Information processing apparatus and information processing method

Abstract

To provide an information processing apparatus for allowing a service client to select a service provider that matches work requirements.SOLUTION: An information processing apparatus includes: workability information acquisition means for acquiring workability information related to a space in which a robot work service provider can provide work in association with the robot work service provider; first spatial information generation means for generating first spatial information related to the space based on the information acquired by the workability information acquisition means; work request information acquisition means for acquiring work request information related to a space in which a robot work service client desires to work in association with the robot work service client; second spatial information generation means for generating second spatial information related to the space based on the information acquired by the work request information acquisition means; and degree-of-match determination means for determining a degree of match based on the first spatial information and the second spatial information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technology for providing work by a robot. [Background technology]

[0002] In recent years, the use of robots has progressed in various fields. While there is a desire to introduce robots, robot sharing services have emerged due to cost considerations. Patent Document 1 proposes a system that accumulates the work records of robots and reserves a robot suitable for the work content you want to reserve. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2020-46791 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the method of Patent Document 1, if there are multiple companies that provide robotic work as a service, the person requesting the service cannot select a company that meets the work requirements. The present invention has been made in consideration of the above-mentioned problems, and aims to enable a person requesting a robot-based work service to select from a plurality of service providers a service provider that meets the work requirements. [Means for solving the problem]

[0005] In order to solve the above problems, the information processing device of the present invention is characterized by comprising: a work availability information acquisition means for acquiring work availability information regarding a space in which a robot work service provider can work, in association with the robot work service provider; a first space information generation means for generating first space information regarding the space based on the information acquired by the work availability information acquisition means; a work request information acquisition means for acquiring work request information regarding a space in which a robot work service client wishes to work, in association with the robot work service client; a second space information generation means for generating second space information regarding the space based on the information acquired by the work request information acquisition means; and a match determination means for determining a match based on the first space information and the second space information. [Effects of the Invention]

[0006] According to the present invention, a requester of a robot-based work service can select a service provider that meets the work requirements desired by the requester from among a plurality of service providers. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is an explanatory diagram illustrating the use of an information processing device according to the present invention. [Figure 2] 1 is a functional block diagram illustrating an example of an information processing device according to a first embodiment. [Figure 3] 1 is a block diagram illustrating an example of a hardware configuration of an information processing apparatus according to a first embodiment. [Figure 4] 10 is a flowchart illustrating an example of an operation of the information processing device according to the first embodiment. [Figure 5] 10 is a flowchart illustrating an example of an operation of a first space information generating unit in the information processing device according to the first embodiment. [Figure 6] FIG. 10 is a functional block diagram illustrating an example of an information processing device according to a fifth embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of a display device of an information processing device according to a fifth embodiment. [Figure 8]10 is a flowchart illustrating an example of an operation of the information processing device according to the first modification. DETAILED DESCRIPTION OF THE INVENTION

[0008] In this embodiment, a user is assumed to be a requester of robot work services. An information processing device is described that determines the degree of match between the requester's request and the service provider's track record so that the user can select a robot work service provider that meets the user's work requirements. In this embodiment, the user's work requirement is that the space in which the provider can perform the robot work and the space in which the requester wishes to request the robot work are similar. To determine the degree of match, the information processing device in this embodiment acquires space information from the service requester and the service provider. Here, space information refers to information about the location where the robot will actually perform the work, and is information that can identify the types of objects present in that location and the positions of each object. The degree of match represents the degree of similarity between the work space in which the robot work service provider can perform the robot work and the space in which the requester wishes to request the robot work service, as determined from the space information. In this embodiment, the more similar the objects present in the space and their placement, the greater the match. Note that the configuration shown in this embodiment is merely an example, and the present invention is not limited to the illustrated configuration.

[0009] FIG. 1 shows a diagram using an information processing device of the present invention. The information processing device of this embodiment is implemented using a PC 100. Reference numeral 101 denotes a display device. A user, a robot work service requester 102, inputs a group of work images of the space in which the user wishes to request work as work request information 103 into the information processing device. Robot work service providers 104a to 104c input work availability information 105a to 105c into PC 100 as information indicating the conditions under which they are each available to work. PC 100 determines the degree of match and displays the result on display device 101.

[0010] A functional block diagram showing an information processing device of the present invention is shown in Figure 2. Note that the functional blocks shown in Figure 2 do not have to be built into the same housing, and may be configured as separate devices connected to each other via signal paths.

[0011] The information processing device 200 according to this embodiment is composed of a work availability information acquisition unit 210, a first space information generation unit 220, a work request information acquisition unit 230, a second space information generation unit 240, and a matching degree determination unit 250. The work availability information acquisition unit 210 acquires, from the robot work service provider 104, a group of captured images of a space in which the robot work service provider 104 is capable of robot work, as work availability information. The work availability information acquisition unit 210 acquires the work availability information in association with the robot work service provider 104. The work request information acquisition unit 230 acquires, as work request information, a group of captured images of a space in which a requester wishes to request robot work. The work request information acquisition unit 230 acquires the work request information in association with the robot work service requester 102.

[0012] The first space information generation unit 220 generates first space information from the work availability information of the robot work service provider 104 acquired by the work availability information acquisition unit 210. The second space information generation unit 240 generates second space information from the work request information of the robot work service client 102 acquired by the work request information acquisition unit 230. The match degree determination unit 250 determines the match degree based on the first space information generated by the first space information generation unit 220 and the second space information generated by the second space information generation unit 240.

