GL.

[0040] Next, the processing flow for generating a graph search path will be described in detail using the flowchart in FIG. In step S111, the geometric route generation unit 103 determines whether or not the geometric route AL can be generated. If it is determined that the route generation of the geometric route AL is possible, the process proceeds to step S112. On the other hand, if it is determined that the route generation of the geometric route AL is not possible, the process proceeds to step S113.

[0041] If it is determined in step S111 that route generation of the geometric route AL is possible, then in step S112, the graph search route generation unit 104 sets the target position, that is, the end point of the geometric route AL, as the connection point CP.

[0042] If it is determined in step S111 that route generation of the geometric route AL is not possible, in step S113, the graph search route generation unit 104 sets the target position to the parking target position EP, and proceeds to the processing of step S114.

[0043] In step S114, the graph search path generation unit 104 performs a path generation process using a graph search algorithm based on the parking start position SP and the target position. The path generation process calculates a reference path, i.e., a graph search path GL. Here, the reference path is a time-varying profile expressed by the vehicle speed, steering angle, and vehicle state (x, y, θ).

[0044] In step S115, it is determined whether the reference route calculated in step S114 can actually be generated. If it is determined that the reference route can be generated, the process proceeds to step S116. On the other hand, if it is determined that the reference route cannot be generated, the process proceeds to step S117.

[0045] If it is determined in step S115 that the route generation process calculated in step S114 is capable of generating a route, in step S116, a reference route, that is, a graph search route GL, is output to the route combination unit 105 as route generation information.

[0046] If it is determined in step S115 that generation of a reference route is not possible, it is determined in step S117 whether the route generation process has been performed up to the upper limit of processing times, i.e., the maximum number of iterations. If it is determined that the upper limit of processing times has not been exceeded, the process proceeds to step S118. On the other hand, if it is determined that the upper limit of processing times has been exceeded, the process ends.

[0047] In step S118, the parameters used in the route generation process are changed, and the process proceeds to step S114 to perform the route generation process again, i.e., regenerate the route. Parameters used in the route generation process include, for example, edge length, edge curvature, and upper limit processing count (maximum number of iterations), but parameters other than those listed above may also be used as long as they are parameters used in graph search route generation.

[0048] 6, in step S105, the route combination unit 105 outputs a route, i.e., a parking route, that combines the geometric route AL from the parking target position EP to the connection point CP generated by the geometric route generation unit 103 and the graph search route GL from the parking start position SP to the connection point CP generated by the graph search route generation unit 104. Note that if it is determined in step S111 that route generation of the geometric route AL is not possible, and the graph search route generation unit 104 is able to generate a route from the parking start position SP to the parking target position EP, the entire parking route from the parking start position SP to the parking target position EP is output as the graph search route GL.

[0049] The process flow for combining routes will be described in detail below using the flowchart in FIG. In step S131, it is determined whether route generation of the geometric route AL is possible. If it is determined that route generation of the geometric route AL is possible, the process proceeds to step S132. On the other hand, if it is determined that route generation is not possible, the process proceeds to step S133.

[0050] In step S132, it is determined whether or not route generation of the graph search path GL is possible. If it is determined that route generation of the graph search path GL is possible, the process proceeds to step S134. On the other hand, if it is determined that route generation is not possible, the process ends.

[0051] If it is determined in step S131 that route generation is not possible, then in step S133 it is determined whether route generation of the graph search path GL is possible. If it is determined that route generation of the graph search path GL is possible, then the process proceeds to step S135. On the other hand, if it is determined that route generation of the graph search path GL is not possible, then the process ends.

[0052] In step S134, the route combination unit 105 combines the geometric route AL and the graph search route GL and outputs the result as route generation information, that is, a parking route.

[0053] If it is determined in step S133 that route generation of the graph search route GL is possible, then in step S135 the graph search route GL is output as route generation information, that is, a parking route. The above is the process flow of the operation of the route generation device of the first embodiment, that is, the route generation method.

