Conveying system

Abstract

To provide a carrier system capable of recording accident images using an unmanned flying object without equipping a manned carrier vehicle with an onboard camera.SOLUTION: In a carrier system S with a manned carrier vehicle 1 and an unmanned flying object 2, the manned carrier vehicle 1 comprises a position detection part 10 to detect a vehicle position and a sound collection part 12 to collect the sound around the vehicle. The unmanned flying object 2 comprises a photographing part 25 to take the picture around the flying object and a flight control part 21 to control the flight to an accident site when the manned carrier vehicle 1 causes an accident using an accident determination part 35 to determine whether or not the manned carrier vehicle 1 causes the accident based on the collected sound by the sound collection part 12. It is configured that the unmanned flying object 2 takes the picture of the accident site by the photographing part 25.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a transportation system including a manned transport vehicle and an unmanned aircraft.

Background Art

[0002] A manned transport vehicle (e.g., a forklift) used in facilities such as factories and warehouses is configured to travel and operate by an operator boarding and operating it. Further, the forklift is configured to perform a cargo handling operation for loading and unloading goods using forks.

[0003] By the way, in the facilities where manned transport vehicles are used, there may occur collision accidents where a manned transport vehicle collides with a rack or a wall while traveling, dropping accidents where a manned transport vehicle drops goods during cargo handling operations, personal injury accidents where a manned transport vehicle collides with a person while traveling or drops goods on a person during cargo handling operations, fire accidents where a fire breaks out during cargo handling operations by a manned transport vehicle, etc.

[0004] Thus, there is a technique of mounting an in-vehicle camera on a manned transport vehicle and detecting dangerous driving based on an image captured by the in-vehicle camera (Patent Document 1, etc.). According to this, it is possible to prevent dangerous driving and also record accident images when an accident occurs.

[0005] However, since in-vehicle cameras are expensive, there is a problem that it is difficult to mount them on all manned transport vehicles when the number of manned transport vehicles in a facility is large. Also, since dangerous driving cannot be completely prevented, it is necessary to make a prompt response for appropriate treatment when a personal injury accident or a fire accident occurs.​​​​​​​​​​​​​​​​​[Problems that the invention aims to solve]

[0007] Therefore, the problem that the present invention aims to solve is to provide a transport system that can record accident images using an unmanned aerial vehicle, even when the manned transport vehicle is not equipped with an on-board camera. [Means for solving the problem]

[0008] To solve the above problems, the transport system according to the present invention is In a transport system equipped with a manned transport vehicle and an unmanned aerial vehicle, Manned transport vehicles are A position detection unit that detects the vehicle's position, It includes a sound collection unit that collects sound from around the vehicle, Unmanned aircraft, The camera crew takes pictures of the area around the aircraft, The system includes an accident determination unit that determines whether or not a manned transport vehicle has been involved in an accident based on the sound collected by the sound collection unit, and a flight control unit that controls the manned transport vehicle to fly to the accident site when an accident occurs. The unmanned aerial vehicle is configured to film the accident scene from its camera unit.

[0009] Preferably, The accident assessment department, A data collection unit collects characteristic data on the characteristics of normal sounds when a manned transport vehicle is driving and performing cargo handling operations, and training data based on the relationship between these characteristics and accident sounds when a manned transport vehicle is involved in an accident. The collection unit performs machine learning on the training data collected, and the learning model generation unit generates and stores a learning model using machine learning. The sound collection unit acquires characteristic sound data of the surroundings of the manned transport vehicle at predetermined intervals, and the acquisition unit The learning model generation unit inputs the current sound characteristic data of the surroundings of the manned transport vehicle, acquired from the acquisition unit, into the learning model, and the prediction unit predicts from the learning model whether or not it is an accident sound. It includes a decision unit that determines whether to fly an unmanned aerial vehicle to the accident site based on a prediction unit.

[0010] Preferably, The accident determination unit is configured to determine whether or not an accident involves personal injury, and if it is determined to be a personal injury accident, it is configured to fly an unmanned aerial vehicle equipped with a first-aid kit to the accident site.

[0011] Preferably, The accident determination unit is configured to determine whether or not an accident involves personal injury, and if it is determined to be an accident involving personal injury, it is configured to dispatch an ambulance to the accident scene.