[0013] FIG. 3 is a block diagram showing the hardware configuration of the information processing device 200. 311 denotes a CPU, which functions as a control unit that controls the operation of each unit of the device connected to a system bus 321 based on a computer program stored in a memory (such as a ROM 312) serving as a storage medium. 312 denotes a ROM that stores a BIOS program, a boot program, and other computer programs. 313 denotes a RAM that is used as the main memory of the CPU 311. 314 denotes an external memory such as an HDD or SSD that stores programs processed by the information processing device 200. An input unit 315 performs processing related to the input of information, etc., using a keyboard or mouse. A display unit 316 outputs the results of calculations performed by the information processing device 200 to a display device in accordance with instructions from 311. The display device may be of any type, such as a liquid crystal display device, a projector, or an LED indicator. The display device may be one that is included in the information processing device 200.

[0014] Reference numeral 317 denotes a communication interface that communicates information via a network; the communication interface may be Ethernet, or any type of interface such as USB, serial communication, or wireless communication. The communication interface 317 also communicates with an external server and stores various data in the external server. Reference numeral 318 denotes an I / O that inputs information on robot work capabilities from the robot work service provider 104 and inputs work request information to be requested from the robot work service requester 102. The I / O also outputs the results of the degree of match determined by the degree of match determination unit 250 to the robot work service requester 102, who is the user.

[0015] 1 are realized by causing the CPU 311 included in the information processing device 200 to execute a computer program stored in a memory (such as the ROM 312 or the external memory 314) serving as a storage medium. However, some or all of these may be realized by hardware. The hardware may be a dedicated circuit (ASIC), a processor (a reconfigurable processor, a DSP), or the like.

[0016] 4 is a flowchart illustrating the operation of the information processing device 200. Hereinafter, the flowchart is assumed to be realized by the CPU executing a computer program stored in a memory (such as the ROM 312) serving as a storage medium.

[0017] In this embodiment, the process is divided into the following two processing flows. The first is a processing flow for generating first spatial information from work availability information acquired from the robot work service provider 104. The second is a processing flow for generating second spatial information from the first spatial information and work request information acquired from the client, and determining the degree of match. The processing flow for generating the first spatial information is shown in Fig. 4(A) The information processing device 200 starts operating at any timing when the robot work service provider 104 registers the work availability information.

[0018] In step S400, the work availability information acquisition unit 210 acquires work availability information from the robot work service provider 104. In this embodiment, the work availability information is input as information on the actual work performed by the robot work service provider 104. The proven work information includes a group of images taken by a camera mounted on the robot, the position and orientation of the camera at the point where the images were taken, and three-dimensional position information of feature points on the surface of an object in the captured images.

[0019] In this embodiment, the robot travels autonomously while calculating the position and orientation of the camera using Visual SLAM (Simultaneous Localization and Mapping) that uses images captured by the onboard camera. Each captured image and the position and orientation information of the camera are associated and stored. The captured image group, which is proven work information, is made up of images captured at a predetermined time interval or a predetermined distance interval from among the captured images used in SLAM processing.

[0020] In step S401, the first space information generation unit 220 generates first space information from the information acquired in step S400. In this embodiment, the first space information is an object arrangement characteristic database.

[0021] The detailed processing flow of step S401 is shown in Figure 5. In step S500, the type and position of objects contained in the captured images are recognized. Object type recognition is performed by a neural network that has been trained to output the type of object shown in the image and the position of the object in the image when an image is input.

[0022] The method for recognizing the position of each object type is as follows. First, the 3D position information of the object is obtained from the position information of the object in the image obtained by the neural network and the 3D position information of feature points in the captured image obtained by SLAM processing. Then, by combining this with the position and orientation information of the camera at the point where each captured image was taken, the position information of the object in 3D space is obtained. At this time, all position information is unified into the 3D coordinate system defined by SLAM processing.

[0023] Next, an object type vector and a position vector are generated based on the recognized object type and object position. The object type vector is a one-dimensional column vector, and the first element is a CLS token (a special vector indicating the beginning of data). Next, the object type labels of objects present in the environment are arranged, with the object label corresponding to the first object type information included in the object type information group, followed by the label corresponding to the second object type information, and so on. In addition, a MASK token (a special label indicating that the object type is unknown) is placed as a label corresponding to unknown objects that have not yet been identified. In this embodiment, a numeric label is defined in advance for each object type, and the recognized object type is converted into a numeric label to create an object type vector.

[0024] A position vector is a one-dimensional column vector consisting of three elements, each of which represents the three-dimensional position X, Y, and Z of each object. In other words, each column of the position vector stores the X, Y, and Z values ​​that are the position coordinates of the object in the corresponding column of the object type vector.

[0025] Then, in step S501, an object placement characteristic database is constructed using the information on the recognized object type and object position. The object placement characteristic database is a database that stores placement characteristics that represent the positional relationships of multiple objects. The placement characteristics are knowledge data that indicate the tendency of the three-dimensional positional relationships of objects in the space where the work is performed.

[0026] The object placement characteristic database in this embodiment learns the types and placement relationships of objects in the space where the robot work service provider 104 can work as a neural network. Specifically, it is a neural network in which 24 layers of Ashish et al.'s Transformer ("Attention is All You Need", Ashish et al. NeuralIPS 2017) are stacked. In this embodiment, the number of input dimensions and output dimensions of the Transformer is 512, that is, a maximum of 512 pieces of object characteristic information are input, and the same number of 512-dimensional output is obtained. Specifically, the encoder network used in the method by Jacob et al. is used. (Jacob et al., BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, arXiv 2018)

[0027] The object characteristic information uses the object type vector and position vector generated in step S500.

