JP2023087293A - vehicle controller - Google Patents

Abstract

To autonomously determine operation according to a situation of a worker so as to ensure the safety of the worker and prevent work efficiency from deteriorating when the worker enters a travel route of a traveling vehicle.SOLUTION: A vehicle controller 20 for controlling an autonomously traveling vehicle 1, includes: a person detection unit 44 for detecting a person 52 on a route of the vehicle 1; an evacuation time prediction unit 45 for predicting an evacuation time required for the person 52 to evacuate from the route; an operation plan generation unit 40 for generating an operation plan including determination of the route to a destination of the vehicle 1; and a vehicle control unit 41 for controlling the vehicle according to the generated operation plan. The operation plan generation unit 40 generates a detour route for traveling to the destination by detouring the route, calculates a time required to reach the destination when traveling along the detour route, and determines whether to wait until the person 52 leaves the route or change the route to the detour route based on a calculated result and the predicted evacuation time predicted by the evacuation time prediction unit 45.SELECTED DRAWING: Figure 3

Description

TECHNICAL FIELD The present invention relates to a vehicle control device that controls the operation of autonomously traveling vehicles such as an automatic guided vehicle, an autonomous forklift, and an automatic traveling conveyance robot.

Patent document 1 is known as a background art of this technical field. In Patent Document 1, the problem is "to consider the safety of the worker and the surrounding situation in the automatic driving work, and to judge the autonomous operation without reducing the efficiency of the work", and as a solution, " An autonomous traveling work device capable of automatically traveling and automatically cleaning based on a cleaning plan stored in advance receives one or more surrounding information during execution of automatic traveling cleaning by means of a surrounding information input unit. input, and the alternative action generation unit generates and executes an alternative action that replaces running and/or cleaning based on the cleaning plan according to the input timing and/or input pattern consisting of combinations of one or more surrounding information." is described.

JP 2020-181434 A

In the method described in Patent Document 1, a traveling vehicle that operates autonomously in a work area where workers and the like coexist acquires surrounding information such as human gestures, utterances, and work instruction signboards, and responds to the surrounding information. to autonomously generate and execute alternative actions. When a worker on the vehicle's travel route gives an instruction such as "wait a minute" or "take a detour" by voice or gesture, the robot responds to the given instruction according to a pre-stored or learned movement pattern. generate and execute actions.

When a plurality of traveling vehicles are operated within the same work area, the traveling routes of the vehicles may overlap and interfere with each other. A worker who does not know the positions and travel routes of multiple traveling vehicles gives a detour instruction to a vehicle, and when the vehicle in question follows the instruction, it interferes with the travel routes of other vehicles at the detour destination, A long stoppage is required, and there is a possibility that work efficiency will decrease. In addition, when the worker gives the instruction of ``wait a minute'' to the vehicle and the vehicle waits until the worker gives permission to resume traveling, the required time required for completion of the work by the vehicle increases by the waiting time. At this time, if it is possible to use a detour route with a small decrease in efficiency, there is a possibility that the work can be completed in a shorter time by detouring without following the worker's instructions.

From the above, it can be said that instructions such as a detour/standby from the worker to the vehicle can be a factor of reducing work efficiency by the vehicle. In order to prevent such a decrease in efficiency, it is necessary for workers to fully understand the structure of the work area, the positions of multiple vehicles, the travel routes, etc., and give appropriate instructions to the vehicles. becomes.

In view of the above problems, the present invention is a traveling vehicle that performs work autonomously in an environment where workers coexist. The purpose is to make it possible to autonomously determine the operation according to the worker's situation so that the worker's performance does not decrease.

The problem is a vehicle control device that controls a vehicle that autonomously travels on a route, and includes a person detection unit that detects a person on the route of the vehicle and an evacuation time that predicts the evacuation time required for the person to evacuate from the route. A prediction unit, an operation plan generation unit that generates an operation plan including determination of a route to a destination of the vehicle, and a vehicle control unit that controls the vehicle according to the generated operation plan, the operation plan generation unit comprising: Generating a detour route for moving to the destination by detouring the route, calculating the time required to reach the destination when the detour route is traveled, and comparing the result of the calculation with the predicted evacuation time predicted by the evacuation time prediction unit. and , it is possible to solve the problem by determining whether to wait until the person evacuates from the route or to change the route to a detour route.