[0012] Preferably, The accident determination unit is configured to determine whether or not an accident is a fire accident, and if it is determined to be a fire accident, it is configured to fly an unmanned aerial vehicle equipped with a fire extinguishing kit to the accident site.

[0013] Preferably, The accident determination unit is configured to determine whether or not the accident occurred in a hazardous materials handling area. If it is determined that the accident occurred in a hazardous materials handling area, an unmanned aerial vehicle equipped with an emergency kit for handling hazardous materials is configured to fly to the accident site.

[0014] Preferably, The unmanned aerial vehicle is equipped with a notification unit that alerts the surrounding area to an accident. [Effects of the Invention]

[0015] The transport system according to the present invention is a transport system comprising a manned transport vehicle and an unmanned aerial vehicle, and even when the manned transport vehicle is not equipped with an on-board camera, accident images can be recorded using the unmanned aerial vehicle. [Brief explanation of the drawing]

[0016] [Figure 1] A side view showing the transport system. [Figure 2]Block diagram showing a conveying system. [Figure 3] Flowchart showing the accident handling control procedure of the first embodiment. [Figure 4] Block diagram showing the configuration of the accident determination unit of the second embodiment. [Figure 5] Flowchart showing the accident handling control procedure of the second embodiment.

Mode for Carrying Out the Invention

[0017] Hereinafter, embodiments of the conveying system according to the present invention will be described based on the drawings.

[0018] [First Embodiment] Based on FIGS. 1 to 3, the conveying system of the first embodiment will be described.

[0019] As shown in FIGS. 1 and 2, the conveying system S includes a manned transport vehicle 1 on which an operator O rides and operates. The manned transport vehicle 1 is configured to travel and operate when the operator O rides and operates it. In the present embodiment, the manned transport vehicle 1 is a reach-type forklift, and is configured to be able to perform vehicle travel, fork lifting and lowering, etc. when the operator O rides and operates it.

[0020] The conveying system S includes a plurality of shelves R installed in facilities such as factories and warehouses. The shelf R is provided with a plurality of stepped portions in the height direction and the horizontal direction, and is configured to be able to store the load L at a predetermined position of the stepped portion. The manned transport vehicle 1 performs loading and unloading operations by placing and picking up the load L at a predetermined position of the shelf R.

[0021] The conveying system S includes an unmanned flying body 2 that can be stopped in the air. The unmanned flying body 2 is a drone, and is configured to fly to a predetermined in-air stop position and hover at the predetermined in-air stop position by the rotation of rotors provided at the tip sides of a plurality of arms.

[0022] The transport system S includes a control device 3 for controlling the unmanned aerial vehicle 2. The control device 3 includes a memory unit 30. The memory unit 30 stores a map M consisting of shelves R installed within the facility, passageways, luggage L placed within the facility, etc.

[0023] The storage unit 30 stores the cargo handling tasks T performed by the manned transport vehicle 1 as a cargo handling schedule J. Specifically, the cargo handling schedule J consists of multiple cargo handling tasks T, such as task T1 for retrieving cargo L from a predetermined location on a predetermined shelf R, task T2 for placing cargo L in a predetermined location on a predetermined shelf R, task T3 for placing cargo L in a shipping location, and task T4 for retrieving cargo L from a receiving location, all set in a predetermined order. The cargo handling tasks T also include information on the cargo handling location D2 and cargo handling (retrieval or placement) information for cargo L.

[0024] The management device 3 includes a cargo handling instruction unit 34, which is configured to display the cargo handling tasks T of the cargo handling schedule J transmitted from the storage unit 30 on a display unit 11 located in the driver's seat of the manned transport vehicle 1.

[0025] The display unit 11 is, for example, a touch panel display. The cargo handling instruction unit 34 displays the cargo handling task T that the manned transport vehicle 1 should perform on the display unit 11. The operator O drives and operates the manned transport vehicle 1 to perform cargo handling work according to the cargo handling task T displayed on the display unit 11. When the cargo handling task T is completed, the operator O presses the end button displayed on the display unit 11, and an end signal is sent to the cargo handling instruction unit 34. When the cargo handling instruction unit 34 receives the end signal, it is configured to display the next cargo handling task T that the manned transport vehicle 1 should perform on the display unit 11.

[0026] Operator O can drive the manned transport vehicle 1 to the loading / unloading position D2 and operate the manned transport vehicle 1 according to the loading / unloading task T displayed on the display unit 11 to perform loading / unloading operations on the cargo L.