[0054] <Features and Effects of the Route Generation Device of the First Embodiment> The path generation device 100 of the first embodiment is characterized in that the parking path is a path that combines a geometric path AL from the parking target position EP to the connection point CP generated by the geometric path generation unit 103 and a graph search path GL from the parking start position SP to the connection point CP generated by the graph search path generation unit 104; if the geometric path generation unit 103 is unable to generate a geometric path AL from the parking target position EP to the connection point CP, the graph search path generation unit 104 generates the entire parking path by graph searching from the parking start position SP to the parking target position EP; and if the graph search path generation unit 104 is unable to search for a graph search path GL from the parking start position SP to the connection point CP, the graph search path generation unit 104 changes the parameters used in the graph search algorithm and regenerates the graph search path GL.

[0055] The route generation device and route generation method according to the first example of the first embodiment have the following advantages. (1) The processing load can be reduced by using a graph search algorithm to generate a route up to the complex situation of entering a parking space or near the parking space, while generating a geometric route from within the parking space or near the parking space to the target parking position. (2) By applying a bidirectional graph search algorithm, the speed at which a solution can be obtained is faster than with conventional graph searches that only search in one direction from the initial node to the goal node. In other words, the processing load can be reduced. (3) Even when a geometric path cannot be generated because the passage is narrow and complex or the connection from the parking target position to the connection point is not possible, the route generation of the parking path is possible by applying the graph search algorithm. (4) Even if the graph search route generation unit is unable to find a graph search route from the parking start position to the connection point, the opportunity to generate a route can be avoided by changing the parameters used in the graph search algorithm and regenerating the route.

[0056] Example 2 of Embodiment 1 <Route Generation Device of Second Embodiment> The following describes the route generation device 100 of Example 2. In Example 2, a route that combines a geometric route AL from the parking target position EP to the connection point CP generated by the geometric route generation unit 103 and a graph search route GL from the parking start position SP to the connection point CP generated by the graph search route generation unit 104 is defined as a parking route.

[0057] The geometric path generation unit 103 calculates multiple connection points CP, i.e., the end points of multiple geometric paths AL, and assigns a cost (evaluation index) to each connection point CP. The graph search path generation unit 104 generates a graph search path GL using at least one of the connection points CP and the parking target position EP. If there are multiple solutions for the parking path, the path combination unit 105 selects the parking path with the lowest cost.

[0058] To explain in more detail, the geometric route generation unit 103 generates connection points CP within or near the parking space 30, and if there are multiple connection points CP, it calculates the node-to-node costs of the routes related to the multiple connection points CP, i.e., the evaluation indexes, respectively. The graph search route generation unit 104 generates a graph search route GL using at least one of the multiple connection points CP, and if there are multiple solutions for the parking route, the route combination unit 105 selects the parking route with the smallest sum of the evaluation indexes.

[0059] The above is the basic operation of the path generation device 100 in the second embodiment, and the operation will be described in more detail below.

[0060] The processing flow of the second embodiment, that is, the route generation method, is almost the same as the processing flow of the first embodiment shown in the flowcharts of Figures 6 and 8, but the processing contents of steps S103, S104, and S105 are partially different. Therefore, the following description will be limited to the processing of steps S103, S104, and S105.

[0061] In step S103, as shown in Fig. 9, the geometrical route generation unit 103 generates a plurality of connection points CP and assigns a cost (evaluation index) to each connection point CP. In the example of Fig. 9, three connection points, connection point CP1, connection point CP2, and connection point CP3, are generated. Furthermore, the geometrical route generation unit 103 determines whether or not a route can be generated for the geometrical route AL, and outputs each connection point CP and the cost (evaluation index) corresponding to each connection point CP to the route combination unit 105. The geometrical route generation unit 103 outputs whether or not a route can be generated for the geometrical route AL and the generated plurality of connection points CP to the graph search route generation unit 104.

[0062] The multiple connection points CP are the respective final positions of the multiple evaluation function minimization paths described above, that is, the respective final positions of the multiple evaluation function minimization paths when the weighting coefficient ω is arbitrarily changed. The cost (evaluation index) is a value calculated, for example, from the above-mentioned formula (1).

