Route search device, control method and program

The route search device optimizes multi-agent pathfinding by using a metaheuristic algorithm to evaluate routes based on utility scores, addressing the computational inefficiency of MO-CBS and providing efficient, practical conflict-free routes for multiple vehicles.

JP2024543199AActive Publication Date: 2024-11-19NEC CORP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2024532517
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-12-08
Filing Date
2022-12-07
Publication Date
2024-11-19
Estimated Expiration
2042-12-07

AI Technical Summary

Technical Problem

The multi-objective conflict-based search (MO-CBS) algorithm for multi-agent pathfinding (MAPF) is computationally expensive due to the need to calculate multiple Pareto optimal solutions, making it inefficient for practical applications.

Method used

A route search device and method that uses a metaheuristic algorithm, such as a genetic algorithm, to optimize multiple objectives while minimizing computational cost by evaluating routes based on a utility score that represents the degree to which multiple objectives are optimized, rather than generating the entire set of Pareto-optimal solutions.

Benefits of technology

Provides a computationally less expensive method for generating conflict-free routes for multiple vehicles, offering practical solutions with reduced execution time and eliminating the need for operators to select from a vast set of Pareto-optimal solutions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024543199000001_ABST
    Figure 2024543199000001_ABST
Patent Text Reader

Abstract

The route search device (2000) acquires vehicle information (60) and map information (70) and determines a route set (40) including a route (50) for each of the vehicles (20) in the vehicle set (10). The route set (40) is determined using the vehicle information (60) and map information (70). The route sets in the route set (40) do not compete with each other. To determine the route set, the route search device (2000) executes a route planning algorithm to generate a route for each vehicle. The route planning algorithm evaluates the routes based on a route utility score, which is a scalar value that represents how well the route achieves multiple objectives.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates generally to multi-agent pathfinding problems. [Background technology]

[0002] The multi-agent path finding (MAPF) problem is a problem of searching for a path for each of multiple vehicles such that the vehicles do not collide with each other or with any static obstacles when the multiple vehicles move along a path while optimizing a single objective, such as the total travel distance. Non-Patent Document 1 discloses an algorithm called a Conflict Based Search (CBS) algorithm for solving the MAPF problem. CBS is a two-level search algorithm that is divided into a high-level search and a low-level search. In the high-level search, CBS uses a constraint tree (CT) called a binary tree to find appropriate constraints on the time and position of the vehicles to avoid collisions between the vehicles. In the low-level search, CBS searches for a path for each vehicle under the constraints found in the high-level search.

[0003] The CBS algorithm disclosed by [1] cannot handle multiple objectives because it evaluates paths based on a single objective, i.e., path length. [2] discloses an algorithm called multi-objective conflict-based search (MO-CBS) that extends CBS to handle multiple objectives. Note that a generalization of the MAPF problem to handle multiple objectives is called multiple-objective MAPF (MOMAPF). MO-CBS generates multiple CTs, each with a root node that contains an initial Pareto optimal solution. At the root node, collisions between vehicles are not considered. It then generates child nodes to resolve the detected collisions. This approach also considers a graph with a given cost. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] Guni Sharon, Roni Stern, Ariel Felner, and Nathan R. Sturtevant, "Conflict-Based Search for Optimal Multi-Agent Pathfinding," Elsevier, Artificial Intelligence, Volume 219, pages 40-66, February 2015. [Non-Patent Document 2] Zhongqiang Ren, Sivakumar Rathinam, and Howie Choset, "Multi-objective conflict-based search for multi-agent pathfinding," [online], January 11, 2021, [Retrieved December 7, 2021],<arXiv, https: / / arxiv.org / pdf / 2101.03805v2.pdf> Retrieved from [Non-Patent Document 3] Wei Chu and Zoubin Ghahramani, "Priority Learning with Gaussian Processes," ACM, the 22nd International Conference on Machine Learning, August 7, 2005. [Non-Patent Document 4] Eric Brochu, Vlad M. Cora, and Nando de Freitas, "Tutorial on Bayesian Optimization of Expensive Cost Functions with Applications to Active User Modeling and Hierarchical Reinforcement Learning", [online], December 12, 2010, [Retrieved October 6, 2021],<arXiv, https: / / arxiv.org / pdf / 1012.2599.pdf> Retrieved from Summary of the Invention [Problem to be solved by the invention]

[0005] MO-CBS is computationally expensive since it has to compute multiple Pareto optimal solutions. The objective of the present disclosure is to provide a computationally less expensive method for providing a set of routes for multiple vehicles while taking into account multiple objectives. [Means for solving the problem]

[0006] A route search device according to the present disclosure includes at least one processor and a memory that stores instructions, and the at least one processor executes the instructions to obtain vehicle information and map information, the vehicle information indicating a pair of a start position and a destination position for each of a plurality of vehicles, the map information indicating a map of a space in which the vehicles move, and using the vehicle information and the map information to determine a route set including routes for each of the vehicles, the routes of the route set being configured to be mutually exclusive, the determination of the route set includes executing a route planning algorithm to generate the routes for each of the vehicles, and the route planning algorithm evaluates the routes based on utility scores of the routes, the utility scores being scalar values ​​representing the degree to which a plurality of objectives are optimized by the routes.

[0007] A control method according to the present disclosure is implemented by a computer, the control method including: obtaining vehicle information and map information, the vehicle information indicating a pair of start and destination locations for each of a plurality of vehicles, the map information indicating a map of a space in which the vehicles travel, determining a path set including paths for each of the vehicles using the vehicle information and the map information, the paths in the path set being non-conflicting with each other, the determining of the path set including running a path planning algorithm to generate the paths for each of the vehicles, the path planning algorithm evaluating the paths based on utility scores for the paths, the utility scores being scalar values ​​representing the degree to which a plurality of objectives are optimized by the paths.

[0008] The non-transitory computer-readable storage medium of the present disclosure stores a program that causes a computer to execute the control method of the present disclosure described above. Effect of the Invention

[0009] The present disclosure provides a computationally less expensive method for providing a set of routes for multiple vehicles while taking multiple objectives into account. [Brief description of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an overview of a route search device according to a first embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of a functional configuration of the route search device. [Diagram 3] FIG. 2 is a block diagram showing an example of a hardware configuration of a computer that realizes the route search device. [Figure 4] 4 is a flowchart showing an example of processing executed by the route search device of the first embodiment. [Diagram 5] FIG. 2 is a diagram illustrating an example of a structure of vehicle information in a table format. [Figure 6] 1 is a flowchart showing the overall flow of CBS. [Figure 7]1 is a flowchart showing an example of the flow of a GA path planner executed by the MAPF solution unit. [Figure 8] FIG. 13 is a diagram showing an example of an intersection step. [Figure 9] FIG. 13 illustrates the removal of waypoints from candidate paths for mutations. [Figure 10] FIG. 1 illustrates the addition of one or more waypoints to a candidate path for a mutation. [Figure 11] FIG. 1 illustrates the addition of one or more waypoints to a candidate path for a mutation. [Figure 12] FIG. 11 is a diagram illustrating an overview of a route search device according to a second embodiment. [Figure 13] FIG. 11 is a block diagram showing an example of a functional configuration of a route search device according to a second embodiment. [Figure 14] 11 is a flowchart showing an example of processing executed by the route search device of the second embodiment. [Figure 15] FIG. 13 is a diagram visually presenting multiple candidates for a set of routes. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings. In each drawing, the same elements are given the same reference numerals, and duplicated descriptions will be omitted as necessary. Furthermore, the storage unit is formed of one or more storage devices.