According to the present invention, in a traveling vehicle that autonomously works in an environment where workers coexist, the time required for a person present on the route of the traveling vehicle to evacuate is acquired, and the time required for the person to evacuate is autonomously waiting/detouring/running. By judging the resumption, it is possible to prevent the decrease in efficiency that occurs when avoiding the worker.
Further features related to the present invention will become apparent from the description of the specification and the accompanying drawings. Further, problems, configurations and effects other than those described above will be clarified by the following description of the embodiments.

1 is a diagram showing a configuration example of an autonomous vehicle in Embodiments 1 and 2 of the present invention; FIG. FIG. 2 is a diagram showing a configuration example of a control system of an autonomous vehicle in Embodiments 1 and 2 of the present invention; FIG. 2 is a block diagram showing processing of a vehicle control device in Embodiment 1 of the present invention; FIG. 2 is a diagram showing a travel route of an autonomous vehicle in Embodiment 1 of the present invention; The figure which shows the process flow which a vehicle control apparatus in Example 1 of this invention performs after a person detection part detects a person on a course. The block diagram which shows the process of a vehicle control apparatus in Example 2 of this invention. The figure which shows the driving route of the autonomous vehicle in Example 2 of this invention. The figure which shows the process flow which a vehicle control apparatus performs in Example 2 of this invention, after a person detection part detects a person on a course. The block diagram which shows the process of a vehicle control apparatus in Example 3 of this invention. The figure which shows the driving|running route of the autonomous vehicle in Example 3 of this invention. The figure which shows the process flow which a vehicle control apparatus performs in Example 3 of this invention after a person detection part detects a person on a course.

[Example 1]
BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments according to the present invention will be described with reference to the drawings. The following examples are specific examples suitable for the present invention, and the technical scope to which the present invention can be applied is not limited to these modes. For example, although the following embodiments describe embodiments of the present invention by taking a forklift capable of autonomous travel as an example, in addition to transportation equipment such as AGVs (Automated Guided Vehicles) and AMRs (Autonomous Mobile Robots), people can It can be applied to all devices that run autonomously in coexisting environments.

FIG. 1 shows a configuration example of an autonomous vehicle 1 (hereinafter also referred to as vehicle 1) according to an embodiment of the present invention. An autonomous vehicle 1 includes a traveling mechanism such as tires 2, and a work mechanism including a fork 3, a mast 4, and the like for performing predetermined work. Workers and obstacles existing around the vehicle 1 are detected by a front sensor 5 and a rear sensor 6 installed on the vehicle 1 . By installing the panel 7, the indicator lamp 8, and the speaker 9, it is possible to notify the surroundings of the vehicle 1 status (running, cargo handling operation, etc.) and scheduled operation (running start, retreat, turning, etc.). do. Also, by installing a microphone 10 and a camera 11, it is possible to observe the voices and behaviors of workers around the vehicle 1 and the state around the vehicle 1. FIG. Further, by operating the touch panel 12, it is possible to directly input instructions to the vehicle 1. FIG.

FIG. 2 shows a configuration example of the control system of the autonomous vehicle 1. As shown in FIG. The vehicle control device 20 includes a CPU 21, a memory 22, an input/output processing unit 23, a communication unit 24, and the like, and generates commands for running the autonomous vehicle 1 and performing work. A travel mechanism PLC (Programmable Logic Controller) 26 that controls the tires 2 and brakes 25 and a work mechanism PLC 27 that controls the fork 3 and mast 4 execute control based on commands from the vehicle control device 20 . Data obtained from the surrounding detection means 28 (the front sensor 5 and the rear sensor 6) and the information input means 29 (the microphone 10, the camera 11, and the touch panel 12) are transmitted to the vehicle control device 20. FIG. Data output from the information output means 30 (panel 7, indicator lamp 8, speaker 9) is transmitted from the vehicle control device 20. FIG. The vehicle control device 20 communicates with the control server 32 via the communication module 31 and receives work instructions. The position and travel route of other vehicles 33 other than the own vehicle 1, the work execution status, and the worker's position information and status obtained from the infrastructure sensor 34 installed in the work area and the beacon 35 possessed by the worker are also controlled. It is available from server 32 .

