Autonomous body movement control system, control device, and control method

Abstract

To provide an autonomous body movement control system, a control device, and a control method that are able to achieve both safety and productivity in a field in which vehicles and workers are mixedly present.SOLUTION: Environment information that is information on an environment in a field is generated based on measurement results of position information of persons and autonomous mobile bodies in a field in which persons and the autonomous mobile bodies are mixedly present. The environment information is analyzed to detect, as a dangerous area, an area in the field in which a contact between a person and an autonomous mobile body is highly likely to occur. Movement control of the autonomous mobile body is performed based on the detected dangerous area. Movement paths of the persons are predicted based on the position information of the persons in the field. A person who is likely to view the dangerous area is selected based on the predicted movement paths of the persons. An instruction is given to the person to photograph the dangerous area with a camera carried by the selected person so as to update environmental information based on images captured by the camera.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an autonomous object movement control system, a control device, and a control method. [Background technology]

[0002] In recent years, with the decline in the working population due to the low birthrate and aging population, there are growing expectations for automatic and autonomous system control to resolve labor shortages and improve productivity. For example, in fields where people and machines (vehicles, etc.) coexist, such as logistics warehouses, it is possible to achieve both safety and productivity by performing automatic and autonomous control of each object.

[0003] Known technologies for ensuring safety when there is an autonomous body (e.g., a vehicle) subject to movement control in the field where work is performed involve installing sensors such as cameras and LiDAR around the vehicle and its driving route, and controlling the vehicle's speed, etc. by detecting danger areas where objects are predicted to jump into the vehicle's driving route.

[0004] For example, Patent Document 1 discloses a risk calculation device including a traffic environment information acquisition means for acquiring traffic environment information during vehicle travel, a blind spot area detection means for detecting blind spot areas formed by obstacles, a dynamic information extraction means for extracting dynamic information that contributes to the risk of the blind spot area from the traffic environment information acquired by the traffic environment information acquisition means, and a risk calculation means for setting the risk of the blind spot area based on the extracted dynamic information that contributes to the risk of the blind spot area. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2012-104029 A Summary of the Invention [Problem to be solved by the invention]

[0006] In the above-mentioned conventional technology, dangerous areas such as blind spots are detected from obstacle position information, and the degree of danger is estimated and updated from dynamic information such as people entering and exiting the vehicle, thereby controlling the vehicle.

[0007] However, in fields such as logistics warehouses where there are a large number of danger areas around the driving paths of autonomous objects such as vehicles and where the positions of the danger areas change from moment to moment, it is necessary to constantly take into consideration things like vehicles jumping out into the street, which may result in the vehicle's speed being frequently slowed down, resulting in reduced productivity.

[0008] The present invention has been made in consideration of the above, and aims to provide an autonomous object movement control system, a control device, and a control method that can achieve both safety and productivity in fields where vehicles and workers are mixed. [Means for solving the problem]

[0009] The present application includes a number of means for solving the above-mentioned problems. One example of such an autonomous body movement control system is an autonomous body movement control system that controls the movement of an autonomous moving body in a field where people and autonomous moving bodies are mixed, and includes a number of measurement devices that measure the positions of people in the field and position information of the autonomous moving bodies, and an autonomous body movement control device that generates environmental information, which is information about the environment in the field, based on the measurement results from the measurement devices, analyzes the environmental information to detect areas in the field where contact between the people and the autonomous moving bodies is likely to occur as dangerous areas, controls the movement of the autonomous moving body based on the detected dangerous areas, predicts a movement path of the people based on position information of the people in the field, selects people who are likely to visually observe the dangerous area based on the predicted movement path of the people, instructs the people to photograph the dangerous area with a camera carried by the selected people, and updates the environmental information based on the image photographed by the camera. Effect of the Invention

[0010] According to the present invention, in a field where vehicles and workers are mixed, danger areas where an object is predicted to intrude into the vehicle's driving path are detected, and the number of detected danger areas is appropriately reduced depending on the level of danger, thereby achieving both safety and productivity. [Brief description of the drawings]

[0011] [Figure 1] 1 is a functional block diagram showing an overall configuration of an autonomous object movement control system according to a first embodiment. [Diagram 2] FIG. 4 is a diagram illustrating an example of environmental information generated by an environmental information generating unit. [Diagram 3] FIG. 4 is a functional block diagram showing details of a danger area detection unit. [Figure 4] 10 is a diagram showing an example of a blind spot area extracted by a blind spot area extraction unit; FIG. [Diagram 5] 13 shows an example of the contents of a photographing instruction displayed on the display of the smart glasses by the photographing instruction unit. [Figure 6] 13 shows an example of the contents of a photographing instruction displayed on the display of the smart glasses by the photographing instruction unit. [Figure 7] 4 is a functional block diagram showing details of an environment information update unit. FIG. [Figure 8] 13 is a flowchart showing the processing contents of a risk region updating unit. [Figure 9] FIG. 11 is a functional block diagram showing an overall configuration of an autonomous object movement control system according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0013] In the following description, when there are multiple identical components, an alphabet may be added to the end of the symbol (number), but the alphabet may be omitted and the multiple components may be collectively referred to as obstacle 13, for example, obstacles 13a, 13b, 13c, 13d, and 13e.

