WO2023079845A1

WO2023079845A1 - Information processing device, information processing method, and program

Info

Publication number: WO2023079845A1
Application number: PCT/JP2022/034884
Authority: WO
Inventors: 陸也江副; 啓輔前田; 諒渡辺
Original assignee: ソニーグループ株式会社
Priority date: 2021-11-02
Filing date: 2022-09-20
Publication date: 2023-05-11

Abstract

To estimate the position of a mobile object at a high precision, an information processing device comprises an acquisition unit that acquires a plurality of pieces of position information on an arbitrary mobile object on the basis of sensing information obtained from a sensor mounted in each of a plurality of mobile objects, and an estimation unit that superimposes probability distributions of the plurality of pieces of position information on the arbitrary mobile object acquired by the acquisition unit on one another to estimate the information on the position of the arbitrary mobile object.

Description

Information processing device, information processing method and program

The present disclosure relates to an information processing device, an information processing method, and a program.

In recent years, technologies for estimating the position of mobile objects such as robots have been developed. For example, when a robot moves in a certain environment, it estimates its own position by dead reckoning using sensing information from an internal sensor of the robot. In addition, the robot estimates its own position by star reckoning using sensing information obtained by an external sensor detecting a feature such as a marker.

For example, Patent Document 1 discloses a technique in which a robot with a small estimation error due to dead reckoning estimates the position of another robot with a large estimation error, and provides the estimated position information to the other robot.

JP-A-7-129237

However, with the technology described in Patent Document 1, it is difficult for both robots to estimate each other's positions with high accuracy when both of the two robots have large estimation errors.

Therefore, the present disclosure proposes a new and improved information processing device, information processing method, and program capable of estimating the position of a mobile object with higher accuracy.

According to the present disclosure, an acquisition unit that acquires a plurality of pieces of position information of an arbitrary moving object based on sensing information obtained by sensors mounted on each of a plurality of moving objects; and an estimating unit for estimating position information of the arbitrary moving body by superimposing probability distributions of a plurality of position information of the moving bodies.

Further, according to the present disclosure, acquiring a plurality of position information of an arbitrary mobile object based on sensing information obtained by sensors mounted on each of a plurality of mobile objects; and estimating the position information of the arbitrary moving object by superimposing the probability distributions of a plurality of position information of the computer-implemented information processing method.

Further, according to the present disclosure, the computer has an acquisition function for acquiring a plurality of position information of an arbitrary moving body based on sensing information obtained by sensors mounted on each of a plurality of moving bodies, and the acquisition function and an estimating function of estimating the position information of the arbitrary moving object by superimposing the obtained probability distributions of the plurality of position information of the arbitrary moving object.

1 is an explanatory diagram for explaining an example of an information processing system according to the present disclosure; FIG. It is an explanatory view for explaining an example of functional composition of an information processing system concerning this indication. FIG. 4 is an explanatory diagram for explaining an example related to position estimation of a robot according to the present disclosure; FIG. 4 is an explanatory diagram for explaining an overview of how an estimation unit according to the first embodiment estimates position information of a robot; FIG. 7 is an explanatory diagram for explaining an example of operation processing for estimating position information of a robot by superimposing probability distributions according to the first embodiment; FIG. 11 is an explanatory diagram for explaining an example of correcting the position information of the robot according to the second embodiment; FIG. 11 is an explanatory diagram for explaining an example of operation processing for correcting position information of the robot according to the second embodiment; FIG. 11 is an explanatory diagram for describing a modification of the robot according to the present disclosure; It is a block diagram showing the hardware configuration of the server.

Preferred embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In the present specification and drawings, constituent elements having substantially the same functional configuration are denoted by the same reference numerals, thereby omitting redundant description.

Also, in the description of this specification and drawings, robots are distinguished as needed such as a first robot 10A and a second robot 10B. However, the robots are simply referred to as robots 10 when there is no need to distinguish between the robots.

In addition, the "Mode for Carrying Out the Invention" will be explained according to the order of items shown below.
1. Outline of information processing system 1.1. Functional configuration example of information processing system 2 . Example 2.1. Overview 2.2. First embodiment 2.3. Second embodiment 3. Modification 4. Hardware configuration example 5 . supplement

<<1. Information processing system overview >>
As one embodiment of the present disclosure, a mechanism for estimating the position of a mobile object with higher accuracy will be described.

FIG. 1 is an explanatory diagram for explaining an example of an information processing system according to the present disclosure. An information processing system according to the present disclosure includes a network 1, a first robot 10A, a second robot 10B, and a server 20.

(Network 1)
A network 1 according to the present disclosure is a wired or wireless transmission path for information transmitted from devices connected to the network 1 . For example, the network 1 may include a public line network such as the Internet, a telephone line network, a satellite communication network, various LANs (Local Area Networks) including Ethernet (registered trademark), WANs (Wide Area Networks), and the like. The network 1 may also include a dedicated line network such as IP-VPN (Internet Protocol-Virtual Private Network).

The first robot 10A and server 20 and the second robot 10B and server 20 are connected via network 1, respectively.

