Map generation system, information processing apparatus, and map generation method

Abstract

To generate an environment map including track data related to the shape of a track on which a movable body travels even when the track is not present in a detection range of a peripheral environment sensor, or when the track is present in the detection range of the peripheral environment sensor but detection is difficult.SOLUTION: A map generation system has: a SLAM processing unit 4 that, on the basis of data of a peripheral environment sensor 2, an environment map showing an environment around a track and a sensor pose that is the position and / or posture of the peripheral environment sensor 2; a relative coordinate data output unit 6 that outputs the relative coordinates between peripheral environment sensor coordinates representing the position of the peripheral environment sensor 2 and reference coordinates defined with respect to the position of a component of the movable body; and a track data generation unit 5 that generates track data representing the shape of the track displayed on the environment map on the basis of the relative coordinates output from the relative coordinate data output unit. The track data generation unit 5 calculates the locus of the reference coordinates displayed on the environment map and generates the track data on the basis of the calculated locus.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technique for generating a map including information related to the track, which is the travel path of a moving object, in a track transportation system in which the moving object runs on a predetermined track. [Background technology]

[0002] For example, in a track transportation system in which transportation vehicles (hereinafter simply referred to as "vehicles") run on a predetermined track, such as a railway or monorail, if various obstacles such as a person, animal, other moving object, fallen tree, or falling rock suddenly appear on or near the track along which the vehicle runs, the traveling vehicle cannot avoid the obstacle by steering, and must instead decelerate or stop to prevent a collision with the obstacle. Therefore, detecting obstacles on or near the track is extremely important for ensuring the safety and operational efficiency of the track transportation system.

[0003] One of the main methods for detecting obstacles on or near the track is for a moving vehicle to constantly monitor its direction of travel, i.e., ahead. Conventionally, when manned operation was the norm, such ahead monitoring was performed solely by the driver's visual inspection. However, in recent years, in order to operate trains more safely and efficiently, various technologies have been proposed for monitoring ahead using cameras mounted on the vehicle, various sensors such as LiDAR (Light Detection and Ranging) (hereinafter sometimes collectively referred to as "surrounding environment sensors"), and for detecting obstacles on the track using these sensors (for example, Patent Documents 1 to 3). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-023017 [Patent Document 2] Patent No. 7216699 [Patent Document 3] Patent No. 7412665 Summary of the Invention [Problem to be solved by the invention]

[0005] However, if only the surrounding environment sensor is used to detect obstacles, it is conceivable that it will detect obstacles not only on and near the track ahead, but also in other areas. In this case, if it is not possible to distinguish between obstacles on and near the track ahead and obstacles in other areas, for example, the surrounding environment sensor may detect a person walking on a public road along the track, causing the vehicle to unnecessarily slow down or stop. Therefore, it is conceivable to, for example, recognize the shape of the track and, based on that shape, detect only obstacles on and near the track.

[0006] As a method for recognizing the shape of the trajectory ahead of a vehicle, there is a method for recognizing the shape of the trajectory contained in data obtained from a surrounding environment sensor such as a camera, as described in Patent Document 1, for example. However, this method requires that the trajectory be within the detection range of the surrounding environment sensor and that the trajectory be detectable. In other words, when performing recognition using a camera, for example, there may be a situation where an obstacle exists beyond a hill, making the trajectory around the obstacle a blind spot, or where it is difficult to recognize the trajectory at night or due to thick fog, and even if the obstacle can be recognized, the shape of the trajectory around it cannot be recognized.

[0007] Another possible method for recognizing the shape of the trajectory ahead of the vehicle is to create map data including the trajectory shape in advance, and then estimate the position and orientation on the map while the vehicle is traveling to determine the shape of the trajectory ahead of the vehicle. This method makes it possible to recognize the shape of the trajectory even when the trajectory ahead of the vehicle cannot be recognized by the surrounding environment sensor. However, when using this method, it is necessary to create map data including the trajectory shape in advance.

[0008] One possible method for creating map data including trajectory shapes is to estimate the current position and orientation of a traveling vehicle on a map, and at the same time, use a surrounding environment sensor to recognize the trajectory shape in the sensor data, thereby adding trajectory data to the map, as in the lane estimation method described in Patent Document 2. However, this method, like Patent Document 1, requires recognition of the trajectory shape from the output results of the surrounding environment sensor, and there is still a risk that trajectory data will be lost if the trajectory is in a blind spot of the surrounding environment sensor or if trajectory recognition fails.

[0009] The present invention has been made in consideration of the above-mentioned problems, and aims to provide a technology that can generate an environmental map including trajectory data regarding the shape of a trajectory even when the trajectory on which a moving body is traveling is not within the detection range of a surrounding environment sensor, or when the trajectory is within the detection range of a surrounding environment sensor but is difficult to detect. [Means for solving the problem]

[0010] A map generation system according to the present invention generates an environmental map including trajectory data relating to the shape of a trajectory traveled by a mobile object. The system includes: an environmental sensor mounted on the mobile object and capable of acquiring environmental information about the surroundings of the mobile object; and a computer connected to the environmental sensor for data communication and including at least a processor and a storage device. The computer includes a SLAM processing unit that estimates an environmental map representing the environment around the trajectory and a sensor pose representing the position and / or attitude of the environmental sensor to be displayed on the environmental map based on the sensor data acquired by the environmental sensor; a relative coordinate data output unit that outputs relative coordinates between the environmental sensor coordinates representing the position of the environmental sensor and reference coordinates defined based on the positions of components of the mobile object; and a trajectory data generation unit that generates trajectory data representing the shape of the trajectory to be displayed on the environmental map based on the relative coordinates output by the relative coordinate data output unit and the output of the SLAM processing unit. The trajectory data generation unit calculates a trajectory of the reference coordinates to be displayed on the environmental map and generates the trajectory data based on the calculated trajectory.

