Self-driving robot system, determination adjustment method, and program

Abstract

To provide an autonomous traveling type robot system that is less likely to repeat the same erroneous determination in determining whether an object is a person or an obstacle.SOLUTION: An autonomous traveling type robot system 300 including an autonomous traveling type robot 100 that autonomously travels on a predetermined floor, comprises: a sensor unit 140 that detects an object around the autonomous traveling type robot 100 and acquires sensing data about the detected object; a determination unit 124 that determines whether the object is a person or an obstacle based on the sensing data; and an evaluation unit 125 for evaluating that a determination result by the determination unit 124 is an erroneous determination when the sensing data and the determination result are stored in an erroneous determination database 132 as history information of erroneous determination. If the evaluation unit 125 evaluates that the determination result is an erroneous determination, the determination unit 124 performs at least one of correcting the determination result and adjusting an object determination method.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an autonomous driving robot system, a determination adjustment method, and a program.

Background Art

[0002] Patent Document 1 discloses a method of receiving three-dimensional image data from an imaging device, segmenting the received three-dimensional image data into objects, identifying a person corresponding to at least a part of the filtered object, and causing a mobile robot to follow the identified person.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the method described in Patent Document 1, in the identification of an object and a person, even if an incorrect identification result is derived, the identification result cannot be corrected or the identification method cannot be adjusted, so there is a high possibility of repeating incorrect identification.

[0005] Therefore, the present disclosure provides an autonomous driving robot system, a determination adjustment method, and a program that are less likely to repeat the same misjudgment in determining whether an object is a person or an obstacle.

Means for Solving the Problems

[0006] An autonomous driving robot system according to an aspect of the present disclosure is an autonomous driving robot system including an autonomous driving robot that autonomously travels on a predetermined floor, the system comprising: a sensor unit configured to detect an object around the autonomous driving robot and acquire sensing data regarding the detected object; a determination unit configured to determine whether the object is a person or an obstacle based on the sensing data; and an evaluation unit configured to evaluate that the determination result by the determination unit is a misjudgment when the sensing data and the determination result are registered in a misjudgment database as misjudgment history information. The determination unit is configured to perform at least one of correcting the determination result and adjusting the method for determining the object when the evaluation unit evaluates that the determination result is a misjudgment.

[0007] A determination adjustment method according to an aspect of the present disclosure is a determination adjustment method executed by one or more computers. The one or more computers are configured to detect an object around an autonomous driving robot, acquire sensing data regarding the detected object, determine whether the object is a person or an obstacle based on the acquired sensing data, evaluate that the determination result is a misjudgment when the sensing data and the determination result are registered in a misjudgment database as misjudgment history information, and perform at least one of correcting the determination result and adjusting the method for determining the object when the determination result is evaluated as a misjudgment.

[0008] A program according to an aspect of the present disclosure is a program for causing one or more computers to execute the determination adjustment method.

Advantages of the Invention

[0009] According to the present disclosure, it is difficult to repeat the same misjudgment in determining whether an object is a person or an obstacle.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11A

Figure 11B

Figure 11C

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments will be specifically described with reference to the drawings. Note that all of the embodiments described below are illustrative or specific examples. The numerical values, shapes, materials, components, arrangement positions and connection forms of the components, steps, order of steps, etc. shown in the following embodiments are merely examples and are not intended to limit the scope of the claims. Also, each drawing is not necessarily drawn precisely. In each drawing, substantially the same configuration is denoted by the same reference numeral, and redundant descriptions may be omitted or simplified.

[0012] Note that each drawing is a schematic diagram and is not necessarily drawn precisely. Also, in each drawing, substantially the same configuration is denoted by the same reference numeral, and redundant descriptions may be omitted or simplified.

[0013] Note that in the following, terms indicating the shapes of elements such as a substantially circular shape, a substantially rectangular shape, and a substantially polygonal shape do not represent a strict meaning, but mean a substantially equivalent range, for example, including a difference of about several percent.

[0014] (Embodiment) Hereinafter, an autonomous driving type robot system according to an embodiment will be described. The autonomous driving type robot system according to the embodiment detects an object around an autonomous driving type robot that autonomously travels in a predetermined area, determines whether the detected object is a person or an obstacle, and when the determination result is a misjudgment, performs at least one of correction of the determination result and adjustment of the object determination method. The autonomous driving type robot system evaluates whether the determination result is incorrect based on a misjudgment database storing misjudgment history information, and performs at least one of correction of the determination result and adjustment of the determination method, so that it is difficult to repeat the same misjudgment. Hereinafter, the configuration of the autonomous driving type robot system will be described.

[0015] [1. Configuration] FIG. 1 is a block diagram showing an example of the functional configuration of an autonomous driving type robot system according to an embodiment. The autonomous driving type robot system 300 includes, for example, an autonomous driving type robot 100 and a terminal device 200. Hereinafter, each configuration will be described.

[0016] [1-1. Autonomous Driving Type Robot] The autonomous driving type robot 100 is a robot that autonomously travels on a predetermined floor. In the embodiment, an example in which the autonomous driving type robot 100 is an autonomous driving type robot cleaner having a cleaning function will be described, but the present invention is not limited to this example. For example, the autonomous driving type robot 100 may have an article management, transportation, security, guidance, exploration, or disinfection function.

[0017] As shown in FIG. 1, the autonomous driving type robot 100 includes, for example, a communication unit 110, a control unit 120, a storage unit 130, a sensor unit 140, a notification unit 150, a traveling unit 160, and a cleaning unit 170.

[0018] Hereinafter, in addition to FIG. 1, the configuration of the autonomous driving robot 100 will be described with reference to FIGS. 2 and 3. FIG. 2 is a perspective view of the autonomous driving robot 100 in the embodiment as viewed from the upper diagonal side. FIG. 3 is a bottom view showing the appearance of the autonomous driving robot 100 in the embodiment as viewed from the back side.

[0019] [Communication Unit] The communication unit 110 is a communication circuit for the autonomous driving robot 100 to communicate with the terminal device 200. The communication unit 110 may include a communication circuit (communication module) for communicating via the wide area communication network 10 and a communication circuit (communication module) for communicating via the local communication network. The communication unit 110 is, for example, a wireless communication circuit for performing wireless communication. Note that the communication standard of the communication performed by the communication unit 110 is not particularly limited.