(Robot 10)
The robot 10 according to the present disclosure is an example of a mobile object and autonomously moves within a certain environment. In the first embodiment described later, two robots 10 such as the first robot 10A and the second robot 10B are described as an example of the plurality of robots 10, but the number of the plurality of robots 10 is three. machine or more. Also, the number of robots 10 described in the second embodiment and modification may be one.

Also, the robot 10 estimates its own position or the positions of other robots 10 based on the sensing information acquired by the sensors provided in the robot 10 . Alternatively, the robot 10 may transmit sensing information acquired by a sensor to the server 20 . In this case, the server 20 that has received the sensing information may estimate the position of the robot 10 based on the received sensing information. The details of the sensors included in the robot 10 will be described later.

(Server 20)
The server 20 according to the present disclosure is an example of an information processing device, and acquires a plurality of pieces of position information of an arbitrary robot 10 based on sensing information obtained by each sensor included in each of the plurality of robots 10 . For example, the server 20 acquires the positional information of the first robot 10A and the positional information of the second robot 10B based on the sensing information obtained by the sensors of the first robot 10A. Also, the server 20 acquires the position information of the first robot 10A and the position information of the second robot 10B based on the sensing information obtained by the sensors of the second robot 10B.

Also, the server 20 estimates the position information of any robot 10 by superimposing the probability distributions of a plurality of position information of any robot 10 . For example, the server 20 estimates the position information of the first robot 10A by superimposing the probability distributions of two pieces of position information of the first robot 10A acquired from each of the first robot 10A and the second robot 10B. You may In addition, the server 20 estimates the position information of the second robot 10B by superimposing the probability distributions of the two pieces of position information of the second robot 10B acquired from each of the first robot 10A and the second robot 10B. You may

The outline of the information processing system according to the present disclosure has been described above. Next, a functional configuration example of an information processing system according to the present disclosure will be described with reference to FIG.

<<1.1. Example of functional configuration of information processing system>>
FIG. 2 is an explanatory diagram for explaining a functional configuration example of an information processing system according to the present disclosure.

(Robot 10)
The robot 10 according to the present disclosure includes a camera 110, an IMU (Inertial Measurement Unit) 120, a wheel encoder 130, a storage unit 140, a communication unit 150, and a control unit 160, as shown in FIG. .

The camera 110 according to the present disclosure is an example of an external sensor, and is a device that acquires sensing information including an image by photographing. For example, the camera 110 acquires sensing information including distance information from the camera 110 to the other robot 10 or the Alvar marker by photographing the other robot 10 or the Alvar marker.

Also, the camera 110 according to the present disclosure is preferably a camera without an infrared LED and an IR cut filter, in order to acquire the time when the camera 110 captured the image. Note that the Alvar marker is an example of a feature. Also, in the following description, the Alvar marker may simply be referred to as a marker.

The IMU 120 according to the present disclosure is an example of an internal sensor, and is a device that detects inertial motion of the robot 10 . For example, the IMU 120 acquires sensing information including angular acceleration information of the wheels of the robot 10 when the robot 10 moves.

The wheel encoder 130 according to the present disclosure is an example of an internal sensor, and acquires sensing information including vehicle speed pulses of the wheels of the robot 10 when the robot 10 moves.

The storage unit 140 according to the present disclosure holds software and various data. For example, the storage unit 140 holds map information of the environment in which the robot 10 moves and information related to the self-position of the robot 10 . The storage unit 140 also holds position information of markers placed in the environment in which the robot 10 moves. In addition, the storage unit 140 may hold information related to the target route in the environment.

The communication unit 150 according to the present disclosure performs various communications with the communication unit 210 included in the server 20. For example, the communication unit 150 transmits information regarding the self-position of the robot 10 estimated by the estimation unit 161 to the server 20 . Also, the communication unit 150 may transmit the position information of the other robot 10 estimated by the estimation unit 161 to the server 20 .

Also, the communication unit 150 may transmit various sensing information obtained by the camera 110 , the IMU 120 and the wheel encoder 130 to the server 20 .

The control unit 160 according to the present disclosure controls the overall operation of the robot 10. The control unit 160 according to the present disclosure includes an estimation unit 161 as shown in FIG. 2 .

The estimating unit 161 according to the present disclosure estimates the position of the robot 10 based on sensing information obtained by sensors provided in the robot 10 . For example, the estimator 161 estimates the self-position of the robot 10 based on the angular velocity information obtained by the IMU 120 and the vehicle speed pulse obtained by the wheel encoder 130 . A method of estimating the self-position of the robot 10 using such an internal sensor is called dead reckoning.

Also, the estimation unit 161 according to the present disclosure estimates the self-position of the robot 10 based on the distance information from the camera 110 to the marker obtained by the camera 110 photographing the marker. Further, the estimation unit 161 may estimate the position of the other robot 10 based on distance information from the camera 110 to the other robot 10 obtained by photographing the other robot 10 with the camera 110 . A method of estimating the position information of the robot 10 using such an external sensor is called star reckoning.

Although the details will be described later, the information related to the self-position of the robot 10 estimated by the estimation unit 161 and the position information of the other robots 10 each have an error circle according to a probability distribution. Moreover, the probability distribution according to the present disclosure is an example of Gaussian distribution.