[0011] Other problems and solutions disclosed in the present application will be made clear in the detailed description and drawings. [Effects of the Invention]

[0012] According to the present invention, even when the trajectory on which a moving body is traveling does not exist within the detection range of a surrounding environment sensor, or when the trajectory exists within the detection range of a surrounding environment sensor but is difficult to detect, an environmental map can be generated that includes trajectory data regarding the shape of the trajectory. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a map generation system. [Figure 2] 10A and 10B are diagrams illustrating examples of setting surrounding environment sensor coordinates and reference coordinates. [Figure 3] FIG. 10 is an explanatory diagram of various coordinates in the map generation system according to the second embodiment. [Figure 4] FIG. 10 is an explanatory diagram of a smoothing process executed by the map generation system according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] In the following description, an "interface apparatus" may refer to one or more interface devices. The one or more interface devices may be at least one of the following: One or more I / O (Input / Output) interface devices. The I / O (Input / Output) interface devices are interface devices for at least one of the I / O device and a remote display computer. The I / O interface device for the display computer may be a communications interface device. The at least one I / O device may be a user interface device, for example, either an input interface device such as a keyboard and pointing device, or an output interface device such as a display device. One or more communication interface devices. The one or more communication interface devices may be one or more homogeneous communication interface devices (e.g., one or more NICs (Network Interface Cards)) or two or more heterogeneous communication interface devices (e.g., an NIC and an HBA (Host Bus Adapter)).

[0015] In the following description, "memory" refers to one or more memory devices, which are an example of one or more storage devices, and may typically be a primary storage device. At least one memory device in the memory may be a volatile memory device or a non-volatile memory device.

[0016] In the following description, an "auxiliary storage device" may refer to one or more auxiliary storage devices, which are an example of one or more storage devices. The auxiliary storage device may typically be a non-volatile storage device (e.g., a persistent storage device), and specifically may be, for example, a hard disk drive (HDD), a solid state drive (SSD), a non-volatile memory express (NVME) drive, or a storage class memory (SCM).

[0017] In the following description, the term "storage device" may refer to at least one memory, including a memory and an auxiliary storage device.

[0018] Furthermore, in the following description, a "processor" may refer to one or more processor devices. The at least one processor device may typically be a microprocessor device such as a CPU (Central Processing Unit), but may also include other types of processor devices such as a GPU (Graphics Processing Unit). The at least one processor device may be single-core or multi-core. The at least one processor device may also be a processor core. The at least one processor device may also be a broader processor device such as a circuit that is a collection of gate arrays written in a hardware description language that performs some or all of the processing (e.g., an FPGA (Field-Programmable Gate Array), a CPLD (Complex Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit)).

[0019] Furthermore, in the following description, functions may be described using the expression "xxx unit." However, the functions may be realized by one or more computer programs (hereinafter simply referred to as "programs") executed by a processor, by one or more hardware circuits (e.g., FPGAs or ASICs), or by a combination thereof. When a function is realized by a program executed by a processor, the specified processing is performed using a storage device and / or an interface device, etc., as appropriate, and therefore the function may be considered to be at least a part of the processor. Processing described using a function as the subject may be processing performed by a processor or a device having the processor. A program may be installed from a program source. The program source may be, for example, a computer that distributes the program or a computer-readable recording medium (e.g., a non-transitory recording medium). The description of each function is merely an example; multiple functions may be combined into one function, or one function may be divided into multiple functions.

[0020] In the following description, a process may be described using a "program" as the subject, but the process described using a program as the subject may also be a process performed by a processor or a device having that processor. Two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0021] Furthermore, in the following description, a "map generation system" or an "on-vehicle device" may be a system (e.g., an on-premise system) configured with one or more physical computers, or may be configured to include a system (e.g., a cloud computing system) implemented on a group of physical computing resources (e.g., a cloud infrastructure). When a map generation system or an on-vehicle device "displays" display information, it may mean that the display information is displayed on a display device possessed by the computer, or that the computer transmits the display information to a display computer (in the latter case, the display information is displayed by the display computer).

[0022] Various embodiments will now be described in detail with reference to the drawings.

[0023] In the following description, the same or similar components will be designated by common reference numerals, and redundant description may be omitted.

[0024] Furthermore, when there are multiple elements having the same or similar functions, the multiple elements may be described by using the same reference numeral with different subscripts to distinguish between them. On the other hand, when there is no need to distinguish between the multiple elements, the subscripts may be omitted. [Example]

[0025] <Example of map generation system configuration> First, a configuration example of a map generation system 1 according to a first embodiment (and second and third embodiments described later) will be described with reference to Fig. 1. The first embodiment is an example for explaining the basic operation of the map generation system 1.

[0026] FIG. 1 is a diagram illustrating an example of the configuration of a map generation system 1. As shown in FIG.

[0027] The map generation system 1 is a computer system capable of generating a map including information related to the track, which is the route along which a moving object travels, in a track transportation system in which the moving object travels on a predetermined track, and is realized by at least one surrounding environment sensor 2 and at least one vehicle-mounted computer device (hereinafter also referred to as "vehicle-mounted device 3"), as illustrated in Figure 1.