[0020] [Control Unit] The control unit 120 performs various information processes for controlling the operation of the autonomous driving robot 100. The control unit 120 is realized by, for example, a microcomputer or a microcontroller, but may also be realized by a processor. The control unit 120 includes, as functional components, for example, an acquisition unit 121, a self-position calculation unit 122, a map creation unit 123, a determination unit 124, an evaluation unit 125, an object position calculation unit 126, a travel plan creation unit 127, a travel control unit 128, and a cleaning control unit 129. The functions of these components are realized, for example, by a microcomputer, a microcontroller, or a processor constituting the control unit 120 executing a computer program stored in the storage unit 130.

[0021] [Acquisition Unit] The acquisition unit 121 acquires the sensing data acquired by the sensor unit 140.

[0022] [Self-Position Calculation Unit] The self-location calculation unit 122 estimates the self-location indicating the current position of the main body 101 of the autonomous mobile robot 100 on the map. For example, the self-location calculation unit 122 calculates the current position of the autonomous mobile robot 100 on the map by, for example, SLAM based on the sensing data obtained from various sensors included in the sensor unit 140 described later and the map information of the map created by the map creation unit 123. The various sensors will be described later.

[0023] [Map Creation Unit] The map creation unit 123 creates a map of a predetermined floor on which the autonomous mobile robot 100 travels. The map creation unit 123 may create a map of a predetermined floor by a map creation technique such as SLAM (Simultaneous Localization and Mapping), or may acquire map information input from an external device (not shown) via a network. Further, the map information may be stored in the storage unit 130 in advance, and in this case, the map creation unit 123 may read and acquire the map information from the storage unit 130.

[0024] In addition, the map creation unit 123 may create, for example, a cleaning history map as a cleaning result. More specifically, the map creation unit 123 creates a cleaning history map by associating a travel route, an object determination result, the type and amount of collected garbage, etc. on a map indicating a predetermined floor.

[0025] [Determination Unit] The determination unit 124 determines whether an object detected around the autonomous mobile robot 100 is a person or an obstacle based on the sensing data acquired by the sensor unit 140. More specifically, the determination unit extracts a feature amount included in the sensing data and determines whether the object is a person or an obstacle based on the extracted feature amount. The feature amount is, for example, point cloud information when the sensor unit 140 is LiDAR (Light Detection And Ranging), but is not limited thereto. For example, when the sensor unit 140 is a camera, the feature amount may be pixel information.

[0026] When the determination unit 124 is evaluated by the evaluation unit 125 described later that the determination result is a false determination, the determination unit 124 performs at least one of correction of the determination result and adjustment of the object determination method.

[0027] For example, when the determination unit 124 determines that an object is an obstacle and the position of the object moves when the autonomous mobile robot 100 approaches the object, the determination unit 124 may determine whether the position of the object moves and output the determination result to the evaluation unit 125. Then, when the evaluation unit 125 evaluates that the determination result is a false determination, the determination unit 124 corrects the object in the determination result from an obstacle to a person, and stores the corrected determination result as history information of false determination in a false determination database 132 described later. In this case, the determination unit 124 may adjust the determination method. For example, in the determination of whether an object is a person, when the determination unit 124 determines that it is a person's ankle (i.e., a person) when the diameter of the object is 10 cm or more, and determines a person's leg as a chair leg (i.e., an obstacle), the threshold value may be corrected so that a diameter of 8.5 cm or more is determined to be a person's leg. The threshold value may be a range of values with a statistical width, or a value obtained by adjusting the standard deviation or sigma.

[0028] In addition, in the determination of whether an object is a person or an obstacle, when history information indicating that the object is falsely detected as a person and history information indicating that the object is falsely detected as an obstacle are stored in the false determination database 132, the determination unit 124 may adjust the object determination method so as to determine the object detected by the sensor unit 140 as an obstacle.

[0029] [Evaluation Unit] The evaluation unit 125 evaluates whether the determination result by the determination unit is a correct determination or an incorrect determination. FIG. 4 is a diagram showing the evaluation of the correctness of the determination result. For example, as shown in FIG. 4(a), when the object detected by the sensor unit 140 (in other words, the object to be detected) is an obstacle and the determination unit 124 determines the object as a person, the evaluation unit 125 evaluates that the determination result by the determination unit 124 is an incorrect determination. Also, as shown in FIG. 4(b), when the object to be detected is a person and the determination unit 124 determines the object as a person, the evaluation unit 125 evaluates that the determination result by the determination unit 124 is a correct determination. Further, as shown in FIG. 4(c), when the object to be detected is a person and the determination unit 124 determines the object as an obstacle, the evaluation unit 125 evaluates that the determination result by the determination unit 124 is an incorrect determination. Also, as shown in FIG. 4(d), when the object to be detected is an obstacle and the determination unit 124 determines the object as an obstacle, the evaluation unit 125 evaluates that the determination result by the determination unit 124 is a correct determination.

[0030] More specifically, when the sensing data of the object acquired by the sensor unit 140 and the determination result by the determination unit 124 are registered in the incorrect determination database 132 as the history information of incorrect determinations, the evaluation unit 125 evaluates that the determination result by the determination unit 124 is an incorrect determination. The sensing data of the object more specifically includes feature amounts indicating the object, and the feature amounts are, for example, point cloud information indicating the object acquired by the position sensor 141 when the sensor unit 140 includes the position sensor 141 (e.g., LiDAR). Also, for example, the feature amounts indicating the object included in the sensing data acquired by the camera 142 are pixel information.

[0031] When the evaluation unit 125 further receives an input operation for correcting an object from a person to an obstacle with respect to the determination result by the reception unit 240 of the terminal device 200 described later, the evaluation unit 125 evaluates that the determination result determined by the determination unit 124 is a false determination, and uses the determination result as history information of false determination, and associates the sensing data of the object (more specifically, the feature amount included in the sensing data), the determination result, and the corrected determination result received by the reception unit 240, and may register them in the false determination database 132.

[0032] In addition, when the determination unit 124 determines that the object is an obstacle and it is determined that the position of the object has moved when the autonomous mobile robot 100 approaches the object, the evaluation unit 125 evaluates that the determination result that the object is an obstacle is a false determination, and associates the sensing data of the object (for example, the feature amount included in the sensing data) and the determination result as history information of false determination, and may register them in the false determination database 132.

[0033] FIG. 5 is a diagram showing an operation example of the autonomous mobile robot and a person when the person is erroneously determined to be an object. When the autonomous mobile robot 100 determines that the detected object is an obstacle, the autonomous mobile robot 100 performs an operation of approaching the object to avoid it. At this time, for example, the person moves backward (see (a) in FIG. 5) or moves (see (b) in FIG. 5) in order to avoid a collision with the autonomous mobile robot 100. As described above, when the determination unit 124 determines that the object is an obstacle and it is determined that the position of the object has moved when the autonomous mobile robot 100 approaches the object, the evaluation unit 125 evaluates that the determination result by the determination unit 124 is a false determination.