[0012] EMBODIMENT 1 <Summary> Fig. 1 is a diagram showing an overview of a route search device 2000 according to embodiment 1. Note that the overview shown in Fig. 1 shows an example of the operation of the route search device 2000 in order to make the route search device 2000 easier to understand, and is not intended to limit or narrow the range of operations that the route search device 2000 can take.

[0013] The path search device 2000 operates to generate a path set 40 for the vehicle set 10. The path set 40 is a collection of paths 50 and includes a path 50 for each of the multiple vehicles 20 included in the vehicle set 10. Each vehicle 20 is configured to travel from its start location to its destination location along its corresponding path 50.

[0014] The vehicle set 10 includes N vehicles {v1, ..., vN}. The route search device 2000 needs to generate a set of routes {p1, ..., pN} for the vehicle set 10, where a route pi corresponds to each vehicle vi of i from 1 to N.

[0015] A vehicle set 10 is a collection of vehicles 20 and may be associated with an entity 30. The entity 30 may be any entity responsible for the vehicle set 10. For example, the entity 30 may be an operator of the vehicles 20 in the vehicle set 10 or a company that owns or manages the vehicle set 10.

[0016] Vehicle 20 may be any moving object that is controllable to move along its corresponding path 50. In some implementations, vehicle 20 may be any type of autonomous vehicle, such as an automatic guided vehicle (AGV), a drone, etc. In other implementations, vehicle 20 may be any type of moving object that is manually operated.

[0017] The start position and the target position are predefined for each vehicle 20. To know the start position and the target position of the vehicle 20, the path search device 2000 can obtain vehicle information 60 indicating the start position and the target position of each vehicle 20 in the vehicle set 10.

[0018] There are at least two requirements for the generation of the path set 40. First, the path set 40 is required to be conflict-free, i.e., each path 50 does not conflict with any of the other paths in the path set 40. Second, the path set 40 needs to be generated such that a number of predefined objectives are substantially optimized. There are various objectives that may be considered. Some examples of the objectives include efficiency, safety, and smoothness of the paths 50 in the path set 40. These objectives are described in more detail below.

[0019] In order to find a path set 40 that satisfies at least the above two requirements, the path search device 2000 generates the path set 40 by solving a multi-objective multi-agent path finding (MOMAPF) problem. Hereinafter, the algorithm executed by the path search device 2000 to solve the MOMAPF problem is referred to as a "MOMAPF solver." The MOMAPF solver repeatedly generates a path set 40 until it finds a path set 40 that satisfies the above two requirements, i.e., no conflict and substantially optimizing multiple objectives.

[0020] In order to define the MOMAPF problem to be solved, at least (1) a map of the space in which the vehicles 20 can move, and (2) a start position and a destination position of each vehicle 20 are required. Regarding (1), the route search device 2000 obtains map information 70 indicating a map of the space in which the vehicles 20 can move. Regarding (2), as described above, the vehicle information 60 indicates the start position and the destination position of each vehicle 20.

[0021] To satisfy the second requirement, the route search device 2000 considers the utility of each route 50. The utility of a route 50 is defined such that the better the route 50 is from the viewpoint of multiple objectives, the higher the utility of the route 50 is. The route search device 2000 measures the utility of the route 50 using a utility function defined to calculate a utility score of the route 50 representing the degree to which the multiple objectives are optimized by the route 50. As will be described in detail later, the utility function may be defined as a weighted sum of multiple objective terms, each of which represents the degree to which the corresponding objective is optimized.

[0022] To enable the MOMAPF solver to evaluate the utility of each path 50, the MOMAPF solver generates each path 50 using a path planning algorithm, such as a metaheuristic algorithm (e.g., an evolutionary algorithm (EA)), a heuristic search algorithm, an exhaustive search algorithm, or the like. In the following, for purposes of example, it is assumed that the path planning algorithm is implemented as a metaheuristic algorithm, and the metaheuristic algorithm used by the MOMAPF solver to generate each path 50 is referred to as the "EA path planner." The EA path planner uses a utility function to calculate a utility score for each candidate path 50 generated by it.

[0023] <Examples of effects> According to the route search device 2000 of the first embodiment, a route set 40 including conflict-free routes for a plurality of vehicles 20 in the vehicle set 10 is generated. The route search device 2000 can find a set of best routes from the viewpoint of the plurality of objectives because it uses a utility function that scalarizes the degree to which the plurality of objectives are optimized. Therefore, unlike the MO-CBS disclosed by Non-Patent Document 2 that provides an entire set of Pareto solutions, the route search device 2000 can provide a single set of conflict-free routes with the highest utility instead of providing multiple Pareto optimal conflict-free routes.

[0024] The route search device 2000 is more advantageous than MO-CBS in practicality and efficiency. Specifically, the route search device 2000 can provide a solution that is one of the entire set of Pareto optimal solutions or a solution close to it without calculating the entire set of Pareto optimal solutions, and therefore can provide a practical solution to an operator or the like in much less execution time than MO-CBS. In other words, the route search device 2000 can provide a solution in a manner that is less computationally expensive than that disclosed by Non-Patent Document 2. In addition, the route search device 2000 does not require the operator to select an optimal solution from the entire set of Pareto optimal solutions, thereby reducing the time and effort required for the operator to obtain a solution. Furthermore, it may be sufficient for the operator to know a single optimal solution, and it may not be practical for the operator to know the entire set of Pareto optimal solutions.

[0025] The route search device 2000 will be described in more detail below.

[0026] <Example of functional configuration> 2 shows an example of a functional configuration of the route search device 2000. The route search device 2000 includes an acquisition unit 2020 and a MOMAPF solution unit 2040. The acquisition unit 2020 acquires vehicle information 60 and map information 70. The MOMAPF solution unit 2040 solves a MOMAPF problem in which a map is defined by the map information 70 and a start position and a destination position of each vehicle 20 are defined by the vehicle information 60, and generates a route set 40 for the vehicle set 10. The MOMAPF problem is solved by executing a MOMAPF solver. In the MOMAPF solver, an EA route planner is called for each vehicle 20 to generate a route 50 for the vehicle 20. In the EA route planner, a utility function is used to evaluate the route 50 from the viewpoint of multiple objectives.

[0027] <Example of hardware configuration> The route search device 2000 may be realized by one or more computers. Each of the one or more computers may be a dedicated computer created for realizing the route search device 2000, or may be a general-purpose computer such as a personal computer (PC), a server machine, or a mobile device.

[0028] The route search device 2000 can be realized by installing an application on a computer. The application is realized by a program that causes the computer to function as the route search device 2000. In other words, the program implements the functional components of the route search device 2000.

[0029] 3 is a block diagram showing an example of a hardware configuration of a computer 1000 that realizes the route search device 2000. In the figure, the computer 1000 includes a bus 1020, a processor 1040, a memory 1060, a storage device 1080, an input / output interface 1100, and a network interface 1120.

[0030] The bus 1020 is a data communication path for the processor 1040, the memory 1060, the storage device 1080, the input / output interface 1100, and the network interface 1120 to transmit and receive data to and from each other. The processor 1040 is a processor such as a central processing unit (CPU), a graphics processing unit (GPU), or a field-programmable gate array (FPGA). The memory 1060 is a main storage element such as a random access memory (RAM) or a read only memory (ROM). The storage device 1080 is an auxiliary storage element such as a hard disk, a solid state drive (SSD), or a memory card. The input / output interface 1100 is an interface between the computer 1000 and a peripheral device (such as a keyboard, a mouse, or a display device). The network interface 1120 is an interface between the computer 1000 and a network. The network may be a local area network (LAN) or a wide area network (WAN).