[0014] <First embodiment> A first embodiment of the present invention will be described in detail with reference to FIGS.

[0015] FIG. 1 is a functional block diagram showing the overall configuration of an autonomous object movement control system according to the present embodiment.

[0016] In Fig. 1, the autonomous body movement control system is a device that measures the positions of autonomous bodies (hereinafter referred to as autonomous moving bodies) such as vehicles that perform autonomous work and travel within a logistics drive, workers, obstacles, etc., based on information from multiple measurement devices arranged in a field such as a logistics warehouse, and controls the autonomous travel of the vehicle, etc., and has multiple measurement devices 2a and 2b, an autonomous body movement control device 1 equipped with an environmental information generation unit 3, a dangerous area detection unit 4, an autonomous body control unit 5, a travel path prediction unit 6, a worker selection unit 7, a photography instruction unit 8, an environmental information update unit 9, and a memory unit 200, a memory device 201, and a wearable camera 14. Each function of the autonomous body movement control device 1 is realized in a computer having a calculation unit such as a CPU, and an internal / external memory device such as an HDD or SSD.

[0017] The multiple measurement devices 2a and 2b are, for example, sensors such as a monocular camera that captures various locations in the field and LiDAR (Light Detection and Ranging). When a monocular camera is used as the measurement devices 2a and 2b, the monocular camera functions as a measurement device that measures the position of an autonomous moving object or a person in the field from the captured image and the preset position information of the monocular camera in the field. Similarly, when a LiDAR is used as the measurement devices 2a and 2b, the LiDAR functions as a measurement device that measures the position of an autonomous moving object or a person in the field from the measured distance data and the preset position information of the LiDAR in the field. Note that the measurement devices 2a and 2b are not limited to monocular cameras and LiDARs, and for example, stereo cameras and distance sensors can be used as measurement devices. In addition, the multiple measurement devices 2a and 2b do not all need to be the same type, and different types of measurement devices can be used together. Hereinafter, measurement devices including the measurement devices 2a and 2b may be collectively referred to as sensors.

[0018] The environmental information generation unit 3 is a functional unit that generates environmental information indicating the positions of vehicles, people (hereinafter also referred to as workers), and obstacles by analyzing information obtained from multiple measuring devices 2a, 2b, and stores the information in the memory unit 200 or updates the environmental information in the memory unit 200.

[0019] The danger area detection unit 4 is a functional unit that analyzes the environmental information in the storage unit 200, detects areas where there is a high possibility of contact between a worker and a vehicle or areas that increase the possibility of contact between a worker and a vehicle as danger areas, and incorporates the areas into the environmental information in the storage unit 200 or updates the information on danger areas included in the environmental information. Examples of danger areas include areas that may be blind spots of on-board sensors mounted on the vehicle or infrastructure sensors installed in the field due to obstacles such as luggage.

[0020] The autonomous body control unit 5 is a functional unit that determines the route and speed of the vehicle based on the information on dangerous areas included in the environmental information in the storage unit 200, and issues instructions to the vehicle.

[0021] The movement path prediction unit 6 is a functional unit that predicts the movement path of the worker based on the position information of the worker acquired by the measurement devices 2a and 2b and the work plan information stored in the storage device 201 in advance.

[0022] The worker selection unit 7 is a functional unit that selects a worker who is likely to move near the danger area detected by the danger area detection unit 4, based on the worker's movement path predicted by the movement path prediction unit 6.

[0023] The photography instruction unit 8 is a functional unit that instructs the worker selected by the worker selection unit 7 to photograph the danger area with the wearable camera owned by the worker. The wearable camera is, for example, a camera mounted on a helmet worn by the worker for photographing the work situation, a camera mounted on a work smartphone, or smart glasses equipped with a photographing function.

[0024] Environmental information update unit 9 is a functional unit that updates the environmental information in storage unit 200 based on an image (photographing information) captured by the wearable camera.

[0025] FIG. 2 is a diagram illustrating an example of environmental information generated by the environmental information generating unit.

[0026] As shown in Fig. 2, the environmental information is generated as an environmental map 10 by the environmental information generating unit 3. The environmental map 10 includes position information of a vehicle 11, position information of a worker 12, position information of obstacles 13a, 13b, 13c, 13d, and 13e, and a candidate driving route 40 for the vehicle 11, which is shown by a shaded area. Note that Fig. 2 also shows the position information of measuring devices 2a and 2b in the field.