[0034] [Object position calculation unit] The object position calculation unit 126 calculates the relative position of the object with respect to the autonomous mobile robot 100 based on the sensing data acquired by the sensor unit 140. For example, when the sensor unit 140 includes a position sensor 141 that can acquire depth data, the relative position of the object with respect to the autonomous mobile robot is calculated based on the depth data acquired by the position sensor 141.

[0035] [Travel Route Planning Unit] Based on a map indicating a predetermined floor and its own position, the travel route planning unit 127 creates a travel plan. For example, when the autonomous mobile robot 100 is an autonomous mobile robot vacuum cleaner having a cleaning function, the travel route planning unit 127 may further create a cleaning plan. The cleaning plan may include, for example, when there are a plurality of cleaning areas (e.g., rooms or sections) that the autonomous mobile robot 100 should clean, the cleaning order for cleaning these cleaning areas, the travel route and cleaning mode in each cleaning area, and the like. The cleaning mode is, for example, a combination of the travel speed of the autonomous mobile robot 100, the suction intensity for sucking dust on the floor surface, and the rotational speed of the brush.

[0036] Also, for example, when an object is detected in the traveling direction (i.e., the front) of the autonomous mobile robot 100, the travel route planning unit 127 changes the travel plan based on the map and its own position, in addition to the determination result by the determination unit 124 and the relative position of the object with respect to the autonomous mobile robot 100. Specifically, the travel route planning unit 127 changes the travel plan based on the travel pattern stored in the pattern database 133 described later.

[0037] FIG. 6 is a diagram showing an operation example of the autonomous mobile robot 100 corresponding to the determination result shown in FIG. 4. The travel plan creation unit 127 reflects a travel pattern for avoiding an object in the travel plan according to the determination result by the determination unit 124. For example, as shown in FIGS. 6(a) and 6(b), when the determination unit 124 erroneously determines that the obstacle is a person, and when the determination unit 124 correctly determines that the person is a person, the travel plan creation unit 127 adds to the travel plan a travel pattern in which the autonomous mobile robot 100 avoids the object while maintaining a certain distance from the object, based on the pattern database 133. Further, for example, as shown in FIGS. 6(c) and 6(d), when the determination unit 124 erroneously determines that the person is an obstacle, and when the determination unit 124 correctly determines that the obstacle is an obstacle, the travel plan creation unit 127 adds to the travel plan a travel pattern in which the autonomous mobile robot 100 approaches the object to a predetermined distance and then avoids the object, based on the pattern database 133.

[0038] Note that when the determination result is corrected by the determination unit 124 as described above with reference to FIG. 5, for example, the travel plan creation unit 127 reflects in the travel plan a travel pattern for avoiding an object according to the corrected determination result.

[0039] Note that when avoiding a person, the travel plan creation unit 127 may change the cleaning mode such as reducing the rotation speed of the brush or stopping the rotation of the brush.

[0040] [Travel control unit] The travel control unit 128 controls the travel unit 160 so that the autonomous mobile robot 100 travels according to the travel plan. More specifically, the travel control unit 128 performs information processing for controlling the operation of the travel unit 160 based on the travel plan. For example, in addition to the travel plan, the travel control unit 128 derives control conditions for the travel unit 160 based on information such as a map indicating a predetermined floor and the self-position, and generates a control signal for controlling the operation of the travel unit 160 based on the control conditions. The travel control unit 128 outputs the generated control signal to the travel unit 160.

[0041] Note that since details such as the derivation of the control conditions for the traveling unit 160 are the same as those of conventional autonomous mobile robots, the description thereof will be omitted.

[0042] [Cleaning control unit] The cleaning control unit 129 controls the cleaning unit 170 so that the autonomous mobile robot 100 performs cleaning according to the cleaning plan. More specifically, the cleaning control unit 129 performs information processing for controlling the operation of the cleaning unit 170 based on the cleaning plan. For example, in addition to the cleaning plan, the cleaning control unit 129 derives the control conditions for the cleaning unit 170 based on information such as a map indicating a predetermined floor and its own position, and generates a control signal for controlling the operation of the cleaning unit 170 based on the control conditions. The cleaning control unit 129 outputs the generated control signal to the cleaning unit 170. Note that since details such as the derivation of the control conditions for the cleaning unit 170 are the same as those of conventional autonomous mobile robot cleaners, the description thereof will be omitted.

[0043] [Storage unit] The storage unit 130 is a storage device that stores a map indicating a predetermined floor, sensing data regarding an object detected by the sensor unit 140, and a computer program executed by the control unit 120. The storage unit 130 is realized, for example, by an HDD (Hard Disk Drive), but may also be realized by a semiconductor memory.

[0044] The human determination database 131 is a database referred to by the determination unit 124 in determining whether an object is a human or an obstacle. For example, the human determination database 131 stores sensing data (for example, a feature amount indicating a human included in the sensing data) in advance. For example, the sensing data may be a point cloud, the radius of a circular fitting of the point cloud, and the variation of points.

[0045] The misjudgment database 132 stores historical information on misjudging a person as an obstacle and historical information on misjudging an obstacle as a person. The misjudgment database 132 may be a single database or may be databases separated by types of misjudgments. FIG. 7 is a diagram showing an example of data stored in the misjudgment database 132. FIG. 8 is a diagram showing another example of data stored in the misjudgment database 132. For example, as shown in FIG. 7, in the misjudgment database 132, as historical information when misjudging a person as an obstacle, sensing data, a determination result, an evaluation result, and a corrected determination result may be associated and stored. Also, for example, as shown in FIG. 8, as historical information when misjudging an obstacle as a person, the position where the object was detected, sensing data, a determination result, an evaluation result, and a corrected determination result may be associated and stored.

[0046] The pattern database 133 stores the type of object (person or obstacle), the distance from the autonomous mobile robot 100 to the object, and the travel pattern in association with each other. FIG. 9 is a diagram showing an example of data stored in the pattern database 133. As shown in FIG. 9, for each type of object, travel patterns corresponding to the distance between the autonomous mobile robot 100 and the object are stored.

[0047] [Sensor unit] The sensor unit 140 detects objects around the autonomous mobile robot 100 and acquires sensing data regarding the detected objects. The sensor unit 140 includes at least one sensor. For example, as shown in FIG. 2, the sensor unit 140 may include a position sensor 141, a camera 142, and an obstacle sensor 143, but this is an example and is not particularly limited thereto.