[0031] The storage device 1080 can store the above-mentioned programs. The processor 1040 executes the programs to realize each functional component of the route search device 2000.

[0032] The hardware configuration of the computer 1000 is not limited to the configuration shown in FIG. For example, as described above, the route search device 2000 may be realized by a plurality of computers. In this case, these computers may be connected to each other via a network.

[0033] <Processing flow> 4 is a flowchart showing an example of processing executed by the route search device 2000. The acquisition unit 2020 acquires the vehicle information 60 and the map information 70 (S102). The MOMAPF solution finding unit 2040 executes a MOMAPF solver to solve a MOMAPF problem defined by the map indicated by the map information 70 and the start position and the target position of the vehicle 20 indicated by the vehicle information 60 (S104).

[0034] <Acquisition of vehicle information 60: S102> The acquisition unit 2020 acquires vehicle information 60 (S102). The vehicle information 60 indicates a start position and a target position of each vehicle. FIG. 5 shows an example of the configuration of the vehicle information 60 in a table format. The vehicle information 60 in FIG. 5 includes tuples of a vehicle identifier 22, a start position 24, and a target position 26. Each tuple indicates a pair of a start position and a target position of the corresponding vehicle.

[0035] There are various methods for acquiring the vehicle information 60. For example, the vehicle information 60 is stored in advance in association with the identifier of the corresponding entity in a storage unit accessible by the route search device 2000. In this case, the acquisition unit 2020 acquires the vehicle information 60 associated with the identifier of the entity 30 from the storage unit. Note that the acquisition unit 2020 acquires the identifier of the entity 30 by any means, such as accepting a user input specifying the identifier of the entity 30.

[0036] In another embodiment, the acquisition unit 2020 may acquire the vehicle information 60 by receiving the vehicle information 60 transmitted from a mobile device or another computer, such as a PC, operated by the entity 30 .

[0037] <Getting map information 70: S102> The acquisition unit 2020 acquires map information 70 (S102). The map information 70 represents a map of the space in which the vehicle 20 moves. Theoretically, the map can be represented as a graph G=(V, E), where V is a set of vertices and E is a set of edges. The vertices represent positions, and the edges represent connections between positions.

[0038] There are various ways to implement a spatial map for the MOMAPF problem. In some implementations, the map is implemented as a two-dimensional (2D) or three-dimensional (3D) grid map. In this case, each position is represented by a cell in the grid map. Further, each connection between positions is represented by a connection between cells in the grid map.

[0039] The map information 70 can also indicate the positions of each stationary obstacle such as a wall or a shelf. Each obstacle is defined by one or more positions (for example, cells of the grid map) that are permanently occupied at least during the movement of the vehicle 20.

[0040] There may be various ways to obtain the map information 70. For example, the map information 70 is pre-stored in a storage unit accessible to the path search device 2000. In this case, the acquisition unit 2020 acquires the map information 70 from the storage unit. In another embodiment, the acquisition unit 2020 may acquire the map information 70 by receiving the map information 70 sent from another computer.

[0041] <Solving the MOMAPF problem: S104> The MOMAPF solving unit 2040 executes a MOMAPF solver to solve the MOMAPF problem defined based on the map information 70 and the vehicle information 60, and generates a set of paths 40 for the set of vehicles 10. In some implementations, the MOMAPF solver is implemented by a modified version of the conflict-based search (CBS) algorithm. Note that the original version of CBS is disclosed in Non-Patent Document 1. Hereinafter, the modified version of CBS adopted by the path search device 2000 is referred to as "modified CBS".

[0042] CBS is a two-level search algorithm that is divided into a high-level search and a low-level search. The high-level search is performed using a binary tree called the Constraint Tree (CT). Each node of the CT contains (1) the time and location constraints associated with the conflicts detected by the low-level search performed in its parent node, (2) a single candidate solution (i.e., the set of candidates for all vehicle routes) that satisfies all the constraints implied by that node and its ancestors, and (3) an evaluation of the solution, which is the sum of the total route durations of all vehicles in the original CBS. The root node of the CT contains an empty set called constraints.

[0043] The constraints included in the nodes indicate which vehicles 20 are prohibited from occupying which positions at which times. For example, it is detected that at time T1, vehicles A1 and A2 collide with each other at position L1. In this case, the collision can be avoided by adopting a constraint that "vehicle A1 must not occupy position L1 at time T1" or a constraint that "vehicle A2 must not occupy position L1 at time T1."

[0044] For each node in CT, the low-level search is invoked for the vehicle 20 whose path 50 needs to be replanned. In the low-level search, the original CBS is used as the path planning algorithm. * A search algorithm is used to find a new path for the vehicle while satisfying the constraints implied by the current node and its ancestors. On the other hand, the modified CBS uses an EA path planner (i.e., a metaheuristic algorithm) as the path planning algorithm in the low-level search.

[0045] The overall flow of the CBS will be described below with reference to FIG. 6. FIG. 6 is a flowchart showing the overall flow of the CBS. Please note that the overall flow shown in FIG. 6 is common between the original CBS and the modified CBS. First, the CT is initialized by generating a root node and adding it to the open list (S202). The step of generating a node of the CT includes the steps of (1) generating a candidate solution for the node under the constraints indicated by the node and its ancestors, and (2) evaluating the solution. The solution and its evaluation are set to the node. The open list includes one or more nodes whose candidate solutions should be checked for whether they are conflict-free or not.

[0046] Note that when generating the root node, the candidate solution is generated by invoking the path planning algorithm for each vehicle individually to generate a path for each vehicle. On the other hand, when generating nodes other than the root node, the candidate solution is generated by applying the path planning algorithm to a single vehicle that needs to re-plan its path due to a conflict with another path, and replacing the vehicle's old path with the new path. Except for this new path, the candidate solution for this node is the same as the candidate solution for the parent node.

[0047] Steps S204 to S208 are repeated until a conflict-free solution is found. In step S204, the best node is searched for from the open list. The best node is the node with the highest rating. In the case of the original CBS, the node with the lowest cost is searched for as the best node. On the other hand, as will be described in more detail later, the modified CBS searches for the node with the highest utility as the best node.

[0048] The searched node is checked to see if its corresponding candidate solution is conflict-free (S206). If the candidate solution corresponding to the searched node is conflict-free (S206: YES), the CBS outputs this candidate solution as a solution to the MOMAPF problem to be solved, and then terminates (S210).

[0049] On the other hand, if the candidate solution corresponding to the found node is not conflict-free (S206: NO), a child node of the found node is generated and added to the open list (S208).

[0050] The modified CBS differs from the original CBS in at least two ways. First, the modified CBS is A * Instead of a search algorithm, we use the EA path planner as the path planning algorithm in the low-level search. Secondly, the modified CBS evaluates candidate solutions from the perspective of multiple objectives. * Due to the nature of the algorithm, the original CBS cannot handle multiple objectives, but only a single objective (path length), whereas evolutionary algorithms do not have this limitation, so the EA path planner can handle multiple objectives.

[0051] These two points will be explained in more detail below.

[0052] <<Evolutionary Algorithms for Low-Level Search>> As mentioned above, in the modified CBS, the path planning algorithm for low-level search is implemented by an EA path planner. In some implementations, the EA path planner is implemented by a genetic algorithm, which belongs to the evolutionary algorithm. In the following, the EA path planner implemented by a genetic algorithm and adopted for low-level search in the modified CBS is called the "GA path planner."

