Information processing device and information processing method

Abstract

To improve the accuracy of estimating the position of a moving object. [Solution] An information processing device comprising: a feature point extraction unit that extracts feature points from sensor data obtained by a sensor mounted on a moving body; an identification unit that identifies objects having the feature points; and a matching processing unit that matches a first feature point group consisting of first feature points extracted in a first stage with a second feature point group consisting of second feature points extracted in a second stage based on the identification results by the identification unit for the first feature points or the second feature points.

Description

[Technical Field]

[0001] The present invention relates to an information processing device and an information processing method. [Background technology]

[0002] In recent years, various technologies for controlling the autonomous driving of a mobile object have been researched. For example, there is a technology that creates a map for estimating the position and orientation of a sensor mounted on the mobile object, calculates the position and orientation of the sensor by referring to the created map, and controls the mobile object based on the calculated position and orientation of the sensor. In this technology, the map is updated based on sensor values ​​at multiple times in order to respond to changes in the environment in which the mobile object autonomously drives.

[0003] Regarding map updating technology, Patent Document 1 discloses a technology for improving map accuracy by sensor fusion of sensor means with different characteristics, namely, a distance measurement means and an image capture means. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-99384 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology disclosed in Patent Document 1 leaves room for improvement in terms of improving the accuracy of estimating the position of a moving object.

[0006] Therefore, the present invention has been made in consideration of the above problems, and an object of the present invention is to provide a technique that can improve the accuracy of estimating the position of a moving object. [Means for solving the problem]

[0007] In order to solve the above problem, according to one aspect of the present invention, there is provided an information processing device comprising: a feature point extraction unit that extracts feature points from sensor data obtained by a sensor mounted on a moving body; an identification unit that identifies an object having the feature points; and a matching processing unit that matches a first feature point group consisting of first feature points extracted in a first stage with a second feature point group consisting of second feature points extracted in a second stage based on the identification result by the identification unit for the first feature points or the second feature points.

[0008] The identification unit may determine a weight for the feature point according to the result of identifying an object having the feature point, and the matching processing unit may perform the matching based on the weight determined by the identification unit.

[0009] The identification unit may determine a weight according to the mobility of the object, which is a result of identification of the feature point, as the weight of the feature point.

[0010] The identification unit may be configured to determine a weight for a feature point so that the lower the mobility of the object as a result of identification of the feature point, the greater the weight that the feature point is assigned, and the greater the impact that the feature point has on the matching result.

[0011] The information processing device may further include a memory unit that stores the first feature points of the first feature point group in association with position information, the sensor may be mounted on a moving body, and the matching processing unit may estimate position information of the moving body in the second stage by the matching.

[0012] The information processing device may further include an environmental change determination unit that determines whether or not there has been a change between the arrangement of the first feature point group and the arrangement of the second feature point group, and a memory management unit that updates the information stored in the memory unit when the environmental change determination unit determines that there has been a change.

[0013] The identification unit may determine weights of the first feature points in the first feature point group to weights according to the results of identifying objects having the first feature points, and the memory management unit may preferentially update information about first feature points in the first feature point group that have been determined to have lower weights.

[0014] In order to solve the above-mentioned problem, according to another aspect of the present invention, there is provided an information processing method including: extracting feature points from sensor data obtained by a sensor; identifying an object having the feature points; and matching a first feature point group consisting of first feature points extracted in a first stage with a second feature point group consisting of second feature points extracted in a second stage based on a result of identifying the first feature points or the second feature points. [Effects of the Invention]

[0015] According to the present invention as described above, it is possible to improve the accuracy of estimating the position of a moving object. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is an explanatory diagram showing an example of operation of a position estimation system 1 according to an embodiment of the present invention. [Figure 2] 1 is an explanatory diagram showing the configuration of an information processing device 30 according to an embodiment of the present invention. [Figure 3] FIG. 2 is an explanatory diagram showing a specific example of a database stored in a storage unit 330. [Figure 4] 10 is a flowchart showing the operation of an information processing device 30 according to an embodiment of the present invention at the map creation stage. [Figure 5] 10 is a flowchart showing the operation of an information processing device 30 in an operation stage according to an embodiment of the present invention. [Figure 6] FIG. 1 is a block diagram showing an example of a hardware configuration 90. DETAILED DESCRIPTION OF THE INVENTION

[0017] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted.