[0048] For example, the position sensor 141 is installed on the upper surface of the autonomous mobile robot 100, and acquires the positional relationship including the distance and direction from the walls existing around the autonomous mobile robot 100, the obstacles existing in the traveling direction (so-called, the front) of the autonomous mobile robot 100, and objects including people. Here, the obstacle is an object other than the wall partitioning a predetermined space, is located in the traveling direction of the autonomous mobile robot 100, and is an object that obstructs the traveling of the autonomous mobile robot 100. The obstacles are, for example, chairs, desks, beds, sofas, floor cushions, cushions, bags, clothes, portable electric devices (for example, irons, humidifiers, air purifiers, etc.). The position sensor 141 may be, for example, a LiDAR or a laser rangefinder that emits light and detects the positional relationship (for example, the position of the object and the distance from itself to the object) based on the light reflected by the obstacle and returned.

[0049] The camera 142 is, for example, an imaging device that images the surroundings of the autonomous mobile robot 100. The camera 142 may image a still image or may image a moving image. The camera 142 may be an RGB camera or may be an RGB-D camera.

[0050] The obstacle sensor 143 detects, for example, an object (hereinafter referred to as an obstacle candidate) that becomes an obstacle around itself, particularly in the traveling direction of the autonomous mobile robot 100, by a method different from that of the position sensor 141, and acquires the positional relationship of the obstacle candidate with respect to itself. The obstacle sensor 143 is, for example, a sensor such as an ultrasonic sensor or a distance measuring sensor. For example, the obstacle sensor 143 may be a ToF camera or a stereo camera. In the present embodiment, the obstacle sensor 143 is, for example, an ultrasonic sensor. The obstacle sensor 143 has a transmission unit 143a disposed at the center in front of the main body 101, and reception units 143b disposed on both sides of the transmission unit 143a, respectively. The reception units 143b receive the ultrasonic waves transmitted from the transmission unit 143a and reflected by the obstacle candidate, thereby detecting the distance and position of the obstacle candidate.

[0051] Although not shown, the sensor unit 140 may include other types of sensors. For example, the other types of sensors may be a floor sensor 144, an encoder, an acceleration sensor, a contact sensor, and the like.

[0052] [Notification unit] The notification unit 150 notifies the user of information. For example, the notification unit 150 may notify the user of the determination result. For example, the notification unit 150 may notify the user whether the determination unit 124 has determined an object as a person or an obstacle using at least any one of sound, light, and an image. The notification unit 150 may be realized by, for example, at least any one of a speaker, a lamp, and a display panel. The speaker outputs sound or voice. The lamp lights up or blinks. The display panel is a liquid crystal panel, an organic EL panel, or the like, and displays an image. Also, for example, the notification unit 150 may notify the user of information (for example, the determination result, etc.) via the communication unit 110. In this case, the notification unit 150 generates information to be notified to the user and outputs the generated information to the terminal device 200.

[0053] [Travel unit] The travel unit 160 causes the autonomous mobile robot 100 to travel based on an instruction from the travel control unit 128. The travel unit 160 includes wheels 161 (see FIG. 3) that travel on the floor, a travel motor (not shown in FIG. 3) that applies torque to the wheels 161, and a housing that houses the travel motor. Also, the autonomous mobile robot 100 is a two-wheeled type with casters 162 (see FIG. 3) as auxiliary wheels, and by independently controlling the two wheels 161, the autonomous mobile robot 100 can travel freely such as straight ahead, backward, left rotation, and right rotation. Note that the number of wheels 161 is not limited to two, and may be one or three or more.

[0054] [Cleaning unit] The cleaning unit 170 sucks dust on the floor from the suction port 172 (see FIG. 3) based on an instruction from the cleaning control unit 129, and stores the sucked dust inside the main body 101 within the main body 101. The cleaning unit 170 includes a brush rotation motor (not shown in FIG. 3) that rotates the side brush 171 (see FIG. 2), a suction motor (not shown in FIG. 3) that sucks dust from the suction port 172, a power transmission unit (not shown in FIG. 3) that transmits power to these motors, and a storage unit (not shown in FIG. 3) that stores the sucked dust, etc.

[0055] [1-2. Terminal Device] Next, the terminal device 200 will be described. The terminal device 200 is, for example, a portable information terminal such as a smartphone or a tablet terminal owned by a user, but may also be a stationary information terminal such as a personal computer. Further, the terminal device 200 may be a dedicated terminal of the autonomous driving robot system 300. The terminal device 200 includes, for example, a communication unit 210, a control unit 220, a storage unit 230, a reception unit 240, and a display unit 250. Each configuration will be described below.

[0056] [Communication Unit] The communication unit 210 is a communication circuit for the terminal device 200 to communicate with the autonomous driving robot 100. The communication unit 210 may include a communication circuit (communication module) for communicating via a wide area communication network and a communication circuit (communication module) for communicating via a local communication network. The communication unit 210 is, for example, a wireless communication circuit that performs wireless communication. The communication standard of the communication performed by the communication unit 210 is not particularly limited.

[0057] [Control Unit] The control unit 220 performs display control of an image to the reception unit 240 and identification processing of an instruction input by the user (for example, voice recognition processing if it is an input by voice). The control unit 220 may be realized by, for example, a microcomputer or may be realized by a processor.

[0058] [Storage Unit] The storage unit 230 is a storage device that stores a dedicated application program for execution by the control unit 220. The storage unit 230 is realized by, for example, a semiconductor memory or the like.

[0059] [Reception unit] The reception unit 240 receives the user's instructions. More specifically, the reception unit 240 receives an input operation for transmitting the user's instructions to the autonomous driving robot 100. The reception unit 240 may be realized by, for example, a touch panel, a display panel, a hardware button, or a microphone. The touch panel may be, for example, a capacitive touch panel or a resistive film touch panel. The display panel has an image display function and a function of receiving manual input from the user, and receives an input operation to a numeric keypad image or the like displayed on a display panel such as a liquid crystal panel or an organic EL (Electro Luminescence) panel. The microphone receives the user's voice input.

[0060] [Display unit] The display unit 250 displays notifications (for example, determination results, cleaning results, etc.) output by the autonomous driving robot 100, and a map of a predetermined floor. The display unit 250 is, for example, a display panel such as a liquid crystal panel or an organic EL panel.