[0063] In other words, the geometric route generation unit 103 outputs multiple evaluation function minimization routes, costs, and whether or not the route can be generated for the geometric route AL to the route combination unit 105, while outputting whether or not the route can be generated for the geometric route AL and the final positions, i.e., the terminal ends, of each of the multiple evaluation function minimization routes as connection points CP to the graph search route generation unit 104.

[0064] In step S104, the processing content of the flowchart for graph search path generation according to embodiment 1 (FIG. 7) is partially changed, as in the flowchart for graph search path generation according to embodiment 2 shown in FIG. Only the parts that differ from the flowchart for graph search path generation according to embodiment 1 will be explained below.

[0065] In step S104 of the flowchart in FIG. 6, the graph search path generation unit 104 generates a graph search path GL using at least one of the connection point CP and the parking target position EP.

[0066] In step S142 of the flowchart in Fig. 10, the connection point CP and the parking target position EP are set as the target position (including multiple target positions). If there are multiple connection points CP, multiple target positions are set.

[0067] In step S144, a route generation process for a graph search route GL is performed using a graph search algorithm based on the parking start position SP and the target position. If there are multiple target positions, a route generation process corresponding to the multiple positions is performed. In the above explanation, parallel processing is used as an example, but other methods that can generate routes for multiple positions are also applicable.

[0068] In step S144, when the graph search route generation unit 104 generates a route from the parking start position SP to the target position, it outputs the sum of costs (node ​​costs) for each calculated node as route generation information to the route combination unit 105. As a method for calculating the node costs, for example, the calculation method disclosed in Patent Document 1 for calculating the sum of node costs, that is, the total cost, may be applied.

[0069] In step S115, it is determined whether the route calculated in step S144 can be generated. If it is determined that route generation is possible, the process proceeds to step S116. On the other hand, if it is determined that route generation is not possible, the process ends.

[0070] In step S105 of the flowchart in Fig. 6, the content of the process in step S134 shown in the route combination flowchart in Fig. 8 is partially different. The following description will be limited to the process in step S134.

[0071] In step S134, if there are multiple solutions for the geometric route AL and the graph search route GL, the route combination unit 105 selects the route with the smallest cost and outputs it as route generation information.

[0072] If the total cost of route generation is L, the generation cost of the geometric route AL is C1, the generation cost of the graph search route GL is C2, and the route generation correction coefficient that corrects the cost ratio is α, the total cost L can be expressed as shown in the following equation (2).

[0073]

number

[0074] <Features and Effects of the Route Generation Device and Route Generation Method of the Second Embodiment> The route generation device and route generation method of the second embodiment are characterized in that the geometric route generation unit 103 calculates multiple connection points CP and assigns a cost to each connection point CP, the graph search route generation unit 104 generates a graph search route GL using at least one of the connection points CP and the parking target position EP, and if there are multiple solutions for the route, the route with the lowest cost is selected.

[0075] The route generation device and route generation method of the second embodiment have the following advantages. (1) When there are multiple solutions for a route, an efficient parking route can be generated by selecting the route with the lowest cost.

[0076] Example 3 of Embodiment 1 <Route Generation Device and Route Generation Method of Third Embodiment> The following describes a route generation device and a route generation method according to Example 3. In Example 3, if the surrounding environment changes before and after route generation and an obstacle 40 is detected on the route, and the graph search route generation unit 104 is unable to find a graph search route GL up to a connection point CP when the route is regenerated, the geometric route generation unit 103 sets a new connection point CP (single or multiple connection points) on the geometric route AL that does not collide with the obstacle 40, and regenerates the route. The above is the basic operation of the route generation device 100 and route generation method of embodiment 3. The operation of the route generation device 100 of embodiment 3 will be described in more detail below.