[0028] The surrounding environment sensor 2 and the in-vehicle device 3 are connected to be able to communicate data via an appropriate wired or wireless communication network (not shown), and as a whole constitute a map generation system 1. The surrounding environment sensor 2 and the in-vehicle device 3 are connected to the communication network via wires via well-known communication devices (not shown), but may also be connected wirelessly.

[0029] Furthermore, user terminals (not shown), such as laptop PCs, tablets, smartphones, etc., owned by users of the map generation system 1, such as operators of a rail transport system such as a railway or monorail in which the map generation system 1 has been installed, and drivers of moving bodies related to the rail transport system (for example, trains if the rail transport system is a railway), may be connected to the surrounding environment sensors 2 and on-board devices 3 constituting the map generation system 1 so as to enable mutual data communication via an appropriate communication network such as the Internet or a dedicated line. In this case, each user terminal and the communication network may be connected wirelessly or by wire. In this case, the map generation system 1 may further include a user terminal as a component.

[0030] Furthermore, other computer devices, server devices, etc. (hereinafter also referred to as "other devices") may be connected to the surrounding environment sensor 2 and the in-vehicle device 3 constituting this map generation system 1 so as to be able to communicate data via an appropriate communication network (not shown) such as the Internet or a dedicated line. In this case, the other devices and the communication network may be connected by wire or wirelessly via well-known communication equipment (not shown). In this case, the map generation system 1 may further include the other devices as components.

[0031] As described above, in this embodiment, the map generation system 1 is described as being realized by at least one surrounding environment sensor 2 and at least one in-vehicle device 3. However, for example, the map generation system 1 may be configured to include a plurality of surrounding environment sensors 2 and a plurality of in-vehicle devices 3.

[0032] In addition, in this embodiment, as illustrated in Fig. 1, the surrounding environment sensor 2 and the on-board device 3 are described as separate devices. However, the surrounding environment sensor 2 and the on-board device 3 that constitute the map generation system 1 may be integrally configured as the same device. In this case, for example, the surrounding environment sensor 2 may be configured to include some or all of the functions performed by the on-board device 3. Furthermore, for example, the on-board device 3 may be configured to include some or all of the functions performed by the surrounding environment sensor 2.

[0033] (Example of hardware configuration) Next, an example of the hardware configuration of the map generation system 1 will be described with reference to FIG.

[0034] As described above, the map generation system 1 includes at least one surrounding environment sensor 2 and at least one in-vehicle device 3.

[0035] The surrounding environment sensor 2 is a sensor device mounted on a moving body in a rail transportation system in which the map generation system 1 is installed, senses the conditions around the moving body (particularly in front of the moving body), and transmits the sensing data to the on-board device 3. Specific examples of the surrounding environment sensor 2 include various sensor devices capable of acquiring the shape of the environment around the sensor, such as LiDAR (Light Detection and Ranging), cameras, and millimeter-wave radar. When a camera is used as the surrounding environment sensor 2, various cameras can be used, such as a monocular camera, a stereo camera, and an infrared camera. Note that a single moving body may be equipped with a single surrounding environment sensor 2, or multiple sensors may be equipped for redundancy. When multiple surrounding environment sensors 2 are mounted on a moving body, the surrounding environment sensor 2 may be composed of a single type of sensor device or a combination of multiple types of sensor devices.

[0036] For example, when the moving body equipped with the surrounding environment sensor 2 is a train and the train is moving forward, the surrounding environment sensor 2 installed in the leading car on the forward side is used.

[0037] The in-vehicle device 3 is realized by a computer having at least a storage device including a memory and an auxiliary storage device, an interface device including at least a communication interface, and a processor connected to them. In the in-vehicle device 3, the interface device may include an input interface and / or an output interface.

[0038] The following description will be given assuming that the vehicle-mounted device 3 is realized by a single vehicle-mounted computer device having one or more processors (not shown), one or more memories (not shown), one or more auxiliary storage devices (not shown), one or more communication interfaces (not shown), one or more input interfaces (not shown), one or more output interfaces (not shown), and wired or wireless communication lines connecting them.

[0039] The auxiliary storage device is an auxiliary storage device made up of a nonvolatile storage element such as a flash memory. Specific examples of this auxiliary storage device include a solid state drive (SSD) and a hard disk drive (HDD). The auxiliary storage device stores at least a map generation program (not shown). This map generation program is a computer program for implementing the functions required for the map generation system 1.

[0040] That is, by executing the map generation program by the processor, functions are realized that are performed by each functional unit of the in-vehicle device 3, such as the SLAM processing unit 4, trajectory data generation unit 5, and relative coordinate data output unit 6, which will be described later. In other words, by executing the map generation program by the processor, various processes, which will be described later, are performed by the in-vehicle device 3.

[0041] The map generation program is provided to the in-vehicle device 3 from various removable media such as a CD-ROM or a flash memory or via a network, and is stored in a non-volatile auxiliary storage device, which is a non-temporary storage medium. Therefore, it is preferable that the in-vehicle device 3 has an interface for reading data from the removable media.

[0042] The map generation program may also be installed from a program source. The program source may be, for example, a computer on which the program is distributed or a computer-readable recording medium. The map generation program may also be composed of a device driver, an operating system, various application programs located at higher levels than these, and a library that provides common functions to these programs. Furthermore, two or more programs may be realized as one map generation program, or one map generation program may be realized as two or more programs.