FIG. 3 shows an overview of the processing performed by the vehicle control device according to the first embodiment of the present invention, and FIG. 4 shows the travel route of the autonomous vehicle 1. As shown in FIG. The motion plan generation unit 40 determines the travel route of the vehicle 1 and generates a motion plan according to work instructions given from the control server 32 . For example, as shown in FIG. 4 , when the work instruction from the control server 32 is to pick up a package at a destination 50 , the operation plan generator 40 generates a travel route 51 to the destination 50 . The vehicle control unit 41 controls the travel mechanism 42 and the working mechanism 43 according to the motion plan generated by the motion plan generation unit 40 .

The person detection unit 44 uses observation data obtained from the surroundings detection means 28 to detect a person (worker working within the work area) 52 present on the route of the vehicle 1 . Vehicle control unit 41 receives detection of person 52 and stops the vehicle to prevent a collision. The evacuation time prediction unit 45 predicts the evacuation time required for the person 52 to evacuate from the route of the vehicle. The action plan generation unit 40 uses the evacuation time predicted by the evacuation time prediction unit 45 to estimate the time required to reach the destination 50 when the person 52 waits until the person 52 evacuates and continues traveling along the current travel route 51. , and the time required to reach the destination 50 in the case of changing the travel route to the detour route 53 and traveling, and it is determined whether to wait or detour so as to shorten the required time.

Vehicle control unit 41 controls the vehicle according to the operation plan modified by operation plan generation unit 40 . By predicting the time required for the person 52 on the route to evacuate, that is, the time the vehicle 1 must stop and wait, and detouring if the waiting time is expected to be long, the vehicle 1 to reduce downtime and improve work efficiency. Here, when the person 52 retreats immediately after the vehicle 1 approaches, or when the person 52 retreats before the predicted evacuation time elapses, the vehicle 1 may immediately resume running. This makes it possible to reduce unnecessary waiting time.

To predict the evacuation time in the evacuation time prediction unit 45, information such as the position, walking speed, and work details of the person 52, and the position, size, weight, characteristics, number, state, etc. of objects existing around the person 52 are used. use the information of Examples of information about a person include when a person is near a shelf where packages are stored (position), when a person is standing still (walking speed), when a person is carrying packages or pushing a trolley (work content). For example, it can be predicted that the person is working and it will take a certain amount of time to evacuate.

On the other hand, if the person is in a wide passage with no objects around (position) or if the person is walking (walking speed), the person is moving or not doing any particular work and can be evacuated immediately. It can be predicted that In addition, examples of information about objects around a person include a package far away from the person (position), a large package near the person (size), a heavy object around the person (weight), and a person's surroundings. When there are packages that need to be handled with care, such as chemicals and hazardous materials, in the area (characteristics), when a large number of packages are scattered around the person (number), and when there are unpacked packages around the person (state) In such cases, it can be expected that it will take time to withdraw the baggage and that it will not be possible to evacuate immediately. Conversely, if these luggage do not exist, it can be expected that the person can evacuate in a short period of time. Information about these objects around the person can be stored in association with the work that the person is doing.

The evacuation request presentation unit 46 receives the detection of the person 52 by the person detection unit 44, and uses the information output means 30 to present information (evacuation request) 54 for requesting the person 52 to evacuate from the route. . When the speaker 9 is used, a voice such as "please evacuate" is output. Presenting a request by voice is effective for a person who does not visually recognize the vehicle. When using the panel 7, a message such as "please save" is displayed on the screen. When the indicator lamp 8 is used, the pattern corresponding to the evacuation request is displayed among the previously known display patterns of the indicator lamp. Evacuation requests using message displays and indicator lights are effective for noisy places and people wearing earplugs.

It is also possible to use a projector to display a message such as "please evacuate" on the road surface, etc., or to use an arrow or the like to indicate a recommended evacuation destination for a person. Further, if the worker has a beacon 35 for measuring the position information of the worker, the beacon 35 may be equipped with a voice output function, a screen display function, or the like to notify the request. The request notification by the beacon 35 is effective for making a request to a person who is far away and for whom it is difficult to make a request by voice or display from the vehicle. By actively requesting the person 52 on the route of the vehicle 1 to evacuate using the above means, the person 52 is prevented from noticing the approach of the vehicle and delaying evacuation, and the work efficiency of the vehicle 1 is improved. .

