Information processing device, information processing method, and computer program

Abstract

To provide an information processing device capable of improving efficiency of operation of a mobile.SOLUTION: An information processing device calculates a transit area where a mobile passes and sets an object detection range for detecting an object around the mobile when detecting the object by a sensor on the basis of the calculated transit area.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a computer program for detecting objects around a moving body. [Background technology]

[0002] Autonomous mobile robots and other mobile objects use sensors such as cameras, laser scanners, and LiDAR (Light Detection and Ranging) to detect obstacles while moving, and when they detect an obstacle, they take control to avoid collisions by detouring or stopping. The wider the detection range, the faster the mobile object can detect an object around it, but each time an object is detected, the mobile object must perform collision avoidance processing, which may delay its arrival at its destination.

[0003] Patent Document 1 discloses a technique for determining the presence or absence of an object in the traveling direction of a moving body, and suppressing the detection of an object that does not hinder the traveling of the moving body. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6677516 Summary of the Invention [Problem to be solved by the invention]

[0005] The configuration of Patent Document 1 may detect an obstacle that exists in an area that the vehicle will not actually pass through. As a result, the collision avoidance process of the vehicle causes a delay in arrival at the destination, which reduces the efficiency of the vehicle's operation.

[0006] The present invention has been made in view of the above problems, and has an object to provide an information processing device that can improve the efficiency of operation of a mobile object. [Means for solving the problem]

[0007] In the information processing device, a first object detection means for detecting an object around the moving body by a first sensor; a second object detection means for detecting an object around the moving body by a second sensor; an object identification means for identifying the object based on the characteristics of the object detected by the first object detection means; an object movement range estimation means for estimating a movement range of the object identified by the object identification means; and an object detection range setting means for setting an object detection range in which the second object detection means detects an object based on the object identified by the object identification means and the movement range estimated by the object movement range estimation means. . [Effects of the Invention]

[0008] According to the present invention, an information processing device that can improve the efficiency of operation of a mobile object can be realized. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram showing the internal configuration of an information processing device according to a first embodiment. [Figure 2] 1 is a functional block diagram of a mobile object equipped with an information processing device 100 according to a first embodiment. [Figure 3] 3 is a flowchart illustrating the operation of the information processing device according to the first embodiment. [Figure 4] 4 is a flowchart illustrating details of step S304 in FIG. 3. [Figure 5] FIG. 10 is a functional block diagram of an information processing device according to a second embodiment. [Figure 6] 10 is a flowchart illustrating the operation of the information processing device according to the second embodiment. [Figure 7] 10(A) and 10(B) are diagrams showing display examples according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. However, the present invention is not limited to the following embodiment. In each drawing, the same members or elements are given the same reference numerals, and duplicated descriptions will be omitted or simplified.

[0011] (Embodiment 1) As a first embodiment of an information processing device according to the present invention, an information processing device that changes a detection range of an obstacle by a sensor based on an area in which a moving object travels will be described below. Note that the moving object in this embodiment is an autonomous moving object such as an AGV (Automated Guided Vehicle) or an AMR (Autonomous Mobile Robot). However, the moving object is not limited to an autonomous moving object.

[0012] 1 is a diagram showing the internal configuration of an information processing device according to embodiment 1. The information processing device 100 includes a CPU 101 as a computer, a memory 102, a storage device 103, an input device 104, an output device 105, an I / O 108, and a sensor 109, which are interconnected by a bus 106.

[0013] In this embodiment, the sensor 109 is, for example, a passive stereo camera, which detects the presence or absence of an obstacle from the distance values ​​of feature points in the stereo image. By limiting this detection range to the area in which the mobile object travels, it is possible to prevent the detection of objects that exist in areas that the mobile object does not actually pass through. This reduces the collision avoidance processing of the mobile object, thereby improving operation efficiency. Note that the following description will be given assuming that the size and route of the mobile object have been input in advance into a storage device within the mobile object.

[0014] The CPU 101 executes a program 107 stored in the storage device 103, thereby executing a program for calculating an area through which a moving object will pass and a program for controlling the range within which a sensor detects an object. The memory 102 temporarily stores the programs and data that the CPU 101 reads from the storage device 103.