(Server 20)
The server 20 according to the present disclosure includes a communication unit 210 and a control unit 220, as shown in FIG.

The communication unit 210 according to the present disclosure performs various communications with the robot 10. For example, the communication unit 210 is an example of an acquisition unit and receives position information of an arbitrary robot 10 from a plurality of robots 10 . For example, the communication unit 210 receives information regarding the self-position of the first robot 10A and position information of the second robot 10B from the first robot 10A. Further, the communication unit 210 receives information related to the self-position of the second robot 10B and position information of the first robot 10A from the second robot 10B.

Also, the communication unit 210 may receive various sensing information from a plurality of robots 10 . For example, the communication unit 210 receives various sensing information obtained by the camera 110, the IMU 120, and the wheel encoder 130 of each of the first robot 10A and the second robot 10B from the first robot 10A and the second robot 10B. may receive.

The control unit 220 according to the present disclosure controls the overall operation of the server 20. The control unit 220 includes an estimation unit 221 and a correction unit 225, as shown in FIG.

The estimating unit 221 estimates the position of an arbitrary robot 10 by superimposing the probability distributions of a plurality of pieces of positional information of the arbitrary robot 10 received by the communication unit 210 . Details will be described later.

Also, the estimation unit 221 according to the present disclosure may be an acquisition unit. For example, the communication unit 210 may receive various sensing information from the robot 10, and the estimating unit 221 may estimate position information of any robot 10 based on the sensing information. For example, if the arbitrary robot 10 is the first robot 10A, the estimation unit 221 estimates the position information of the first robot 10A based on various sensing information received by the communication unit 210 from the first robot 10A. may Furthermore, the estimation unit 221 may estimate the position information of the first robot 10A based on various sensing information received by the communication unit 210 from the second robot 10B.

Then, the estimation unit 221 may estimate the position information of the arbitrary robot 10 by superimposing the probability distributions of the estimated plurality of position information of the arbitrary robot 10 .

The correction unit 225 corrects the position information of any robot 10 to the position information estimated by the estimation unit 221 . For example, the correction unit 225 causes the communication unit 210 to transmit correction information based on the position information estimated by the estimation unit 221 .

The functional configuration example of the information processing system according to the present disclosure has been described above. Next, an embodiment of an information processing system according to the present disclosure will be described with reference to FIG.

<<2. Example>>
<<2.1. Overview＞＞
FIG. 3 is an explanatory diagram for explaining an example related to position estimation of the robot 10 according to the present disclosure. First, the robot 10 according to the present disclosure autonomously moves within an environment (for example, a factory or the like). At this time, the robot 10 moves in the environment while estimating its own position by constantly performing the above-described dead reckoning.

On the other hand, dead reckoning can cause errors in estimating the self-position due to disturbances such as wheel slippage of the robot 10 . In other words, the longer the moving distance of the robot 10 is, the more the probability and amount of error in estimating the self-position due to dead reckoning can increase. In this way, the self-position of the robot 10 has, for example, a Gaussian distribution error circle (hereinafter sometimes simply referred to as an error circle), and the error circle becomes larger as the movement distance increases. obtain.

Then, as the error circle becomes larger, the reliability of the self-position estimated by the robot 10 may become lower. Therefore, the robot 10 estimates its own position by performing star reckoning based on sensing information obtained by photographing the marker MA placed at a predetermined position. Since the markers are placed at predetermined positions, the robot 10 can estimate its own position with higher accuracy than dead reckoning. Therefore, it is desirable that at least one or more markers MA are installed in the environment in which the robot 10 moves.

By updating the self-position of the robot 10 estimated by dead reckoning to the self-position of the robot 10 estimated by star reckoning using the marker MA, the error circle of the self-position of the robot 10 is also reduced. can be.

For example, as shown in FIG. 3, the first robot 10A and the second robot 10B autonomously move in the environment while estimating their own position by dead reckoning. Then, the first robot 10A, which has approached the imaging range of the marker MA, further estimates its own position by star reckoning.

For example, when the movement distance of the second robot 10B from the position estimated by star reckoning is longer than that of the first robot 10A, as shown in FIG. The error circle C2 possessed by the second robot 10B can be larger than the circle C1.

As described above, the plurality of robots 10 move in a certain environment while estimating their own positions by dead reckoning. After reaching the imaging range of the marker MA, the robot 10 further estimates its own position by star reckoning. In this way, the robot 10 can move within the environment while maintaining the estimation accuracy of the self-position by updating the self-position as needed. On the other hand, there are cases where the area and the number of markers that can be placed in the environment are limited.

Therefore, the robot 10 may use another robot 10 as a star reckoning marker. For example, the second robot 10B may estimate the position of the first robot 10A based on sensing information obtained by photographing the first robot 10A. The second robot 10B may then transmit the estimated position information of the first robot 10A to the server 20 . Furthermore, the first robot 10A may transmit to the server 20 information related to its own position estimated by dead reckoning. Note that the position of the other robot 10 estimated by the robot 10 includes an error circle resulting from star reckoning in addition to the error circle associated with the self-position estimated by the robot 10 through dead reckoning.