[0028] The process flow for determining the degree of match is shown in Fig. 4(B). In step S402, the work request information acquisition unit 230 acquires work request information related to the space from the person requesting the robot work. In this embodiment, the work request information includes a group of captured images of the space where the robot work is requested, information about the position and orientation of the camera when capturing the images, and information about the three-dimensional position of the surface of the object in the captured images.

[0029] In step S403, the second space information generation unit 240 generates second space information using the information acquired in step S402 as input. Here, an object type vector and a position vector in the work request space are generated. The method of generating the object type vector and the position vector is the same as in step S401. That is, the second space information generation unit generates second space information related to the space based on the information acquired by the work request information acquisition unit. The second space information generation unit generates object type information indicating the type and position information of each of multiple objects present in the space where the robot work service requester desires work to be performed.

[0030] In step S404, the match determination unit 250 determines the match based on the first spatial information generated in step S401 and the second spatial information generated in step S403. The object type vector and position vector, which are the second spatial information, are input to the object placement characteristic database, which is the first spatial information. The output object type vector and position vector (third spatial information) are then compared with the object type vector and position vector of the input second spatial information, and the match is determined from the degree of match between the position vectors of each object type. The third spatial information generation means generates third spatial information related to space, information including object type information and position information.

[0031] The degree of match of the position vectors for each object type is determined by first comparing the object type group in the second spatial information with the object type group in the third spatial information in order, and excluding object types and position vector information that do not match from the second spatial information and the third spatial information. For each remaining object type, the distance between the position in the second spatial information and the position in the third spatial information is calculated. If the calculated distance is less than a threshold, 1 is added to the degree of match. This process is performed for all remaining object types, and the degree of match is determined by averaging the values ​​of 1 or 0 calculated for each object type. This is the processing flow executed by the information processing device.

[0032] According to this embodiment, a requester of a robot work service can select a robot work service provider that meets the work requirements.

[0033] In this embodiment, the requester of the robot work is assumed to be a user. The degree of match determined by the degree of match determination unit 250 can be used to determine whether or not to request the robot work service provider 104. The higher the degree of match, the more similar the work space desired by the robot work service requester 102 is to the workable space of the robot work service provider 104. Therefore, since the requested space is less difficult for the robot work service provider 104, the robot work service requester 102 may select a robot work service provider 104 with a high degree of match from among multiple robot work service providers 104. In other words, the degree of match determination unit 250 determines the degree of match based on first space information related to a specific robot work service requester and second space information related to multiple robot work service requesters.

[0034] In this embodiment, the object placement characteristic database used to generate the first or second spatial information is a neural network model using a Transformer, but is not limited to this. As long as it can recognize the placement characteristics of objects, it can be any network, such as a convolutional network, a fully connected network, or an RCN, and is not particularly limited. It may also be a database that stores object placement characteristic group information. When using such a database, this can be achieved by configuring it to output similar object characteristic group information, the most frequent object characteristic group information, or the most similar object characteristic group information from the registered object characteristic group information. Using such a configuration can be achieved with a smaller amount of calculation than a neural network.

[0035] Furthermore, although the above description has been given of object type vectors and position vectors being input to the object placement characteristic database, this is not limiting. Any expression that expresses object type information and position information for each object in a manner that can be recognized by the object placement characteristic database will suffice. For example, object type information may be an alphabetic label instead of a numeric label, or may be character string data representing the name of the object. Regarding the position information for each object, the ID of the voxel in which the object is located may be used instead of X, Y, and Z coordinate values ​​in three-dimensional space.

[0036] Furthermore, the spatial information on work history acquired from the robot work service provider 104 is a group of images taken by a camera mounted on the robot and the position and orientation of the camera at the point where the images were taken, but this is not limited to this. As long as the type and position of the object can be identified, the method of acquiring the information is not limited. For example, images taken by a camera not mounted on the robot, such as a surveillance camera, may also be used as input.

[0037] Furthermore, object type and object position information may be extracted from a layout diagram of the work area, rather than from images captured by a camera. Here, an object layout diagram is a plan view of space in which object types are superimposed in association with positions corresponding to the positions of objects existing in space. From this layout diagram, relative position information of objects can be obtained. Furthermore, digital data recording object types and positions may be used instead of a physical layout diagram. In this case, object positions may be expressed as three-dimensional position information in space, rather than two-dimensional position information on a plane. Drawing information such as that described above allows for more accurate acquisition of object type and position information.

[0038] Furthermore, instead of images captured by a camera, information measured by a different sensor other than a camera, such as LiDAR, that can measure the shape of a space and the distance to an object, can be used in conjunction with object type information. This allows the distance between the measurement point and the object to be measured, and can be used to calculate the position of each object, which is used to calculate the position vector. In this case, it is possible to calculate the object position from the sensor measurement value, without using SLAM or calculating the object position from captured images.

[0039] Furthermore, although the spatial information with work experience acquired from the robot work service provider 104 includes the group of captured images as well as the position and orientation of the camera, which are the results of previously performing SLAM processing, and the three-dimensional position information of feature points on the captured images, this is not limited to this. The spatial information with work experience may be only the group of captured images, and the first spatial information generation unit 220 may perform SLAM processing using the group of captured images to calculate the position and orientation of the camera and the three-dimensional position information of feature points corresponding to objects on the captured images.