[0015] The memory 102 is also used as an area for the CPU 101 to execute various programs. The storage device 103 stores the results calculated by the operating system (OS) and the program 107, as well as the route and size of the moving object.

[0016] The input device 104 accepts input from the user using a keyboard and a mouse. The output device 105 outputs information input by the input device 104 and the execution results of a program executed by the CPU 101. Reference numeral 108 denotes an I / O, to which a sensor 109 for detecting an object is connected and which acquires a detection signal from the sensor 109.

[0017] Fig. 2 is a functional block diagram of a mobile object equipped with the information processing device 100 according to embodiment 1. Note that some of the functional blocks shown in Fig. 2 are realized by causing a CPU 101, which serves as a computer included in the information processing device 100, to execute a computer program stored in a storage device 103, which serves as a storage medium.

[0018] However, some or all of these functions may be implemented by hardware, which may be a dedicated circuit (ASIC) or a processor (reconfigurable processor, DSP).

[0019] Furthermore, the individual functional blocks of the information processing device 100 shown in Fig. 2 do not have to be built into the same housing, but may be configured as separate devices connected to each other via signal paths. The above explanation regarding Fig. 2 also applies to Fig. 5, which will be described later.

[0020] The moving object 210 includes the information processing device 100 and a measurement unit 211. The information processing device 100 includes a passing area calculation unit 201, an object detection range setting unit 202, and an object detection unit 203. The measurement unit 211 calculates the distance to each feature point in the stereo image based on information input from the sensor 109, and outputs the calculated distance to the object detection unit 203.

[0021] The passing area calculation unit 201 calculates a passing area through which the moving body passes while traveling, based on the size and route of the moving body. The passing area includes an area through which a connected object that moves connected to the moving body or a load carried on the moving body passes. The object detection range setting unit 202 controls the object detection unit 203 to set an object detection range in which an object is detected, based on the passing area calculated by the passing area calculation unit 201.

[0022] The object detection range setting unit 202 sets the object detection range to include at least the passing area calculated by the passing area calculation unit 201. The object detection unit 203 detects the presence or absence of an object based on information input from the measurement unit 211. That is, the object detection unit 203 is used to detect objects around the moving body 210 using the sensor 109.

[0023] Fig. 3 is an operational flowchart of the information processing device 100 according to the first embodiment, and Fig. 4 is a flowchart for explaining the details of step S304 in Fig. 3. Note that the CPU 101, which serves as a computer within the information processing device 100, executes a computer program stored in the storage device 103, thereby performing the operations of the steps in the flowcharts of Fig. 3 and Fig. 4.

[0024] In step S301, as an initialization process accompanying the execution of the process, the size and route information of the moving object 210 are loaded from the storage device 103 into the memory 102.

[0025] In step S302 (passing area calculation step), the passing area (spatial area) through which the moving object passes is calculated by the passing area calculation unit 201. The calculation method is based on the size and route of the moving object stored in memory 102, and calculates the spatial area through which the moving object passes when moving along the route.

[0026] In step S303 (object detection range setting step), object detection range setting unit 202 sets the object detection range of sensor 109 to a range corresponding to the passage area (spatial area) through which the moving object passes, calculated in step S302. That is, an object detection range for detecting an object is set in step S304 as an object detection step, based on the passage area calculated in step S302 as a passage area calculation step.

[0027] In step S304 (object detection step), the object detection unit 203 detects an object within the area set in step S303. That is, by detecting objects around the moving body 210 using the sensor 109, it is determined whether an object in the depth direction is included in the traveling area, for example, from an image captured after setting the detection range.

[0028] After step S304 is completed, the process returns to step S302, and steps S302 to S304 are repeated until an end operation is detected in an end operation detection step (not shown).

[0029] The object detection step in step S304 will be described using the flowchart in Fig. 4. In step S401, measurement information of the detected object is acquired. In step S402, it is determined whether the measurement value to the detected object is within the detection range set in step S303, and if it is within the range, the process proceeds to step S403, where the detected object is determined to be an obstacle. On the other hand, if it is outside the range, the process proceeds to step S404, where the detected object is determined not to be an obstacle.