[0027] The information input to the autonomous body movement control device 1 is a combination of the measurement results of sensors fixed in the field (hereinafter referred to as infrastructure sensors) and the measurement results of sensors mounted on the vehicle (hereinafter referred to as vehicle-mounted sensors), and by performing calibration between the sensors in advance, it is possible to handle the results of all sensors in the same coordinate space. Note that the information is not limited to the above information as long as it is possible to measure the position and type of the target.

[0028] The environmental information handled in this embodiment is a two-dimensional image capturing a bird's-eye view of the field, such as the environmental map 10, and the maximum height information within the pixel area is embedded in each pixel value, making it possible to grasp the position information and height information of the target. Note that the method of acquiring and expressing the environmental information is not particularly limited as long as it is possible to grasp the position information and height information of people, vehicles, and obstacles, and candidate routes on which the vehicle can travel. For example, the environmental information generating unit 3 may not only generate new environmental information from the information of the measuring devices 2a and 2b, but may also update the environmental information based on past environmental information and the latest sensor information.

[0029] FIG. 3 is a functional block diagram showing the details of the danger area detection unit.

[0030] In FIG. 3, the danger area detection unit 4 includes a vehicle driving route generation unit 30, a blind spot area extraction unit 31, a people flow information acquisition unit 32, and a danger area determination unit 33.

[0031] The vehicle driving route generating unit 30 is a functional unit that generates candidate information for a vehicle driving route from the environmental information in the storage unit 200 .

[0032] The blind spot area extraction unit 31 is a functional unit that analyzes obstacle information present in the vicinity of a candidate driving route of the vehicle, and extracts areas that may be blind spots (blind spot areas) from on-board sensors and infrastructure sensors.

[0033] The people flow information acquisition unit 32 is a functional unit that acquires people flow information indicating the entry and exit of workers into and from the blind spot area acquired by the blind spot area extraction unit 31.

[0034] The danger area determining unit 33 is a functional unit that determines danger areas existing near the vehicle travel route based on blind spot areas and pedestrian flow information.

[0035] Hereinafter, the processing functions of each functional unit of the danger area detection unit 4 will be described in detail.

[0036] The vehicle driving path generating unit 30 generates one or more possible driving paths along which the vehicle may travel by using the environmental map 10. The method of generating the driving paths is not particularly limited as long as it is a method capable of outputting one or more possible vehicle driving paths on the environmental map 10, such as inputting position information of a starting point and a destination point and outputting one or more driving paths from route information on the environmental map 10 along which the vehicle may travel.

[0037] FIG. 4 is a diagram illustrating an example of a blind spot area extracted by the blind spot area extraction unit.

[0038] FIG. 4 shows one of the vehicle driving route candidates 40 output by the vehicle driving route generating unit 30, a vehicle traveling direction 41, and blind spot areas 42a, 42b, and 42c.

[0039] The blind spot area extraction unit 31 extracts blind spots that are expected to occur due to surrounding obstacles 13 with respect to the driving route candidate 40 output by the vehicle driving route generation unit 30 in the environmental map 10. The blind spot area is extracted using the shooting areas of the measurement devices 2a and 2b around the driving route candidate 40 and the position information and height information of the obstacles. The shooting areas of the measurement devices 2a and 2b can be estimated by acquiring the position and orientation of the sensor on the environmental map 10 in advance for the infrastructure sensor, and can be estimated from the vehicle's traveling direction 41 and the sensor orientation information for the vehicle-mounted sensor. For example, in FIG. 4, when the shooting area of ​​the infrastructure sensor matches the driving route candidate 40 and the height of the five obstacles 13 is higher than the height of the worker, three blind spot areas 42a, 42b, and 42c are extracted. When the traveling direction of the vehicle is opposite to the traveling direction 41, it is determined that the area between the obstacles 13d and 13e (blind spot area 42c) can be measured by the on-board sensor, and therefore only the blind spot areas 42a and 42b are extracted. There are no particular limitations on the method as long as it is possible to estimate the blind spot area from the vehicle by utilizing the information on the environment map 10 or the like other than the above example.

[0040] The people flow information acquisition unit 32 estimates people flow information by analyzing sensor information in the blind spot area 42 extracted by the blind spot area extraction unit 31. The people flow information may be information that allows the entry and exit of workers into the blind spot area to be grasped, and is not particularly limited to the number of workers who entered and exited the blind spot area per certain period of time.

[0041] The danger area determining unit 33 uses the people flow information acquired from the people flow information acquiring unit 32 to determine a danger area from within the blind spot area 42 acquired from the blind spot area extracting unit 31 .