The notification unit 47 uses the information output means 30 to notify the person 52 on the route of the determination result of waiting/detour/running restart by the operation plan generating unit 40 . As with the request presentation by the evacuation request presenting unit 46 described above, the notification method can be voice using the speaker 9, display using the panel 7, indicator lamp 8, projector, or notification using the beacon 35. FIG. When the vehicle 1 waits until the person 52 evacuates, a message such as "I will wait until the person 52 evacuates" or a corresponding display pattern is output. When detouring, a message such as "detour" or a corresponding display pattern is output. When resuming running, a message such as "Running will start" or a corresponding display pattern is output. By notifying the person 52 on the course of the future motion of the vehicle 1 in advance, the person 52 can avoid the danger of collision or the like that occurs because the person 52 cannot predict the motion of the vehicle 1.例文帳に追加

If the person 52 does not evacuate after the evacuation time predicted by the evacuation time prediction unit 45 has passed after the operation plan generation unit 40 determines the standby, the evacuation request presentation unit 46 executes the evacuation request 54 again. If the evacuation is delayed because the person 52 does not notice the presentation of the evacuation request 54 or the notice 55 of waiting, this directly leads to a decrease in the work efficiency of the vehicle 1 . Therefore, when the evacuation by the person 52 is slow, the request is presented again to prompt the evacuation, thereby preventing the work efficiency from being lowered.

FIG. 5 is a diagram showing a processing flow executed by the vehicle control device 20 after the person detection unit 44 detects the person 52 on the route. At step 60, the vehicle control unit 41 controls the traveling mechanism 42 to stop the vehicle 1 from traveling. At step 61 , the evacuation request presentation unit 46 outputs the evacuation request 54 .

At step 62, the evacuation time prediction unit 45 predicts the time required for the person 52 to evacuate. A prediction model 63 created and recorded in advance by simulation, machine learning, etc. is used to predict the evacuation time of the person 52 by inputting information 64 such as information such as the position and movement of the person 52 and objects existing around the person 52. .

At step 65, the operation plan generator 40 uses the estimated evacuation time of the person 52 to calculate the time required to reach the destination 50 when the vehicle waits until the person 52 evacuates and then resumes running.

At step 66, the route with the shortest required time to the destination 50 is generated among detour routes avoiding the place where the person 52 is present, and the required time is calculated. At this time, map information of the work area, positions of other vehicles 33, travel routes, work execution statuses, etc. 67 are acquired from the control server 32, and detour routes 53 that do not interfere with the other vehicles 33 are generated. As shown in FIG. 4, since the other vehicle 33 is scheduled to travel on the detour routes 53(a) and 53(b) at the same time when the own vehicle 1 travels, the detour route 53(c) is generated on which the other vehicle 33 does not travel. . By comparing the required time to the destination 50 using the detour route 53 ( c ) that does not interfere with the running of the other vehicle 33 when judging whether to detour or wait in the steps described later, It becomes possible to make a judgment after considering the efficiency drop that occurs.

In step 68, the required time for waiting for the person 52 to evacuate is compared with the required time for running the detour route 53(c). If it is determined in step 69 that the required time will be shorter if the detour is taken, then in step 70 the operation plan is corrected so that the vehicle travels along the detour route 53(c), and a detour notification is output to the person 52. do.

At step 72, the vehicle control unit 41 resumes running using the detour route. If the required time is shorter when waiting, in step 73, the system waits until the person 52 evacuates and outputs a standby notification 74 to the person 52.例文帳に追加If it is determined in step 75 that the person 52 has evacuated, the vehicle resumes running. If it is determined in step 76 that the evacuation time predicted in step 62 has elapsed without the person 52 evacuating, the evacuation request presenting unit 46 outputs the evacuation request 54 again in step 77 .