[0040] As described above, the work request information acquired from the robot work service client 102 includes, in addition to the group of captured images, the position and orientation of the camera, which are the results of SLAM processing performed in advance, and 3D position information of feature points on the captured images, but this is not limited to this. The work request information may include only the group of captured images, and the second spatial information generation unit 240 may perform SLAM processing using the group of captured images to calculate the position and orientation of the camera and 3D position information of feature points corresponding to objects on the captured images.

[0041] Regarding the method for calculating the degree of match of the position vectors of each object type in the method for determining the degree of match, the degree of match is calculated based on whether the distance between the result of searching the first spatial information and the same type of object in the second spatial information is equal to or greater than a predetermined threshold, but the method is not limited to this. Multiple predetermined thresholds may be set, and multiple numerical values ​​may be prepared to be set according to the thresholds, and these numerical values ​​may be added together. The tolerance for the amount of change for each object type differs. By setting a threshold, it is possible to take into account the tolerance for each object type. Alternatively, the amount of change may be added directly, and the reciprocal thereof may be used as the degree of match. This makes it possible to directly reflect the magnitude of the amount of change in the degree of match.

[0042] The method for calculating the degree of match between position vectors of each object type in the method for determining the degree of match has been described as being calculated based on the positions of objects of the same type, but this is not limited to this. It is also possible to calculate the number of objects of the same type for the third spatial information and the second spatial information, which are search results of the first spatial information, and determine that the greater the number, the higher the degree of match. This makes it possible to evaluate the degree of match even when the accuracy of measuring the object positions is low.

[0043] Furthermore, the degree of match may be determined based on both the positions of the same type of object and the number of objects of the same type. In this case, it goes without saying that the closer the positions of the same type of object are and the greater the number of objects of the same type, the higher the degree of match.

[0044] The degree of match may be normalized by dividing it by the number of objects, which makes it possible to compare the degrees of match even when the number of objects in the requested space differs among multiple pieces of work request information.

[0045] Furthermore, when presenting the results of the degree of match to the user, factors that contributed to a high or low degree of match may also be output. A predetermined number of object types with high positional match are selected from the top, and those object types are output as factors contributing to a high degree of match. On the other hand, a predetermined number of object types with low positional match are selected from the bottom, and output as factors contributing to a low degree of match. Furthermore, if there is an object type that exists only in either the third spatial information or the second spatial information, that object type will be output as a factor contributing to a low degree of match, as it will be a factor contributing to a low degree of match.

[0046] The proposed method may be used to determine the degree of match between the requester's workspace and the user's available workspace, with the robot work service provider 104 as the user. In this case, the requester may be multiple people, and the degree of match may be output for each requester. The user can determine the difficulty of the requester's work based on the obtained degree of match. Specifically, the higher the degree of match, the closer the requester's workspace is to the space where the user has worked, and therefore the lower the degree of difficulty of the work can be determined. The robot work service requester 102 may be a user, and the degree of match with multiple robot work service providers 104 may be determined, and the results may be presented to the user as a ranking in descending order of degree of match. [Example 2]

[0047] In Example 1, the degree of match was determined by comparing the positional relationship of objects existing in space with the spatial information of the robot work service provider's proven track record and the spatial information of the space that the robot work service requester wanted to request.

[0048] In this embodiment, the values ​​of parameters (hereinafter referred to as "spatial information parameters") related to the difficulty of the task and the time required for the task are determined from the positional relationship of the objects.The degree of match is then determined based on the degree of proximity between the values ​​of the spatial information parameters of the robot task service provider's track record and the request of the robot task service client.Only the differences from the first embodiment will be briefly explained.

[0049] In this embodiment, the configuration diagram and processing flow are the same as in the first embodiment. The method of recognizing the placement information of each object type is the same as in the first embodiment, using an object placement characteristic database. In this embodiment, it is assumed that the robot will perform three types of work: cleaning, delivery, and security. Spatial information parameters to be considered for each robot work type are defined in advance. Spatial information parameters are generated for each robot work type.

[0050] First, we define spatial information parameters common to cleaning, delivery, and security work types. We define the width of the aisle and the size of the steps as essential conditions for the robot to move.

[0051] Next, spatial information parameters are defined for each robot work type. If the robot's work type is cleaning, the material to be cleaned is added to the spatial information parameters. The material is necessary as information to determine the cleaning method, such as wiping with water or suction. If the robot's work type is delivery, the spatial parameter is the number of times the robot turns along the delivery route. For delivery work, it is necessary to determine whether the package can be delivered safely. Therefore, a condition for stable delivery is whether the route has few turns. If the robot's work type is security, spatial information parameters are not added.

[0052] In step S400, the work availability information acquisition unit 210 acquires work availability information associated with the robot service work provider. The work availability information in this embodiment is the same as in embodiment 1 and is as follows: a group of images captured by a camera, the position and orientation of the camera at the point where the images were captured, three-dimensional position information of feature points on the surface of an object in the captured images, and information required to calculate each spatial information parameter. Specifically, the additional information required to calculate the passage width is the orientation and size of the object in space. The additional information required to calculate the material is the material type and position information of each material. The additional information required to calculate the number of turns is information regarding the robot's movement path.

[0053] In step S401, the work availability information acquisition unit 210 generates first spatial information from the information acquired in association with the robot work service provider. Note that the position information in this embodiment is unified into the coordinate system defined by the SLAM processing, as in the first embodiment.