[0042] The method of determining a danger area is not particularly limited as long as it can select a blind spot area that is expected to be highly dangerous based on people flow information as a danger area, such as a method of determining as a danger area a blind spot area where the frequency of workers entering and exiting the blind spot area until immediately before the danger area is determined to be greater than a threshold value, or a method of determining as a danger area a blind spot area where the number of workers entering the blind spot area is significantly greater than the number of workers exiting the blind spot area.

[0043] In addition, a method may be used in which blind spots near points where a high rate of contact between vehicles and workers is expected to occur may be determined as danger areas based on not only people flow information but also the relative positions of obstacles and vehicles, or a method may be used in which the user sets an area on the environmental map 10 in advance using a GUI or the like, and blind spots within the set area are determined as danger areas.

[0044] The danger area detection unit 4 outputs information about the danger area determined by the danger area determination unit 33 to the worker selection unit 7 , and adds / updates the danger area information in the environment information in the storage unit 200 .

[0045] The autonomous body control unit 5 is a functional unit that controls the route and speed of the autonomous body (vehicle) based on information on one or more vehicle travel route candidates 40 and information on dangerous areas existing around each travel route candidate. The method of controlling the travel route of the autonomous body includes a method of determining a final travel route from among the travel route candidates and controlling the vehicle so that the center of the vehicle travels on the center of the route. The method of determining the final travel route is not particularly limited, and may include a method of determining the route with the fewest number of dangerous areas around as the final route among the travel route candidates, or a method of determining the route with the shortest distance as the final route when it is necessary to move the vehicle quickly by acquiring information on the progress of work in the field (whole warehouse). The method of determining the speed includes a method of controlling the speed to be slower than the normal speed predetermined in the warehouse on the route just before approaching the dangerous area and to travel at the normal speed on other routes, and a method of calculating a danger level that can determine the level of the dangerous area from human flow information in advance and controlling the speed according to the danger level.

[0046] The movement path prediction unit 6 is a functional unit that predicts a movement path on the environment map 10 for each worker based on the worker information measured by the measuring devices 2a and 2b and the work plan information of the corresponding worker.

[0047] The measurement information of the worker by the measuring devices 2a and 2b is information from which the latest position and behavior of the worker can be ascertained, and the work plan information in the storage device 201 is information from which the content of the work to be performed by the worker on that day can be ascertained.

[0048] As a method of predicting a movement path, for example, when the work area and the planned work time for one day can be known as work plan information, a method of predicting the movement path of a worker based on the current time, current position information, and position information of the current and next work areas may be used. In addition, when a worker is recognized to have traveled back and forth between two areas by analyzing trajectory information acquired by a sensor, a method of predicting the movement path of the worker based on the current position and the position information of the two areas may be used. In addition, a method of predicting the movement path of a worker based on the amount and direction of movement of the worker from the trajectory information of the worker up to the last moment, assuming that the worker moves in a uniform linear motion, without using work plan information, may be used. In addition, any method is not particularly limited as long as it is possible to predict the next location to which the worker will move and estimate the movement path based on the trajectory information of the worker obtained by a sensor and work plan information of the worker.

[0049] The worker selection unit 7 selects workers who may move near the danger areas on the environmental map 10 based on the danger areas extracted by the danger area detection unit 4 and the movement path information of the workers estimated by the movement path prediction unit 6. The selection method is not particularly limited, and may be a method of selecting one worker closest to each danger area, or a method of selecting multiple workers moving near each danger area. Alternatively, a method may be used to select a worker who can capture the danger area with a wearable camera without moving from the current position, using the current position information of the worker and the angle of view information of the wearable camera worn by the worker.

[0050] The photographing instruction unit 8 is a functional unit that instructs the selected worker to photograph the danger area with the wearable camera. In this embodiment, an example in which smart glasses equipped with a photographing function are used as the wearable camera will be described.

[0051] 5 and 6 show examples of the contents of shooting instructions displayed on the display of the smart glasses by the shooting instruction unit.

[0052] Figure 5 illustrates a method in which the danger area to be photographed and the photographing direction are indicated by an arrow 51a in the worker's viewpoint 50a through the smart glasses of a worker who is passing near the danger area to be photographed.

[0053] FIG. 6 illustrates a method of instructing the shooting position and direction by displaying an environmental map showing a danger area 51c to be shot and an arrow 51b indicating the shooting direction in the worker's viewpoint 50b through the smart glasses of a worker who passes near the danger area to be shot, focusing on the danger area. There are no particular limitations on the method as long as the worker can grasp the danger area to be shot. Also, if the danger area can be shot by simply changing the viewpoint from the worker's current position, a simple voice instruction such as "Please look in the direction of XX" may be used. Also, if instructions to the worker and camera shooting by the worker are possible, a device other than smart glasses may be used. For example, a method of clearly indicating the danger area to be shot and the shooting direction by projection mapping or the like to a worker wearing only a wearable camera may be used.