According to the first embodiment described above, by predicting the time required for a person on the route to evacuate and determining whether to detour/standby and resume running so that the time required to reach the destination is shortened, the waiting time until the person evacuates By avoiding or shortening the waiting time, it reduces the decrease in work efficiency caused by people entering the vehicle's travel route. At this time, the positions and travel routes of other vehicles are also taken into consideration to prevent a decrease in efficiency caused by interference with other vehicles at detour destinations. Furthermore, by using voice and display to actively urge people on the route to evacuate, it is possible to prevent delays in people's evacuation actions. In addition, by notifying the person of the motion of the vehicle when the vehicle resumes running, it becomes possible to predict the motion of the vehicle by the person and prevent accidents such as contact.

[Example 2]
FIG. 6 shows an overview of the processing performed by the vehicle control device 20 according to the second embodiment of the present invention, and FIG. 7 shows the travel route of the autonomous vehicle 1. The processes of the person detection unit 44, the vehicle control unit 41, and the notification unit 47 are the same as those of the first embodiment, and the description thereof will be omitted.

A difference of this embodiment from the first embodiment is that it further includes a save time requesting unit 80 and a save time acquiring unit 81 .

The evacuation time requesting unit 80 uses the information output means 30 to output an information provision request 82 regarding the time required for the evacuation of the person 52 to the person 52 detected by the person detection unit 44 . The request method uses the speaker 9, the panel 7, the beacon 35, etc., in the same way as the evacuation request presenting unit 46 and the notification unit 47 described above, to send a message such as "Please tell me the time required for evacuation" or a corresponding display. Output a pattern.

The evacuation time acquisition unit 81 acquires from the person 52 the reply information 83 regarding the evacuation time that the person 52 has input to the information input means 29 in response to the provision request 82 . The response information regarding the evacuation time acquired from the person 52 does not necessarily have to be a numerical value such as "○ seconds" or "○ minutes", but a large granularity such as "1 to 2 minutes", or "large" or "medium". ', 'Small', or other information or instructions such as 'Retreat immediately' or 'Detour because it is not possible to evacuate'.

When the microphone 10 is used as the information input means 29, a person's utterance such as "It will take 1 to 2 minutes", "Retreat time: medium", etc. is acquired as voice, and the presented retraction time information and instructions are identified. When using the touch panel 12, options are displayed on the screen and the person presses them, or the person inputs numerical values. When the camera 11 is used, a gesture or the like by the person 52 is acquired, and the evacuation time information or instruction associated in advance is identified. When the beacon 35 is used, a button may be installed on the beacon 35 and pressed by a person.

The operation plan generation unit 40 determines standby/detour/restart of traveling so that the time required to reach the destination 50 is shortened according to the information and instructions regarding the evacuation time acquired by the evacuation time acquisition unit 81 . If the accuracy of the evacuation time prediction unit 45 in the first embodiment is poor, the evacuation time of the person 52 on the route cannot be predicted appropriately, and the work efficiency decreases. By acquiring information about time, it becomes possible to improve the efficiency of decisions to wait/detour/restart traveling with a higher degree of certainty.

When the evacuation time acquisition unit 81 does not receive the response information 83 regarding the evacuation time from the person 52 for a certain period of time, the evacuation time request unit 80 executes the provision request 82 again. Similarly to the evacuation request 54 by the evacuation request presenting unit 46 , if the provision of the response information 83 is delayed due to the person 52 not noticing it, the working efficiency of the vehicle 1 is directly affected. When the provision of the response information 83 by the person 52 is delayed, the provision request 82 is executed again to prompt the response information 83 regarding the evacuation time, thereby preventing a decrease in work efficiency.

FIG. 8 shows a processing flow executed by the vehicle control device 20 after the person detection unit 44 has detected the person 52 . Steps 60, 65, 66, 68, 69, 70, 72, 73, 75, 76, and 77 are the same as in the first embodiment. Further, in this embodiment, at step 84, the evacuation time request unit 80 outputs to the person 52 a request 82 for providing information on the time required for evacuation.

At step 86, the evacuation time acquisition unit 81 acquires reply information 83 regarding the evacuation time from the person 52 as a reply to step 84 ("Yes" at step 85). If the response information 83 regarding the evacuation time is not obtained for a certain period of time ("No" in step 85), the process returns to step 84 to request the information regarding the evacuation time again.