[0077] <Route generation method using the route generation device of the third embodiment> The processing flow of Example 3, i.e., the route generation method, is almost the same as the processing flow of Examples 1 and 2 of Embodiment 1 shown in the flowcharts of Figures 6, 8, and 10, but the content of the processing of step S103 is partially different. The following description will be limited to the processing of step S103.

[0078] In step S103 of the flowchart in Figure 6, if the graph search path generation unit 104 finds a graph search path GL from the parking start position SP to the connection point CP once (Figure 11), but then the surrounding environment changes due to an obstacle 40, or some other reason makes it impossible to generate the path (Figure 12), the geometric path generation unit 103 regenerates a new geometric path AL and connection point CP that does not come into contact with the obstacle 40, in other words, that can avoid the obstacle 40 (Figure 13). Note that this connection point CP may be single or multiple.

[0079] The path forming method of the third embodiment provides the following effects. (1) Even if route generation becomes impossible due to circumstances such as changes in the surrounding environment caused by obstacles, the geometric route generation unit can increase the chances of route generation by regenerating a geometric route and connection points that do not come into contact with obstacles.

[0080] <Advantages of First Embodiment> The advantages of the route generation device and route generation method according to the first embodiment are listed below. (1) The processing load can be reduced by using a graph search algorithm to generate a route up to the complex situation of entering a parking space or near the parking space, while generating a geometric route from within the parking space or near the parking space to the target parking position. (2) By applying a bidirectional graph search algorithm, the speed at which a solution can be obtained is faster than with conventional graph searches that only search in one direction from the initial node to the goal node. In other words, the processing load can be reduced. (3) Even when a geometric path cannot be generated because the passage is narrow and complex or the connection from the parking target position to the connection point is not possible, the route generation of the parking path is possible by applying the graph search algorithm. (4) Even if the graph search route generation unit is unable to find a graph search route from the parking start position to the connection point, the opportunity to generate a route can be avoided by changing the parameters used in the graph search algorithm and regenerating the route. (5) If there are multiple solutions for a route, an efficient parking route can be generated by selecting the route with the lowest cost. (6) Even if route generation becomes impossible due to circumstances such as changes in the surrounding environment caused by obstacles, the geometric route generation unit can increase the chances of route generation by regenerating a geometric route and connection points that do not come into contact with obstacles.

[0081] Embodiment 2 <Configuration of parking assistance system according to embodiment 2> 14 is a block diagram showing the configuration of a parking assistance system 500 according to Embodiment 2. The parking assistance system 500 according to Embodiment 2 includes the path generation device 100 according to Embodiment 1 and a vehicle control device 200.

[0082] The vehicle control device 200 performs vehicle control to park the vehicle 10a at the parking target position EP based on the route generation information output from the route combination unit 105 of the route generation device 100. The vehicle control device 200 calculates a target steering amount according to the steering angle and vehicle state profile over time generated by the route combination unit 105, and parks the vehicle 10a at the parking target position EP. Furthermore, the vehicle control device 200 calculates a target vehicle speed according to the vehicle speed profile over time generated by the route combination unit 105 of the route generation device 100, and smoothly guides the vehicle 10a to the parking target position EP.

[0083] The target steering amount and the target acceleration / deceleration in the vehicle control device 200 can be calculated using a known calculation method such as a calculation method using feedback control or a calculation method using MPC (Model Predictive Control).

[0084] When the surrounding environment changes, the vehicle control device 200 causes the geometric route generation unit 103 and the graph search route generation unit 104 to re-form the route, and if the route generation fails, determines to abort.

[0085] The vehicle control device 200 stops the vehicle 10a in response to the determination of suspension, and the vehicle continues to be stopped for a certain period of time, for example. Furthermore, if the vehicle control device 200 determines that parking the vehicle 10a to the parking target position EP is difficult due to the influence of a change in the surrounding environment, etc., the vehicle control device 200 suspends the parking control.

[0086] 15 is a schematic diagram of a vehicle 10a equipped with a parking assistance system 500 according to embodiment 2. The parking assistance system 500 and an actuator 530 are installed in the vehicle 10a.