[0018] <Location estimation system overview> An embodiment of the present invention relates to a position estimation system for estimating the position of a moving object. An overview of the position estimation system according to an embodiment of the present invention will be described below with reference to FIG.

[0019] 1 is an explanatory diagram showing an example of operation of a position estimation system 1 according to an embodiment of the present invention. As shown in FIG. 1, the position estimation system 1 includes a mobile object 10, an external sensor 20, and an information processing device 30. The external sensor 20 and the information processing device 30 are mounted on the mobile object 10 and move together with the mobile object 10.

[0020] The mobile body 10 has a movement mechanism and is capable of movement by the movement mechanism. The movement mechanism includes a drive mechanism such as an engine or a motor, a transmission mechanism that transmits the driving force obtained by the drive mechanism, and a driven mechanism that is driven based on the driving force transmitted by the transmission mechanism. The driven mechanism may be a wheel for traveling on a traveling surface, a propeller for flying in the air, or a screw for obtaining thrust underwater. Furthermore, the mobile body 10 may be a mobile body without a human on board, or a mobile body with a human on board. Furthermore, the mobile body may move according to human operation, or may move autonomously.

[0021] The external sensor 20 is a sensor that acquires sensor data that indicates the situation around the external sensor 20. The external sensor 20 may be, for example, a laser sensor such as a 3D-Lidar (Light Detection And Ranging) sensor. In this case, the external sensor 20 acquires, as sensor data, a distance image that indicates the distance to a subject for each pixel.

[0022] The information processing device 30 creates a map of the environment in which the mobile object 10 travels, estimates the position of the mobile object 10 based on the map, and updates the map based on the sensor data acquired by the external sensor 20. The function of controlling the movement of the mobile object 10 may be implemented in the information processing device 30 or may be installed in another device. Also, while FIG. 1 shows an example in which the information processing device 30 is installed in the mobile object 10, the information processing device 30 does not have to be installed in the mobile object 10. In this case, the information processing device 30 can operate by receiving the sensor data acquired by the external sensor 20 via a network, for example.

[0023] (background) Regarding the creation of the above-mentioned maps, one possible technology is to improve the accuracy of the map by sensor fusion of two or more different sensor means, such as a distance measurement means and an image capture means. However, this technology has the disadvantage of requiring two or more different sensor means. In addition, when the surrounding environment changes frequently, the calculation cost becomes high, and the more frequently the map is updated, the more distortion there becomes. As the map distortion increases, the accuracy of the position estimation based on the map also deteriorates.

[0024] Furthermore, depending on the environment in which a mobile object is operated, there may be a mixture of objects whose positions change easily and objects whose positions do not change easily. For example, in a factory, the positions of highly mobile objects such as people, pallets, and carts change frequently, while the positions of less mobile objects such as walls, pillars, and equipment generally do not change. The above technology estimates the position without taking into account the mobility of such objects, so from this perspective, there is room for improvement in the accuracy of position estimation.

[0025] The present inventors have taken the above circumstances into consideration and have devised an embodiment of the present invention. According to this embodiment of the present invention, it is possible to suppress the accumulation of errors due to map updates and improve the accuracy of position estimation. The configuration and operation of an information processing device 30 according to this embodiment of the present invention will be described in detail below.

[0026] <Configuration of information processing device 30> 2 is an explanatory diagram showing the configuration of an information processing device 30 according to an embodiment of the present invention. As shown in FIG. 2, the information processing device 30 according to an embodiment of the present invention has a control unit 310 and a storage unit 330.

[0027] The control unit 310 controls the overall operation of the information processing device 30. Specifically, the control unit 310 has a map creation unit 311, a feature point extraction unit 312, a feature point identification unit 313, a database construction unit 314, a self-position estimation unit 315, and an environmental change recognition unit 316, as shown in FIG.

[0028] The map creation unit 311 creates a map of the environment in which the mobile object 10 travels, based on sensor data from the external sensor 20. For example, the map creation unit 311 may create the map while calculating the position and orientation of the mobile object 10 using SLAM (Simultaneous Localization and Mapping) technology. The map is data including three-dimensional coordinates of a point cloud corresponding to each object, including walls, pillars, etc. The map is stored in the storage unit 330.