[0054] When the spatial information parameter includes aisle width, the object placement characteristic database generated as the first spatial information is as follows: It contains four items: an object type vector indicating the object type, a position vector indicating the object's position information, an orientation vector indicating the object's orientation, and a size vector indicating the object's length, width, and width. Regarding the orientation of an object, for example, if the shape is close to a rectangle, the direction parallel to the long side is considered the object's orientation, and the system is trained to output results that are close to human subjectivity for recognition. The length, width, and width of an object are defined as the size in the same direction as the orientation vector as width, the perpendicular direction as length, and the vertical direction as width.

[0055] When there is a step in the spatial information parameters, the object position information is calculated by taking the position information measured at the object's position on the floor surface as a position vector, and generating an object placement characteristics database by inputting the object type vector and position vector. At this time, the position information converted into a position vector is expressed in the coordinate system for SLAM processing.

[0056] If the spatial information parameters include a material, the object's position and material type are recognized based on the workable information. The object's position is recognized in the same manner as in step S401. The object's material is recognized by a neural network that has been trained to input an image and output the object's type and material shown in the image. Position vector information for the material type is generated by associating the object's position vector with each object's material. The material type vector and the position vector listing the material positions are added to the object placement characteristics database.

[0057] If the spatial information parameters include the number of turns, a waypoint vector is added as path information to generate the object placement characteristic database. A waypoint is a point along the robot's path. In this embodiment, the position of the waypoint is expressed by X, Y, and Z coordinate values ​​in the three-dimensional space of the coordinate system defined by SLAM processing.

[0058] In step S402, the work request information acquisition unit 230 acquires, as work request information, information on the type, position, orientation, and size of the object, similar to the work availability information in step S400. If the work type of the robot is delivery, it also acquires the position information of the waypoint.

[0059] In step S403, a vector, which is second spatial information, is generated from the work request information acquired in step S402. The generated vector is the same as the vector input to the object arrangement characteristic database in step S401.

[0060] In step S404, the match determination unit 250 searches the object placement characteristic database, which is the first space information, by inputting the object type information and position information contained in the second space information as keys, and obtains third space information including the object type information and position information. Next, the match determination unit 250 determines the match by comparing the values ​​of the object type information and position information obtained from the third space information with the values ​​of the object type information and position information obtained from the second space information.

[0061] That is, the work availability information acquisition unit 210 acquires work availability information related to the space in which the robot work service provider can work, in association with the robot work service provider. The first space information generation unit 220 generates first space information related to the space, which is an object placement characteristic database representing the placement relationship of multiple objects in the space in which the robot work service provider can work, based on the information acquired by the work availability information acquisition unit 210. The work request information acquisition unit 230 acquires work request information related to the space in which the robot work service client wishes to work, in association with the robot work service client. The second space information generation unit 240 generates second space information, which is object type information representing the type and location information of each of multiple objects present in the space in which the robot work service client wishes to work, based on the information acquired by the work request information acquisition unit 230. The third space information generation means searches the object placement characteristic database using the object type information and location information included in the second space information as keys, and generates third space information, which is information including the object type information and location information. The match determination unit 250 determines the match based on the object type information and position information included in the third space information and the object type information and position information included in the second space information.

[0062] Next, we will explain how to calculate the values ​​of spatial information parameters. When calculating the parameter value for aisle width, the distance to the nearest object for each object is calculated in the input and output vectors. Since the position, orientation, and size of each object are known, the outer frame of the object is obtained, and the shortest distance between the outer frames of the objects is calculated to determine the distance to the nearest object. The distance to the nearest object is calculated for each object, and a list of these values ​​is stored as the parameter value.

[0063] To find the step, calculate the difference in coordinate values ​​of the components perpendicular to the floor among the coordinate components that represent the positions of the nearest objects in the input and output vectors. Calculate the height difference between each object and the nearest object, and store a list of these values ​​as parameter values.

[0064] To calculate the number of turns, the nearest waypoints are connected by a line segment, and the robot is defined as turning if the angle between the two line segments at each waypoint is equal to or greater than a predetermined threshold, and the number of turns is counted.

[0065] When you request a material, you get a list of material types.

[0066] The degree of match is calculated by multiplying the evaluation value calculated for each spatial information parameter by a coefficient determined for each spatial information parameter and summing the results for the spatial information parameter group. However, if any of the evaluation values ​​of the spatial information parameters is negative, the degree of match is set to -1.

[0067] The aisle width evaluation value is the minimum aisle width calculated based on the input vector minus the minimum aisle width calculated based on the output vector. The step evaluation value is the maximum step calculated based on the output vector minus the maximum step calculated based on the input vector. The number of turns evaluation value is the number of turns calculated based on the output vector minus the number of turns calculated based on the input vector. The material evaluation value is 1 if all of the material types included in the input vector are included in the output vector, and -1 if not.

[0068] This concludes the description of Example 2. Door width information may be added to the passage width of the spatial information parameters. When working in multiple rooms, it becomes possible to reflect in the degree of match whether or not the door width can be passed through.

[0069] Although the method of calculating the degree of match has been described as multiplying the evaluation value calculated for each spatial information parameter by a coefficient determined for each spatial information parameter and then summing the results for the spatial information parameter group, this is not limited to this. The evaluation value may be expressed as 1 or 0 instead of a value calculated using a method defined for each spatial information parameter. This makes it possible to calculate the degree of match using only matching spatial information parameters.

[0070] Weights may also be set taking into account the importance of spatial information parameters. Specifically, a larger weight is assigned to the passage width and step height than to other spatial information parameters. This makes it possible to determine a match that reflects whether each spatial information parameter is an essential condition that must be met, or whether it is a parameter that the user wants to emphasize.