[0054] FIG. 7 is a functional block diagram showing details of the environment information update unit.

[0055] 7, the environment information updating unit 9 includes a camera information acquiring unit 60, a person position measuring unit 61, a person behavior predicting unit 62, and a danger area updating unit 63.

[0056] The camera information acquisition unit 60 is a functional unit that acquires information about the camera with which the photographer photographed the dangerous area in response to an instruction from the photography instruction unit 8.

[0057] The person position measuring unit 61 is a functional unit that measures the position information of the worker from camera information and captured images.

[0058] The human behavior prediction unit 62 is a functional unit that predicts the behavior of a worker from a captured image.

[0059] The danger area update unit 63 is a functional unit that analyzes the camera information, the worker's position information, and the behavior prediction information to determine whether or not the photographed danger area is dangerous.

[0060] Hereinafter, the processing function of each functional unit of the environment information update unit 9 will be described in detail.

[0061] The camera information acquisition unit 60 acquires information about the camera that captured the dangerous area. The information to be acquired includes the position information of the camera on the environment map 10, external parameter information indicating the orientation and height of the camera at the time of shooting, and internal parameter information indicating the focal length of the camera. The position information of the camera is acquired by utilizing the position information of the worker measured by an infrastructure sensor. The external parameter information at the time of shooting is acquired by a method such as analyzing the captured image and estimating the external parameters of the camera from the vanishing line. The internal parameter information of the camera is acquired in advance from the design value information of the camera used for shooting. Note that the height information of the photographer may be used for the height of the camera. In addition, the position information of the camera and the orientation of the camera at the time of shooting may be acquired by specifying the shooting position and the orientation of the camera at the time of shooting in advance by the shooting instruction unit 8. The method of specifying the camera position includes a method of specifying the position with arrows 51a, 51b on the display of the smart glasses as exemplified in FIG. 5 and FIG. 6, and the method of specifying the orientation of the camera includes a method of displaying the angle of the camera acquired by a gyro sensor or the like on the display of the smart glasses and instructing the photographer to shoot at a predetermined camera angle.

[0062] The person position measuring unit 61 measures the position of the worker from the captured image using the camera information output from the camera information acquiring unit 60. As a measuring method, the distance between the camera and the worker in real space is estimated based on the position of the worker in the captured image and the external and internal parameters of the camera, and the approximate position of the worker on the environment map 10 is measured by combining the estimated distance with the position information of the camera. As a method for acquiring the position of the worker in the captured image, there is a method for obtaining a circumscribing rectangle of the worker in the captured image by utilizing a dictionary capable of detecting an object in an image generated in advance from learning data by machine learning or the like, and calculating the center of the lower end as the position. Note that, in the person position measuring unit 61, if the worker does not exist in the captured image, the position information is not output, and information informing that the worker does not exist is output to the danger area updating unit 63. In addition, other than the above example, any method is not particularly limited as long as it can acquire approximate position information of the worker on the environment map 10 in the captured image.

[0063] The person behavior prediction unit 62 analyzes the captured image and predicts the behavior of the worker whose position information is output from the person position measurement unit 61. Methods for predicting the behavior include a method of estimating the movement path of the worker as the behavior, such as that estimated by the movement path prediction unit 6, and a method of determining the work content of the worker by image processing and estimating the behavior, such as whether the worker will continue working there for a while or move on to the next work, and there are no particular limitations as long as the information on the behavior can be used to determine whether the worker will approach a dangerous area in the future.

[0064] The danger area update unit 63 updates information about the captured danger area based on the camera position information estimated by the camera information acquisition unit 60, the position information of the worker in the captured image obtained by the person position measurement unit 61, and the behavior information of the worker predicted by the person behavior prediction unit 62.

[0065] FIG. 8 is a flowchart showing the process contents of the risk area updating unit.

[0066] 8, the danger region update unit 63 performs a loop process of steps S100 to S110 for the number of workers N in the captured image. However, there are cases where the loop process ends depending on the processing result of step S103.

[0067] In the loop process (steps S100 to S110) of the danger area update unit 63, first, the position information of the worker T seconds after the task difference on the environment map 10 is estimated from the position information of the worker in the captured image and the action prediction information (step S101). Note that the value of the time T is not particularly limited and may be set to a predetermined fixed value, or set to an approximate estimated value of the time when the vehicle is expected to pass near the danger area based on the positional relationship between the current position of the vehicle to be controlled and the danger area.