[0030] The result of the determination as to whether or not the detected object is an obstacle may be displayed or notified to the user using, for example, text data, sound, or light on a display unit. Alternatively, based on the determination result, a drive unit (not shown) of the moving body may be driven and controlled to decelerate, avoid, or stop the moving body so as to prevent the moving body from colliding with the detected object.

[0031] As described above, according to the information processing device 100 of the first embodiment, the area through which the moving object passes is set as the object detection range. Therefore, even if an object outside the area through which the moving object passes is detected, it is not regarded as an obstacle, thereby reducing unnecessary avoidance operations and improving the efficiency of operation of the moving object.

[0032] In the above explanation, an example was shown in which a passive stereo camera was used as the sensor, but any type of sensor can be used as long as it can detect the position and distance of an object. For example, it can be an active stereo camera, a TOF (Time-Of-Flight) camera, or a LiDAR sensor.

[0033] In addition, in the first embodiment, an example was shown in which the detection range of the sensor was the area through which the moving object passes, but the detection range may also be the detection range of the first embodiment and a range up to at least the distance at which the moving object can stop (stopping distance).

[0034] For example, by calculating the braking distance based on the current speed, acceleration, etc. of the moving object, and setting the area through which the moving object passes from the current point up to the braking or stopping distance as the passing area and the detection range, it is possible to further suppress the detection of objects that do not hinder the moving object's travel. Note that the stopping distance here is defined as the free-travel distance (the delay until the user applies the brakes and the distance traveled during the program processing time) + braking distance (the distance traveled after the brakes are applied).

[0035] In addition, in the above explanation, an example was shown in which the detection range was set based on the area through which the moving object passed, but it is also possible to calculate an area only up to the braking distance without using the area through which the moving object passed in step S302 and set this as the detection range.

[0036] In the first embodiment, an example was shown in which the travel area consisting of the route of the moving object was set as the detection range of the sensor, but this travel area may not only be the route, but also an area including deviations (errors) that occur when traveling along the route. A moving object travels along a route, but there are cases in which the moving object cannot travel faithfully along the route depending on the environment and traveling conditions of the moving object.

[0037] For example, depending on the coefficient of friction between the road surface and the wheels of a moving object, one wheel of the moving object may slip, causing it to wobble, or multiple wheels of the moving object may slip, or a difference in the direction of the inner or outer wheels may occur when the moving object turns, causing it to deviate from the intended path. Also, a moving object carrying tall luggage may be blown off course by a crosswind.

[0038] In the case of wobbling or slipping, the difference between the expected acceleration and inertial force and their direction when the moving object travels along the route and the values ​​when it actually travels is calculated, and the difference is included in the size of the moving object to determine the passing area. Also, if the road surface is wet or slippery, this is taken into consideration when calculating the passing area. If the moving object is blown by a crosswind, the passing area is calculated taking into account the amount of movement required to return to the original route.

[0039] The inner wheel difference and outer wheel difference are calculated from the path of the moving object, the position of the wheels of the moving object, and the turning angle. Alternatively, the passing area may be calculated by performing an expansion process on the area defined by the size of the moving object and adding a certain amount of margin.

[0040] Alternatively, if the location of wobble or slippage is known, the passing area may be calculated by adding a margin to only that portion of the route. That is, the passing area calculation unit 201 may calculate the passing area based on the braking performance of the moving object 210, the speed during travel, the route, etc.

[0041] Furthermore, the detection range in the first embodiment may be set based only on distance. That is, the detection range may be limited to a predetermined distance range. In this case, the detection range is set by changing parameters related to distance measurement of the sensor. Specifically, in the case of a passive stereo camera, the parallax during stereo matching is limited. In addition, in the case of a sensor that measures distance images or LiDAR, the detection range can be defined from the measured distance value.

[0042] Alternatively, the detection range in the first embodiment may be set only in the ranges in the left-right and up-down directions without considering the distance. Specifically, the detection range can be limited as parameters to the position where the moving object passes and the ranges in the up-down and left-right directions for the area of ​​the image captured in stereo images.