[0053] 7 is a flow chart showing an example of the flow of the GA path planner executed by the MOMAPF solver 2040. Note that, as mentioned above, a low-level search is performed for a vehicle 20 at a node of CT under the constraints implied by that node and its ancestors. Hereinafter, the vehicle 20 for which the GA path planner is called is referred to as the "target vehicle."

[0054] First, the GA path planner generates an initial population of candidate paths for the target vehicle under constraints corresponding to the current node of CT and its ancestors (S302). In a general GA algorithm, the term "population" means a set of candidate solutions. In the case of the GA path planner, the population represents a set of candidate paths for the target vehicle (i.e., candidate paths 50). The population is initialized by randomly generating multiple candidate paths, which are paths from the start position of the target vehicle to the goal position.

[0055] Steps S304 to S312 are repeatedly executed until it is determined in step S306 that a predefined end condition is satisfied. The end condition will be described later.

[0056] In S304, the GA route planner uses the utility function to evaluate each candidate route in the population. The GA route planner then checks whether a termination condition is met (S306). If the termination condition is met (S306: YES), the GA route planner outputs the candidate route with the highest utility in the current population (S314) and then terminates.

[0057] If the termination condition is not met (S306: NO), the GA path planner applies genetic operators (selection, crossover, and mutation) to the population to transform the population into the next generation. In step S308, the GA path planner selects a survivor from the population. The survivor is a candidate path that is retained in the population. In other words, the remainder of the population (i.e., candidate paths other than the survivor) is removed from the population. There are various well-known methods for selecting a survivor in a GA algorithm, for example, random selection, and any one of them can be used.

[0058] Next, the GA path planner modifies one or more candidate paths in the population by crossover to generate new candidate paths, and adds the generated candidate paths to the population (S310).Then, the GA path planner modifies one or more candidate paths in the population with mutations to generate new candidate paths, and adds the generated candidate paths to the population (S312).The details of these recombinations will be described later. Note that recombination by mutation may be performed before recombination by crossover.

[0059] After applying the genetic operators to the population, the GA path planner returns to step S304: Evaluate the population, thereby repeatedly transforming the population to the next generation and evaluating the population until the termination condition is met.

[0060] Various termination conditions can be employed for the GA path planner. For example, the termination condition may include a condition that the number of iterations reaches a predefined threshold. In this case, the GA path planner terminates when it executes step S306 more than the predefined number of times.

[0061] Alternatively or additionally, the termination condition may include a condition that the change in fitness level is less than a predefined threshold for a given number of iterations. This means that the GA path planner runs until it converges. In a GA algorithm, the fitness level represents how close the current solution is to the optimal solution for the given problem. In the GA path planner, in each iteration, the highest utility score calculated for the candidate paths in the population can be used as the value of the fitness level.

[0062] Crossover and mutational recombination are described in more detail below.

[0063] <<<Recombination by crossover>>> The crossover step is primarily responsible for improving generations to obtain better candidate paths. This improvement is achieved by recombining two or more individuals (pathway candidates in the population), called parents, to generate better solutions, called offspring.

[0064] Behind the GA pathway planner, the crossover step involves combining two parent candidate pathways, i.e., survivors after the selection step, into a new offspring pathway. Figure 8 shows an example of the crossover step. Candidate pathways 80-1 and 80-2 have two common positions 90-1 and 90-2. We apply crossover recombination to candidate pathways 80-1 and 80-2, thereby generating candidate pathways 80-3 and 80-4. Specifically, candidate pathways 80-3 and 80-4 are generated by swapping the portion of candidate pathway 80-1 between positions 90-1 and 90-2 with the portion of candidate pathway 80-2 between positions 90-1 and 90-2.

[0065] The candidate paths to which the crossover step is applied must have at least one common location among them. Thus, the GA path planner can search the population for one or more pairs of two candidate paths that have at least one common location, and apply the crossover step to the pair or pairs found.

[0066] <<<Recombination involving mutations>>> The mutation step is intended to provide the necessary diversity, explore the solution space, and prevent the population from getting stuck in a local optimum. In a GA path planner, one or more types of mutational moves are used to explore potentially better solutions. For example, a GA path planner modifies parts of a candidate path by performing random moves or informed moves. In the case of random moves, the GA path planner randomly selects one or more parts of the candidate path and modifies the selected parts by random means.

[0067] More specifically, the GA path planner randomly selects a waypoint that is located before the earliest conflict. Note that a waypoint is a set of positions and times that describe a single point in a path. Then, a set of possible recombinations in the neighborhood of the randomly selected waypoint is determined, and one move is randomly selected from among them. There can be two types of possible recombinations: detours and wait moves. A detour is a recombination that spatially modifies a part of the path. A wait move is a recombination that adds a new waypoint whose position is the same as the position of the randomly selected waypoint and whose time is different from the time of the randomly selected waypoint, thereby adding one more time step to the path. Note that the GA path planner can randomly select more than one waypoint and perform one move for each of the randomly selected waypoints.

[0068] If the recombined path is infeasible, the selection is repeated until a feasible solution is found. If the set of possible recombinations does not contain a feasible move, the set is incremented in the sense that the number of detours and waiting steps around the selected waypoint is increased.

[0069] For the notified move, the GA route planner detects one or more portions of the candidate route that satisfy a predefined condition and modifies the detected portions in a predefined manner. In some implementations, the notified move may include the removal of one or more waypoints. When performing the removal of waypoints, the GA route planner detects waypoints that form a detour and removes those waypoints to remove the detour from the candidate route. FIG. 9 illustrates the removal of waypoints from a candidate route of a mutation. For simplicity, FIG. 9 illustrates only waypoints where the vehicle changes direction. In the upper diagram of FIG. 9, the candidate route 80-5 includes waypoints 100-1, 100-2, 100-3, and 100-4 that form a detour. In this example, a new candidate route 80-6 is generated by removing waypoints 100-1 to 100-4. By removing waypoints where the vehicle changes direction, the number of turns in the candidate route is reduced, and thus the smoothness of the candidate route is increased.

[0070] 9, the candidate route 80-7 includes waypoints 100-5, 100-6, and 100-7 that form a detour. In this example, a new candidate route 80-8 is generated by deleting waypoints 100-1 to 100-3.

[0071] In other implementations, the notified movement may include adding waypoints. The adding of waypoints may be performed to resolve conflicts with paths of vehicles other than the subject vehicle. Specifically, the GA path planner detects one or more portions of a candidate path that conflict with paths of vehicles other than the subject vehicle. The GA path planner then adds waypoints to the candidate path to avoid the collision.

[0072] There are at least two ways to add a waypoint to a path: adding a waypoint in space and adding a waypoint in time. Figures 10 and 11 show adding one or more waypoints to a candidate path for mutation. In Figure 10, a candidate path 80-9 has an edge that conflicts with a path 130-1 whose direction is opposite to that of the candidate path 80-9. An edge conflict is a type of conflict where two vehicles travel through the same edge from opposite directions.

[0073] The GA path planner can randomly add waypoints around the locations of the edge conflicts, thereby adding detours to the candidate path 80-9 to resolve the edge conflicts with path 130-1. Specifically, four waypoints 100-8, 100-9, 100-10, and 100-11 are added to the candidate path 80-9, thereby generating the candidate path 80-10.