[0068] Next, the distance between the center position of the danger area on the environment map 10 and the position of the worker T seconds later is calculated (step S102), and it is determined whether the distance value is equal to or greater than a predetermined threshold value (step S103).

[0069] If the determination result in step S103 is YES, that is, if the distance is equal to or greater than the threshold, the dangerous area is determined to be "safe" (step S104), and if there is another worker in the captured image, the processes of steps S101 to S104 are repeated (steps S100 to S110).

[0070] In the loop process of steps S100 to S110, if it is determined that all workers in all captured images are "safe" (step S104), the dangerous area is deleted from the environmental information (step S120), and the process ends.

[0071] Furthermore, in the loop process of steps S100 to S110, if the determination result in step S103 is NO, that is, if the distance is less than the threshold, the danger area is determined to be "dangerous" (step S130), and the process ends.

[0072] The danger area update unit 63 finally judges whether the danger area is "safe" or "dangerous" by the process shown in the flowchart of FIG. 8, and if the judgment result is "safe", the corresponding danger area information in the environment information is deleted, and if the judgment result is "dangerous", the environment information is not updated. In addition, in the case where the captured image includes a plurality of danger areas, the danger area update unit 63 may execute a loop process to perform the process of FIG. 8 for each danger area. In addition, in the present embodiment, the danger area in the environment information is judged by classifying into "safe" or "dangerous", but this is not limited thereto. For example, when the danger area detection unit 4 calculates a danger level that can judge the level of the danger area from people flow information or the like in advance, the danger area update unit 63 may use a method of correcting the danger level of the corresponding danger area. In addition, other than the method exemplified in the present embodiment, any method may be used as long as it can update the danger area using the position information and behavior information of the worker, and the position information of the danger area.

[0073] In the present embodiment configured as described above, in an autonomous body movement control system that controls the movement of an autonomous moving body based on position information of objects and obstacles in a field where vehicles and workers are mixed, by selecting a worker who is moving near a danger area where an object is predicted to jump out, or who has the vicinity of a danger area in his or her field of view, and instructing the system to take a photograph using a wearable camera, it is possible to reduce the number of danger areas and achieve both safety and productivity.

[0074] <Second embodiment> A second embodiment of the present invention will now be described in detail with reference to FIG.

[0075] This embodiment shows a case in which an autonomous body movement control system controls the movement of an autonomous body based on position information of objects and obstacles in a field where vehicles and workers are mixed, takes into account the progress of the work of the worker or autonomous body, selects a worker or small autonomous body that is moving near a danger area where an object is predicted to jump out, or that has the vicinity of a danger area in its field of view, and instructs the system to take a picture using a camera, thereby reducing the number of danger areas and achieving both safety and productivity.

[0076] 9 is a functional block diagram showing the overall configuration of an autonomous body movement control system according to this embodiment. In the figure, the same members as those in the first embodiment are given the same reference numerals, and the description thereof will be omitted.

[0077] In FIG. 9, the autonomous body movement control system is a device that measures the positions of autonomous bodies such as vehicles (hereinafter referred to as autonomous moving bodies) that perform autonomous work and travel within a logistics drive, workers, obstacles, etc., based on information from multiple measurement devices arranged in a field such as a logistics warehouse, and controls the autonomous travel of the vehicle, etc., and has multiple measurement devices 2a, 2b, an autonomous body movement control device 1A that is equipped with an environmental information generation unit 3, a danger area detection unit 4, an autonomous body control unit 5, a movement path prediction unit 6, a work progress information acquisition unit 71, a photographer selection unit 72, a photography instruction unit 8, an environmental information update unit 9, and a memory unit 200, memory devices 201, 202, and a wearable camera 14.

[0078] The environmental information generating unit 3, the dangerous area detecting unit 4, the autonomous body control unit 5, the moving path predicting unit 6, the photographing instruction unit 8, and the environmental information updating unit 9 have the same functions as those in the first embodiment, and therefore the description thereof will be omitted.

[0079] The work progress information acquisition unit 71 is a functional unit that acquires work progress information that indicates the work progress status of workers and autonomous bodies.

[0080] The photographer selection unit 72 is a functional unit that receives the work progress information status stored in the storage device 202, the movement route of the worker, and the position of the dangerous area as input, and selects a photographer to instruct the camera to take pictures of the dangerous area.

[0081] In this embodiment, it is assumed that the field contains a mixture of large autonomous moving objects such as forklifts that are dangerous to come into contact with workers, small autonomous objects such as autonomous mobile robots (AMRs) that are safe even if they come into contact with workers, and workers.

[0082] The processing functions of the work progress information acquisition unit 71 and the photographer selection unit 72 of the autonomous body movement control device 1A will be described in detail below.