[0061] FIG. 10 is a diagram showing an example of a display screen. As shown in FIG. 10, the display unit 250 displays, as a cleaning result, for example, a cleaning history map. The cleaning history map shows, on a map indicating a predetermined floor cleaned by the autonomous driving robot 100, for example, the amount of collected garbage and the determination result of detected objects (for example, an icon indicating a person). The cleaning history map may be generated by the notification unit 150 using the map information created by the map creation unit 123 of the autonomous driving robot 100, or may be created by the map creation unit 123. Further, the display unit 250 may display an icon for receiving the user's instructions.

[0062] In the embodiment, an example in which the autonomous driving robot system 300 includes the autonomous driving robot 100 and the terminal device 200 has been described. However, the components included in the autonomous driving robot system 300 may be distributed among a plurality of devices in any manner. For example, among the components of the autonomous driving robot 100 in the embodiment, the evaluation unit 125 and the error determination database 132 may be provided in the edge server.

[0063] [2. Operation] Next, the operation of the autonomous driving robot system 300 according to the embodiment will be described. FIGS. 11A, 11B, and 11C are flowcharts showing an example of the operation of the autonomous driving robot system 300 according to the embodiment. Hereinafter, an example of the operation when the sensing data acquired by the sensor unit 140 includes the point cloud data (point cloud information) acquired by the position sensor 141 (for example, LiDAR) will be described.

[0064] First, the power of the autonomous driving robot 100 is turned on by the user's operation (S01). Next, when the control unit 120 of the autonomous driving robot 100 acquires an instruction to start cleaning a predetermined floor (hereinafter, also referred to as a cleaning start instruction) (S02), the acquisition unit 121 is caused to acquire a map indicating the predetermined floor from the storage unit 130 (S03), and the sensor unit 140 is caused to start acquiring sensing data (S04). The sensor unit 140 detects objects around the autonomous driving robot and acquires sensing data regarding the detected objects. The sensing data includes, for example, point cloud information indicating the positional relationship between the autonomous driving robot 100 and the objects.

[0065] Next, the acquisition unit 121 of the autonomous driving robot 100 acquires the sensing data acquired by the sensor unit 140. Here, the acquisition unit 121 acquires, for example, point cloud information indicating the positional relationship between itself (that is, the autonomous driving robot 100) and the surrounding objects (S05).

[0066] Next, the self-position calculation unit 122 calculates a self-position indicating the current position of the main body 101 of the autonomous mobile robot 100 on the map based on the acquired map and sensing data (S06).

[0067] Next, the travel plan creation unit 127 creates a travel plan based on the map indicating a predetermined floor and the self-position (S07). FIG. 12 is a diagram schematically showing an example of the travel plan. The broken line shown in FIG. 12 indicates the travel route. For example, the travel plan creation unit 127 creates a cleaning plan including the travel routes of each room and the cleaning mode in a predetermined area. Although not shown in FIG. 11A, when the travel control unit 128 and the cleaning control unit 129 acquire the travel plan created by the travel plan creation unit 127, they start controlling the operations of the travel unit 160 and the cleaning unit 170 according to the acquired travel plan. Thereby, the autonomous mobile robot 100 travels on a predetermined floor and performs cleaning (S08).

[0068] Next, when the determination unit 124 of the autonomous mobile robot 100 acquires sensing data from the sensor unit 140 (not shown), it determines whether an object is detected in the traveling direction of the autonomous mobile robot 100, that is, in the forward direction (S09).

[0069] When the determination unit 124 determines that no object is detected in front of the autonomous mobile robot 100 (No in S09), the control unit 120 determines whether cleaning is completed (S10). If the control unit 120 determines that cleaning is not completed (No in S10), it returns to the process of step S05. On the other hand, when the control unit 120 determines that cleaning is completed (Yes in S10), it transmits the cleaning result (for example, the cleaning history map) to the terminal device 200. When the terminal device 200 acquires the cleaning result via the communication unit 210, it causes the display unit 250 to display the cleaning result. Thereby, the display unit 250 of the terminal device 200 presents the cleaning result to the user (S11).

[0070] Next, when the control unit 120 receives an input operation of an instruction to end cleaning (hereinafter referred to as an end instruction) by the reception unit 240 of the terminal device 200 (S12), it ends the cleaning.

[0071] On the other hand, in step S09, when the determination unit 124 determines that an object has been detected in front of the autonomous driving robot 100 (Yes in S09), a feature amount (here, a point cloud) is extracted from the sensing data (not shown), and it is determined whether the extracted point cloud indicates a person (S13). For example, the determination unit 124 determines whether the point cloud indicates a person based on the person determination database 131.

[0072] When the determination unit 124 determines that the point cloud does not indicate a person (No in S13), it is determined that the object detected in front of the autonomous driving robot 100 is an obstacle (not shown). Next, the evaluation unit 125 determines whether the point cloud data (hereinafter, point cloud information) is stored in the misjudgment database 132 (S14). When it is determined that the point cloud information is not stored in the misjudgment database 132 (No in S14), the evaluation unit 125 evaluates the determination result by the determination unit 124 as a correct determination (not shown).

[0073] Although not shown, the travel plan creation unit 127 reflects a travel pattern for avoiding an obstacle in the travel plan based on the determination result by the determination unit 124, and the travel control unit 128 controls the operation of the travel unit 160 according to the travel plan. As a result, the autonomous driving robot 100 approaches the object according to the travel pattern reflected in the travel plan by the travel plan creation unit 127 (S15). Specifically, this will be described with reference to FIG. 13. FIG. 13 is a diagram schematically showing the operation when the autonomous driving robot 100 determines the detected object as an obstacle. As shown in FIG. 13, the autonomous driving robot 100 approaches the obstacle 1 according to the travel plan. At this time, the determination unit 124 determines whether the position of the object has moved (S16). When the determination unit 124 determines that the position of the object has not moved (No in S16), the evaluation unit 125 evaluates the determination result by the determination unit 124 that the object is an obstacle as a correct determination (S17).

[0074] Next, the object position calculation unit 126 calculates the position of the object based on its own position and the positional relationship (S18). Then, by the travel control unit 128 controlling the operation of the travel unit 160 according to the travel plan, the autonomous mobile robot 100 approaches and avoids the object (here, an obstacle) (S19). Specifically, it will be described with reference to FIG. 14. FIG. 14 is a diagram schematically showing the operation of the autonomous mobile robot 100 avoiding an obstacle. The autonomous mobile robot 100 approaches the obstacle 1, stops in front of the obstacle 1 (for example, at a distance of 100 mm), and then turns around and travels.