[0071] Furthermore, the importance of this spatial information parameter can be determined not only based on whether or not the robot can operate, but also based on whether or not it is important to the robot work service provider 104 or the robot work service requester 102. Alternatively, it may reflect whether or not it is important to a third party that will be affected by the implementation of the robot work service.

[0072] Although the method of calculating the result value has been described using an evaluation value, it is not limited to this. The evaluation value may be calculated by calculating and comparing histogram distributions based on the list of third spatial information and the list of second spatial information. The degree to which the distribution of the second spatial information overlaps with the distribution of the third spatial information is calculated, and this value is used as the evaluation value. The overlapping distributions are calculated as the area of ​​the overlapping portion, which is used as the evaluation value. In this case, a determination is made as to whether the result is below a maximum threshold or above a minimum threshold, depending on the spatial information parameters. If the result is negative, the area of ​​that portion is used as a negative value to calculate the evaluation value. Comparing the distributions makes it possible to compare them with the work performance trends of the robot work service provider 104, enabling the degree of match to be calculated taking into account conditions with a greater number of achievements.

[0073] In this embodiment, spatial information parameters are set for each robot task type, but this is not limiting. Regardless of the task type of the robot task, the aisle width, step height, number of turns, and material mentioned for cleaning and delivery may be set and used to determine the degree of match. This makes it possible to compare the spatial information of the task history with the spatial information of the task request, regardless of the task type. [Example 3]

[0074] In the second embodiment, a method for determining the degree of match between the parameter values ​​of the object placement for a space where the robot work service provider has worked and the parameter values ​​for the space that is the target of the service request was described. In this case, the parameter values ​​of the service provider's parameters were determined based on the object placement characteristic database after the object placement characteristic database was generated.

[0075] However, the method for determining the parameter values ​​of object placement for a space where a robot work service provider has performed work is not limited to this, and the parameter values ​​may be determined without generating an object placement characteristic database. Specifically, spatial information parameters are provided for each robot work type, and the values ​​of the spatial information parameters are determined in the same manner as the method used in step S403 in the second embodiment. From the SLAM processing results, the position and orientation of the camera at the point where the image was taken, as well as three-dimensional position information of feature points corresponding to each object in the captured image, are calculated and used to calculate the spatial information parameter values.

[0076] When determining parameter values ​​for object placement without generating an object placement characteristic database, the work availability information acquisition unit 210 acquires work availability information regarding the space in which the robot work service provider can work, in association with the robot work service provider. The first space information generation unit 220 generates first space information regarding the space based on the information acquired by the work availability information acquisition unit 210. The work request information acquisition unit 230 acquires work request information regarding the space in which the robot work service client desires to work, in association with the robot work service client. The second space information generation means generates second space information regarding the space based on the information acquired by the work request information acquisition unit 230. The match degree determination unit 250 determines the match degree based on the first space information and the second space information.

[0077] In the above explanation, the requester of the robot work is assumed to be a user. The higher the degree of match, the more similar the work space that the robot work service requester 102 wishes to request is to the workable space of the robot work service provider 104. Therefore, a specific robot work service requester 102 may select a robot work service provider 104 with a high degree of match from among multiple robot work service providers 104. In this case, the degree of match determination unit 250 determines the degree of match based on the second space information related to the specific robot work service requester 102 and the first space information related to the multiple robot work service providers 104.

[0078] The user may also be a provider of robot work. In this case, a specific robot work service provider 104 may select a robot work service requester 102 with a high degree of match from among multiple robot work service requesters 102. In this case, the match determination unit 250 determines the degree of match based on first spatial information related to the specific robot work service provider 104 and second spatial information related to the multiple robot work service requesters 102.

[0079] Although the results of SLAM processing are used to calculate the values ​​of spatial information parameters, this is not limiting. For work availability information or work request information, values ​​of physical space, such as passageway width or door width, may be measured using a measuring device capable of measuring distances. These may also be calculated from architectural drawings. Parameters related to robot movement, such as the number of turns and waypoints, may be calculated by acquiring robot control information.

[0080] Furthermore, when generating the first space information, the space information parameter value may be calculated by selecting information on a space similar to the space for which the work is requested from the work availability information. For example, if the type of space that the robot work service requester wants to request is an office, the first space information may be generated by limiting the work availability information to those with a space type of office. This allows for a more accurate calculation of the degree of match. [Example 4]

[0081] In this embodiment, a method will be described in which information other than the spatial information parameters used in embodiments 2 and 3 is used to determine the degree of match. In addition to spatial information such as aisle width and floor material mentioned in embodiments 2 and 3, information related to the difficulty of the robot work, such as the weight of the item to be delivered and the lighting environment, is also included. In this embodiment, information related to the difficulty of the robot work is added to the parameters and used to determine the degree of match.

[0082] The method for determining the degree of match is the same as the method in the second embodiment, in which the evaluation value obtained for each spatial information parameter is multiplied by a coefficient determined for each spatial information parameter, and the results are summed for the spatial information parameter group.

[0083] This concludes the description of Example 4. This example makes it possible to determine the degree of match by taking into account not only object location information and spatial information, but also information related to the difficulty of the robot work. This allows the robot work service requester 102 to select a provider who can complete the work or can complete the work in a short period of time. The robot work service provider 104 can also receive requests from providers who can complete the work or can complete the work in a short period of time. [Example 5]

[0084] In the first embodiment, an example was described in which factors that contributed to a high or low degree of match are also output when the result of the degree of match is presented to the requester of the robot work service. In this embodiment, an example is shown in which the combined use of robots with different values ​​for two spatial parameters, such as a robot that can navigate a passage with high steps and a robot that can navigate a passage with a narrow width, is proposed.