In the second embodiment described above, information on the time required for evacuation is directly obtained from a person on the route, thereby avoiding the evacuation time prediction required in the first embodiment and more reliably reducing the reduction in efficiency. In addition, by accumulating the evacuation time obtained by using this embodiment and information on people, etc., and performing machine learning, etc., it is possible to improve the accuracy of the prediction model used in the first embodiment.

[Example 3]
FIG. 9 shows an overview of the processing performed by the vehicle control device 20 according to the third embodiment of the present invention, and FIG. 10 shows the travel route of the autonomous vehicle 1. In FIG. Also in this embodiment, the processes performed by the person detection unit 44, the evacuation request presentation unit 46, the vehicle control unit 41, and the notification unit 47 are the same as those in the first and second embodiments, and the description thereof will be omitted.

This embodiment differs from Embodiments 1 and 2 in that the evacuation time requesting unit 80 requests the control server 32, not the person 52, to provide information regarding the evacuation time. .

In this embodiment, the evacuation time request unit 80 requests the external device such as the control server 32 to provide information on the time required for the person 52 to evacuate with respect to the person 52 on the route detected by the person detection unit 44. do. The control server 32 predicts the time required for the person 52 to evacuate, similar to the evacuation time prediction unit 45, from the information on the position and motion of the person 52 and the objects around the person obtained from the infrastructure sensor 34 and the beacon 35.

The evacuation time acquisition unit 81 acquires information about the evacuation time of the person 52 from the control server 32 as reply information to the evacuation time request unit 80 . If the prediction of the evacuation time of the person 52 requires a large amount of calculation, there is a possibility that resources will be insufficient for prediction on the vehicle control device 20 mounted on the vehicle 1, so prediction is performed by an external device such as the control server 32. By providing the result to the vehicle control device 20, it is possible to perform prediction without increasing the amount of calculation that the vehicle control device 20 can use.

The operation plan generation unit 40 determines standby/detour/restart of travel so as to shorten the time required to reach the destination 50 according to the information about the evacuation time acquired by the evacuation time acquisition unit 81 . This point is the same as the second embodiment.

Here, consider a case where the efficiency of both the detour and standby is greatly reduced when the action plan generated by the action plan generating unit 40 is executed. As an example, if the predicted evacuation time of the person 52 is extremely long, only the detour route 53(c) can be selected because other vehicles 33 exist in many of the selectable detour routes 53 and the efficiency is greatly reduced. and the like. In order to prevent the completion of the work in progress from being delayed due to such a large decrease in efficiency, the work is transferred to another vehicle 86 that can perform the work in place of the own vehicle 1 . Work transfer can be performed via the control server 32 . As a result, it is possible to effectively utilize a plurality of vehicles and prevent a large decrease in work efficiency.

FIG. 11 shows a processing flow executed by the vehicle control device 20 after the person detection unit 44 has detected the person 52 . Steps 60, 65, 66, 68, 69, 70, 72, 73, 74, 75, 76, and 77 are the same as in Example 1 and Example 2.

Further in this embodiment, at step 90, the evacuation time requesting unit 80 outputs to the control server 32 a request 91 for information regarding the time required for the person 52 to evacuate. At step 92 , the evacuation time acquisition unit 81 acquires information 93 on evacuation time from the control server 32 as a reply to step 92 .

If the time required to reach the destination 50 calculated in steps 65 and 66 both detour and wait exceeds a certain period of time ("No" in step 94), the action plan generator 40 can execute the work on behalf of the own vehicle 1. It is determined whether or not another vehicle 86 exists. Then, in step 97, the motion plan generation unit 40 generates a motion plan for withdrawal from the site or execution of the next scheduled work, and in step 72, the vehicle resumes running.

In the third embodiment described above, it is possible to predict the evacuation time by an external device such as a server instead of on the vehicle, thereby reducing the processing load of the vehicle control device and improving the prediction accuracy. Furthermore, if the execution of the action plan generated by the action plan generating unit 40 causes a very large decrease in efficiency, another vehicle to which execution can be transferred is searched, and the action can be transferred. , it becomes possible to suppress the decrease in efficiency of the system as a whole.