[0029] The feature point extraction unit 312 extracts feature points from the map created by the map creation unit 311. The map created by the map creation unit 311 includes a point cloud of each object, which is sensor data acquired by the external sensor 20. Therefore, it can be said that the feature point extraction unit 312 extracts feature points from the sensor data acquired by the external sensor 20. The feature point extraction unit 312 can also extract feature points from the point cloud of each object acquired by the external sensor 20 in real time. Note that the feature points extracted by the feature point extraction unit 312 in the map creation stage, which is an example of the first stage, may be referred to as first feature points, and a set thereof may be referred to as a first feature point group. Note that the feature points extracted by the feature point extraction unit 312 in the operation stage, which is an example of the second stage, may be referred to as second feature points, and a set thereof may be referred to as a second feature point group.

[0030] The feature point identification unit 313 is an example of an identification unit, and identifies an object having each feature point extracted by the feature point extraction unit 312. For example, the feature point identification unit 313 identifies whether the object having the feature point extracted by the feature point extraction unit 312 is a pillar, a wall, equipment, a person, a pallet, a shelf cart, or the like. The feature point identification unit 313 can perform this identification using point cloud processing technology, machine learning technology, or other technology.

[0031] Then, the feature point identification unit 313 determines the weight of the feature point according to the identification result of the object having the feature point. At this time, the feature point identification unit 313 determines the weight of the feature point according to the ease with which the position of the object indicated by the identification result changes (i.e., the degree of mobility).

[0032] Specifically, the feature point identification unit 313 may determine a weight for a feature point that is greater the lower the mobility of the object indicated by the identification result. For example, pillars, walls, and equipment are less mobile and less likely to change position than people, pallets, and shelf carts. Therefore, when the identification result indicates a pillar, wall, or equipment, the feature point identification unit 313 may determine a weight for the feature point that is greater than when the identification result indicates a person, pallet, or shelf cart. The greater the weight determined for a feature point, the greater the influence it has on the matching result, which will be described later. Note that the weight corresponding to each object may be set in advance.

[0033] The database construction unit 314 stores the results of the classification by the feature point identification unit 313, the determined weights, and the like in the storage unit 330. Specifically, the database construction unit 314 associates the results of the classification by the feature point identification unit 313 as attributes with the feature points that make up the map, and also associates the weights determined by the feature point identification unit 313 with the feature points.

[0034] Fig. 3 is an explanatory diagram showing a specific example of a database stored in storage unit 330. As shown in Fig. 3, in the database stored in storage unit 330, feature points, three-dimensional coordinates (position information), attributes, and weights are associated with each other.

[0035] For example, in the example shown in Figure 3, feature point C1 is associated with three-dimensional coordinates "X1, Y1, Z1," an attribute "pillar," and a weight of "1.0." On the other hand, feature point C31 is associated with three-dimensional coordinates "X3, Y3, Z3," an attribute "palette," and a weight of "0.2." Because the pillar corresponding to feature point C1 has lower mobility than the pallet corresponding to feature point C31, feature point C1 is associated with a weight of "1.0," which is higher than the weight of feature point C31, "0.2."

[0036] The database construction unit 314 also functions as a memory management unit that updates the information (database) stored in the memory unit 330 described above when the environmental change recognition unit 316, which will be described later, recognizes that there has been a change in the environment.

[0037] In the operation stage, the self-location estimation unit 315 estimates the self-location of the mobile object 10 based on the map stored in the storage unit 330 and sensor data acquired in real time from the external sensor 20. Specifically, the self-location estimation unit 315 functions as a matching processing unit that matches a first group of feature points constituting the map stored in the storage unit 330 with a second group of feature points acquired in real time, and estimates the self-location of the mobile object 10 based on position information of the first feature points that have successfully matched with the second group of feature points. In this case, the self-location estimation unit 315 performs the matching based on the result of identification by the feature point identification unit 313.

[0038] For example, the self-location estimation unit 315 may estimate the three-dimensional coordinates of each of the second feature points when the position and posture of the moving body 10 is each of a plurality of position and postures, and may perform self-location estimation of the moving body 10 using the least squares method. More specifically, the self-location estimation unit 315 extracts a plurality of pairs of corresponding feature points between the first feature point group and the second feature point group for each tentative position and posture of the moving body 10, and calculates a sum of the squares of the differences in the three-dimensional coordinates of the feature points of each pair multiplied by weights determined for the feature points (hereinafter, this may be referred to as a matching score). Then, the position in the tentative position and posture of the moving body 10 for which the sum is smallest may be estimated as the position of the moving body 10. Here, since the weights of the corresponding feature points between the first feature point group and the second feature point group may be the same, the self-location estimation unit 315 may estimate the position using only the weights of the first feature points or the weights of the second feature points.