[0043] In this way, object detection range setting unit 202 sets the object detection range by changing the parameters so that the object detection range includes the passing area calculated by passing area calculation unit 201. The parameters include at least one of a parameter such as parallax in sensor 109 or a parameter related to the detection range in object detection.

[0044] (Embodiment 2) In the first embodiment, the detection range was set to a range corresponding to the spatial region through which the moving object passes. In contrast, in the second embodiment, a type of object around the moving object is identified that can at least determine whether it is a moving object, and the obstacle detection range of the sensor is changed based on the area in space that the object occupies. In this embodiment, the sensor detects an object in front of the moving object using a passive stereo camera, and identifies the object by image recognition of the object obtained from the sensor.

[0045] Specifically, the system identifies the object by matching the captured image with a template image of the object stored in advance, and then sets the detection range based on the identification results so that objects that are unlikely to move near the moving body on their own are not detected as obstacles. This method eliminates from detection objects that are unlikely to collide with the moving body, thereby reducing the collision avoidance process for the moving body and improving operation efficiency.

[0046] The hardware configuration of the information processing device according to the second embodiment is substantially the same as that shown in Fig. 1, except for the configuration of the sensor 109. Note that an image for template matching and the range of movement of an object in that image are input to the storage device 103.

[0047] The program 107 stored in the storage device 103 includes a program for controlling the range in which the sensor detects an object and a program for identifying the detected object by template matching. The sensor 109 is composed of a first sensor 109a and a second sensor 109b, and the first sensor 109a and the second sensor 109b are connected to the I / O 108.

[0048] 5 is a functional block diagram of an information processing device 100 according to embodiment 2. The moving body 210 includes the information processing device 100, a first measurement unit 511, and a second measurement unit 512. The information processing device 100 includes a first object detection unit 501, an object identification unit 502, an object movement range estimation unit 503, an object detection range setting unit 504, and a second object detection unit 505.

[0049] The first measurement unit 511 calculates the distance to each feature point in the stereo image based on the information input from the first sensor 109a and outputs the distance to the first object detection unit 501. The second measurement unit 512 calculates the distance to each feature point in the stereo image based on the information input from the second sensor 109b and outputs the distance to the second object detection unit 505.

[0050] The first object detection unit 501 outputs the presence or absence of an object and the distance to the object based on the information input from the first measurement unit 511. That is, the first sensor 901a detects objects around the moving body. The object identification unit 502 identifies the object based on characteristics such as the type, attribute, and size of the object detected by the first object detection unit 501. The object movement range estimation unit 503 estimates the movement range (movement range) of the object identified by the object identification unit 502.

[0051] The object detection range setting unit 504 (object detection range setting means) sets (controls) the object detection range in which the second object detection unit 505 detects an object, based on (the position of) the object identified by the object identification unit 502 and the object movement range estimated by the object movement range estimation unit 503. The second object detection unit 505 detects the presence or absence of an object based on information input from the second measurement unit 512. That is, the second sensor 901b detects objects around the moving body.

[0052] Fig. 6 is an operation flowchart of the information processing device 100 according to embodiment 2. Note that the CPU 101 as a computer in the information processing device 100 executes a computer program stored in the storage device 103, thereby performing the operation of each step in the flowchart of Fig. 6.

[0053] In step S601, as an initialization process accompanying the execution of processing, route information, an image for template matching, and accompanying information for that image are loaded from the storage device 103 to the memory 102. In step S602, the first object detection unit 501 detects objects around the moving body.

[0054] That is, in step S602 (first object detection step), an object around the moving object is detected by the first sensor. As in the first embodiment, the detection method is to detect the object by stereo matching feature points of images captured by the passive stereo camera of the sensor 109a.

[0055] In step S603, it is determined whether the object detected by object identification unit 502 is a moving object. That is, in step S603 (object identification step), the object is identified based on the characteristics of the object detected in step S602 as the first object detection step. The method of identification is to identify the detected object by matching the image detected in step S602 with a template image of the object having accompanying information on its movement range that has been registered in advance.

[0056] In step S604 (object movement range estimation step), the movement range of the object identified in step S603 as the object identification step is estimated. The movement range is estimated from the movement range or movement presence / absence information associated with the matched image. Furthermore, even if an object can be detected, if the type or movement of the object cannot be identified, it is treated as moving over the entire area.