[0027] The manned transport vehicle 1 is equipped with a position detection unit 10. The position detection unit 10 consists of sensors that detect the surrounding environment, such as a laser sensor, GPS sensor, and electromagnetic induction sensor, or a receiver that receives signals from positioning satellites. The position detection unit 10 is configured to detect the vehicle position D1 of the manned transport vehicle 1.

[0028] The manned transport vehicle 1 is further equipped with a sound collection unit 12. The sound collection unit 12 is installed in a predetermined position on the vehicle, such as the head guard, and is configured to collect sounds from around the vehicle. Therefore, in the event of a collision accident in which the manned transport vehicle 1 collides with a rack R or a wall while in motion, a personal injury accident in which the manned transport vehicle 1 collides with a person while in motion or drops cargo L on a person during cargo handling operations, or a fire accident in which a fire occurs due to the improper handling of the manned transport vehicle 1 or cargo L, the sound collection unit 12 is configured to collect the sounds of each accident.

[0029] The unmanned aerial vehicle 2 is equipped with a position detection unit 20. The position detection unit 20 consists of, for example, a laser sensor that acquires SLAM (Simultaneous Localization and Mapping) data using LiDAR (Light Detection and Ranging), a motion sensor that acquires odometry data, and a receiver that receives signals from positioning satellites, and can detect the position of the unmanned aerial vehicle 2.

[0030] The unmanned aerial vehicle 2 is equipped with a flight control unit 21. The flight control unit 21 is configured to control the rotation of the rotor blades. Based on the detection results of the position detection unit 20 and the control of the flight control unit 21, the unmanned aerial vehicle 2 can fly to a predetermined aerial stopping position and hover at that aerial stopping position.

[0031] The placement determination unit 32 is further configured to determine the aerial stopping position where the unmanned aerial vehicle 2 will hover. When the manned transport vehicle 1 has an accident, the placement determination unit 32 determines that the vehicle position D1 of the manned transport vehicle 1 is the accident site, and that the unmanned aerial vehicle 2 will fly to and be positioned at the accident site under the control of the flight control unit 21.

[0032] The unmanned aerial vehicle 2 is equipped with a memory unit 22. The memory unit 22 stores notification sounds and notification images. The notification sounds consist of voices or siren sounds to notify those in the surrounding area that an accident has occurred, and the notification images consist of notification texts or diagrams projected onto the floor of the accident site to notify those in the surrounding area that an accident has occurred.

[0033] The unmanned aerial vehicle 2 is equipped with a notification unit 26. The notification unit 26 consists of, for example, a speaker that generates a notification sound and a projector that projects a notification image.

[0034] The unmanned aerial vehicle 2 is equipped with an imaging unit 25 that has a CCD image sensor, a CMOS image sensor, etc. The imaging unit 25 is configured to be able to photograph the accident site from above when the manned transport vehicle 1 is involved in an accident.

[0035] The control device 3 includes an accident determination unit 35. The accident determination unit 35 is configured to determine whether or not the manned transport vehicle 1 has been involved in an accident, based on the sound data of the surroundings of the manned transport vehicle 1 acquired by the sound collection unit 12.

[0036] The memory unit 30 stores sound data and organizes it into a database. The sound data consists of normal sound data when the manned transport vehicle 1 performs normal cargo handling operations and travels, collision accident sound data when the manned transport vehicle 1 collides with a rack R or wall, etc. while traveling, dropping accident sound data when the manned transport vehicle 1 drops cargo L during cargo handling operations, personal injury accident sound data when the manned transport vehicle 1 collides with a person while traveling or drops cargo L on a person during cargo handling operations, and fire accident sound data when a fire occurs due to the manned transport vehicle 1 mishandling cargo L during cargo handling operations.

[0037] The accident determination unit 35 compares the sound data stored in the memory unit 30 with the sound data collected by the sound collection unit 12 to measure the degree of difference and agreement in sound volume, pitch, and timbre. The accident determination unit 35 may also set numerical parameters associated with the sound volume, pitch, and timbre values ​​in the accident sound data, weighted averaged using weighting coefficients. The accident determination unit 35 is configured to determine an accident sound based on the measured degree of difference and agreement of the sounds.