[0075] On the other hand, in step S14, when the evaluation unit 125 determines that the point cloud information is stored in the misjudgment database 132 (Yes in S14), it evaluates that the determination result by the determination unit 124 is a misjudgment (S20). Also, in step S16, when the determination unit 124 determines in step S15 that the position of the object has moved when the autonomous mobile robot 100 approaches the object (Yes in S16), the evaluation unit 125 evaluates that the determination result by the determination unit 124 is a misjudgment (S20). Specifically, it will be described with reference to FIG. 15. FIG. 15 is a diagram schematically showing the movement of person 2 when the autonomous mobile robot 100 approaches person 2. As shown in FIG. 15, when the determination unit 124 determines that the object is an obstacle, the autonomous mobile robot 100 approaches the object. However, when the object is not an obstacle but a person, person 2 moves backward (arrow A) to avoid the autonomous mobile robot 100. At this time, the determination unit 124 of the autonomous mobile robot 100 determines that the object has moved, and the evaluation unit 125 evaluates that the determination result that the object is an obstacle based on the determination of the movement of the object by the determination unit 124 is a misjudgment.

[0076] Note that the evaluation unit 125 may evaluate that the determination result that the object is an obstacle is a false determination by detecting that the autonomous mobile robot 100 has come into contact with a person by the sensor unit 140 (for example, a contact sensor). FIGS. 16 and 17 are diagrams schematically showing the operation of the autonomous mobile robot 100 when an object is erroneously determined to be an obstacle. When the determination unit 124 determines that the object is an obstacle, the autonomous mobile robot 100 approaches the object. However, if the person 2 is not aware of the approach of the autonomous mobile robot 100, the autonomous mobile robot 100 will come into contact with the person 2.

[0077] Next, when the evaluation unit 125 evaluates in step S20 that the determination result that the object is an obstacle is a false determination, the determination unit 124 corrects the determination result. More specifically, for the determination result evaluated as a false determination in step S20, the object is corrected from an obstacle to a person (S21).

[0078] Next, the object position calculation unit 126 calculates the position of the object based on its own position and the positional relationship (S22). Then, by the travel control unit 128 controlling the operation of the travel unit 160 according to the travel plan, the autonomous mobile robot 100 greatly avoids while maintaining a distance from the object (here, a person) (S23). Specifically, this will be described with reference to FIGS. 18 and 19. FIG. 18 is a diagram schematically showing the operation when the autonomous mobile robot 100 determines the detected object as a person. FIG. 19 is a diagram schematically showing the operation of the autonomous mobile robot 100 avoiding the person 2. As shown in FIGS. 18 and 19, the autonomous mobile robot 100 maintains a predetermined distance from the person 2 and greatly avoids around the person.

[0079] On the other hand, in step S13, when the determination unit 124 determines that the point cloud indicates a person (Yes in S13), it determines that the object detected in front of the autonomous driving robot 100 is a person (not shown). Next, the evaluation unit 125 determines whether the point cloud data (so-called point cloud information) is stored in the misjudgment database 132 (S24). When it is determined that the point cloud information is not stored in the misjudgment database 132 (No in S14), the process of step S22 is performed. On the other hand, when the evaluation unit 125 determines that the point cloud information is stored in the misjudgment database 132 (Yes in S24), it evaluates the determination result by the determination unit 124 as a misjudgment (S25).

[0080] Next, when the determination result that the object is a person is evaluated as a misjudgment by the evaluation unit 125 in step S25, the determination unit 124 corrects the determination result. More specifically, after correcting the object from a person to an obstacle for the determination result evaluated as a misjudgment in step S25 (S26), the process of step S18 is performed.

[0081] Next, after the processes of step S19 and step S23, the control unit 120 of the autonomous driving robot 100 determines whether the cleaning is completed (S27). When the control unit 120 determines that the cleaning is not completed (No in S27), it returns to the process of step S05. On the other hand, when the control unit 120 determines that the cleaning is completed (Yes in S27), it determines whether a person has been avoided during the cleaning (S28). When the control unit 120 determines that a person has not been avoided during the cleaning (No in S28), the process of step S11 is performed.

[0082] On the other hand, in step S28, when the control unit 120 determines that it is avoiding people during cleaning (Yes in S28), it identifies the position where it has avoided people during cleaning (hereinafter also referred to as the person avoidance position), and outputs the position information to the travel plan creation unit 127 (not shown). The travel plan creation unit 127 creates a travel plan to revisit the position where it has avoided people during cleaning based on the map, its own position, and the position information, and outputs the created travel plan to the travel control unit 128 (not shown). By controlling the operation of the travel unit 160 by the travel control unit 128, the autonomous driving type robot 100 revisits the position where it has avoided people (S29). Specifically, it will be described with reference to FIG. 20. FIG. 20 is a diagram schematically showing the operation of the autonomous driving type robot revisiting the position where it has avoided people. As shown in FIG. 20, the autonomous driving type robot 100 revisits the position where it has avoided people, detects the object again at the position where the object was detected during cleaning, and determines whether the object is a person when the object is detected. Although not shown in FIGS. 11C and 20, when the object is not detected by the sensor unit 140, the autonomous driving type robot 100 cleans the position where it has avoided person 2.

[0083] When the determination unit 124 detects the object again at the position where it has avoided people and determines that the object is a person (Yes in S30), the control unit 120 causes the map creation unit 123 to associate the detection position with the cleaning history map (described as the map in FIG. 11C) (S31). Next, the control unit 120 determines whether all the person avoidance positions have been revisited (S32). On the other hand, when the determination unit 124 determines that the object is not detected again at the position where it has avoided people (No in S30), the process of step S32 is performed.

[0084] When the control unit 120 determines that not all the human avoidance positions have been revisited (No in S32), the process returns to the process of step S29. On the other hand, when the control unit 120 determines that all the human avoidance positions have been revisited (Yes in S32), it outputs the cleaning result (for example, a cleaning history map, etc.) to the terminal device 200 (not shown). When the control unit 220 of the terminal device 200 acquires the cleaning result output from the autonomous mobile robot 100, it presents the cleaning result to the user by causing the display unit 250 to display the cleaning result (S33). Here, the process of step S33 will be specifically described with reference to FIG. 22.

[0085] FIG. 21 is a diagram showing an example of the cleaning result displayed on the display screen. For example, in FIG. 21, it shows the history details of the cleaning history map shown in FIG. 10. In the process of step S33, when the control unit 220 of the terminal device 200 acquires the cleaning result (see FIG. 10) output from the autonomous mobile robot 100, it causes the display unit 250 to display the cleaning result. Then, for example, when the user touches the human mark on the cleaning history map displayed on the display unit 250 in FIG. 10, the reception unit 240 receives an instruction to magnify and display the area around the human mark. Then, based on the instruction, the control unit 220 causes the display unit 250 to magnify and display the map around the human mark. Further, when a person touches the tab of the history details, the reception unit 240 receives an instruction to display the travel trajectory of the autonomous mobile robot 100. Then, the control unit 220 causes the display unit 250 to display the cleaning result shown in FIG. 21. In this way, the process of step S33 may include a process of receiving an instruction regarding display and changing the display.