[0043] Memory is a primary storage device that is primarily made up of volatile memory elements such as RAM (Random Access Memory). Memory also includes ROM, which is made up of nonvolatile memory elements. ROM stores unchanging programs (e.g., BIOS). This memory temporarily stores data representing various information read from auxiliary storage devices and various data acquired via communication interfaces and / or input interfaces.

[0044] The processor is a processor device such as a CPU (Central Processing Unit) and various co-processors. The processor loads various computer programs, including a map generation program, into a memory and executes them, thereby performing overall control of the in-vehicle device 3 itself and also managing a control unit (described in detail later) that executes various types of arithmetic processing.

[0045] The interface device includes a communication interface that controls a communication unit described below, an input interface that controls an input unit described below, and an output interface that controls an output unit described below.

[0046] The communication interface is a network interface device that controls communication with the surrounding environment sensor 2, user terminals, other devices, etc., via a communication network in accordance with a predetermined protocol.

[0047] The input interface is an interface to which an input device such as a touch panel or a keyboard is connected and which accepts input from a user.

[0048] The output interface is an interface to which various display devices such as a liquid crystal display or a touch screen are connected as output devices, and outputs the results of program execution in a format that can be viewed by the user.

[0049] The in-vehicle device 3 may be an independent device or an embedded device.

[0050] (Example of function block) Next, an example of various functional blocks provided in the in-vehicle device 3 constituting the map generation system 1 will be described with reference to Fig. 1. Note that each block described below does not represent a hardware-based configuration, but represents a functional block.

[0051] The in-vehicle device 3 is configured to include at least the following functional blocks: a control unit (not shown) implemented mainly by the processor, a storage unit (not shown) implemented by the storage device, and a communication unit (not shown) implemented by the communication interface. The in-vehicle device 3 may also include a user interface unit (not shown) implemented by the input interface and / or output interface as a functional block.

[0052] The control unit executes various data processing operations based on the programs and data stored in the storage unit and the data acquired by the communication unit. The control unit also functions as an interface between the storage unit and the communication unit.

[0053] As shown in FIG. 1, the control unit has at least the following functional blocks: a SLAM processing unit 4, a trajectory data generating unit 5, and a relative coordinate data output unit 6.

[0054] The SLAM processing unit 4 executes SLAM processing (described in detail later).

[0055] The trajectory data generating unit 5 executes a process for generating trajectory data (described in detail later).

[0056] The relative coordinate data output unit 6 executes a process for outputting relative coordinate data (described in detail later).

[0057] The control unit is configured using a processor, and can realize these functional blocks by executing the map generation program described above. Note that instead of a processor, the control unit may be configured using a logic circuit such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The control unit may also be configured by combining a processor and a logic circuit.

[0058] The storage unit is configured using a storage device consisting of, for example, a memory and an auxiliary storage device, and stores programs that supply various processing commands to the control unit, and data representing various information used in the processing executed by the control unit.

[0059] The control unit can execute various processes by reading and writing the information from and to the storage unit.

[0060] The communication unit is responsible for communication processing with the surrounding environment sensor 2 and other devices via a communication network. The communication unit is configured using, for example, a NIC (Network Interface Card) or an HBA (Host Bus Adapter).

[0061] The user interface section is configured to include functional blocks of an input section and an output section.

[0062] The input unit is responsible for input-related processes, such as accepting input operations from the user, among other processes related to the user interface. The input unit is configured using input devices such as a touch panel or a keyboard, and detects various operations from the user.

[0063] The output unit is responsible for output-related processes such as displaying various screens on a display device, outputting audio, etc. The output unit is configured using various display devices such as a liquid crystal display, a touch screen, etc.

[0064] Note that the inclusion of an input unit and / or an output unit is not essential, for example, when remotely logging in to the in-vehicle device 3 from another external device such as a user terminal, when receiving input information from an external device via a communication interface, or when providing output information to an external device, etc. In this case, the in-vehicle device 3 may receive access from the external device via the communication unit using a predetermined protocol, for example.

[0065] That is, each component of the in-vehicle device 3 is realized by hardware including a processor, storage devices such as memory and auxiliary storage devices, wired or wireless communication lines and interface devices that connect them, and software that is stored in the storage devices and supplies processing instructions to the arithmetic unit (processor).

[0066] The above description of the functions of the map generation system 1 has been given assuming that each function of the in-vehicle device 3 constituting the map generation system 1 is implemented integrally by a single computer. However, each of these functions may be implemented by multiple interconnected computers and / or server devices. Furthermore, the in-vehicle device 3 may be configured to include a general-purpose computer such as a laptop PC with a web browser installed thereon, or may be configured to include a web server and various portable devices.

[0067] The on-board device 3 is a computer system configured on a single physical computer or on multiple logically or physically configured computers, and may operate on a virtual computer constructed on multiple physical computer resources. For example, functional units such as the SLAM processing unit 4, trajectory data generation unit 5, and relative coordinate data output unit 6 may each operate on a separate physical or logical computer, or multiple units may be combined to operate on a single physical or logical computer.

[0068] Furthermore, the above description of each function is merely an example, and multiple functions may be combined into one function, or one function may be divided into multiple functions.

[0069] Furthermore, the in-vehicle device 3 may have other functions in addition to the above-described functions. For example, the in-vehicle device 3 may be configured to include some or all of the functions of the surrounding environment sensor 2, as described above.

[0070] <Example of map generation system operation> Next, an example of the operation of the map generation system 1 will be described below based on the flow of an actual process.