[0057] In step S605, if the identified object and its movement range are such that the object is unlikely to move close to the moving object on its own, the object is prevented from being detected as an obstacle. To this end, the detection range of the second sensor 109b is set to the closest distance from the moving object to the identified object within the detection range of the sensor so that the movement range of the object is not included in the detection range of the sensor.

[0058] That is, in step S605 (object detection range setting step), an object detection range for detecting an object in step S606 is set based on the object identified in step S603 and the movement range estimated in step S604.

[0059] At this time, the object detection range setting unit 504 sets the object detection range based on the positional relationship between the object and the moving body identified by the object identification unit 502. At this time, the detection range is set by changing the sensor parameters or the object detection processing parameters as shown in the first embodiment.

[0060] In step S606, the second sensor 901b is used to detect whether or not an object exists within the detection range set in step S605. That is, in step S606 (second object detection step), the second sensor detects an object around the moving body 210. If the presence of an object is detected, the process of determining that the object is an obstacle is repeated until an end operation is detected in an end operation detection step (not shown).

[0061] In this way, objects that are unlikely to come close to the moving object are detected first, and the object is not detected as an obstacle. Then, it is possible to check whether there are any other obstacles between the moving object and the detected object. For example, suppose a wall is detected within the operating range. If the moving object approaches the wall and then takes a route that runs along the wall, even if the wall is detected, the wall will not be detected as an obstacle. Therefore, the moving object can continue running without stopping.

[0062] As described above, according to the information processing device 100 of the second embodiment, it is possible to improve the efficiency of operation of a mobile body by first detecting an object that is unlikely to come near the mobile body and setting a detection range so that the object is not detected as an obstacle.

[0063] Although the second embodiment shows an example in which a plurality of sensors and object detection units are used, a single sensor and object detection unit may be used. Specifically, a first sensor may detect all objects, identify an object among them, and then reset the detection range to the distance to the identified object to detect the object. In this way, detection for recognizing an object and detection of objects other than the recognized object may be performed alternately.

[0064] Although the second embodiment shows an example in which an object is determined by matching similar images, the method for determination is not limited to this. For example, an object may be recognized from an image using machine learning techniques such as deep learning.

[0065] In addition, in the second embodiment, an example was shown in which an object is identified and an object whose range of movement overlaps with the detection range is detected, but if it is known that the object will not collide, the identified object may be excluded from the detection target regardless of the range of movement of the object. For example, in an environment where multiple moving objects are operating, when one moving object is chasing another moving object, the chasing moving object will always include the preceding (leading) moving object in the detection range of the sensor.

[0066] Normally, when a leading moving object is detected, the pursuing moving object will take evasive action.Specifically, in step S603 in Figure 6, to determine whether the detected object is a moving object, the object is identified using an identifier such as a two-dimensional barcode attached to the moving object or object recognition such as deep learning.

[0067] If it is a moving object, step S604 checks whether the path of the specific moving object and the vehicle's own path intersect at the same time or whether they are traveling in the same direction. If it is determined that they do not intersect, meaning that the possibility of a collision is not normally possible, the preceding moving object is not detected as an obstacle. Alternatively, the section in which the preceding moving object is traveling in the same direction is identified from the route information, and the preceding moving object is not detected as an obstacle while traveling in that section.

[0068] In the second embodiment, the detection result (presence or absence of an obstacle, etc.) in step S606 may also be notified to an external terminal or the like by data such as a message, sound, light, etc., to prompt the external terminal or the like to control the moving object. Alternatively, based on the detection result in step S606, the moving object may be controlled to slow down, avoid collision, or stop in order to prevent the moving object from colliding with the detected object. Furthermore, if the detection range becomes shorter than the braking distance, the moving object may be controlled so that the detection range becomes the braking distance.

[0069] In the second embodiment, the detection area is determined based on a single detection result, but an object that is determined to be a fixed object based on the object detection history at the same location in the past may be excluded from the detection area of ​​the second object detection unit 405.