Then, the estimating unit 221 included in the server 20 is based on the information related to the self-position of the first robot 10A received from the first robot 10A and the position information of the first robot 10A received from the second robot 10B. , to estimate the position information of the first robot 10A. A specific example of estimating the position information of the robot 10 by the estimation unit 221 according to the first embodiment will be described below with reference to FIG. Note that the first embodiment, the second embodiment, and the modifications described below may be executed in combination with each other, or only one of them may be executed without being combined.

<2.2. First embodiment>
(overview)
FIG. 4 is an explanatory diagram for explaining an overview of how the estimation unit 221 according to the first embodiment estimates the position information of the robot 10. As shown in FIG. In FIG. 4, the self-position estimated by the first robot 10A has an error circle C1 of Gaussian distribution. The position of the first robot 10A estimated by the second robot 10B by star reckoning has an error circle C3 of Gaussian distribution.

The estimation unit 221 estimates the position information of the first robot 10A by, for example, superimposing each Gaussian distribution of the position information of the first robot 10A received from the first robot 10A and the second robot 10B. may The position information of the first robot 10A estimated by superposition of Gaussian distributions has an error circle C4. As shown in FIG. 4, the error circle C4 of the position information of the first robot 10A estimated by superimposing Gaussian distributions can be smaller than the error circles C1 and C3.

Also, during star reckoning, the second robot acquires an image of the first robot 10A with the camera 110 of the second robot 10B, and estimates the position information of the first robot 10A from the image. Further, the second robot 10B holds the time when the image used for estimating the position information of the first robot 10A was taken. Then, the second robot 10B transmits to the server 20 the position information of the first robot 10A and the information about the shooting time.

At this time, the communication unit 150 may transmit, for example, the time in milliseconds and the parity bit or checksum through LED communication. Further, the communication unit 150 may transmit the position information of the first robot 10A using another communication standard such as WiFi (registered trademark).

Then, the estimation unit 221 included in the server 20 stores the Gaussian distribution of the first robot 10A estimated by the second robot by star reckoning and The position information of the first robot 10A may be estimated by superimposing the Gaussian distribution of the self-position estimated by the first robot 10A by dead reckoning.

As a result, the error circle C4 of the position information of the first robot 10A estimated by superimposing the Gaussian distributions can be smaller than the error circle C1 of the self-position recognized by the first robot 10A.

The second robot 10B may transmit the estimated position information of the first robot 10A to the server 20, and may transmit the time when the first robot 10A was photographed to the first robot 10A. In this case, the first robot 10A may transmit to the server 20 information related to its own position estimated by dead reckoning at the same time as when the image was taken by the second robot 10B.

In addition, the estimation unit 221 superimposes the Gaussian distribution of the position information of the second robot 10B received from the first robot 10A and the second robot 10B in the same manner as the method described above, thereby obtaining the position information of the second robot 10B. location information may be estimated. For example, the estimation unit 221 has a Gaussian distribution included in the position information of the second robot 10B estimated by the first robot 10A by star reckoning, and the information related to the self-position estimated by the second robot 10B by dead reckoning. The position information of the second robot 10B may be estimated by superimposing the Gaussian distribution. As a result, the estimating unit 221 can reduce the error circle included in the self-position information recognized by both the first robot 10A and the second robot 10B.

The outline of how the estimation unit 221 according to the first embodiment estimates the position information of the robot 10 has been described above. Next, an example of operation processing for estimating position information of the robot 10 by superimposing probability distributions according to the first embodiment will be described with reference to FIG.

(Example of operation processing)
FIG. 5 is an explanatory diagram for explaining an example of operation processing for estimating position information of the robot 10 by superimposing probability distributions according to the first embodiment. First, the first robot 10A moves in the environment while estimating its own position by dead reckoning (S101).

Also, like the first robot 10A, the second robot 10B moves in the environment while estimating its own position by dead reckoning (S105).

Subsequently, when the first robot 10A and the second robot 10B are within a predetermined distance, the first robot 10A takes an image of the second robot 10B (S109). Here, the predetermined distance may be any distance at which the first robot 10A can photograph the second robot 10B.

Similarly to the first robot 10A, the second robot 10B takes an image of the first robot 10A when the first robot 10A and the second robot 10B are within a predetermined distance (S113). .

Subsequently, the first robot 10A estimates position information of the second robot 10B by star reckoning based on sensing information obtained by photographing the second robot 10B (S117).

Also, the second robot 10B estimates position information of the first robot 10A by star reckoning based on sensing information obtained by photographing the first robot 10A (S121).

Subsequently, the first robot 10A transmits to the server 20 the information related to its own position and the position information of the second robot 10B estimated by star reckoning. In addition, the first robot 10A transmits to the server 20 the information about the shooting time of the image used for estimating the position information of the second robot 10B (S125).

Subsequently, the second robot 10B transmits to the server 20 the information related to its own position and the position information of the first robot 10A estimated by star reckoning. In addition, the second robot 10B transmits to the server 20 the information about the shooting time of the image used for estimating the position information of the first robot 10A (S129).