[0085] Consider two robots capable of performing the same task that a robotic work service provider can provide, each with different spatial parameters. For example, suppose robot A can navigate through passageways with step heights of 7 cm or less and passageways with widths of 30 cm or more, while robot B can navigate through passageways with step heights of 3 cm or less and passageways with widths of 20 cm or more. The spatial parameters of the second spatial information requested by the client are a maximum step height of 5 cm and a minimum width of 25 cm. If only one robot is available, robot A alone cannot navigate through a 25 cm wide area, and robot B alone cannot navigate through a 5 cm wide area. Using either robot alone would result in a low match in either the step height or the width. Therefore, a robotic work service requester can be offered a combination of robots, with robot A used in areas with 5 cm step heights and robot B used in areas with 25 cm widths. The robotic work service provider capable of providing the two robots may be the same or different. While the above example illustrates two robots with different spatial parameters, the same applies to cases where there are three or more robots. [Example 6]

[0086] In this embodiment, a case will be described in which a notification unit is provided that notifies the user of the degree of match determined by the degree of match determination unit 250.

[0087] A configuration diagram of this embodiment is shown in Figure 6. The notification unit 600 notifies the user of the degree of match determined by the degree-of-match determination unit 250. In this embodiment, the content shown in Figure 7(A) is displayed on the display device 101. If the user is a robot work service client 102, work request information 103 and a ranking 701 of robot work service providers 104 determined from the degree of match determined by the degree-of-match determination unit 250 are displayed. In other words, information linking robot work service providers with the degree of match is presented to the robot work service client.

[0088] By providing the notification unit 600, it is possible to check the robot work service providers 104 with a high degree of match.

[0089] Note that a selection means (not shown) may be provided that allows the user, the robot work service requester 102, to select a robot work service provider 104 listed in the ranking 701. This allows the user to immediately select a robot work service provider 104 after receiving notification of the degree of match, and complete the entire process up to requesting a robot work service.

[0090] If the user is a robot work service provider 104, an example of the display is shown in Figure 7(B). By displaying the degree of match and work request information from each requester together, the robot work service provider 104 can determine which request will have the lowest work difficulty. A ranking 702 of the degree of match with the robot work service requester 102 is also notified. In other words, information linking the robot work service requester with the degree of match is presented to the robot work service provider.

[0091] Note that a selection means (not shown) may be provided that allows the user, who is the robot work service provider 104, to select a robot work service client 102 listed in the ranking 702. This allows the user to immediately select a robot work service client 102 after receiving notification of the degree of match, thereby completing the entire process up to receiving an order for a robot work service.

[0092] The displayed content is not limited to that shown in FIG. 7. The degree of match may be displayed as a numerical bar or graph instead of a numerical value. Alternatively, the degree of match may be displayed as a level such as high, medium, or low. Information obtained from sources other than the degree of match results, such as estimated cost or available reservation dates, is not limited. The notification method of the notification unit 600 is also not limited to a display, and may be audible notification. [Variation 1]

[0093] In this modified example, a case will be described in which a storage unit is provided that stores first space information generated from work availability information acquired from the robot work service provider 104. Only the points that differ from the other embodiments will be briefly described.

[0094] A spatial information accumulation unit (not shown) accumulates the first spatial information generated by the first spatial information generation unit 220.

[0095] The flow of the storage process of the first spatial information in this embodiment is shown in Fig. 8. In step S600, the first spatial information storage unit stores the first spatial information generated in step S401. At this time, the storage destination is a memory (ROM 312, external memory 314, etc.) serving as a storage medium.

[0096] This modification makes it possible to store the work capability information obtained from the robot work service provider 104, and to determine the degree of match using more information. Since more information can be used to learn the object placement characteristic database, improved accuracy can be expected.

[0097] Although the first spatial information accumulation method has been described as accumulating all work results as a single data set, this is not limiting. For example, the spatial information may be divided and accumulated for each robot work type. Alternatively, the spatial information may be divided and accumulated for each parameter.