[0071] First, the control unit of the map generation system 1 inputs, as parameters, the translation and rotation amounts from the coordinates of the surrounding environment sensor 2 to the reference coordinates defined using the components of the mobile body on which the surrounding environment sensor 2 is mounted, acquired via the communication unit or the input unit, to the relative coordinate data output unit 6. Note that the values ​​of these translation and rotation amounts are acquired, for example, by the user of the map generation system 1 performing an input operation.

[0072] When the parameters are input, the relative coordinate data output unit 6 calculates the relative coordinate Tsr, which is defined by the amount of translation and rotation from the coordinates of the surrounding environment sensor 2 to the reference coordinate, based on the parameters, and outputs it to the trajectory data generation unit 5.

[0073] Next, the user drives the mobile object along a desired trajectory for which a map is to be created, and performs an input operation to instruct the surrounding environment sensor 2 to periodically acquire surrounding environment sensor data S, which is data representing the status of the surrounding environment, etc. The control unit of the map generation system 1, which receives this user's input operation via the communication unit or input unit, transmits the instruction to the surrounding environment sensor 2. As a result, the surrounding environment sensor 2 acquires surrounding environment sensor data S={s_1, s_2, . . . , s_N} at time T={t_1, t_2, . . . , t_N}. Then, after the mobile object has completed its travel, the surrounding environment sensor 2 outputs the surrounding environment sensor data S to the SLAM processing unit 4.

[0074] The SLAM processing unit 4 generates map data M indicating the shapes of objects around the trajectory based on the surrounding environment sensor data S, using a general SLAM method described in, for example, Patent Document 3, and also generates sensor pose data Ps={ps_1, ps_2, ..., ps_N} indicating the position and orientation of the surrounding environment sensor 2 on the map data M at each time T.

[0075] Then, the SLAM processing unit 4 outputs the generated map data M and sensor pose data Ps to the trajectory data generating unit 5.

[0076] That is, when a mobile body equipped with a surrounding environment sensor 2 travels on a trajectory, the SLAM processing unit 4 estimates and outputs a map of the area around the trajectory and the sensor pose at each time based on the sensor data acquired by the surrounding environment sensor 2.

[0077] The trajectory data generation unit 5 generates reference coordinate pose data Pr={pr_1, pr_2, ..., pr_N} representing the position and posture on the map data M of the reference coordinates at each time, based on the sensor pose data Ps received from the SLAM processing unit 4 and the relative coordinates Tsr received from the relative coordinate data output unit 6.

[0078] Here, an example of setting the position coordinates (hereinafter also referred to as "surrounding environment sensor coordinates") and reference coordinates that indicate the position of the surrounding environment sensor 2 mounted on the moving body will be described with reference to FIG.

[0079] FIG. 2 is a diagram showing an example of setting the surrounding environment sensor coordinates and the reference coordinates.

[0080] In FIG. 2, coordinates 11 are position coordinates of the surrounding environment sensor 2, and when the surrounding environment sensor 2 is a LiDAR, for example, they are reference coordinates of a point cloud output by the sensor.

[0081] Also, in Figure 2, coordinate 12 is a reference coordinate, and in the case of a railway vehicle, for example, it is considered that the coordinate is defined as the point on the axis of rotation connecting the car body 13 and the bogie 14 that intersects with a plane passing through the top surface of the track 15.

[0082] When the reference coordinates 12 are set as described above, the reference coordinate pose data Pr has its origin passing through the center of the track and each axis substantially coincides with the coordinates indicating the traveling direction and vertical direction of the track on the map data M. Therefore, according to the present invention, even when it is impossible or difficult to obtain information about the track position and the like from the surrounding environment sensor data S, for example, because the track is not within the detection range of the surrounding environment sensor 2 or there is snow on the track, it is possible to generate the track data accurately and reliably by using the reference coordinate pose data Pr as the track data.

[0083] In this way, the trajectory data generation unit 5 uses the relative coordinates from the surrounding environment sensor coordinates 11 to the reference coordinates 12 defined using parts on the moving body output from the relative coordinate data output unit 6 and the output of the SLAM processing unit 4 to determine the trajectory of the reference coordinates 12 on the map, and outputs the trajectory as trajectory data.

[0084] Although the present embodiment has been described with reference to an example in which the surrounding environment sensor 2 is a LiDAR, the surrounding environment sensor 2 may be any sensor that outputs data according to the shape and properties of surrounding objects, and the SLAM processing unit 4 may use the sensor data to simultaneously generate the pose of the surrounding environment sensor 2 and map data M of the trajectory surroundings. That is, as described above, the surrounding environment sensor 2 may be configured with, for example, a camera or various radars such as millimeter-wave radar.

[0085] Furthermore, the surrounding environment sensor 2 may be a receiver (GNSS receiver and / or beacon receiver) capable of sensing radio waves from various GNSS (Global Navigation Satellite System) satellites, including GPS (Global Positioning System) satellites, and beacons installed around the orbit, and the SLAM processing unit 4 may estimate only the pose of the surrounding environment sensor 2 at each time based on the received signal of the sensor.

[0086] According to the map generation system 1 of this embodiment, even in an environment where, for example, the area around the orbit is surrounded by objects with monotonous shapes and pose estimation using a camera or LiDAR is difficult, it is possible to generate orbit data as a pose in a general-purpose coordinate system such as latitude and longitude.

[0087] The map generation system 1 according to the first embodiment has been described above. [Example]

[0088] Next, a map generation system 1 according to a second embodiment will be described, focusing on the differences from the map generation system 1 according to the first embodiment.