[0070] Specifically, the object, its image, and its position are stored in step S603 in Fig. 5. Then, a branch is provided before step S604, and at this branch, it is determined whether the detected object has been detected in the past.

[0071] In the determination process, it is determined whether an object was previously detected at the same position, and whether the detected object is the same as the currently detected object even if template matching is performed. If there is a match in all aspects, it is determined that the object is the same as the previously detected object. If so, it is treated as a stationary object and the process proceeds to step S605. If there is no match, it is determined to be a different object, and the movement range is estimated in step S604.

[0072] In the second embodiment, an example is shown in which an object detected by a moving body is identified by template matching, but if the object can be determined to be a stationary object without identification, it may be excluded from the detection area of ​​the second object detection unit 405.

[0073] Specifically, the system stores in advance the map data of the area where the moving object will travel as information that can be used to determine whether the object is stationary. This map data includes fixed objects such as walls and pillars, and by associating the map data with the moving object's position and direction, it is possible to determine the position and direction in which the moving object is traveling on the map data.

[0074] Furthermore, in the second embodiment, an example is shown in which a detected object is identified and the detection range is set based on its position, but it is also possible to estimate the area in space that the detected object may occupy and set the detection range based on that area.

[0075] Specifically, when identifying the detected object by template matching in step S603, the area matched with the same template image is determined to be the same object, thereby estimating the area occupied by the object. After that, the movement range for the object's area is estimated, and the object is detected by determining whether the movement range is included in the detection range.

[0076] (Embodiment 3) In the first and second embodiments, the object detection ranges determined for each are controlled, but in the third embodiment, switching is made between the first and second embodiments based on the speed of a moving object. The internal configuration and functional block diagram of the information processing device according to the third embodiment uses the configurations and functions of the first and second embodiments. Furthermore, a determination unit is provided to determine which function to use.

[0077] The flowchart of the information processing device 100 according to the third embodiment uses the flows of the first and second embodiments, but a branch is provided at the front to determine which process to perform before entering each flow. This branch is determined by the above-mentioned determination unit, and if the moving object is traveling at a speed equal to or less than a threshold for the braking distance, the detection range of the sensor is controlled based on the area in which the moving object is traveling, according to the process of the first embodiment. On the other hand, if the moving object is traveling at a speed higher than the threshold, the detection range of the sensor is changed based on the result of identifying objects around the moving object, according to the process of the second embodiment.

[0078] (Embodiment 4) In the third embodiment, an example was shown in which the first embodiment and the second embodiment were switched over, but in the fourth embodiment, the first embodiment and the second embodiment are used together. The internal configuration of the information processing device according to the third embodiment is the same as that of the second embodiment, and the functional block diagram adds the passing area calculation unit of the first embodiment to the second embodiment.

[0079] The processing steps include identifying the type and attributes of an object detected within the detection range of the sensor according to embodiment 2, and estimating the movement range of the detected object. Then, the passing area of ​​the moving body according to embodiment 1 is calculated, and the detection area is set so as to detect objects present within the passing area and objects whose passing area and the estimated movement range overlap.

[0080] (Embodiment 5) In the first, second, third and fourth embodiments, examples have been shown in which the detection range is controlled, but in the fifth embodiment, the detection results and obstacle determination results are presented to the user on a display device. An example of this will be described with reference to FIG.

[0081] 7(A) and (B) are diagrams showing display examples according to embodiment 5. Fig. 7(A) is an image 701 captured using a passive stereo camera, in which a person 702, a wall 703, a wall 704, and a wall 705 are reflected. Fig. 7(B) is a diagram showing a UI screen 711 that displays the results of object detection based on the image shown in Fig. 7(A) and the obstacle detection area, and various confirmations and display settings can be made on the UI screen 711.

[0082] Marks 712, 713, 714, and 715 indicate the type of detected object, and distinguish whether it is a moving object or not. That is, a moving object is represented by mark 712, and stationary objects are represented by marks 713 to 715. Furthermore, the nearest moving object is indicated by mark 716, and the distance to that is displayed as distance value 751.

[0083] A detection range 722 is a visualization of the detection range, and objects included in this detection range 722 are targets for obstacle detection. There is a wall 705 at the back of the detection range 722, but if the wall 705 is identified, it will be identified as an immovable object, and therefore the wall 705 is not included in the detection range 722.