[0039] The above-described method for estimating the self-location of the moving body 10 is merely an example, and various other methods using the weight of each feature point can also be applied to one embodiment of the present invention. For example, the self-location estimation unit 315 may estimate the self-location of the moving body 10 by inputting the three-dimensional coordinates of each second feature point and the weight of each second feature point into a trained model that outputs the position of the moving body 10 in response to input of the three-dimensional coordinates of each feature point and the weight of each feature point. In this case, the trained model may output an index indicating the likelihood of the output position of the moving body 10 as a matching score.

[0040] The environmental change recognition unit 316 recognizes whether or not an environmental change has occurred, that is, whether or not a change has occurred between the arrangement of the first feature point group and the arrangement of the second feature point group. For example, the environmental change recognition unit 316 may recognize that an environmental change has occurred when the smallest matching score calculated by the self-position estimation unit 315 is greater than a threshold value.

[0041] The storage unit 330 stores various data used in the operation of the information processing device 30. For example, the storage unit 330 stores the database described with reference to Fig. 3. Note that although Fig. 2 shows an example in which the storage unit 330 is provided inside the information processing device 30, the functions of the storage unit 330 may be implemented outside the information processing device 30.

[0042] <Operation of information processing device 30> The configuration of the information processing device 30 according to one embodiment of the present invention has been described above. Next, the operation of the information processing device 30 according to one embodiment of the present invention will be summarized.

[0043] (Map creation stage) FIG. 4 is a flowchart showing the operation of the information processing device 30 according to one embodiment of the present invention in the map creation stage.

[0044] First, as shown in FIG. 4, while the mobile object 10 is traveling, the external sensor 20 acquires sensor data, and the map creation unit 311 of the information processing device 30 creates a map of the environment in which the mobile object 10 is traveling (S21).

[0045] Then, the feature point extraction unit 312 extracts feature points from the map created by the map creation unit 311 (S22). Next, the feature point identification unit 313 identifies an object having each feature point extracted by the feature point extraction unit 312 (S23). For example, the feature point identification unit 313 identifies whether the object having the feature point extracted by the feature point extraction unit 312 is a pillar, a wall, equipment, a person, a pallet, a shelf cart, or the like.

[0046] Furthermore, the feature point identification unit 313 determines a weight according to the result of identifying an object having the feature point as the weight of the feature point (S24).

[0047] Thereafter, the database construction unit 314 associates the results of the identification by the feature point identification unit 313 as attributes with the feature points that make up the map in the storage unit 330, and also associates the weights determined by the feature point identification unit 313 with the attributes (S25).

[0048] (Operational stage) FIG. 5 is a flowchart showing the operation of the information processing device 30 in the operation stage according to one embodiment of the present invention.

[0049] 5, the feature point extraction unit 312 acquires sensor data from the external sensor 20 in real time (S31), and extracts feature points from the acquired sensor data (S32). Subsequently, the feature point identification unit 313 identifies, for each feature point extracted by the feature point extraction unit 312, an object having the feature point (S33).

[0050] Furthermore, the feature point identification unit 313 determines a weight according to the result of identifying an object having the feature point as the weight of the feature point (S34).

[0051] Thereafter, the self-location estimation unit 315 performs matching between the first feature point group constituting the map stored in the storage unit 330 and the second feature point group acquired in real time, thereby estimating the self-location of the moving object 10 (S35). At this time, the self-location estimation unit 315 performs the matching using weights of at least either the first feature points or the second feature points.

[0052] Then, the environmental change recognition unit 316 recognizes whether or not there has been a change between the arrangement of the first feature point group and the arrangement of the second feature point group, that is, whether or not there has been an environmental change (S36). If it is recognized that there has been no environmental change (S36 / NO), the processing from S31 is repeated.

[0053] On the other hand, if it is recognized that an environmental change has occurred (S36 / YES), the database construction unit 314 updates (S37) the database stored in the storage unit 330. For example, the database construction unit 314 controls the deletion of feature points from the map based on the weights of the feature points, and controls the addition of feature points from the second feature point group to the map based on the weights of the feature points.