[0074] In Figure 11, candidate path 80-11 has a vertex that conflicts with path 130-2 at location L1 at time T1. A vertex conflict is a type of conflict where two vehicles occupy the same location at the same time. A vertex conflict can be resolved if one vehicle waits until the other vehicle has passed the location where the collision occurs.

[0075] Therefore, in the case of FIG. 11, the GA path planner can randomly add waypoints to several random positions that are located before the position of the vertex conflict and do not conflict with another existing vehicle. In FIG. 11, the GA path planner can add two waypoints 100-12 and waypoint 100-13 to the candidate path 80-11, thereby generating a candidate path 80-12. The waypoint 100-12 indicates (position L2, time T2), while the waypoint 100-13 indicates (position L2, time T3), where T2 < T1 < T3. By adding two waypoints that indicate the same position but different times, a waiting operation is added to the candidate path. In the case of FIG. 11, the target vehicle is scheduled to stay at the position L2 from time T2 to time T3. Therefore, the vehicle moving along the path 130-2 passes through the position L1 while the target vehicle stays at the position L2. As a result, the vertex conflict is resolved.

[0076] <<Evaluation of Candidate Paths>> During the execution of the GA path planner, each candidate path in the population is evaluated from multiple objective perspectives. Specifically, the candidate path is evaluated using a utility function that calculates the utility score of the candidate path. The utility score is a scalar value representing the degree to which multiple objectives are optimized. In this way, from the perspective of multiple objectives, the utility of the candidate path is scalarized as the utility score by the utility function.

[0077] There are various possible objectives. Some examples of objectives are (1) efficiency, (2) safety, and (3) smoothness. The efficiency of a candidate path can be defined as the total length of the candidate path. Specifically, the shorter the total length of the candidate path, the more efficient the candidate path is evaluated. In this case, the efficiency of the candidate path can be calculated as follows.

Equation

[0078] The safety of a candidate path can be defined as the shortest distance between the path of the target vehicle and an obstacle. Specifically, the longer the shortest distance between the target vehicle and an obstacle, the safer the path is evaluated to be. In this case, the safety of a candidate path can be calculated as follows:

number

[0079] In another example, the safety of a candidate path can be calculated as follows:

number

[0080] The smoothness of a candidate path can be defined as the average change in angle during movement along the candidate path. Specifically, the smaller the average change in angle in a candidate path, the smoother the candidate path is evaluated to be. The smoothness of a candidate path can be calculated as follows:

number

[0081] In another example, the smoothness of a candidate path may be defined as the number of turns. In this case, the smoothness of a candidate path may be calculated as follows:

number

[0082] As mentioned above, the utility of a candidate route is calculated using a utility function that outputs a scalar value called a utility score. For example, the utility function may be defined as a weighted sum of multiple objective terms, where each objective term represents the degree to which its corresponding objective is optimized. In this case, the utility function may be defined as follows:

number

[0083] If efficiency, safety, and smoothness are used as objectives, the utility function can be defined as follows:

number

[0084] The weight assigned to each objective may be predefined manually, however, as will be explained in more detail below, the weights of the objectives may be dynamically determined by the route search device 2000 based on user preferences.

[0085] In the above description, it should be noted that the smaller the efficiency, safety, and smoothness described above are, the better. Therefore, the smaller the utility score u(P), the higher the utility of the candidate path P is evaluated to be. Therefore, the GA path planner selects the candidate path with the lowest utility score as the candidate path with the highest utility.

[0086] It should also be noted that the objectives to be considered are not limited to efficiency, safety, and smoothness of the route: for example, the energy consumption of the vehicles or the task allocation of the vehicles can be treated as objectives.

[0087] It should also be noted that the utility of a route is not limited to the weighted sum of multiple objectives. Any method that can calculate a single scalar value by taking into account the degree of optimization of multiple objectives can be adopted. For example, the Chebyshev method can be adopted.

[0088] To determine the best node in step 204 of FIG. 6, the MOMAPF solver evaluates the utility of the candidate path set 40 for each node. The utility of a candidate path set 40 may be calculated based on the utility scores of each path in the candidate. For example, the MOMAPF solver calculates the utility score of the path set as the sum of the utility scores of all paths in the path set. In another embodiment, the MOMAPF solver calculates the utility score of a path as a statistic (e.g., average, minimum, maximum, etc.) of the utility scores of all paths in the path set.

[0089] If the smaller the utility score, the higher the utility of the path, the smaller the utility score of the path, the higher the utility of the path set.Thus, the node selected as the best node by the MOMAPF solver contains the candidate path set whose utility score is the smallest among all.

[0090] <Result output> The MOMAPF solving unit 2040 obtains a route set 40 as a solution of the MOMAPF problem solved by the MOMAPF solver. The route search device 2000 can output information indicating the route set 40 (hereinafter, output information). There are various methods for outputting the output information. In some implementations, the route search device 2000 can store the output information in a storage device. In other implementations, the route search device 2000 can output the output information to a display device so that the display device displays the output information. In this case, the display device can display the map indicated by the map information 70, the start position and the destination position of each vehicle 20 indicated by the vehicle information 60, and the route 05 of each vehicle 20 included in the route set 40. In other implementations, the route search device 2000 can transmit the output information to any computer that uses the route set in some way.

[0091] EMBODIMENT 2 <Summary> Fig. 12 shows an overview of a route search device 2000 of embodiment 2. Note that the overview shown in Fig. 12 shows an implementation example of the operation of the route search device 2000 to make the route search device 2000 easier to understand, and is not intended to limit or narrow the range of operations that the route search device 2000 can perform.

[0092] The route search device 2000 of embodiment 2 is the same as the route search device of embodiment 1, except that, for example, it elicits user preferences regarding the importance of each objective considered in the utility function (e.g., appropriate weights of the objectives in the utility function defined as a weighted sum) and generates a new utility function whose configuration is determined based on the user preferences.

[0093] The specific method of constructing the utility function depends on the type of the utility function. For example, when the utility function is defined as a weighted sum of multiple objectives, the configuration of the utility function is a set of weights of the objectives. In the first embodiment, the configuration of the utility function may be defined in advance.

[0094] Specifically, the route search device 2000 of the second embodiment repeatedly solves the MOMAPF problem while updating the utility function until an appropriate utility function is found. In each iteration, the route search device 2000 provides the user with multiple candidates of the route set 40 generated by the MOMAPF solver using utility functions having different configurations, allows the user to select one of the candidates, and generates a new utility function whose configuration is determined based on the configuration of the utility function for the selected candidate.

[0095] <Examples of effects> Since the route search device 2000 evaluates the candidates in the route set 40 using the utility score of the route calculated using the utility function, the accuracy of the evaluation depends on the configuration of the utility function. Specifically, the more appropriately the utility function is configured, the more accurately the utility score represents the utility of the route. However, it may be difficult for a user to grasp the appropriate configuration of the utility function by himself / herself.

[0096] According to the route search device 2000 of the second embodiment, the utility function is iteratively modified based on a user selection of a route set from a plurality of candidates, thereby improving the utility function. Thus, the route search device 2000 can automatically generate a utility function that can accurately calculate the utility of a route. As a result, the route search device 2000 can accurately assign a high utility to the route set 40.

[0097] The route search device 2000 will be described in more detail below.