[0038] The storage unit 30 further stores and databases image data. The image data consists of normal image data when the manned transport vehicle 1 performs normal cargo handling operations and travels, collision accident image data when the manned transport vehicle 1 collides with a rack R or wall, etc. while traveling, dropping accident image data when the manned transport vehicle 1 drops cargo L during cargo handling operations, personal injury accident image data when the manned transport vehicle 1 collides with a person while traveling or drops cargo L on a person during cargo handling operations, and fire accident image data when a fire occurs due to the manned transport vehicle 1 mishandling cargo L during cargo handling operations.

[0039] The accident determination unit 35 further compares the image data stored in the memory unit 30 with the image data acquired by the imaging unit 25 to detect the location of people and the presence or absence of fire. The accident determination unit 35 is configured to determine that an accident is a personal injury accident if the image shows a person lying down or sitting on the floor, and to determine that an accident is a fire accident if the image shows a fire.

[0040] The memory unit 30 also stores the hazardous materials handling areas in map M. The hazardous materials handling areas are areas where the manned transport vehicle 1 handles cargo L containing hazardous materials such as gasoline or oily paints that pose a high risk of fire, or cargo L containing hazardous materials such as mercury or organic solvents that have adverse effects on the human body. The accident determination unit 35 then determines whether the accident occurred in a hazardous materials handling area based on the hazardous materials handling areas stored in the memory unit 30 and the location of the accident site.

[0041] The accident response control procedure will be explained based on Figure 3.

[0042] The sound collection unit 12 of the manned transport vehicle 1 sequentially collects sounds generated around the vehicle of the manned transport vehicle 1 and acquires sound data (step S1). The collected sound data is transmitted to the accident determination unit 35 of the management device 3, and the accident determination unit 35 determines whether or not there is an accident sound based on the transmitted sound data (step S2). If the accident determination unit 35 determines that there is no accident sound, the process returns to step S1, and the sound collection unit 12 of the manned transport vehicle 1 sequentially collects sounds generated around the vehicle of the manned transport vehicle 1 and acquires sound data.

[0043] If the accident detection unit 35 determines that there is an accident sound, it designates the position D1 of the manned transport vehicle 1 that caused the accident as the accident site and controls the flight control unit 21 to have the unmanned aerial vehicle 2 equipped with the imaging unit 25 fly to the accident site (step S3). When the unmanned aerial vehicle 2 arrives at the accident site, the imaging unit 25 starts imaging the accident site (step S4). The image data captured by the imaging unit 25 is stored in the storage unit 30 to be recorded as an accident image (step S5).

[0044] The captured image data is transmitted to the accident determination unit 35 of the management device 3, and the accident determination unit 35 determines whether it is a personal injury accident based on the transmitted image data (step S6). If the accident determination unit 35 determines that it is a personal injury accident, it notifies an ambulance and / or the unmanned aerial vehicle 2 equipped with a first-aid kit flies to the accident site (step S7).

[0045] The accident determination unit 35 further determines whether it is a fire accident based on the transmitted image data (step S8). When the accident determination unit 35 determines that it is a fire accident, the unmanned aircraft 2 equipped with a fire extinguishing kit flies to the accident site (step S9).

[0046] The accident determination unit 35 further determines, based on the location of the accident site, whether the accident occurred in a hazardous materials handling area (step S10). If the accident determination unit 35 determines that the accident occurred in a hazardous materials handling area, the unmanned aerial vehicle 2 equipped with an emergency kit for hazardous materials flies to the accident site (step S11).

[0047] Furthermore, if necessary, the notification unit 26 of the unmanned aircraft 2 may emit a notification sound (e.g., a siren or voice) through a speaker, or display a notification message (e.g., an alarm message such as "An accident has occurred nearby! Please be careful!") or a notification image (e.g., an illustration of the accident) using a projector to notify those around the manned transport vehicle 1 of the accident.

[0048] Then, the accident processing control from steps S1 to S11 is repeatedly performed to sequentially determine whether the manned transport vehicle 1 has been involved in an accident and to record accident images.

[0049] [Second Embodiment] The transport system of the second embodiment will now be described. Note that, to avoid redundant explanations, the same configuration as in the first embodiment may be omitted.

[0050] As shown in Figure 4, the accident determination unit 35 includes a collection unit 350 that collects training data 356. The training data 356 includes feature data D related to the characteristics of sound. In this embodiment, the feature data D related to various sound characteristics are loudness, pitch, and timbre.