Then, the estimation unit 221 included in the server 20 superimposes the probability distribution of the position information of the first robot 10A estimated by the second robot 10B and the probability distribution of the self-position received from the first robot 10A. Thus, the position information of the first robot 10A is estimated (S133). Here, the self-position of the first robot 10A on which the probability distribution is superimposed is obtained by the first robot 10A at the same time as the photographing time of the image used by the second robot 10B for estimating the position information of the first robot 10A. It is desirable that the self-position is estimated by

Subsequently, the estimation unit 221 included in the server 20 overlaps the probability distribution of the position information of the second robot 10B estimated by the first robot 10A and the probability distribution of the self-position received from the second robot 10B. By matching, the position information of the second robot 10B is estimated (S137). Here, the self-position of the second robot 10B on which the probability distribution is superimposed is the second robot 10B at the same time as the time when the image used by the first robot 10A for estimating the position information of the second robot 10B was captured. It is desirable that the self-position is estimated by

Then, the correction unit 225 included in the server 20 generates correction information regarding the position information of the first robot 10A estimated by the estimation unit 221 and correction information regarding the position information of the second robot 10B (S141).

Then, the communication unit 210 included in the server 20 transmits the generated correction information regarding the position information of the first robot 10A to the first robot 10A (S145).

Further, the communication unit 210 included in the server 20 transmits the generated correction information regarding the position information of the second robot 10B to the second robot 10B (S149).

Subsequently, the first robot 10A corrects its own position based on the correction information received from the server 20 (S153).

Also, the second robot 10B corrects the self-position of the second robot 10B based on the correction information received from the server 20 (S157), and the information processing system according to the present disclosure ends the processing.

An example of operation processing for estimating position information of the robot 10 by superimposing probability distributions according to the first embodiment has been described above. According to the first embodiment described above, the server 20 according to the present disclosure can estimate the position information of any robot 10 with higher accuracy. By estimating the position information, it is possible to correct the position information of the plurality of robots 10 . Next, a specific example of correcting the position information of the robot 10 by the correction unit 225 according to the second embodiment will be described with reference to FIG.

<2.3. Second embodiment>
(overview)
FIG. 6 is an explanatory diagram for explaining an example of correcting the position information of the robot 10 according to the second embodiment. As described above, the robot 10 can estimate the self-position of the robot 10 with higher accuracy by photographing the marker MA as shown in FIG. 3 and performing star reckoning.

Then, the robot 10 corrects the recognized self-position from the self-position estimated by dead reckoning to the self-position estimated by star reckoning, thereby recognizing the self-position with higher accuracy. can be

On the other hand, the rapid correction of the self-position recognized by the robot 10 makes it necessary to return to the changed target path, which may make the operation of the robot 10 unstable.

Therefore, the correction unit 225 according to the present disclosure may continuously correct the position information of the robot 10 . For example, the correction unit 225 may continuously correct the position information of the robot 10 according to the movement distance of the robot 10 .

For example, the robot 10 moves while estimating its own position by dead reckoning. Here, the position of the robot 10 estimated by dead reckoning is assumed to be a self-position SL1. In estimating the self-position of the robot 10 by dead reckoning, an estimation error may increase according to the moving distance of the robot 10 as described above.

Here, assuming that the actual position of the robot 10 is the actual position RL1, as shown in FIG. can grow.

Therefore, when the robot 10 approaches a distance at which the marker installed in the environment can be photographed, the camera 110 acquires an image of the marker. Next, the estimation unit 161 estimates the self-position of the robot 10 by star reckoning based on the acquired image. Here, the self position recognized by the robot 10 by dead reckoning at the time of photographing the marker is assumed to be self position ST, and the self position estimated by star reckoning is assumed to be estimated position STL.

Then, the estimation unit 221 continues to estimate the self-position of the robot 10 by dead reckoning when the robot 10 moves. At this time, the corrected position CL1 of the robot 10 when corrected to the position estimated by star reckoning and the uncorrected position SL2 of the robot 10 when not corrected to the position estimated by star reckoning are always kept. presume.

Then, the correction unit 225 may continuously correct the position information of the robot 10 according to the movement distance of the robot 10 based on the corrected position CL1 and the uncorrected position SL2. For example, the correction unit 225 may constantly calculate the corrected position CL1 and the uncorrected position SL2, and change the usage ratio in the extended Kalman filter according to the movement distance of the robot 10, for example.

For example, the correction unit 225 of the robot 10, which has captured a certain marker and estimated its own position by star reckoning, will obtain a post-correction position CL1 after correction by star reckoning until it reaches the area where the marker is installed next time. may be continuously corrected so that the usage ratio of is from 0% to 100%. This makes it possible to suppress sudden changes in the self-position recognized by the robot 10 . The position of the robot 10 that is continuously corrected by the correction unit 225 is defined as a corrected position CL2.

Further, according to the above-described correction of the self-position recognized by the robot 10, the deviation between the actual position RL2, which is the actual position of the robot 10, and the corrected position CL2 is suppressed, and the rapid self-position of the robot 10 is corrected. can reduce the possibility that the operation of the robot 10 becomes unstable.