[0098] <Example of functional configuration> 13 is a block diagram showing an example of a functional configuration of a route search device 2000 according to the second embodiment. The route search device 2000 according to the second embodiment further includes a candidate providing unit 2060 and a preference eliciting unit 2080, in comparison with the route search device 2000 according to the first embodiment. The candidate providing unit 2060 provides two or more route set 40 candidates acquired as a solution to the MOMAPF problem to the user by a selectable means using different utility functions. The preference eliciting unit 2100 acquires information indicating which route set 40 candidate the user has selected, and generates a new utility function based on the user's selection.

[0099] Next, the MOMAPF solving unit 2040 calculates the MOMAPF solver using the new utility function. Then, the candidate providing unit 2060 provides the candidate path set 40 generated using the new utility function to the user together with the candidate path set 40 last selected by the user. Until a predefined termination condition is satisfied, the route search device 2000 repeatedly generates candidates for the route set 40 while providing multiple candidates for the route set 40 by a selectable means and generating a new utility function based on the user's selection of the candidate path set 40.

[0100] <Hardware configuration example> The route search device 2000 of the second embodiment can be realized by one or more computers similar to those that realize the route search device 2000 of the first embodiment. Therefore, the hardware configuration thereof can also be shown in FIG.

[0101] <Processing flow> 14 is a flowchart showing an example of processing executed by the route search device 2000 in the embodiment 2. The acquisition unit 2020 in the embodiment 2 acquires the vehicle information 60 and the map information 70 by the same means as in the embodiment 1 (S402). The MOMAPF solution-finding unit 2040 initializes a plurality of utility functions having different configurations (S404).

[0102] Steps S406 to S414 are repeatedly executed until a predefined termination condition is satisfied. The MOMAPF solution-finding unit 2040 executes the MOMAPF solver (S406). In the first iteration, the MOMAPF solver is executed for each of the multiple utility functions initialized in step S404. On the other hand, in the second and subsequent iterations, the MOMAPF solver is executed for the utility function generated in the previous step S412.

[0103] The candidate providing unit 2060 provides two or more candidates for the route set 40 (S408) and acquires a selection from the user (S410). The preference eliciting unit 2080 generates a new utility function based on the acquired selection (S412).

[0104] The preference elicitation unit 2080 checks whether the end condition is satisfied (S414). If the end condition is satisfied (S414: YES), the route search device 2000 outputs the route set 40 that is the user's latest selection (S416).

[0105] On the other hand, if the termination condition is not satisfied (S414: NO), the MOMAPF solution finding unit 2040 executes the MOMAPF solver using the new utility function (S406).

[0106] <Initialization of utility function: S404> The MOMAPF solution finding unit 2040 initializes a plurality of utility functions (S404). In this step, the MOMAPF solution finding unit 2040 generates a plurality of utility functions having different configurations. Assume that the utility functions are defined by the above formula (7), and two utility functions are generated in the initialization step. In this case, the MOMAPF solution finding unit 2040 can generate two utility functions, u_1(P) with the configuration of "w_1=a, w_2=b, w_3=c", and u_2(P) with the configuration of "w_1=d, w_2=e, w_3=f", where the values ​​of a, b, c, d, e, and f are real numbers equal to or greater than 0, and a+b+c=1, and d+e+f=1.

[0107] There are various ways to initialize the utility function. In some implementations, the utility function is generated in a random way. For example, the weights for each objective are determined randomly.

[0108] <Execution of MOMAPF Solver: S406> The MOMAPF solving unit 2040 executes the MOMAPF solver to generate candidates for the path set 40 (S406). In the first iteration (i.e., immediately after the initialization of the utility function), the MOMAPF solving unit 2040 executes the MOMAPF solver for each of the plurality of utility functions generated in the initialization step. When executing the MOMAPF solver using a specific utility function, this utility function is used to evaluate the candidate paths in the MOMAPF solver.

[0109] In subsequent iterations, the MOMAPF solver is executed using the new utility function generated in the most recent step 412. Therefore, the candidate paths are evaluated using the new utility function.

[0110] Note that since solving multiple MOMAPF problems can be time-consuming, the user may not want to wait for multiple executions of the MOMAPF solver. Therefore, in some implementations, after acquiring the vehicle information 60 and the map information 70, the route search device can calculate the solution to the MOMAPF problem for each of the possible utility functions that can be proposed to the user without synchronizing with the elicitation of the user's preferences. By doing so, the solutions to the MOMAPF problems can be prepared in advance for each of the possible utility functions.

[0111] Therefore, when the MOMAPF solver is run with a new utility function, it can first determine whether a solution corresponding to the new utility function is already prepared. If a solution is prepared, the MOMAPF solver provides the prepared solution by retrieving it from the storage device in which the prepared solution is stored, without solving the MOMAPF problem at that time. On the other hand, if a solution is not yet prepared, the MOMAPF solver solves the MAPF problem using the new utility function and provides the solution.

[0112] <Providing a set of candidate routes: S408> The candidate providing unit 2060 provides multiple candidates for the path set 40 generated using different utility functions (S408). In the first iteration, the MOMAPF solving unit 2040 executes the MOMAPF solver using utility functions with different configurations, thereby obtaining multiple candidates for the path set 40. The candidate providing unit 2060 can provide these multiple candidates to the user so that the user can compare them with each other.

[0113] In the second and subsequent iterations, the MOMAPF solver 2040 runs the MOMAPF solver using the new utility function generated in the most recent step 412, thereby obtaining new candidates for the path set 40. The multiple candidates for the path set 40 to be provided to the user are then modified by replacing the candidates for the path set 40 that were not selected by the user in the previous iteration with the new candidates for the path set 40 generated in the current iteration. In this way, the candidate providing unit 2060 provides the new candidates for the path set 40 generated in the current iteration along with the candidates for the path set 40 selected in the previous iteration to the user, so that the user can compare the new candidates with the previously selected candidates.

[0114] The candidate providing unit 2060 preferably visually provides multiple candidates of the path set 40 so that the user can easily compare them with each other. FIG. 15 shows the visual presentation of multiple candidates of the path set 40. The window 110 is a window that can be displayed on a display device that can be viewed by the user, for example, a display device such as the user's mobile device or PC. In FIG. 15, the utility function is defined by Equation (7), which is a weighted sum of efficiency, safety, and smoothness.

[0115] The window 110 visually shows two candidates for the route set 40. The candidate on the left is generated using a utility function with the weights of efficiency (EF), safety (SA), and smoothness (SM) being a1, b1, and c1, respectively. The candidate on the right is generated using a utility function with the weights of efficiency (EF), safety (SA), and smoothness (SM) being a2, b2, and c2, respectively. The window 110 also displays the total travel time (the efficiency of the route set 40), the safety degree, and the smoothness degree, and the user can select one of the candidates for the route set 40 while taking these values ​​into consideration.

[0116] The input interface 120 includes two buttons, the left button is used to select configuration 1 and the right button is used to select configuration 2. The user can select any of the candidates in the path set 40 by pressing the corresponding button.

[0117] <Get user selection: S410> The preference elicitation unit 2080 acquires the user's selection (S410). There are various methods for acquiring which option the user selected. For example, in the case illustrated in FIG. 15, the preference elicitation unit 2080 acquires information indicating which button the user pressed.

[0118] <Generation of utility functions: S412> The preference elicitation unit 2080 generates a new utility function based on the user's selection of candidates in the route set 40. Specifically, the preference elicitation unit 2080 determines a new configuration of the utility function based on the user's selection of candidates in the route set 40, and generates a utility function of the determined configuration.