[0087] The actuator 530 includes an Electronic Power Steering (EPS) unit 535, a powertrain unit 536, a brake unit 537, an EPS controller 531, a powertrain controller 532, and a brake controller 533. The actuator 530 controls the EPS, the brake, and the accelerator so that the vehicle 10a follows a target steering amount and a target acceleration / deceleration.

[0088] The vehicle control device 200 then processes information input from various connected sensors (not shown) according to a program stored in the ROM, transmits a target control amount to the EPS controller 531, transmits a target driving force to the powertrain controller 532, and transmits a target braking force to the brake controller 533.

[0089] The EPS controller 531 controls the EPS unit 535 based on the target control amount transmitted from the vehicle control device 200. The EPS controller 531 can control, for example, the steering angle so that the vehicle 10a travels along a target trajectory.

[0090] The powertrain controller 532 controls the powertrain unit 536 so as to realize the target driving force transmitted from the vehicle control device 200 .

[0091] In the description of the second embodiment, a vehicle using only an engine as a driving force source is given as an example, but the present invention may also be applied to a vehicle using only an electric motor as a driving force source, or a vehicle using both an engine and an electric motor as a driving force source.

[0092] The brake controller 533 controls the brake unit 537 so as to realize the target braking force transmitted from the vehicle control device 200 . The above is an overview of the configuration and operation of the parking assistance system 500 including the path generation device 100 and the vehicle control device 200.

[0093] <Advantages of the Second Embodiment> As described above, according to the parking assistance system of embodiment 2, a parking path is generated using the path generation device of embodiment 1, which has the effect of appropriately responding to the surrounding environment and reducing the processing load, thereby enabling efficient parking control to be achieved.

[0094] The above has described a configuration in which the functions of each component of the path generation device 100 according to the first embodiment and the parking assistance system 500 according to the second embodiment are realized by either hardware or software, etc. However, the present invention is not limited to this, and the path generation device 100 and the parking assistance system 500 may be configured such that some of the components are realized by dedicated hardware and other components are realized by software, etc.

[0095] For example, as shown in Figures 16 and 17, the functions of some components can be realized by a processing circuit 800 as dedicated hardware, and the functions of other components can be realized by the processing circuit 800 as a processor 801 reading and executing a program stored in a memory device 802 for executing the route generation method of embodiment 1 on a computer or the like.

[0096] Furthermore, as shown in FIG. 17, the setting data used by each functional unit of the route generation device 100 and the parking assistance system 500 may be installed in the storage device 802 from a recording medium 803 that stores a part of the software, i.e., a program 804 for executing the route generation method of embodiment 1 on a computer or the like.

[0097] As described above, the path generation device 100 according to the first embodiment and the parking assistance system 500 according to the second embodiment can realize the above-described functions by hardware, software, or a combination of these.

[0098] <Summary of various aspects of the present application> Various aspects of the present application will be summarized below as appendices.

[0099] (Appendix 1) a surrounding environment information acquisition unit that acquires information about the surrounding environment of the vehicle; a vehicle position estimation unit that estimates a vehicle position; a geometric route generation unit that generates a geometric route using an equation that represents a geometric shape of the route; a graph search path generator that generates a graph search path using a graph search algorithm that searches for a path using a plurality of nodes and a plurality of edges connecting the nodes; a route combination unit that generates a parking route from a parking start position to a parking target position within a parking space by combining the geometric route and the graph search route; A route generation device comprising:

[0100] (Appendix 2) The route generation device described in Appendix 1, characterized in that the parking route is a route that combines the geometric route, which is a route from the parking target position to a connection point generated by the geometric route generation unit, and the graph search route, which is a route from the parking start position to the connection point generated by the graph search route generation unit.

[0101] (Appendix 3) The route generation device described in Appendix 2 is characterized in that, when generating the geometric route, the geometric route generation unit generates an end point of the geometric route as a connection point, and if there are multiple connection points, calculates route evaluation indexes for each of the multiple connection points, the graph search route generation unit generates the graph search route using at least one of the multiple connection points, and if there are multiple solutions for the parking route, the route combination unit selects the parking route with the smallest sum of the evaluation indexes.