[0086] Next, when the reception unit 240 receives an instruction to correct the determination result (hereinafter also referred to as a correction instruction) (S34), the control unit 220 of the terminal device 200 outputs the correction instruction to the autonomous driving robot 100 (not shown in FIG. 11C). When the control unit 120 of the autonomous driving robot 100 acquires the correction instruction (not shown), the evaluation unit 125 updates the misjudgment database 132 by associating the sensing data, the determination result, and the corrected determination result and storing them in the misjudgment database 132 (S35). FIG. 22 is a diagram showing an example of receiving an input operation for correcting the determination result. As shown in FIG. 22, for example, when the user touches the human mark, the reception unit 240 receives a correction request, and the control unit 220 causes the display unit 250 to display a message "Do you want to change the human to an obstacle?". Then, when the user touches "Yes", the reception unit 240 receives a correction instruction to change the human to an obstacle, and the control unit 220 outputs the correction instruction to the autonomous driving robot 100.

[0087] When the control unit 220 receives an instruction to end the correction of the determination result from the reception unit 240 (S36), it outputs the instruction to the autonomous driving robot 100 (not shown). Then, when the control unit 120 of the autonomous driving robot 100 acquires the instruction, it outputs the corrected cleaning result (for example, a corrected cleaning history map, etc.) to the terminal device 200 (not shown). Then, when the control unit 220 of the terminal device 200 acquires the corrected cleaning result, it causes the display unit 250 to display the corrected cleaning result. Note that the process of step S36 may be performed after presenting the corrected cleaning result to the user. That is, after the user confirms the corrected cleaning result, for example, by touching the end button displayed on the display unit 250, the reception unit 240 may receive an end instruction.

[0088] [3. Effects, etc.] As described above, the autonomous driving robot system 300 according to the embodiment is an autonomous driving robot system including an autonomous driving robot 100 that autonomously travels on a predetermined floor, and includes a sensor unit 140 that detects an object around the autonomous driving robot 100 and acquires sensing data regarding the detected object, a determination unit 124 that determines whether the object is a person or an obstacle based on the sensing data, and an evaluation unit 125 that evaluates that the determination result by the determination unit 124 is a misjudgment when the sensing data and the determination result are stored in a misjudgment database 132 as misjudgment history information. The determination unit 124 performs at least one of correction of the determination result and adjustment of the object determination method when the evaluation unit 125 evaluates that the determination result is a misjudgment.

[0089] Thereby, when it is evaluated that the determination result as to whether the object is a person or an obstacle is a misjudgment, the autonomous driving robot system 300 performs at least one of correction of the determination result and adjustment of the determination method, so that it is difficult to repeat the same misjudgment.

[0090] For example, in the autonomous driving robot system 300 according to the embodiment, the determination unit 124 extracts feature amounts included in the sensing data, determines whether the object is a person or an obstacle based on the extracted feature amounts, and in the misjudgment database 132, the determination result determined to be an obstacle when the object is a person, and the determination result determined to be a person when the object is an obstacle are linked and stored as misjudgment history information with the feature amounts included in the sensing data, the determination result, and the corrected determination result.

[0091] Thereby, the autonomous driving robot system 300 can determine whether the object is a person or an obstacle based on the feature amounts included in the sensing data. The feature amounts may be, for example, point clouds detected by LiDAR or pixel information included in an image captured by a camera. Further, the autonomous driving robot system 300 can evaluate the correctness of the determination result based on the misjudgment database 132 in which the misjudgment history information is stored.

[0092] For example, the autonomous driving robot system 300 according to the embodiment further includes a notification unit 150 that notifies a user of information, and a reception unit 240 that receives an input operation by the user. The notification unit 150 notifies the user of the determination result, the reception unit 240 receives an input operation for correcting the determination result by the user, and when the evaluation unit 125 further receives an input operation for correcting an object from a person to an obstacle with respect to the determination result by the reception unit 240, the evaluation unit 125 evaluates that the determination result is a false determination, and associates the feature amount included in the sensing data, the determination result, and the corrected determination result with each other as false determination history information and stores them in the false determination database 132.

[0093] Thereby, the autonomous driving robot system 300 receives an input operation for correcting the determination result by the user, and stores, as false determination history information, the determination result that erroneously determines an obstacle as a person in the false determination database 132. Therefore, the autonomous driving robot system 300 can reduce the probability of erroneously determining the same obstacle as a person by performing the determination of the object based on the false determination database 132.

[0094] For example, in the autonomous driving robot system 300 according to the embodiment, when the determination unit 124 determines that an object is an obstacle, the autonomous driving robot 100 approaches the object. When the evaluation unit 125 determines that the position of the object has moved when the autonomous driving robot 100 approaches the object by the determination unit 124, the evaluation unit 125 evaluates that the determination result that the object is determined to be an obstacle is a false determination, and associates the feature amount included in the sensing data regarding the object and the determination result with each other as false determination history information and stores them in the false determination database. The determination unit 124 corrects the object from an obstacle to a person for the determination result evaluated as a false determination, and stores the corrected determination result in the false determination database 132 as false determination history information.

[0095] As a result, when an object is determined to be an obstacle by the determination unit 124 and the determination result is not stored in the misjudgment database 132, for example, the autonomous driving robot system 300 can evaluate whether it is a misjudgment based on the presence or absence of movement of the object when approaching the object. Further, when it is evaluated that it is a misjudgment, the autonomous driving robot system 300 can update the misjudgment database 132, thereby reducing the probability of misjudging a person as an obstacle again.

[0096] For example, in the autonomous driving robot system 300 according to the embodiment, when determining whether an object is a person or an obstacle, the determination unit 124 adjusts the determination method of the object so as to determine the object as an obstacle when the misjudgment database 132 stores the history information that the object is misdetected as a person and the history information that the object is misdetected as an obstacle.

[0097] As a result, the autonomous driving robot system 300 can avoid the autonomous driving robot 100 from colliding with a person by adjusting the determination method so that an object is determined to be an obstacle based on the sensing data.

[0098] For example, in the autonomous driving robot system 300 according to the embodiment, the autonomous driving robot 100 is an autonomous driving robot cleaner having a cleaning function.

[0099] As a result, according to the autonomous driving robot system 300, the autonomous driving robot 100 can safely travel and clean a predetermined space.