[0098] The disclosure of this embodiment includes the following configuration. (Configuration 1) a work availability information acquisition means for acquiring work availability information relating to a space in which a robot work service provider can work, in association with the robot work service provider; a first space information generating means for generating first space information relating to the space based on the information acquired by the work availability information acquiring means; a work request information acquisition means for acquiring work request information relating to a space in which a robot work service requester desires to perform work, in association with the robot work service requester; second space information generation means for generating second space information relating to the space based on the information acquired by the work request information acquisition means; an information processing apparatus comprising: a matching degree determining means for determining a matching degree based on the first spatial information and the second spatial information. (Configuration 2) The information processing device according to configuration 1, characterized in that, based on the degree of match determined by the degree of match determination means, information linking the robot work service provider with the degree of match is presented to the robot work service requester. (Configuration 3) The information processing device according to configuration 1, characterized in that, based on the degree of match determined by the degree of match determination means, information linking the robot work service requester with the degree of match is presented to the robot work service provider. (Configuration 4) the first spatial information and the second spatial information include a spatial information parameter related to the difficulty of the robot task; 4. The information processing apparatus according to any one of configurations 1 to 3, wherein the degree-of-match determining means determines the degree of match based on the value of the spatial information parameter. (Configuration 5) 5. The information processing device according to configuration 4, wherein the spatial information parameters are defined in advance for each type of robot work, and the values ​​of the spatial information parameters are determined for each type of robot work. (Configuration 6) a work availability information acquisition means for acquiring work availability information relating to a space in which a robot work service provider can work, in association with the robot work service provider; a first space information generation means for generating, based on the information acquired by the work availability information acquisition means, first space information relating to a space, the object location characteristic database representing the location relationship of a plurality of objects in the space in which the robot work service provider can work; a work request information acquisition means for acquiring work request information relating to a space in which a robot work service requester desires to perform work, in association with the robot work service requester; a second space information generating means for generating second space information relating to a space based on the information acquired by the work request information acquiring means, the second space information including object type information indicating the type of each of a plurality of objects present in the space where the robot work service requester desires to perform work, and position information; a third space information generating means for searching the object placement characteristic database using the object type information and the position information included in the second space information as keys to generate third space information relating to the space, the third space information including the object type information and the position information; an information processing device comprising: a matching degree determination means for determining a matching degree based on the object type information and the position information included in the third spatial information, and the object type information and the position information included in the second spatial information. (Configuration 7) the object placement characteristic database includes spatial information parameters related to the difficulty of a robot task; 7. The information processing device according to configuration 6, wherein the degree of match determining means determines the degree of match based on the value of the spatial information parameter. (Configuration 8) 8. The information processing device according to configuration 7, wherein the spatial information parameters are predetermined for each type of work performed by the robot, and the values ​​of the spatial information parameters are generated for each type of work performed by the robot. (Configuration 9) a work availability information acquisition step of acquiring work availability information relating to a space in which a robot work service provider can work, in association with the robot work service provider; a first space information generating step of generating first space information relating to the space based on the information acquired by the work availability information acquiring means; a work request information acquisition step of acquiring work request information relating to a space in which a robot work service requester desires to perform work, in association with the robot work service requester; a second space information generating step of generating second space information relating to the space based on the information acquired by the work request information acquiring means; and a match determination step of determining a match based on the first spatial information and the second spatial information.

[0099] The present invention has been described in detail above based on its preferred embodiments, but the present invention is not limited to the above embodiments, and various modifications are possible based on the gist of the present invention, and these modifications are not excluded from the scope of the present invention. [Explanation of symbols]

[0100] 100: Information processing device 101:Display device 102: Robot work service requester 103: Work request information 104: Robot work service provider 105: Work availability information

Claims

1. a work availability information acquisition means for acquiring work availability information relating to a space in which a robot work service provider can work, in association with the robot work service provider; a first space information generating means for generating first space information relating to the space based on the information acquired by the work availability information acquiring means; a work request information acquisition means for acquiring work request information relating to a space in which a robot work service requester desires to work, in association with the robot work service requester; second space information generating means for generating second space information relating to the space based on the information acquired by the work request information acquiring means; an information processing apparatus comprising: a matching degree determining means for determining a matching degree based on the first spatial information and the second spatial information.

2. 2. The information processing apparatus according to claim 1, wherein, based on the degree of match determined by the degree-of-match determining means, information linking a robot work service provider with the degree of match is presented to the robot work service requester.

3. 2. The information processing device according to claim 1, wherein, based on the degree of match determined by the degree-of-match determining means, information linking the robot work service requester with the degree of match is presented to the robot work service provider.

4. the first spatial information and the second spatial information include a spatial information parameter related to a difficulty level of a robot task; 2. The information processing apparatus according to claim 1, wherein said matching degree determining means determines said matching degree based on values ​​of said spatial information parameters.

5. 5. The information processing apparatus according to claim 4, wherein the spatial information parameters are defined in advance for each type of robot work, and the values ​​of the spatial information parameters are determined for each type of robot work.

6. a work availability information acquisition means for acquiring work availability information relating to a space in which a robot work service provider can work, in association with the robot work service provider; a first space information generation means for generating, based on the information acquired by the work availability information acquisition means, first space information relating to a space, the object location characteristic database representing the location relationship of a plurality of objects in a space in which the robot work service provider can work; a work request information acquisition means for acquiring work request information relating to a space in which a robot work service requester desires to work, in association with the robot work service requester; a second space information generating means for generating second space information relating to a space based on the information acquired by the work request information acquiring means, the second space information including object type information indicating the type of each of a plurality of objects present in the space where the robot work service requester desires to perform work, and position information; a third space information generating means for searching the object placement characteristic database using the object type information and the position information included in the second space information as keys to generate third space information relating to the space, the third space information including the object type information and the position information; and a matching degree determination means for determining a matching degree based on the object type information and the position information included in the third spatial information, and the object type information and the position information included in the second spatial information.

7. the object placement characteristic database includes spatial information parameters related to the difficulty of a robot task; 7. The information processing apparatus according to claim 6, wherein said matching degree determining means determines said matching degree based on values ​​of said spatial information parameters.

8. 8. The information processing apparatus according to claim 7, wherein the spatial information parameters are predetermined for each type of work performed by the robot, and the values ​​of the spatial information parameters are generated for each type of work performed by the robot.

9. a work availability information acquisition step of acquiring work availability information relating to a space in which a robot work service provider can work, in association with the robot work service provider; a first space information generating step of generating first space information relating to the space based on the information acquired by the work availability information acquiring means; a work request information acquisition step of acquiring work request information relating to a space in which a robot work service requester desires to perform work, in association with the robot work service requester; a second space information generating step of generating second space information relating to the space based on the information acquired by the work request information acquiring means; and a match determination step of determining a match based on the first spatial information and the second spatial information.

Images