[0084] The UI screen 711 further has a button 721 for switching the display of the moving object passing area on and off, a button 731 for switching the display of the movement range of a detected object on and off, and a slide bar 741 for setting a margin of the size of the moving object to absorb deviations when the moving object moves.

[0085] By switching on button 721, which is used to switch the display of the moving object passing area ON / OFF, the moving object passing area is displayed by displaying detection range 722. By switching on button 731, which is used to switch on / off the display of the movement range of the detected object, the range in which the detected object moves is displayed. Person 702 has been identified as a moving object, and his movement range is expressed by range 732.

[0086] 7(B), the position of person 702 is not included in the moving object's passing area, but since movement range 732 is included in the passing area, person 702 is determined to be an obstacle and can be confirmed on the display. Also, by adjusting the slide bar 741 to set the margin for the moving object's size, the size of the moving object expands or contracts by the set value, and detection range 722 is displayed based on that size.

[0087] (Other embodiments) 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 spirit of the present invention, and these modifications are not excluded from the scope of the present invention.

[0088] For example, in the above-described embodiment, an example in which the present invention is applied to an autonomous moving body has been described. However, the moving body in this embodiment is not limited to an autonomous moving body such as an AGV (Automated Guided Vehicle) or an AMR (Autonomous Mobile Robot).

[0089] Furthermore, the moving body may be any type of moving device that moves, such as a car, train, ship, airplane, robot, or drone.

[0090] Furthermore, at least a part of the information processing system of the embodiment may or may not be mounted on a mobile object. The present invention can also be applied to a case where a mobile object is remotely controlled. The present invention can also be applied to a system consisting of multiple devices, or to an apparatus consisting of a single device. The present embodiment includes the following combinations.

[0091] (Configuration 1) An information processing device comprising: a passing area calculation means for calculating a passing area through which a moving body passes; an object detection means for detecting objects around the moving body using a sensor; and an object detection range setting means for setting an object detection range in which the object detection means detects the object based on the passing area calculated by the passing area calculation means.

[0092] (Configuration 2) The information processing device according to configuration 1, wherein the passing area includes an area through which a connected object that moves while connected to the moving body or a load carried on the moving body passes.

[0093] (Configuration 3) The information processing device according to configuration 1 or 2, wherein the object detection range setting means sets the object detection range so as to include at least the passing area calculated by the passing area calculation means.

[0094] (Configuration 4) The information processing device according to Configuration 3, wherein the object detection range setting means changes at least one of the parameters of the sensor or the parameters of the object detection means so that the object detection range includes at least the passing area calculated by the passing area calculation means.

[0095] (Configuration 5) The information processing device according to configuration 3, wherein the passing area calculation means calculates the passing area based on the braking performance of the moving body, the speed while traveling, and the route.

[0096] (Configuration 6) An information processing device comprising: a first object detection means for detecting an object around a moving body by a first sensor; a second object detection means for detecting an object around the moving body by a second sensor; an object identification means for identifying the object based on features of the object detected by the first object detection means; an object movement range estimation means for estimating a movement range of the object identified by the object identification means; and an object detection range setting means for setting an object detection range in which the second object detection means detects an object based on the object identified by the object identification means and the movement range estimated by the object movement range estimation means.

[0097] (Configuration 7) The information processing device according to configuration 6, wherein the object detection range setting means sets the object detection range based on the positional relationship between the object identified by the object identification means and the moving body.

[0098] (Configuration 8) The information processing device according to any one of configurations 1 to 7, wherein the object detection range setting means sets the object detection range based on a stopping distance of the moving object.

[0099] (Configuration 9) The information processing device according to any one of configurations 1 to 8, characterized in that display or drive control of the moving body is performed based on the detection result of the object detected within the object detection range.

[0100] (Method 1) An information processing method comprising: a passing area calculation step of calculating a passing area through which a moving body passes; an object detection step of detecting objects around the moving body using a sensor; and an object detection range setting step of setting an object detection range in which the object is detected in the object detection step based on the passing area calculated in the passing area calculation step.