According to the embodiments of the present invention described above, the following effects are obtained.
(1) A vehicle control apparatus according to an embodiment of the present invention includes a person detection unit that detects a person on the route of the vehicle, and an evacuation time prediction unit that predicts the evacuation time required for the person to evacuate from the route. a vehicle control unit for controlling the vehicle according to the generated operation plan, the operation plan generating unit for detouring the route to generate a detour route to move to the destination, and calculate the time required to reach the destination when traveling on the detour route, and the calculation result and the predicted evacuation time predicted by the evacuation time prediction unit, Based on this, it is determined whether to wait until the person leaves the route or change the route to a detour route.

With the above configuration, in a traveling vehicle that autonomously works in an environment where workers coexist, it acquires the time required for a person on the route of the traveling vehicle to evacuate, and autonomously waits, detours, and resumes travel. By judging, it is possible to prevent a decrease in efficiency that occurs when avoiding the worker.

(2) If the person leaves the route earlier than the predicted withdrawal time, the action plan generator determines to change the action plan and continue traveling on the route. As a result, even if the estimated time is not calculated accurately, such as when the accuracy of the prediction model used by the evacuation time prediction unit is low, or when the work by people finishes earlier than expected, it can be handled quickly and accurately. becomes possible.

(3) The evacuation time prediction unit calculates the predicted evacuation time based on information about the person including any of the person's position, walking speed, and work content. By storing this information in advance, various values can be used as parameters, improving the prediction accuracy.

(4) It further includes an evacuation request presenting unit that presents an evacuation request to the person. As a result, when the person remains on the route even after the predicted evacuation time has passed, the person is made to recognize that the predicted elapsed time has passed and the presence of the vehicle, and the It is possible to encourage evacuation.

(5) The operation plan generator includes any of map information of work areas in which vehicles can travel and/or positions of other vehicles traveling in the work area, planned travel routes, work execution statuses, and work execution schedules. It is characterized by using information about other vehicles to determine whether to wait until the person leaves the route or change the route to a detour route. Accordingly, similar to (3), by pre-storing these pieces of information, various values can be used as parameters, improving prediction accuracy.

(6) The apparatus further includes a notification unit that notifies the person of the action plan generated by the action plan generation unit. As a result, it becomes possible for the person working on the vehicle to understand how the vehicle will behave in the future. If there is, it is possible to provide various options such as omitting part of the work and quickly completing the work.

(7) A vehicle control device according to another embodiment of the present invention is communicably connected to a person detection unit for detecting a person on the route of the vehicle, and to the person or the vehicle control device, and detects the person from the route. An evacuation time request unit that requests information about the evacuation time required for the person to evacuate from the route from an external device that can predict the evacuation time required for the person to evacuate, and an evacuation time request unit that receives information from the person or the external device an evacuation time acquisition unit that acquires response information including information about the evacuation time; an operation plan generation unit that generates an operation plan including determination of the route to the destination of the vehicle; and controls the vehicle according to the generated operation plan. and a vehicle control unit, wherein the operation plan generation unit generates a detour route for traveling to the destination by detouring the route, and calculates the time required to reach the destination when traveling along the detour route, Based on the result of the calculation and the reply information, it is determined whether to wait until the person leaves the route or change the route to a detour route.

With the above configuration, by directly obtaining information on the time required for evacuation from a person on the route, it is possible to avoid the prediction of the evacuation time required in the first embodiment, and more reliably reduce the decrease in efficiency. In addition, by accumulating the evacuation time obtained by using this embodiment and information on people, etc., and performing machine learning, etc., it is possible to improve the accuracy of the prediction model used in the first embodiment.

(8) If the evacuation of the person or the provision of information regarding the evacuation time by the person is not performed within a predetermined time, the evacuation time request unit presents the request again. As a result, it is possible to prevent wasteful time from passing as it is when, for example, the person is not aware of the first presentation.

(9) When the evacuation time acquired by the evacuation time requesting unit from the person or the external device and the time required to reach the destination when moving through the detour route exceed a predetermined threshold, the operation plan generating unit It is determined whether there is another vehicle to which the work being executed by the vehicle can be transferred in the work area in which the vehicle is traveling. As a result, when the execution of the generated operation plan causes a very large decrease in efficiency, the system as a whole can be made more efficient by searching for other vehicles to which the execution can be transferred and transferring the operation. It becomes possible to suppress the decrease.