[0054] Specifically, the database construction unit 314 preferentially updates information about first feature points that have been assigned lower weights among the first feature point group. For example, if the weight of a certain first feature point on the map is equal to or less than a threshold and the first feature point is determined to have moved based on the second feature point group, the database construction unit 314 may delete information about the first feature point from the map.

[0055] Furthermore, if the weight of a certain second feature point in the second feature point group is equal to or less than a threshold value and there is no first feature point corresponding to the second feature point at a position equivalent to the position of the second feature point, the database construction unit 314 may add information about the second feature point to the map.

[0056] Thereafter, while the moving body 10 continues autonomous traveling (S38 / YES), the processing from S31 is repeated, and when the moving body 10 finishes autonomous traveling (S38 / NO), this operation ends.

[0057] <Action and effect> According to the embodiment of the present invention described above, various operational effects can be obtained. For example, the self-location estimation unit 315 according to the embodiment of the present invention matches a first group of feature points constituting a map stored in the storage unit 330 with a second group of feature points acquired in real time, based on the results of identifying at least one of the first feature points or the second feature points. With this configuration, matching and position estimation are performed taking into consideration the identity of the object having the first feature points or the second feature points, making it possible to improve the accuracy of position estimation.

[0058] In particular, the feature point identification unit 313 determines a weight for a feature point as the lower the mobility of the object, and the feature point for which a higher weight is determined has a greater influence on the results of matching and position estimation. With this configuration, feature points of objects that are highly mobile and prone to change position are less likely to affect the results of position estimation, making it possible to more reliably improve the accuracy of position estimation. Therefore, stable position estimation is possible even in a factory where people, shelf carts, and the like are frequently moving, for example.

[0059] Furthermore, when the environment in which the mobile object 10 travels changes, the database construction unit 314 according to one embodiment of the present invention preferentially updates information on first feature points that are assigned lower weights among the first feature point group that constitutes the map. This configuration makes it possible to suppress the accumulation of errors due to map updates and maintain a highly accurate map. As a result, it is also possible to improve the accuracy of the self-location estimation of the mobile object 10 performed using the map.

[0060] Furthermore, one embodiment of the present invention can estimate the self-position of the moving body 10 and update maps using, for example, only 3D-Lidar, thereby reducing processing load and costs compared to when multiple types of sensors are used.

[0061] <Hardware configuration> An embodiment of the present invention has been described above. The information processing, such as the location estimation and map update, described above, is realized by a combination of software and hardware. An example of a hardware configuration that can be applied to the information processing device 30 will now be described.

[0062] 6 is a block diagram showing an example of a hardware configuration 90. The hardware configuration 90 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, and a host bus 904. The hardware configuration 90 also includes a bridge 905, an external bus 906, an interface 907, an input device 908, a display device 909, an audio output device 910, a storage device (HDD) 911, a drive 912, and a network interface 915.

[0063] The CPU 901 functions as an arithmetic processing unit and a control unit, and controls overall operation in accordance with various programs. The CPU 901 may also be a microprocessor. The ROM 902 stores programs used by the CPU 901, calculation parameters, etc. The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, etc. These are interconnected by a host bus 904 that is composed of a CPU bus, etc. The functions of the control unit 310 described above can be realized by the cooperation of the CPU 901, ROM 902, RAM 903, and software.

[0064] The host bus 904 is connected to an external bus 906, such as a PCI (Peripheral Component Interconnect / Interface) bus, via a bridge 905. It is not necessary to configure the host bus 904, bridge 905, and external bus 906 separately, and these functions may be implemented on a single bus.

[0065] The input device 908 is composed of input means such as a mouse, keyboard, touch panel, buttons, microphone, sensors, switches, and levers that allow the user to input information, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 901. By operating the input device 908, the user can input various data and instruct processing operations.

[0066] The display device 909 includes, for example, a display device such as a liquid crystal display (LCD) device, a projector device, an OLED (Organic Light Emitting Diode) device, a lamp, etc. The audio output device 910 includes an audio output device such as a speaker and a headphone.