[0100] The determination adjustment method according to the embodiment is a determination adjustment method executed by one or more computers. The one or more computers detect objects around the autonomous driving robot 100, acquire sensing data regarding the detected objects, determine whether the object is a person or an obstacle based on the acquired sensing data, and if the sensing data and the determination result are registered in the misjudgment database 132 as misjudgment history information, evaluate that the determination result is a misjudgment. When the determination result is evaluated as a misjudgment, at least one of correcting the determination result and adjusting the determination method of the object is performed.

[0101] Thereby, when it is evaluated that the determination result of whether the object is a person or an obstacle is a misjudgment, the determination method performs at least one of correcting the determination result and adjusting the determination method, so it is difficult to repeat the same misjudgment.

[0102] (Other embodiments) As described above, the autonomous driving robot system and the determination adjustment method according to one or more aspects of the present disclosure have been described based on the above embodiments, but the present disclosure is not limited to these embodiments. Without departing from the gist of the present disclosure, various modifications conceived by those skilled in the art applied to the embodiments, or forms configured by combining components in different embodiments may also be included within the scope of one or more aspects of the present disclosure.

[0103] Each processing unit included in the autonomous driving robot system according to the above embodiment is typically realized as an LSI which is an integrated circuit. These may be individually integrated into one chip, or may be integrated into one chip so as to include some or all of them.

[0104] Also, the integration into an integrated circuit is not limited to LSI, and it may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI, or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used.

[0105] In the above embodiments, each component may be configured by dedicated hardware or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded in a storage medium such as a hard disk or a semiconductor memory.

[0106] Also, all the numbers used above are for exemplification to specifically explain the present disclosure, and the embodiments of the present disclosure are not limited to the exemplified numbers.

[0107] Also, the division of functional blocks in the block diagram is an example, and a plurality of functional blocks may be realized as one functional block, one functional block may be divided into a plurality, or part of the functions may be transferred to other functional blocks. Also, the functions of a plurality of functional blocks having similar functions may be processed by a single hardware or software in parallel or time-division.

[0108] Also, the order in which each step in the flowchart is executed is for exemplification to specifically explain the present disclosure, and an order other than the above may be used. Also, some of the above steps may be executed simultaneously (in parallel) with other steps.

Industrial Applicability

[0109] The present disclosure is widely applicable to an autonomous driving robot system including an autonomous driving robot.

Explanation of Signs

[0110] 10 Wide Area Communication Network 100 Autonomous Driving Robot 101 Main Body 110 Communication Unit 120 Control Unit 121 Acquisition Unit 122 Self-Position Calculation Unit 123 Map Creation Unit 124 Judgment Unit 125 Evaluation Unit 126 Object Position Calculation Unit 127 Travel Plan Creation Unit 128 Travel Control Unit 129 Cleaning Control Unit 130 Memory Unit 131 Person Judgment Database 132 False Judgment Database 133 Pattern Database 140 Sensor Unit 141 Position Sensor 142 Camera 143 Obstacle Sensor 143a Transmitter 143b Receiver 144 Floor Sensor 150 Notification Unit 160 Travel Unit 161 Wheel 162 Caster 170 Cleaning Unit 171 Side Brush 172 Suction Port 200 Terminal Device 210 Communication Unit 220 Control Unit 230 Memory Unit 240 Reception Unit 250 Display Unit 300 Autonomous Driving Robot System

Claims

1. An autonomous driving robot system comprising an autonomous driving robot that autonomously travels on a predetermined floor, a sensor unit that detects an object around the autonomous driving robot and acquires sensing data regarding the detected object, a determination unit that determines whether the object is a person or an obstacle based on the sensing data, an evaluation unit that evaluates that the determination result by the determination unit is a misjudgment when the sensing data and the determination result are stored in a misjudgment database as misjudgment history information, comprising, when the evaluation unit evaluates that the determination result is a misjudgment, the determination unit performs at least one of correction of the determination result and adjustment of the method for determining the object, an autonomous driving robot system.

2. The determination unit extracts a feature amount included in the sensing data and determines whether the object is a person or an obstacle based on the extracted feature amount, in the misjudgment database, as the misjudgment history information, a determination result in which the object is determined to be an obstacle when the object is a person, and a determination result in which the object is determined to be a person when the object is an obstacle, are linked and stored with the feature amount included in the sensing data, the determination result, and the corrected determination result, The autonomous driving robot system according to claim 1.

3. further comprising a notification unit that notifies a user of information, and a reception unit that receives an input operation by the user, comprising, the notification unit notifies the user of the determination result, the reception unit receives an input operation for correcting the determination result by the user, the evaluation unit further, when an input operation for correcting the object from a person to an obstacle with respect to the determination result is received by the reception unit, evaluates that the determination result is a misjudgment, stores the determination result in the misjudgment database as the misjudgment history information, linking the feature amount included in the sensing data, the determination result, and the corrected determination result, The autonomous driving robot system according to claim 2.

4. when the determination unit determines that the object is an obstacle, the autonomous driving robot approaches the object, the evaluation unit, When it is determined by the determination unit that the position of the object has moved when the autonomous mobile robot approaches the object, it is evaluated that the determination result that the object is an obstacle is a false determination. As the history information of the false determination, the feature amount included in the sensing data regarding the object and the determination result are associated and stored in the false determination database. The determination unit corrects the object from an obstacle to a person for the determination result evaluated as a false determination. The corrected determination result is stored in the false determination database as the history information of the false determination. The autonomous mobile robot system according to claim 2 or 3.

5. In the determination of whether the object is a person or an obstacle, when the false determination database stores the history information that the object is falsely detected as a person and the history information that the object is falsely detected as an obstacle, the determination method of the object is adjusted so as to determine the object as an obstacle. The autonomous mobile robot system according to any one of claims 1 to 4.

6. The autonomous mobile robot is an autonomous mobile robot vacuum cleaner having a cleaning function. The autonomous mobile robot system according to any one of claims 1 to 5.

7. A determination adjustment method executed by one or more computers, wherein the one or more computers detect an object around the autonomous mobile robot and acquire sensing data regarding the detected object, determine whether the object is a person or an obstacle based on the acquired sensing data, when the sensing data and the determination result are registered in the false determination database as the history information of the false determination, it is evaluated that the determination result is a false determination, when it is evaluated that the determination result is a false determination, at least one of the correction of the determination result and the adjustment of the determination method of the object is performed. Determination adjustment method.

8. For causing one or more computers to execute the determination adjustment method according to claim 7 Program.

Images