It should be noted that the present invention is not limited to the above embodiments, and various modifications are possible. For example, the above embodiments have been described in detail in order to facilitate understanding of the present invention, and the present invention is not necessarily limited to aspects having all the described configurations. Also, part of the configuration of one embodiment can be replaced with the configuration of another embodiment. It is also possible to add the configuration of another embodiment to the configuration of one embodiment. Moreover, it is possible to delete a part of the configuration of each embodiment, or to add or replace another configuration.

1: Autonomous Vehicle, 20: Vehicle Control Device, 28: Periphery Detection Means, 29: Information Input Means, 30: Information Output Means, 31: Communication Module, 32: Control Server, 33: Other Vehicles, 40: Operation Plan Generation 41: vehicle control unit 44: person detection unit 45: evacuation time prediction unit 46: evacuation request presentation unit 47: notification unit 50: destination 51: travel route 52: person on the route 53: Detour route 54: Evacuation request 55: Notification 80: Evacuation time request unit 81: Evacuation time acquisition unit 83: Reply information 93: Evacuation time information 86: Other vehicles to which work can be transferred

Claims (9)

A vehicle control device for controlling a vehicle that autonomously travels on a route,
a person detection unit that detects a person on the route of the vehicle;
an evacuation time prediction unit that predicts an evacuation time required for the person to evacuate from the course;
a motion plan generating unit for generating a motion plan including determination of a route to a destination of the vehicle;
a vehicle control unit that controls the vehicle according to the generated operation plan;
The operation plan generation unit generates a detour route that detours the course and moves to the destination, calculates the required time to the destination when traveling along the detour route, and calculates the result of the calculation; Determining whether to wait until the person evacuates from the route or change the route to the detour route based on the predicted evacuation time predicted by the evacuation time prediction unit;
A vehicle control device characterized by: The vehicle control device according to claim 1,
The action plan generation unit decides to change the action plan and continue traveling on the route when the person has withdrawn from the route earlier than the predicted withdrawal time.
A vehicle control device characterized by: The vehicle control device according to claim 1,
The evacuation time prediction unit calculates the predicted evacuation time based on information about the person including one of the person's position, walking speed, and work content.
A vehicle control device characterized by: 2. The vehicle control device according to claim 1, further comprising an evacuation request presenting unit that presents an evacuation request to the person.
A vehicle control device characterized by: The vehicle control device according to claim 1,
The operation plan generation unit includes map information of a work area in which the vehicle can travel and/or positions of other vehicles traveling in the work area, a planned travel route, a work execution status, or a work execution schedule. Using information about other vehicles, it is determined whether to wait until the person evacuates from the route or change the route to the detour route,
A vehicle control device characterized by: The vehicle control device according to claim 1,
Further comprising a notification unit that notifies the person of the action plan generated by the action plan generation unit,
A vehicle control device characterized by: A vehicle control device for controlling a vehicle that autonomously travels on a route,
a person detection unit that detects a person on the route of the vehicle;
Evacuation required for the person to evacuate from the route with respect to an external device communicably connected to the person or the vehicle control device and capable of predicting an evacuation time required for the person to evacuate from the route an evacuation time request unit that requests information about time;
an evacuation time acquisition unit that acquires response information including information about the evacuation time from the person or the external device to the evacuation time request unit;
a motion plan generating unit for generating a motion plan including determination of a route to a destination of the vehicle;
a vehicle control unit that controls the vehicle according to the generated operation plan;
The operation plan generation unit generates a detour route that detours the course and moves to the destination, calculates the required time to the destination when traveling along the detour route, and calculates the result of the calculation; Based on the reply information, it is determined whether to wait until the person retreats from the route or change the route to the detour route.
A vehicle control device characterized by: The vehicle control device according to claim 7,
If the person does not evacuate or the person does not provide information about the evacuation time within a predetermined time, the evacuation time request unit presents the request again.
A vehicle control device characterized by: The vehicle control device according to claim 7,
When the evacuation time acquired by the evacuation time requesting unit from the person or the external device and the time required to reach the destination when traveling the detour route exceed a predetermined threshold, the operation plan generating unit determining whether there is another vehicle in the work area in which the vehicle is traveling, to which the work being executed by the vehicle can be transferred;
A vehicle control device characterized by:

Images