[0101] (Method 2) An information processing method comprising: a first object detection step of detecting objects around a moving body using a first sensor; a second object detection step of detecting objects around the moving body using a second sensor; an object identification step of identifying the object based on characteristics of the object detected in the first object detection step; an object motion range estimation step of estimating a motion range of the object identified in the object identification step; and an object detection range setting step of setting an object detection range for detecting objects in the second object detection step based on the object identified in the object identification step and the motion range estimated in the object motion range estimation step.

[0102] (Program) A computer program for controlling each means of the information processing device according to any one of configurations 1 to 8 by a computer.

[0103] The present invention can also be achieved by directly or remotely supplying a program that realizes the functions of the above-described embodiments to a system or device, and having the system or device read and execute the supplied program code. Therefore, the program code itself that is installed in a computer to realize the functional processing of the present invention by the computer is also included in the technical scope of the present invention.

[0104] In this case, as long as it has the functionality of a program, the form of the program does not matter, such as object code, a program executed by an interpreter, or script data supplied to an OS.

[0105] Recording media for supplying the program include, for example, floppy disks, hard disks, optical disks (CD, DVD), magneto-optical disks, magnetic tapes, non-volatile memory cards, and ROMs.

[0106] Alternatively, the functions of the above-described embodiments may be realized by a computer executing the read program. Alternatively, the OS running on the computer may perform some or all of the actual processing based on the instructions of the program, and the functions of the above-described embodiments may also be realized by this processing.

[0107] Furthermore, the program read from the recording medium is written to a memory provided in a function expansion board inserted into a computer or a function expansion unit connected to the computer, and then, based on instructions from the program, a CPU or GPU provided in the function expansion board or function expansion unit performs some or all of the actual processing, and the functions of the above-mentioned embodiments can also be realized by this processing. [Explanation of symbols]

[0108] 100: Information processing device 201: Passage area calculation section 202: Object detection range setting unit 203: Object detection unit 210: Mobile 211: Measurement section

Claims

1. A first object detection means for detecting an object around a moving object by a first sensor; a second object detection means for detecting an object around the moving body by a second sensor; an object identification means for identifying the object based on the characteristics of the object detected by the first object detection means; an object movement range estimation means for estimating a movement range of the object identified by the object identification means; and an object detection range setting means for setting an object detection range in which the second object detection means detects an object based on the object identified by the object identification means and the movement range estimated by the object movement range estimation means.

2. A passing area calculation means for calculating a passing area through which a moving object passes, 2. The information processing apparatus according to claim 1, wherein the passage area includes an area through which a connected object that moves while connected to the moving object or a load carried on the moving object passes.

3. 3. The information processing apparatus according to claim 2, wherein the object detection range setting means sets the object detection range so as to include at least the passing area calculated by the passing area calculation means.

4. 4. The information processing device according to claim 3, wherein the object detection range setting means changes at least one of the parameters of the second sensor or the parameters of the second object detection means so that the object detection range includes at least the passing area calculated by the passing area calculation means.

5. 4. The information processing apparatus according to claim 3, wherein said passing area calculation means calculates said passing area based on the braking performance of said mobile object, its speed while traveling, and its route.

6. 2. The information processing apparatus according to claim 1, wherein the object detection range setting means sets the object detection range based on a positional relationship between the object identified by the object identifying means and the moving body.

7. 2. The information processing apparatus according to claim 1, wherein the object detection range setting means sets the object detection range based on a stopping distance of the moving object.

8. 2. The information processing apparatus according to claim 1, wherein display or drive control of the moving body is performed based on the detection result of the object detected within the object detection range.

9. An information processing method using a computer to execute the following steps: a first object detection step of detecting an object around the moving object by a first sensor; a second object detection step of detecting an object around the moving body by a second sensor; an object identification step of identifying the object based on features of the object detected in the first object detection step; an object movement range estimation step of estimating a movement range of the object identified in the object identification step; an object detection range setting step of setting an object detection range for detecting an object in the second object detection step based on the object identified in the object identification step and the motion range estimated in the object motion range estimation step.

10. A computer program for controlling each means of the information processing apparatus according to any one of claims 1 to 8 by a computer.

Images