[0083] The work progress information acquisition unit 71 acquires work progress information of workers, large autonomous bodies, and small autonomous bodies in the entire work process. In this embodiment, it is assumed that the field is a logistics warehouse, where work progress information showing the current work status of workers and autonomous bodies with respect to the daily transportation volume of materials and the number of sorting tasks is managed by a system, and that the autonomous body movement control device 1A can receive the work progress information.

[0084] The photographer selection unit 72 selects a photographer who will capture images of a specified danger area with a camera, taking into consideration the effect of work efficiency on the entire work process, based on the work progress information obtained from the storage device 202 by the work progress information acquisition unit 71, the worker's movement path output by the movement path prediction unit 6, and the position information of the danger area on the environmental map 10 extracted by the danger area detection unit 4.

[0085] For example, when selecting a worker, a method may be considered in which a worker who is currently moving and whose movement path passes near a danger area is determined to be the most efficient worker and selected as such, or a method may be considered in which a worker who is currently away from the danger area is selected as such if the worker is making the best progress in his or her work.

[0086] Also, by acquiring the work progress status of the worker and the small autonomous body, if the work progress of the worker is delayed compared to the work progress of the small autonomous body, a method such as selecting the small autonomous body as the photographer may be used. Also, if the work progress of the worker or the small autonomous body is delayed compared to the work progress of the large autonomous body, an option of not selecting a photographer may be adopted, and the large autonomous body may be controlled to slow down or controlled to travel a travel route that is a detour but has the fewest dangerous areas around it. There are no particular limitations on the method as long as it does not select a target whose work progress is delayed.

[0087] The other configurations are similar to those of the first embodiment.

[0088] The present embodiment configured as above can also provide the same effects as the first embodiment.

[0089] Furthermore, in this embodiment, in an autonomous body movement control system that controls the movement of an autonomous body based on position information of objects and obstacles in a field where vehicles and workers are mixed, the system takes into consideration the progress of the work of the worker or autonomous body, selects a worker or small autonomous body that is moving near a danger area where an object is predicted to jump out, or that has the vicinity of a danger area in its field of view, and instructs the system to take a photograph using a camera, thereby reducing the number of danger areas and achieving system control that combines safety and productivity.

[0090] As a modified example of this embodiment, for example, a mechanism may be adopted that encourages the worker selected by the photographer selection unit 72 to take pictures by displaying information that allows the worker to understand the need for taking pictures when the photography instruction unit 8 displays instructions on a display such as smart glasses. For example, a method of displaying the work progress status of the worker, large autonomous body, and small autonomous body, or a method of displaying the effect of photography such as a predicted improvement rate of the work progress of a large autonomous body by photographing a dangerous area, or a predicted improvement rate of the work progress of the entire process, may be considered.

[0091] Also, a mechanism may be adopted in which a worker can respond to a photographing instruction from the photographing instruction unit 8. For example, a method is conceivable in which the photographer selection unit 72 selects multiple workers, the photographing instruction unit 8 clearly indicates the photographing instruction content and whether photographing is possible or not, and one worker who responds that photographing is possible is selected to perform photographing, or in the case where all workers respond that photographing is not possible, a small autonomous body with the best work progress is selected as the photographer.

[0092] <Additional Notes> The present invention is not limited to the above-described embodiments, and includes various modifications and combinations within the scope of the gist of the present invention. The present invention is not limited to those having all the configurations described in the above-described embodiments, and includes those in which some of the configurations are deleted. The above-described configurations, functions, etc. may be realized by designing some or all of them as an integrated circuit, for example. The above-described configurations, functions, etc. may be realized by software, in which a processor interprets and executes a program that realizes each function. [Explanation of symbols]

[0093] 1, 1A... Autonomous body movement control device, 2a, 2b... Measurement device, 3... Environmental information generation unit, 4... Danger area detection unit, 5... Autonomous body control unit, 6... Movement path prediction unit, 7... Worker selection unit, 8... Shooting instruction unit, 9... Environmental information update unit, 10... Environmental map, 11... Vehicle, 12... Worker, 13a, 13b, 13c, 13d, 13e... Obstacle, 14... Wearable camera, 30... Vehicle driving path generation unit, 31... Blind spot area extraction unit, 32 ...people flow information acquisition unit, 33...danger area determination unit, 40...travel route candidates, 41...travel direction, 42a, 42b, 42c...blind spot area, 50a, 50b...worker's viewpoint, 51a, 51b...arrow, 51c...danger area, 60...camera information acquisition unit, 61...person position measurement unit, 62...person behavior prediction unit, 63...danger area update unit, 71...work progress information acquisition unit, 72...photographer selection unit, 200...storage unit, 201, 202...storage devices