[0089] As described above, in the map generation system 1 according to the first embodiment, the trajectory data generation unit 5 calculates the trajectory of the reference coordinates 12 on the map using the relative coordinates from the surrounding environment sensor coordinates 11 to the reference coordinates 12 defined using parts on the moving object, which are output from the relative coordinate data output unit 6, and the output of the SLAM processing unit 4, and outputs the trajectory as trajectory data. However, after calculating the reference coordinate pose data Pr, the trajectory data generation unit 5 may perform a smoothing process so that the reference coordinate pose data Pr is smoothly connected, and generate the smoothed pose data Prs obtained as a result of this smoothing process as trajectory data. Therefore, an example of the operation of the map generation system 1 when the trajectory data generation unit 5 performs such processing will be described below as a second embodiment.

[0090] (Smoothing process) FIG. 3 is an explanatory diagram of various coordinates in the map generation system 1 according to the second embodiment, and shows an example of an environment in which the smoothing process is useful in this embodiment.

[0091] For example, in the case of a vehicle traveling on a curved track 27, in the method shown in the first embodiment, the reference coordinates 22 are obtained based on the pose estimation results of the surrounding environment sensor coordinates 11. On the other hand, for example, if the ideal track data is defined by coordinates (hereinafter also referred to as "ideal track coordinates") 23 in which the midpoint of the top surface of the left and right tracks is the origin, the X axis is the traveling direction, i.e., the track tangent direction, and the Z axis is the direction perpendicular to the track surface, on the curve, displacement occurs between the bogie 25 and the car body 26 on which the sensor is installed, and this causes an error in the yaw direction between the reference coordinates 22 and the ideal track coordinates 23.

[0092] Therefore, in the map generation system 1 according to the second embodiment, in order to eliminate the error in the yaw direction, a smoothing process is performed by the trajectory data generation unit 5. An example of this smoothing process is shown in FIG.

[0093] In the map generation system 1 according to the second embodiment, the trajectory data generation unit 5 first calculates a displacement vector 34 having the origins of the reference coordinate pose data Pr_x(31) obtained at time x and the origin of the reference coordinate pose data Pr_x+1(32) obtained at time x+1 as its start and end points, respectively. Then, the trajectory data generation unit 5 calculates the amount of rotation of the reference coordinate pose data Pr_x(31) from the X axis to the displacement vector 34, and applies the amount of rotation to the reference coordinate pose data Pr_x(31) to calculate smoothed pose data Prs_x(33) corresponding to time x, and outputs the smoothed pose data Prs_x(33) as trajectory data.

[0094] In this way, according to the map generation system 1 of Example 2, it is possible to obtain the orbit shape with high accuracy even when the reference coordinate pose data Pr calculated based on the data of the surrounding environment sensor 2 has an error in the yaw direction with respect to the orbit shape at a curve, etc.

[0095] In this embodiment, the smoothing process executed by the trajectory data generation unit 5 has been described as representing a process of generating smoothed pose data Prs by rotating the reference coordinate pose data Pr. However, the smoothing process is not limited to such a process. For example, the trajectory data generation unit 5 may execute, as the smoothing process, a process of performing a translational transformation based on the reference coordinate pose data Pr at previous and subsequent times so that the origin position exists on a smooth curve.

[0096] The map generation system 1 according to the second embodiment has been described above. [Example]

[0097] Next, the map generation system 1 according to the third embodiment will be described, focusing on the differences from the map generation system 1 according to the first embodiment and / or the second embodiment.

[0098] In one embodiment, the reference coordinates may be defined based on a movable component, which is a component on a moving body whose position relative to the surrounding environment sensor 2 can change, and the relative coordinate data output unit 6 may have a function to output a relative coordinate Tsr from the coordinate of the surrounding environment sensor 2 to the reference coordinate 22. Therefore, an example of the operation of the map generation system 1 when the relative coordinate data output unit 6 has such a function will be described below as Example 3.

[0099] In the map generation system 1 according to the third embodiment, the movable components are, for example, wheels in the relative coordinate data output unit 6. In the map generation system 1 according to the third embodiment, the reference coordinates 22 are defined as the ground contact points of the wheels.

[0100] In the third embodiment, for example, when a mechanical part existing between the surrounding environment sensor coordinates 11 and the reference coordinates 22 is regarded as a link mechanism, the relative coordinate data output unit 6 may have link information such as link lengths related to the link mechanism, and may also have displacement sensors capable of measuring the amount of displacement of each of the movable parts such as rotary shafts and linear shafts. The map generation system 1 of the third embodiment having such a configuration can calculate and output a relative coordinate Tsr from the coordinates of the surrounding environment sensor 2 to the reference coordinates 22 based on the link information and the amount of displacement of the sensors.

[0101] Alternatively, in the third embodiment, the relative coordinate data output unit 6 may acquire the surrounding environment sensor data S, detect the track or structures such as sleepers attached to the track based on the surrounding environment sensor data S, and estimate and output the relative coordinate Tsr based on the detection results.

[0102] In either case, according to the third embodiment, unlike the first embodiment, even when the moving body vibrates greatly due to the suspension or the like, it is possible to accurately estimate the track shape.

[0103] In one embodiment, the SLAM processing unit 4 may store in advance preliminary map data relating to the area for which it is desired to create a map, and output the map data M and trajectory shape data based on that data. For example, while the method shown in the first embodiment can obtain highly accurate maps and trajectory data locally, there is a risk that distortions may occur globally due to the accumulation of errors. However, according to this embodiment, by providing a distortion-free map as preliminary map data, it is possible to obtain a highly accurate map that is globally distortion-free.