Further, the correction unit 225 may continuously correct the self-position recognized by the robot 10 to the position of the robot 10 estimated by the estimation unit 221 according to the first embodiment by superimposing Gaussian distributions. .

(operation processing)
FIG. 7 is an explanatory diagram for explaining an example of operation processing for correcting the position information of the robot 10 according to the second embodiment. First, the robot 10 estimates its own position by dead reckoning (S201).

Subsequently, the robot 10 transmits information on the estimated self-location to the server 20 (S205). In addition, the robot 10 may always transmit to the server 20 information about its own position estimated by dead reckoning.

Then, the camera 110 provided in the robot 10 takes a picture of the marker and acquires an image (S209).

Subsequently, the robot 10 transmits the acquired image to the server 20 (S213).

Then, the estimation unit 221 provided in the server 20 estimates the position information of the robot 10 based on the information and the image regarding the self-position acquired from the robot 10 (S217).

Then, the server 20 generates correction information for correcting the position information of the robot 10 (S221), and transmits the correction information to the robot 10 (S225). Here, the correction information includes information for continuously correcting the self-position of the robot 10 as described above.

Then, the robot 10 corrects the self-position of the robot 10 according to the correction information and the movement distance of the robot 10 (S229), and ends the processing of the information processing system according to the present disclosure.

An example of operation processing related to correction of position information of the robot 10 according to the second embodiment has been described above. Next, a modified example of the robot 10 according to the present disclosure will be described with reference to FIG. 8 .

<<3. Modification>>
FIG. 8 is an explanatory diagram for describing a modification of the robot 10 according to the present disclosure. The robot 10 according to the present disclosure may include a low power consumption microcontroller (MCU: Microcontroller Unit) MC that can operate using regenerative energy of the wheels. The microcontroller MC may implement some or all of the functions of the controller 160 .

For example, when the main power supply of the robot 10 is off, regenerated power from the power supply (Vcc) of the motor driver (DRV) may be input to the microcontroller MC. The microcontroller MC may input sensing information from the IMU 120 and the wheel encoder 130 and continuously estimate the self-position of the robot 10 by dead reckoning even while the main power is off.

As a result, the robot 10 can estimate its own position even if the position of the robot 10 is moved by an external force (for example, manual work by the user) when the main power is off.

Also, when the main power supply of the robot 10 is turned on, it is possible to eliminate the need to perform matching at all positions on the map, making it easier for star recognition to converge. Also, when the main power is turned on, it may be possible to omit the specifying operation by the user. As above, the modified example of the robot 10 according to the present disclosure has been described.

<<4. Hardware configuration example >>
The embodiment according to the present disclosure has been described above. The information processing described above is realized by cooperation between software and hardware of the server 20 described below. Note that the hardware configuration described below can also be applied to the robot 10 .

FIG. 9 is a block diagram showing the hardware configuration of the server 20. As shown in FIG. The server 20 comprises a CPU (Central Processing Unit) 2001 , a ROM (Read Only Memory) 2002 , a RAM (Random Access Memory) 2003 and a host bus 2004 . The server 20 also includes a bridge 2005 , an external bus 2006 , an interface 2007 , an input device 2008 , an output device 2010 , a storage device (HDD) 2011 , a drive 2012 and a communication device 2015 .

The CPU 2001 functions as an arithmetic processing device and a control device, and controls overall operations within the server 20 according to various programs. Also, the CPU 2001 may be a microprocessor. A ROM 2002 stores programs, calculation parameters, and the like used by the CPU 2001 . A RAM 2003 temporarily stores programs used in the execution of the CPU 2001, parameters that change as appropriate during the execution, and the like. These are interconnected by a host bus 2004 comprising a CPU bus or the like. Functions such as the estimation unit 221 and the correction unit 225 described with reference to FIG.

The host bus 2004 is connected via a bridge 2005 to an external bus 2006 such as a PCI (Peripheral Component Interconnect/Interface) bus. It should be noted that the host bus 2004, bridge 2005 and external bus 2006 do not necessarily have to be configured separately, and these functions may be implemented in one bus.

The input device 2008 includes input means for the user to input information, such as a mouse, keyboard, touch panel, button, microphone, switch, and lever, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 2001 . etc. By operating the input device 2008, the user of the server 20 can input various data to the server 20 and instruct processing operations.

The output device 2010 includes display devices such as liquid crystal display devices, OLED devices, and lamps, for example. Further, output device 2010 includes audio output devices such as speakers and headphones. The output device 2010 outputs reproduced content, for example. Specifically, the display device displays various information such as reproduced video data as text or images. On the other hand, the audio output device converts reproduced audio data and the like into audio and outputs the audio.

The storage device 2011 is a device for storing data. The storage device 2011 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, a deletion device that deletes data recorded on the storage medium, and the like. The storage device 2011 is composed of, for example, an HDD (Hard Disk Drive). The storage device 2011 drives a hard disk and stores programs executed by the CPU 2001 and various data.