Claims

1. An autonomous body movement control system that controls the movement of an autonomous body in a field where people and autonomous bodies are mixed, a plurality of measuring devices that measure positions of people in the field and position information of the autonomous moving object; generating environmental information that is information about an environment in the field based on a measurement result from the measurement device; Analyzing the environmental information to detect an area in the field where there is a high possibility of contact between the person and the autonomous moving body as a dangerous area; performing movement control of the autonomous moving body based on the detected danger area; predicting a movement path of the person based on position information of the person within the field; selecting a person who is likely to visually observe the danger area based on the predicted movement path of the person; instructing the selected person to photograph the danger area using a camera carried by the selected person; an autonomous body movement control device that updates the environmental information based on an image captured by the camera; An autonomous object movement control system comprising:

2. 2. The autonomous body movement control system according to claim 1, An autonomous body movement control system, characterized in that the environmental information is the positions of the person, the autonomous body, and obstacles within the field.

3. 2. The autonomous body movement control system according to claim 1, The autonomous body movement control system is characterized in that the autonomous body movement control device detects the danger area using at least one of the following information, which is the result of analyzing the environmental information: route information on which the autonomous body can travel, obstacle position information, obstacle height information, dynamic information of the person, and area information specified by a user from outside.

4. 2. The autonomous body movement control system according to claim 1, An autonomous body movement control system, characterized in that an autonomous body movement control device controls the path and speed of the autonomous body.

5. 2. The autonomous body movement control system according to claim 1, An autonomous body movement control system characterized in that the autonomous body movement control device predicts the movement path of the person based on the position information of the person acquired by the measurement device and a work plan.

6. 2. The autonomous body movement control system according to claim 1, The autonomous body movement control system is characterized in that the autonomous body movement control device selects, as a person who may visually observe the danger area, a person who falls into one of the following categories: a person who may be moving near the danger area, a person who is near the danger area, and a person who can visually observe the danger area by changing the viewpoint.

7. 2. The autonomous body movement control system according to claim 1, The autonomous body movement control system is characterized in that the autonomous body movement control device selects a small robot equipped with a camera function and capable of taking photographs near the danger area as a person who may visually observe the danger area.

8. 2. The autonomous body movement control system according to claim 1, The autonomous body movement control system is characterized in that the autonomous body movement control device changes a method for selecting people who are likely to visually observe the danger area based on work progress information that indicates the work progress status of the person and the autonomous moving body.

9. 2. The autonomous body movement control system according to claim 1, The autonomous body movement control system is characterized in that the autonomous body movement control device uses a display on a smart glass display or a display by projection mapping using a projector as a method of instructing the person to photograph the dangerous area with a camera they carry.

10. 10. The autonomous body movement control system according to claim 9, The autonomous body movement control system is characterized in that the autonomous body movement control device displays at least one of the following information on the display of the smart glasses: shooting position, shooting direction, camera angle, the environmental information, the position of the dangerous area, work progress information, and a predicted improvement rate of work progress due to shooting.

11. 2. The autonomous body movement control system according to claim 1, The autonomous body movement control system is characterized in that the autonomous body movement control device analyzes the measurement results of the measuring device to obtain information on at least one of the person's position and behavior shown in the measurement results, and determines whether the danger area is dangerous by comparing that information with the danger area.

12. 2. The autonomous body movement control system according to claim 1, The autonomous body movement control system is characterized in that the autonomous body movement control device updates at least one of the environmental information, including a position of a person, a position of an obstacle, and a dangerous area.

13. generating environmental information that is information about an environment in a field in which people and autonomous moving objects coexist, based on a position of a person in the field and position information of the autonomous moving object; Analyzing the environmental information to detect an area in the field where there is a high possibility of contact between the person and the autonomous moving body as a dangerous area; performing movement control of the autonomous moving body based on the detected danger area; predicting a movement path of the person based on position information of the person within the field; selecting a person who is likely to visually observe the danger area based on the predicted movement path of the person; instructing the selected person to photograph the danger area using a camera carried by the selected person; The environmental information is updated based on an image captured by the camera. An autonomous object movement control device comprising:

14. A step of measuring position information of a person and position information of the autonomous moving object in a field where people and the autonomous moving object are mixed; A step of generating environmental information that is information about an environment in the field based on measurement results of position information of the person and the autonomous moving body; A step of analyzing the environmental information to detect an area in the field where there is a high possibility of contact between the person and the autonomous moving body as a dangerous area; A step of controlling the movement of the autonomous moving body based on the detected danger area; predicting a movement path of the person based on position information of the person within the field; selecting a person who is likely to visually observe the danger area based on the predicted movement path of the person; a step of instructing the selected person to photograph the danger area using a camera carried by the selected person; updating the environmental information based on an image captured by the camera; An autonomous body movement control method comprising the steps of:

Images