[0067] The storage device 911 is a data storage device configured as an example of a storage unit according to this embodiment. The storage device 911 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, and a deleting device that deletes data recorded on the storage medium. The storage device 911 is configured, for example, by an HDD (Hard Disk Drive) or an SSD (Solid State Drive), or a memory having equivalent functions. This storage device 911 drives storage and stores programs executed by the CPU 901 and various data.

[0068] The drive 912 is a reader / writer for a storage medium, and is built into or externally attached to the hardware configuration 90. The drive 912 reads information recorded on a removable storage medium 84, such as an attached magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 903 or the storage device 911. The drive 912 can also write information to the removable storage medium 84.

[0069] The network interface 915 is, for example, a communication interface configured with a communication device for connecting to a network, etc. The network interface 915 may be a wireless LAN (Local Area Network) compatible communication device or a wired communication device that performs wired communication.

[0070] <Supplementary information> Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that a person skilled in the art to which the present invention pertains can conceive of various modifications and alterations within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

[0071] For example, the steps in the processing of the information processing device 30 in this specification do not necessarily have to be processed in chronological order according to the order described in the flowchart. For example, the steps in the processing of the information processing device 30 may be processed in an order different from the order described in the flowchart, or may be processed in parallel.

[0072] It is also possible to create a computer program that causes hardware such as a CPU, ROM, and RAM built into the information processing device 30 to perform functions equivalent to those of the above-described components of the information processing device 30. A non-transitory storage medium storing the computer program is also provided.

[0073] Furthermore, the functions of the map creation unit 311, feature point extraction unit 312, feature point identification unit 313, database construction unit 314, self-position estimation unit 315, environmental change recognition unit 316, and storage unit 330 described above may be implemented in a single housing, or may be distributed across multiple housings. When the functions are implemented in a single housing, the device having that housing may correspond to the information processing device 30. When the functions are distributed across multiple housings, one or a combination of two or more of the multiple devices having the housings may correspond to the information processing device 30. When the functions are distributed across multiple housings, an interface for inputting and outputting information between the devices having the housings is also implemented. [Explanation of symbols]

[0074] 1. Location estimation system 10 Mobile 20 External Sensor 30 Information processing equipment 310 Control Unit 311 Mapping Department 312 Feature Point Extraction Unit 313 Feature Point Identification Unit 314 Database Construction Department 315 Self-position estimation part 316 Environmental Change Recognition Department 330 Storage section

Claims

1. a feature point extraction unit that extracts feature points from sensor data obtained by a sensor mounted on the moving object; an identification unit that identifies an object having the feature points; a matching processing unit that matches a first feature point group consisting of first feature points extracted in a first stage with a second feature point group consisting of second feature points extracted in a second stage based on a result of classification by the classification unit regarding the first feature points or the second feature points; An information processing device comprising:

2. the identification unit determines a weight of the feature point according to a result of identifying an object having the feature point, The information processing device according to claim 1 , wherein the matching processing unit performs the matching based on a weight determined by the identification unit.

3. The information processing apparatus according to claim 2 , wherein the identification unit determines a weight according to the mobility of the object, which is a result of identification of the feature point, as the weight of the feature point.

4. the identification unit determines a weight for the feature point to be larger as the mobility of the object, which is a result of identification of the feature point, becomes lower; The information processing apparatus according to claim 3 , wherein a feature point having a larger weight determined therefor has a greater influence on the matching result.

5. The information processing device includes: a storage unit that stores the first feature points of the first feature point group in association with position information, The sensor is mounted on a moving body, 5. The information processing device according to claim 1, wherein the matching processing unit estimates position information of the moving object in the second stage by the matching.

6. The information processing device includes: an environmental change determination unit that determines whether or not there has been a change between the arrangement of the first feature point group and the arrangement of the second feature point group; a memory management unit that updates the information stored in the memory unit when the environmental change determination unit determines that the change has occurred; The information processing device according to claim 5 , further comprising:

7. the identification unit determines a weight of the first feature point of the first feature point group according to a result of identification of an object having the first feature point, The information processing apparatus according to claim 6 , wherein the memory management unit preferentially updates information on first feature points that have been determined to have lower weights among the first feature point group.

8. extracting feature points from sensor data obtained by a sensor; identifying an object having the feature points; matching a first feature point group consisting of first feature points extracted in the first stage with a second feature point group consisting of second feature points extracted in the second stage based on the results of classification of the first feature points or the second feature points; An information processing method, including:

Images