[0102] (Appendix 4) 2. The route generation device according to claim 1, wherein if the geometric route generation unit is unable to generate the geometric route, the graph search route generation unit generates the parking route from the parking start position to the parking target position as the graph search route.

[0103] (Appendix 5) The path generation device according to Supplementary Note 2 or 3, wherein the graph search path generation unit uses a graph search algorithm that generates the graph search path by connecting an initial tree consisting of the plurality of nodes and the plurality of edges that starts from an initial node corresponding to the parking start position and heads toward a goal node corresponding to the connection point, and a goal tree consisting of the plurality of nodes and the plurality of edges that starts from the goal node and heads toward the initial node.

[0104] (Appendix 6) 6. The path generation device according to claim 5, wherein, if the graph search path generation unit is unable to generate the graph search path, it changes parameters used in the graph search algorithm and regenerates the graph search path.

[0105] (Appendix 7) 7. The path generation device according to claim 6, wherein the parameters are one or more of the length of the edge, the curvature of the edge, and the maximum number of iterations.

[0106] (Appendix 8) A route generation device according to any one of Supplementary Notes 2, 3, and 5 to 7, characterized in that if the surrounding environment changes after the graph search route generation process, the surrounding environment information acquisition unit acquires information about an obstacle located on the graph search route, and the graph search route generation unit is unable to generate the graph search route, the geometric route generation unit regenerates a geometric route that avoids the obstacle and the connection points.

[0107] (Appendix 9) A path generation device according to any one of Supplementary Notes 1 to 8; a vehicle control device that parks the host vehicle based on the parking path generated by the path generation device; A parking assistance system equipped with

[0108] (Appendix 10) The parking assistance system described in Appendix 9 is characterized in that, when the surrounding environment changes, if the parking path cannot be generated even after both the geometric path generation unit and the graph search path generation unit regenerate the path, the vehicle control device determines to suspend vehicle control of the host vehicle.

[0109] (Appendix 11) 11. The parking assistance system according to claim 10, wherein the vehicle control device stops the host vehicle and suspends parking control in response to a determination of suspension.

[0110] (Appendix 12) A vehicle control method in which the following steps are executed by a processing circuit: generating a geometric path using an equation representing a geometric shape of the path, and an end of the geometric path as a connection point; generating a graph search path based on a graph search algorithm using the nodes and edges connecting the nodes; generating a parking path from a parking start position to a parking target position by combining the geometric path and the graph search path through the connection points; A route generation method comprising:

[0111] (Appendix 13) 13. The path generation method of claim 12, wherein the graph search algorithm generates the graph search path by connecting an initial tree consisting of a plurality of the nodes and a plurality of the edges starting from an initial node corresponding to the parking start position and heading toward a goal node corresponding to the connection point, and a goal tree consisting of a plurality of the nodes and a plurality of the edges starting from the goal node and heading toward the initial node.

[0112] Although the present disclosure describes various exemplary embodiments and examples, the various features, aspects, and functions described in one or more embodiments are not limited to application to a particular embodiment, but may be applied to the embodiments alone or in various combinations.

[0113] Therefore, countless variations not illustrated are conceivable within the scope of the technology disclosed in the present specification, including, for example, cases where at least one component is modified, added, or omitted, and cases where at least one component is extracted and combined with components of another embodiment. [Explanation of symbols]

[0114] 10 Vehicle, 10a Vehicle, 20 Adjacent vehicle, 30 Parking space, 40 Obstacle, 100 Path generation device, 101 Surrounding environment information acquisition unit, 102 Vehicle position estimation unit, 103 Geometric path generation unit, 104 Graph search path generation unit, 105 Path combination unit, 200 Vehicle control device, 500 Parking assistance system, 530 Actuator, 531 EPS controller, 532 Power train controller, 533 Brake controller, 535 EPS unit, 536 Power train unit, 537 Brake unit, 800 Processing circuit, 801 Processor, 802 Storage device, 803 Recording medium, 804 Program, AL Geometric path, CP, CP1, CP2, CP3 Connection point, EP Parking target position, ET Target tree, GL Graph search path, SP Parking start position, ST Initial tree