[0104] The map generation system 1 according to the third embodiment has been described above.

[0105] The above-described embodiments of the present invention can be summarized as follows.

[0106] (1) A map generation system 1 generates an environmental map including trajectory data related to the shape of a trajectory traveled by a mobile object. The system includes at least an environmental sensor 2 mounted on the mobile object and capable of acquiring environmental information about the surroundings of the mobile object, and a computer (on-board device 3) connected to the environmental sensor 2 for data communication and including at least a processor and a storage device. The computer (on-board device 3) includes a SLAM processing unit 4 that estimates an environmental map representing the environment surrounding the trajectory and a sensor pose representing the position and / or attitude of the environmental sensor 2 to be displayed on the environmental map based on the sensor data acquired by the environmental sensor 2, a relative coordinate data output unit 6 that outputs relative coordinates between the environmental sensor coordinates representing the position of the environmental sensor 2 and reference coordinates defined based on the positions of components of the mobile object, and a trajectory data generation unit 5 that generates trajectory data representing the shape of the trajectory to be displayed on the environmental map based on the relative coordinates output by the relative coordinate data output unit 6 and the output of the SLAM processing unit 4. The trajectory data generation unit 5 calculates a trajectory of the reference coordinates to be displayed on the environmental map and generates the trajectory data based on the calculated trajectory. As a result, the map generation system 1 can generate an environmental map including trajectory data relating to the shape of the trajectory even when the trajectory on which the mobile object is traveling is not within the detection range of the surrounding environment sensor 2, or when the trajectory is difficult to detect even though it is within the detection range of the surrounding environment sensor 2. As a result, the user of the map generation system 1 can robustly recognize the trajectory shape of a mobile object traveling on a trajectory, even when the mobile object does not have a sensor capable of directly recognizing the trajectory shape, or when the user has a sensor capable of recognizing the trajectory shape but the recognition of the trajectory shape from the sensor data is unstable.

[0107] (2) The surrounding environment sensor 2 is at least one sensor that outputs data according to the shape and / or properties of surrounding objects.

[0108] (3) The surrounding environment sensor 2 is at least one of a LiDAR (Light Detection and Ranging), a camera, and a laser.

[0109] (4) The surrounding environment sensor 2 is at least one of a GNSS (Global Navigation Satellite System) receiver and a beacon receiver.

[0110] (5) The trajectory data generating unit 5 calculates the pose history on the environmental map of the reference coordinates and performs a smoothing process on the pose history to generate trajectory data.

[0111] (6) The reference coordinates are defined based on movable components, which are components on a moving body whose relative position with respect to the surrounding environment sensor 2 can change, and the relative coordinate data output unit 6 outputs relative coordinates between the surrounding environment sensor coordinates and the reference coordinates.

[0112] (7) The relative coordinate data output unit 6 has a sensor that measures the amount of displacement of a moving part present on the moving body, and outputs relative coordinates between the surrounding environment sensor coordinates and the reference coordinates based on the output of the sensor.

[0113] (8) The relative coordinate data output unit 6 detects the track or structures around the track using data obtained from the surrounding environment sensor 2, and outputs relative coordinates between the surrounding environment sensor coordinates and the reference coordinates using the detection results.

[0114] (9) The SLAM processing unit 4 holds advance map data, which is information about the location where the map is to be generated.

[0115] The present invention is not limited to the above-described embodiments, and can be implemented using any components without departing from the spirit of the present invention.

[0116] Each of the above embodiments is merely an example, and the present invention is not limited to these embodiments as long as the features of the invention are not impaired. Furthermore, although various embodiments have been described above, the present invention is not limited to these embodiments, and not all of these embodiments are necessarily essential to the solution of the present invention. Other embodiments conceivable within the scope of the technical idea of ​​the present invention are also included within the scope of the present invention.

[0117] In the above figures, the control lines and information lines shown are those that are considered necessary for explanation, and do not necessarily show all the control lines and information lines that are necessary for implementation. For example, it can be assumed that in reality, almost all components are interconnected.

[0118] Furthermore, the above-described layout of the functional units of the map generation system 1 and the in-vehicle device 3 is merely an example. The layout of the functional units can be changed to an optimal layout in terms of the performance, processing efficiency, communication efficiency, etc. of the hardware and software provided in the map generation system 1 and the in-vehicle device 3.

[0119] Furthermore, the aforementioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole in hardware, for example by designing them as integrated circuits, or may be realized in software by having a processor interpret and execute a program that realizes each function. [Explanation of symbols]

[0120] 1. Map generation system 2...Surrounding environment sensor 3…In-vehicle device 4...SLAM processing section 5...Trajectory data generation unit 6...Relative coordinate data output section 11...Surrounding environment sensor coordinates 12...Reference coordinates 13...Body 14...Cart 15... Orbit 21...Surrounding environment sensor coordinates 22...Reference coordinates 23...Ideal orbit data 25...Cart 26...Body 27... Orbit 31...Reference coordinate pose data 32...Reference coordinate pose data 33...Smoothed pose data

Claims

1. A map generation system for generating an environmental map including trajectory data relating to the shape of a trajectory on which a moving object travels, a surrounding environment sensor mounted on the moving body and capable of acquiring information about the surrounding environment of the device; a computer connected to the ambient environment sensor so as to be capable of data communication, the computer having at least a processor and a storage device; At least The computer a SLAM processing unit that estimates an environmental map representing the environment surrounding the trajectory and a sensor pose, which is the position and / or attitude of the surrounding environment sensor, to be displayed on the environmental map based on sensor data acquired by the surrounding environment sensor; a relative coordinate data output unit that outputs relative coordinates between the ambient environment sensor coordinates that indicate the position of the ambient environment sensor and reference coordinates that are defined based on the positions of components of the moving object; a trajectory data generation unit that generates trajectory data representing the shape of the trajectory to be displayed on the environmental map based on the relative coordinates output by the relative coordinate data output unit and the output of the SLAM processing unit; and the trajectory data generation unit calculates a trajectory of the reference coordinates to be displayed on the environmental map, and generates trajectory data based on the calculated trajectory. Map generation system.