The drive 2012 is a reader/writer for storage media, and is built in or externally attached to the server 20 . The drive 2012 reads out information recorded on a removable storage medium 2018 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 2003 . Drive 2012 can also write information to removable storage media 3018 .

The communication device 2015 is, for example, a communication interface configured with a communication device or the like for connecting to the network 1. Also, the communication device 2015 may be a wireless LAN compatible communication device, an LTE (Long Term Evolution) compatible communication device, or a wire communication device that performs wired communication.

<<5. Supplement >>
Although the preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, the present disclosure is not limited to such examples. It is clear that a person having ordinary knowledge in the technical field to which the present disclosure belongs can conceive of various modifications or modifications within the scope of the technical idea described in the claims. It is understood that these also naturally belong to the technical scope of the present disclosure.

For example, the robot 10, as an example of an information processing device, may have a configuration having various functions of the server 20 described in this specification. For example, the function of the estimation unit 221 provided in the server 20 may be realized by the estimation unit 161 provided in the robot 10 , and the robot 10 may further include a configuration having the function of the correction unit 225 .

Also, the server 20 according to the first embodiment may acquire position information of the third robot estimated by each of the first robot 10A and the second robot 10B by star reckoning. Then, the estimating unit 221 may estimate the position of the third robot by superimposing the two acquired Gaussian distributions of the position information of the third robot.

Also, each step in the processing of the information processing system in this specification does not necessarily have to be processed in chronological order according to the order described as the flowchart. For example, each step in the processing of the information processing system may be processed in an order different from the order described as the flowchart or in parallel.

It is also possible to create a computer program that causes hardware such as the CPU, ROM, and RAM built into the robot 10 and the server 20 to exhibit functions equivalent to the respective configurations of the robot 10 and the server 20 described above. A non-transitory storage medium storing the computer program is also provided.

Also, the effects described in this specification are merely descriptive or exemplary, and are not limiting. In other words, the technology according to the present disclosure can produce other effects that are obvious to those skilled in the art from the description of this specification, in addition to or instead of the above effects.

Note that the following configuration also belongs to the technical scope of the present disclosure.
(1)
an acquisition unit that acquires a plurality of pieces of position information of an arbitrary moving object based on sensing information obtained by sensors mounted on each of the plurality of moving objects;
an estimating unit that estimates the position information of the arbitrary moving object by superimposing the probability distributions of the plurality of position information of the arbitrary moving object acquired by the acquiring unit;
An information processing device.
(2)
the arbitrary moving body is included in the plurality of moving bodies,
The acquisition unit
Acquiring information related to the self-position of the arbitrary mobile body and position information of the arbitrary mobile body estimated by another mobile body different from the arbitrary mobile body among the plurality of mobile bodies,
The information processing device according to (1) above.
(3)
The acquisition unit
Acquiring information about the time when the other mobile body acquired the position information of the arbitrary mobile body;
The information processing device according to (2) above.
(4)
The estimation unit
The position information of the arbitrary mobile body estimated by the other mobile body and the self-position of the arbitrary mobile body acquired at the time when the other mobile body acquired the position information of the arbitrary mobile body estimating the position information of the arbitrary moving object by superimposing the probability distribution with such information;
The information processing apparatus according to (2) or (3).
(5)
The acquisition unit
Acquiring information related to the self-position of the arbitrary mobile body based on sensing information obtained by an internal sensor mounted on the arbitrary mobile body;
The information processing apparatus according to any one of (1) to (4).
(6)
The acquisition unit
Acquiring position information of the arbitrary mobile body estimated based on sensing information obtained by an external sensor mounted on the other mobile body;
The information processing device according to (5) above.
(7)
The acquisition unit
The arbitrary mobile body estimated based on the sensing information obtained by the external sensor mounted on the other mobile body when the arbitrary mobile body and the other mobile body are within a predetermined distance. to get the location of
The information processing device according to (6) above.
(8)
a correction unit that corrects the position information of the arbitrary moving body to the position information estimated by the estimation unit;
The information processing apparatus according to any one of (1) to (7), further comprising:
(9)
The acquisition unit
Acquiring position information of the arbitrary mobile body obtained by detecting a feature installed in a predetermined area by an external sensor mounted on the arbitrary mobile body,
The correction unit is
correcting the position information of the arbitrary moving body to the position information of the arbitrary moving body obtained by the external sensor detecting the feature;
The information processing device according to (8) above.
(10)
The correction unit is
continuously correcting the position information of the arbitrary moving object;
The information processing device according to (9) above.
(11)
The correction unit is
continuously correcting the position information of the arbitrary moving body according to the movement distance of the arbitrary moving body;
The information processing device according to (10) above.
(12)
The estimation unit
estimating position information when the position information of the arbitrary moving body is not corrected and position information when the position information of the arbitrary moving body is corrected when the arbitrary moving body moves;
The correction unit is
the arbitrary moving object based on the position information when the position information of the arbitrary moving object estimated by the estimation unit is not corrected and the position information when the position information of the arbitrary moving object is corrected; to correct the location information of
The information processing device according to (11) above.
(13)
The correction unit is
continuously correcting the position information of the arbitrary moving body until the arbitrary moving body reaches the area where the next feature is installed from the area where the feature is installed;
The information processing device according to (12) above.
(14)
The plurality of mobile bodies have wheels, and self-positions are always estimated using regenerative energy generated by the rotation of the wheels.
The information processing apparatus according to any one of (1) to (13) above.
(15)
Acquiring a plurality of positional information of an arbitrary moving body based on sensing information obtained by sensors mounted on each of a plurality of moving bodies;
estimating the location information of the arbitrary moving object by superimposing the obtained probability distributions of the plurality of location information of the arbitrary moving object;
A computer-implemented information processing method comprising:
(16)
to the computer,
an acquisition function for acquiring a plurality of pieces of position information of an arbitrary moving object based on sensing information obtained by sensors mounted on each of a plurality of moving objects;
an estimating function for estimating the location information of the arbitrary moving object by superimposing the probability distributions of the plurality of location information of the arbitrary moving object acquired by the acquiring function;
A program that realizes