[0119] There are various methods for determining the configuration of the utility function based on the user's selection of the candidates of the route set 40. In some implementations, the preference elicitation unit 2080 determines the configuration of the utility function using Bayesian optimization. For example, Bayesian optimization by Gaussian process disclosed in Non-Patent Document 3 or Non-Patent Document 4 may be used. More precisely, the Gaussian probit model (Non-Patent Document 3 and Non-Patent Document 4) can be used for priority learning. In this case, the preference elicitation unit 2080 obtains the configuration of the utility function used in generating the candidates of the route set 40 selected by the user in step S410 of the current iteration, and performs Bayesian optimization by Gaussian process using the obtained configuration of the utility function as an input. Then, the preference elicitation unit 2080 obtains a new configuration of the utility function as an output of the Bayesian optimization, and generates a new utility function using the obtained new configuration. In Bayesian optimization by Gaussian process, the Matern kernel is commonly used. However, any kind of kernel may be used by the preference elicitation unit 2080. Also, a commonly used acquisition function is the Upper Confidence Bound.

[0120] <End of preference inducement: S414> When the termination condition is satisfied, the route search device 2000 outputs the route set 40. There are various conditions that can be included in the termination condition. For example, the termination condition may include a condition that "the number of iterations reaches a predefined threshold value." In this case, the route search device 2000 outputs the route set 40 when step S414 exceeds a predefined number of times.

[0121] Alternatively or in addition, the termination condition may include a condition that "the generative model reaches convergence." Note that there are various known methods for determining whether the generative model reaches convergence, and one of these methods may be used to determine whether the generative model reaches convergence.

[0122] <Result output> After the termination condition is satisfied (S414: YES), the route search device 2000 outputs output information indicating candidates for the route set 40 that are the user's latest options as the route set 40. The method of outputting the output information has already been described in the first embodiment.

[0123] Although the present disclosure has been described with reference to the embodiment, the present disclosure is not limited to the above-mentioned embodiment. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

[0124] The program in the present disclosure includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disk or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0125] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes. <Additional Notes> (Appendix 1) A route search device, comprising: At least one processor; A memory for storing instructions, The at least one processor executes the instructions to: Acquiring vehicle information and map information, the vehicle information indicating a pair of a start position and a target position for each of a plurality of vehicles, and the map information indicating a map of a space in which the vehicles move; determining a route set including routes for each of the vehicles using the vehicle information and the map information, the routes in the route set being configured to be non-conflicting with each other; A route search device in which the determination of the route set includes running a route planning algorithm to generate the routes for each of the vehicles, the route planning algorithm evaluating the routes based on a utility score for the route, the utility score being a scalar value representing the degree to which multiple objectives are optimized by the route. (Appendix 2) the determining of the path set comprises executing a modified version of a conflict-based search algorithm, in which a low-level search is performed by executing the path planning algorithm implemented by a metaheuristic algorithm; 2. A route search device as described in claim 1. (Appendix 3) the path planning algorithm calculates the utility score for the target path using a utility function; The utility function is defined as a weighted sum of a number of objective terms, each of which represents a degree to which the objective corresponding to that objective is optimized by the route. 3. The route search device according to claim 1 or 2. (Appendix 4) The plurality of objectives include efficiency of the route, safety of the route, smoothness of the route, or two or more thereof; 4. A route search device as described in claim 3. (Appendix 5) the path planning algorithm calculates the utility score for the target path using a utility function; The determining of the set of paths comprises: providing a plurality of candidate sets of routes to a user in a selectable manner; acquiring information indicating the candidates of the route set selected by the user; generating a new utility function based on the selected candidates of the path set; determining new candidate paths for the set of paths using the new utility function; replacing one of the plurality of candidates of the set of routes to be provided to the user with the new candidate of the set of routes; The route search device according to any one of Supplementary Note 1 to Supplementary Note 4, further comprising: repeatedly executing the above until a termination condition is satisfied. (Appendix 6) The generation of the new utility function comprises: performing a Bayesian optimization using a Gaussian process that uses as input the configuration of the utility function used to generate the candidate set of paths last selected by the user, thereby obtaining a new configuration of the utility function; generating the new utility function using the obtained new configuration; and 6. The route search device of claim 5, further comprising: (Appendix 7) acquiring vehicle information and map information, the vehicle information indicating a pair of a start position and a destination position for each of a plurality of vehicles, and the map information indicating a map of a space in which the vehicles are to move; determining a route set including routes for each of the vehicles using the vehicle information and the map information, the routes in the route set being non-conflicting with each other; determining the set of routes includes running a route planning algorithm to generate the routes for each of the vehicles, the route planning algorithm evaluating the routes based on a utility score for the route, the utility score being a scalar value representing the degree to which a plurality of objectives are optimized by the route; A computer implemented control method. (Appendix 8) the determining of the path set includes executing a modified version of a conflict-based search algorithm that performs a low-level search by executing the path planning algorithm implemented by a metaheuristic algorithm; 8. The control method according to claim 7. (Appendix 9) the path planning algorithm calculates the utility score for the target path using a utility function; The utility function is defined as a weighted sum of a number of objective terms, each of which represents a degree to which the objective corresponding to that objective is optimized by the route. 9. The control method according to claim 7 or 8. (Appendix 10) The plurality of objectives include efficiency of the route, safety of the route, smoothness of the route, or two or more thereof; 10. The control method according to claim 9. (Appendix 11) the path planning algorithm calculates the utility score for the target path using a utility function; The determining of the set of paths comprises: providing a plurality of candidate sets of routes to a user in a selectable manner; acquiring information indicating the candidates of the route set selected by the user; generating a new utility function based on the selected candidates of the path set; determining new candidate paths for the set of paths using the new utility function; replacing one of the plurality of candidates of the set of routes to be provided to the user with the new candidate of the set of routes; 11. The control method according to any one of claims 7 to 10, further comprising repeatedly executing the above until a termination condition is satisfied. (Appendix 12) The generation of the new utility function comprises: performing a Bayesian optimization with a Gaussian process using as input the configuration of the utility function used to generate the candidate set of paths last selected by the user, thereby obtaining a new configuration of the utility function; generating the new utility function using the obtained new configuration; The control method of claim 11, further comprising: (Appendix 13) On the computer, acquiring vehicle information and map information, the vehicle information indicating a pair of a start position and a target position for each of a plurality of vehicles, and the map information indicating a map of a space in which the vehicles are to move; determining a route set including routes for each of the vehicles using the vehicle information and the map information, the routes in the route set being non-conflicting with each other; determining the set of routes includes running a route planning algorithm to generate the routes for each of the vehicles, the route planning algorithm evaluating the routes based on a utility score for the route, the utility score being a scalar value representing the degree to which a plurality of objectives are achieved by the route; A non-transitory computer-readable storage medium for storing a program. (Appendix 14) said determining said path set comprises executing a modified version of a conflict-based search algorithm, in which a low-level search is performed by executing said path planning algorithm implemented by a metaheuristic algorithm; 14. A storage medium as described in claim 13. (Appendix 15) the path planning algorithm calculates the utility score for the target path using a utility function; The utility function is defined as a weighted sum of a number of objective terms, each of which represents a degree to which the objective corresponding to that objective is optimized by the route. 15. A storage medium according to claim 13 or 14. (Appendix 16) The plurality of objectives include efficiency of the route, safety of the route, smoothness of the route, or two or more thereof; 16. The storage medium of claim 15. (Appendix 17) the path planning algorithm calculates the utility score for the target path using a utility function; The determining of the set of paths comprises: providing a plurality of candidate sets of routes to a user in a selectable manner; acquiring information indicating the candidates of the route set selected by the user; generating a new utility function based on the selected candidates of the path set; determining new candidate paths for the set of paths using the new utility function; replacing one of the plurality of candidates of the set of routes to be provided to the user with the new candidate of the set of routes; 17. The storage medium of claim 13, further comprising: repeatedly executing the above-mentioned step until a termination condition is satisfied. (Appendix 18) The generation of the new utility function comprises: performing a Bayesian optimization with a Gaussian process using as input the configuration of the utility function used to generate the candidate set of paths last selected by the user, thereby obtaining a new configuration of the utility function; generating the new utility function using the obtained new configuration; 18. The storage medium of claim 17, further comprising:

[0126] This application claims the benefit of priority based on Japanese Patent Application No. 2021-198987, filed on December 8, 2021, the disclosure of which is incorporated by reference in its entirety into this specification. [Explanation of symbols]

[0127] 10 Vehicle assembly 20 Vehicles 30 Entities 40 Route collection 50 routes 60 Vehicle Information 70 Map Information 80 candidate routes 90 positions 100 waypoints 110 Window 120 Input Interface 1000 Computers 1020 Bus 1040 Processor 1060 Memory 1080 Storage Device 1100 Input / Output Interface 1120 Network Interface 2000 Route search device 2020 Acquisition Department 2040 MOMAPF solver 2060 Candidate Providing Department 2080 Taste Inducement Department

Claims

1. A route search device, comprising: At least one processor; A memory for storing instructions, The at least one processor executes the instructions to: Acquiring vehicle information and map information, the vehicle information indicating a pair of a start position and a target position for each of a plurality of vehicles, and the map information indicating a map of a space in which the vehicles move; determining a route set including routes for each of the vehicles using the vehicle information and the map information, the routes in the route set being configured to be non-conflicting with each other; A route search device in which the determination of the route set includes running a route planning algorithm to generate the routes for each of the vehicles, the route planning algorithm evaluating the routes based on a utility score for the route, the utility score being a scalar value representing the degree to which multiple objectives are optimized by the route.

2. the determining of the path set comprises executing a modified version of a conflict-based search algorithm, in which a low-level search is performed by executing the path planning algorithm implemented by a metaheuristic algorithm; The route search device according to claim 1 .

3. the path planning algorithm calculates the utility score for the target path using a utility function; The utility function is defined as a weighted sum of a number of objective terms, each of which represents a degree to which the objective corresponding to that objective is optimized by the route. The route search device according to claim 1 or 2.

4. The plurality of objectives include efficiency of the route, safety of the route, smoothness of the route, or two or more thereof; The route search device according to claim 3.

5. the path planning algorithm calculates the utility score for the target path using a utility function; The determining of the set of paths comprises: providing a plurality of candidate sets of routes to a user in a selectable manner; acquiring information indicating the candidates of the route set selected by the user; generating a new utility function based on the selected candidates of the path set; determining new candidate paths for the set of paths using the new utility function; replacing one of the plurality of candidates of the set of routes to be provided to the user with the new candidate of the set of routes; The route search device according to claim 1 , further comprising: repeatedly executing the above steps until a termination condition is satisfied.

6. The generation of the new utility function comprises: performing a Bayesian optimization with a Gaussian process using as input the configuration of the utility function used to generate the candidate set of paths last selected by the user, thereby obtaining a new configuration of the utility function; generating the new utility function using the obtained new configuration; and The route search device according to claim 5 , further comprising:

7. acquiring vehicle information and map information, the vehicle information indicating a pair of a start position and a target position for each of a plurality of vehicles, and the map information indicating a map of a space in which the vehicles are to move; determining a route set including routes for each of the vehicles using the vehicle information and the map information, the routes in the route set being non-conflicting with each other; determining the set of routes includes running a route planning algorithm to generate the routes for each of the vehicles, the route planning algorithm evaluating the routes based on a utility score for the route, the utility score being a scalar value representing the degree to which a plurality of objectives are optimized by the route; A computer implemented control method.

8. the determining of the path set includes executing a modified version of a conflict-based search algorithm that performs a low-level search by executing the path planning algorithm implemented by a metaheuristic algorithm; The control method according to claim 7.

9. the path planning algorithm calculates the utility score for the target path using a utility function; The utility function is defined as a weighted sum of a number of objective terms, each of which represents a degree to which the objective corresponding to that objective is optimized by the route. The control method according to claim 7 or 8.

10. The plurality of objectives include efficiency of the route, safety of the route, smoothness of the route, or two or more thereof; The control method according to claim 9.

11. the path planning algorithm calculates the utility score for the target path using a utility function; The determining of the set of paths comprises: providing a plurality of candidate sets of routes to a user in a selectable manner; acquiring information indicating the candidates of the route set selected by the user; generating a new utility function based on the selected candidates of the path set; determining new candidate paths for the set of paths using the new utility function; replacing one of the plurality of candidates of the set of routes to be provided to the user with the new candidate of the set of routes; The control method according to claim 7 , further comprising repeatedly executing the above steps until a termination condition is satisfied.

12. The generation of the new utility function comprises: performing a Bayesian optimization with a Gaussian process using as input the configuration of the utility function used to generate the candidate set of paths last selected by the user, thereby obtaining a new configuration of the utility function; generating the new utility function using the obtained new configuration; The control method of claim 11 , further comprising:

13. On the computer, acquiring vehicle information and map information, the vehicle information indicating a pair of a start position and a target position for each of a plurality of vehicles, and the map information indicating a map of a space in which the vehicles are to move; determining a route set including routes for each of the vehicles using the vehicle information and the map information, the routes in the route set being non-conflicting with each other; determining the set of routes includes running a route planning algorithm to generate the routes for each of the vehicles, the route planning algorithm evaluating the routes based on a utility score for the route, the utility score being a scalar value representing the degree to which a plurality of objectives are achieved by the route; A non-transitory computer-readable storage medium for storing a program.

14. said determining said path set comprises executing a modified version of a conflict-based search algorithm, in which a low-level search is performed by executing said path planning algorithm implemented by a metaheuristic algorithm; The storage medium according to claim 13.

15. the path planning algorithm calculates the utility score for the target path using a utility function; The utility function is defined as a weighted sum of a number of objective terms, each of which represents a degree to which the objective corresponding to that objective is optimized by the route.

15. A storage medium according to claim 13 or claim 14.

16. The plurality of objectives include efficiency of the route, safety of the route, smoothness of the route, or two or more thereof; 16. The storage medium of claim 15.

17. the path planning algorithm calculates the utility score for the target path using a utility function; The determining of the set of paths comprises: providing a plurality of candidate sets of routes to a user in a selectable manner; acquiring information indicating the candidates of the route set selected by the user; generating a new utility function based on the selected candidates of the path set; determining new candidate paths for the set of paths using the new utility function; replacing one of the plurality of candidates of the set of routes to be provided to the user with the new candidate of the set of routes; The storage medium according to claim 13 , further comprising: repeatedly executing the above steps until a termination condition is satisfied.

18. The generation of the new utility function comprises: performing a Bayesian optimization with a Gaussian process using as input the configuration of the utility function used to generate the candidate set of paths last selected by the user, thereby obtaining a new configuration of the utility function; generating the new utility function using the obtained new configuration; The storage medium of claim 17 further comprising:

Citation Information

Patent Citations

  • Intelligent recommendation method for riding route of shared bicycle

    CN113063431A

  • Route searching device for vehicle

    JP1993134601A