2. The map generating system according to claim 1 , wherein the surrounding environment sensor is at least one sensor that outputs data according to the shape and / or properties of surrounding objects.

3. The map generating system according to claim 2 , wherein the surrounding environment sensor is at least one of a LiDAR (Light Detection and Ranging), a camera, and a laser.

4. The map generating system according to claim 1 , wherein the surrounding environment sensor is at least one of a Global Navigation Satellite System (GNSS) receiver and a beacon receiver.

5. The map generation system according to claim 1 , wherein the trajectory data generation unit calculates a pose history of the reference coordinates on the environmental map and performs a smoothing process on the pose history to generate trajectory data.

6. the reference coordinates are defined based on a movable component that is a component on the moving body and whose relative position with respect to the surrounding environment sensor may vary; the relative coordinate data output unit outputs relative coordinates between the surrounding environment sensor coordinates and the reference coordinates. The map generation system of claim 1 .

7. 7. The map generation system according to claim 6, wherein the relative coordinate data output unit has a sensor that measures the amount of displacement of a movable part present on the moving body, and outputs relative coordinates between the surrounding environment sensor coordinates and the reference coordinates based on the output of the sensor.

8. 7. The map generation system according to claim 6, wherein the relative coordinate data output unit detects a track or a structure around the track using data obtained from the surrounding environment sensor, and outputs relative coordinates between the surrounding environment sensor coordinates and the reference coordinates using the detection results.

9. The map generation system according to claim 1 , wherein the SLAM processing unit holds advance map data that is information about a location for which a map is to be generated.

10. An information processing device constituting a map generation system that generates an environmental map including trajectory data relating to the shape of a trajectory on which a moving object travels, The device is configured to include at least a computer that is mounted on the moving body, is connected to a surrounding environment sensor capable of acquiring information about the surrounding environment of the device so as to be able to communicate data with the surrounding environment sensor, and has at least a processor and a storage device; The computer a SLAM processing unit that estimates an environmental map representing the environment surrounding the trajectory and a sensor pose, which is the position and / or attitude of the surrounding environment sensor, to be displayed on the environmental map based on sensor data acquired by the surrounding environment sensor; a relative coordinate data output unit that outputs relative coordinates between the ambient environment sensor coordinates that indicate the position of the ambient environment sensor and reference coordinates that are defined based on the positions of components of the moving object; a trajectory data generation unit that generates trajectory data representing the shape of the trajectory to be displayed on the environmental map based on the relative coordinates output by the relative coordinate data output unit and the output of the SLAM processing unit; and the trajectory data generation unit calculates a trajectory of the reference coordinates to be displayed on the environmental map, and generates trajectory data based on the calculated trajectory. Information processing device.

11. A map generation method for generating an environmental map including trajectory data relating to the shape of a trajectory on which a moving object travels, comprising: a surrounding environment sensor mounted on the moving body and capable of acquiring information about the surrounding environment of the device; a computer connected to the ambient environment sensor so as to be capable of data communication, the computer having at least a processor and a storage device; The method is executed by a map generation system comprising at least The computer an SLAM processing unit estimates an environmental map representing the environment around the trajectory and a sensor pose, which is the position and / or attitude of the surrounding environment sensor, to be displayed on the environmental map based on the sensor data acquired by the surrounding environment sensor; a relative coordinate data output unit outputs relative coordinates between the ambient environment sensor coordinates representing the position of the ambient environment sensor and reference coordinates defined based on the positions of the components of the mobile object; a trajectory data generation unit generates trajectory data representing the shape of the trajectory to be displayed on the environmental map based on the relative coordinates output by the relative coordinate data output unit and the output of the SLAM processing unit; the trajectory data generation unit calculates a trajectory of the reference coordinates to be displayed on the environmental map, and generates trajectory data based on the calculated trajectory. Map generation method.

12. A map generation system for generating an environmental map including trajectory data relating to the shape of a trajectory on which a moving object travels, A computer is mounted on the moving body, is connected to a surrounding environment sensor capable of acquiring information about the surrounding environment of the moving body so as to be capable of data communication, and has at least a processor and a storage device, an SLAM processing unit estimates an environmental map representing the environment around the trajectory and a sensor pose, which is the position and / or attitude of the surrounding environment sensor, to be displayed on the environmental map based on the sensor data acquired by the surrounding environment sensor; a relative coordinate data output unit outputs relative coordinates between the ambient environment sensor coordinates representing the position of the ambient environment sensor and reference coordinates defined based on the positions of the components of the mobile object; a trajectory data generation unit generates trajectory data representing the shape of the trajectory to be displayed on the environmental map based on the relative coordinates output by the relative coordinate data output unit and the output of the SLAM processing unit; The trajectory data generation unit calculates a trajectory of the reference coordinates to be displayed on the environmental map, and generates trajectory data based on the calculated trajectory. causing the computer to execute the steps of: Computer program.

Images