Claims

1. a surrounding environment information acquisition unit that acquires information about the surrounding environment of the vehicle; a vehicle position estimation unit that estimates a vehicle position; a geometric route generation unit that generates a geometric route using an equation that represents a geometric shape of the route; a graph search path generator that generates a graph search path using a graph search algorithm that searches for a path using a plurality of nodes and a plurality of edges connecting the nodes; a route combination unit that generates a parking route from a parking start position to a parking target position within a parking space by combining the geometric route and the graph search route; A route generation device comprising:

2. 2. The route generation device according to claim 1, wherein the parking route is a route that combines the geometric route, which is a route from the parking target position to a connection point, generated by the geometric route generation unit, and the graph search route, which is a route from the parking start position to the connection point, generated by the graph search route generation unit.

3. The route generation device according to claim 2, characterized in that when generating the geometric route, the geometric route generation unit generates an end point of the geometric route as a connection point, and if there are multiple connection points, calculates route evaluation indexes for each of the multiple connection points, the graph search route generation unit generates the graph search route using at least one of the multiple connection points, and if there are multiple solutions for the parking route, the route combination unit selects the parking route with the smallest sum of the evaluation indexes.

4. 2. The route generation device according to claim 1, wherein, when the geometric route generation unit cannot generate the geometric route, the graph search route generation unit generates the parking route from the parking start position to the parking target position as the graph search route.

5. 3. The path generation device according to claim 2, wherein the graph search path generation unit uses a graph search algorithm that generates the graph search path by connecting an initial tree consisting of the plurality of nodes and the plurality of edges that starts from an initial node corresponding to the parking start position and heads toward a goal node corresponding to the connection point, and a goal tree consisting of the plurality of nodes and the plurality of edges that starts from the goal node and heads toward the initial node.

6. 6. The path generation device according to claim 5, wherein, when the graph search path generation unit is unable to generate the graph search path, it changes parameters used in the graph search algorithm and regenerates the graph search path.

7. The path generation device according to claim 6 , wherein the parameter is at least one of the length of the edge, the curvature of the edge, and the maximum number of iterations.

8. A route generation device as described in any one of claims 2, 3, 6, and 7, characterized in that if the surrounding environment changes after the graph search route generation process, the surrounding environment information acquisition unit acquires information about an obstacle located on the graph search route, and the graph search route generation unit is unable to generate the graph search route, the geometric route generation unit regenerates a geometric route that avoids the obstacle and the connection points.

9. A path generation device according to any one of claims 1 to 4, 6 and 7; a vehicle control device that parks the host vehicle based on the parking path generated by the path generation device; A parking assistance system equipped with

10. 10. The parking assistance system according to claim 9, wherein the vehicle control device determines to suspend vehicle control of the host vehicle when the surrounding environment changes and the parking path cannot be generated even after both the geometric path generation unit and the graph search path generation unit regenerate the path.

11. 11. The parking assistance system according to claim 10, wherein the vehicle control device stops the host vehicle and suspends parking control in response to the determination of suspension.

12. A vehicle control method in which the following steps are executed by a processing circuit: generating a geometric path using an equation representing a geometric shape of the path, and an end of the geometric path as a connection point; generating a graph search path based on a graph search algorithm using the nodes and edges connecting the nodes; generating a parking path from a parking start position to a parking target position by combining the geometric path and the graph search path through the connection points; A route generation method comprising:

13. 13. The path generation method according to claim 12, wherein the graph search algorithm generates the graph search path by connecting an initial tree consisting of a plurality of the nodes and a plurality of the edges starting from an initial node corresponding to the parking start position and heading toward a destination node corresponding to the connection point, and a destination tree consisting of a plurality of the nodes and a plurality of the edges starting from the destination node and heading toward the initial node.

Images