1 network 10 robot 110 camera 120 IMU
130 wheel encoder 140 storage unit 150 communication unit 160 control unit 161 estimation unit 20 server 210 communication unit 220 control unit 221 estimation unit 225 correction unit

Claims

an acquisition unit that acquires a plurality of pieces of position information of an arbitrary moving object based on sensing information obtained by sensors mounted on each of the plurality of moving objects;
an estimating unit that estimates the position information of the arbitrary moving object by superimposing the probability distributions of the plurality of position information of the arbitrary moving object acquired by the acquiring unit;
An information processing device.
the arbitrary moving body is included in the plurality of moving bodies,
The acquisition unit
Acquiring information related to the self-position of the arbitrary mobile body and position information of the arbitrary mobile body estimated by another mobile body different from the arbitrary mobile body among the plurality of mobile bodies,
The information processing device according to claim 1 .
The acquisition unit
Acquiring information about the time when the other mobile body acquired the position information of the arbitrary mobile body;
The information processing apparatus according to claim 2.
The estimation unit
The position information of the arbitrary mobile body estimated by the other mobile body and the self-position of the arbitrary mobile body acquired at the time when the other mobile body acquired the position information of the arbitrary mobile body estimating the position information of the arbitrary moving object by superimposing the probability distribution with such information;
The information processing apparatus according to claim 3.
The acquisition unit
Acquiring information related to the self-position of the arbitrary mobile body based on sensing information obtained by an internal sensor mounted on the arbitrary mobile body;
The information processing apparatus according to claim 4.
The acquisition unit
Acquiring position information of the arbitrary mobile body estimated based on sensing information obtained by an external sensor mounted on the other mobile body;
The information processing device according to claim 5 .
The acquisition unit
The arbitrary mobile body estimated based on the sensing information obtained by the external sensor mounted on the other mobile body when the arbitrary mobile body and the other mobile body are within a predetermined distance. to get the location of
The information processing device according to claim 6 .
a correction unit that corrects the position information of the arbitrary moving body to the position information estimated by the estimation unit;
further comprising
The information processing apparatus according to claim 7.
The acquisition unit
Acquiring position information of the arbitrary mobile body obtained by detecting a feature installed in a predetermined area by an external sensor mounted on the arbitrary mobile body,
The correction unit is
correcting the position information of the arbitrary moving body to the position information of the arbitrary moving body obtained by the external sensor detecting the feature;
The information processing apparatus according to claim 8 .
The correction unit is
continuously correcting the position information of the arbitrary moving object;
The information processing apparatus according to claim 9 .
The correction unit is
continuously correcting the position information of the arbitrary moving body according to the movement distance of the arbitrary moving body;
The information processing apparatus according to claim 10.
The estimation unit
estimating position information when the position information of the arbitrary moving body is not corrected and position information when the position information of the arbitrary moving body is corrected when the arbitrary moving body moves;
The correction unit is
the arbitrary moving object based on the position information when the position information of the arbitrary moving object estimated by the estimation unit is not corrected and the position information when the position information of the arbitrary moving object is corrected; to correct the location information of
The information processing device according to claim 11 .
The correction unit is
Continuously correcting the position information of the arbitrary moving body until the arbitrary moving body reaches the area where the next feature is installed from the area where the feature is installed;
The information processing apparatus according to claim 12.
The plurality of mobile bodies have wheels, and self-positions are constantly estimated using regenerative energy generated by the rotation of the wheels.
The information processing apparatus according to claim 13.
Acquiring a plurality of pieces of position information of an arbitrary moving object based on sensing information obtained by sensors mounted on each of the plurality of moving objects;
estimating the location information of the arbitrary moving object by superimposing the obtained probability distributions of the plurality of location information of the arbitrary moving object;
A computer-implemented information processing method comprising:
to the computer,
an acquisition function for acquiring a plurality of pieces of position information of an arbitrary moving object based on sensing information obtained by sensors mounted on each of the plurality of moving objects;
an estimating function for estimating the location information of the arbitrary moving object by superimposing the probability distributions of the plurality of location information of the arbitrary moving object acquired by the acquiring function;
A program that realizes