[0051] The accident determination unit 35 includes a learning model generation unit 351 that performs machine learning on the training data 356 collected by the collection unit 350, and generates and stores a learning model through machine learning. In this embodiment, the learning model generation unit 351 performs supervised learning. In supervised learning, a large amount of training data 356, that is, pairs of input data ID and output data OD, is input to the learning model generation unit 351.

[0052] The input data ID includes the loudness, pitch, and timbre of both normal and accident sounds. The output data OD contains the loudness, pitch, and timbre of the accident sound. The input data ID is evaluated to determine whether or not an accident sound is present.

[0053] Examples of situations in which an accident sound is determined include when the loudness of the sound differs significantly from the normal sound, when the pitch differs significantly from the normal sound, or when the timbre differs significantly from the normal sound. The accident determination unit 35 determines whether or not an accident has occurred based on the numerical parameters of the degree of difference and degree of similarity described above.

[0054] Accident sounds may be set using numerical parameters for loudness, pitch, or timbre, or they may be set using numerical parameters weighted by a weighting coefficient.

[0055] In fact, accident sounds are often easily recognizable because they differ from normal sounds in terms of loudness, pitch, and timbre. Therefore, it can be inferred that there is a certain relationship, such as a correlation, between the degree of difference in loudness, pitch, and timbre from normal sounds and accident sounds.

[0056] The learning model generation unit 351 uses a general machine learning algorithm such as a neural network. The learning model generation unit 351 performs machine learning using the correlated input data ID and output data OD as training data 356 to generate a model (learning model) that estimates output from input, that is, a model that outputs whether or not there is an accident sound when input data ID is input.

[0057] The accident determination unit 35 includes an acquisition unit 355 that acquires the current input data ID at predetermined intervals. As described above, the input data ID is the loudness, pitch, and timbre of the normal sound and the accident sound. The acquisition unit 355 is configured to acquire the input data ID based on the sound data from the sound collection unit 12 using known sound analysis techniques.

[0058] The accident determination unit 35 includes a prediction unit 352 that predicts whether or not a sound is an accident sound based on numerical parameters indicating the degree of difference between a normal sound and an accident sound, by applying the learning model generated by the learning model generation unit 351 to the current input data ID acquired from the acquisition unit 355.

[0059] The accident determination unit 35 includes a decision unit 353, which determines whether to fly the unmanned aircraft 2 to the accident site based on the output data OD predicted by the prediction unit 352.

[0060] The accident response control procedure will be explained based on Figure 5.

[0061] The accident determination unit 35 collects training data 356 using the collection unit 350 (step S21). Then, the learning model generation unit 351 performs machine learning on the training data 356 collected by the collection unit 350 in step S21, and generates and stores a learning model through machine learning (step S22).

[0062] The accident determination unit 35 acquires the sound data collected by the sound collection unit 12 as the current input data ID at predetermined intervals using the acquisition unit 355 (step S23).

[0063] The accident determination unit 35 predicts whether or not an accident sound is present by applying the learning model generated in step S22 to the current input data ID acquired in step S23, using the prediction unit 352 (step S24).

[0064] The accident determination unit 35 determines whether or not there is an accident sound based on the output data OD predicted in step S24 by the determination unit 353 (step S25).

[0065] If the accident detection unit 35 determines that there is an accident sound, it designates the position D1 of the manned transport vehicle 1 that caused the accident as the accident site and controls the flight control unit 21 to have the unmanned aerial vehicle 2 equipped with the imaging unit 25 fly to the accident site (step S26). When the unmanned aerial vehicle 2 arrives at the accident site, the imaging unit 25 starts taking pictures of the accident site (step S27). The image data taken by the imaging unit 25 is stored in the storage unit 30 to be recorded as an accident image (step S28).

[0066] The captured image data is transmitted to the accident determination unit 35 of the management device 3, and the accident determination unit 35 determines whether it is a personal injury accident based on the transmitted image data (step S29). If the accident determination unit 35 determines that it is a personal injury accident, it notifies an ambulance and / or the unmanned aerial vehicle 2 equipped with a first-aid kit flies to the accident site (step S30).

[0067] The accident determination unit 35 further determines whether it is a fire accident based on the transmitted image data (step S31). When the accident determination unit 35 determines that it is a fire accident, the unmanned aircraft 2 equipped with a fire extinguishing kit flies to the accident site (step S32).

[0068] The accident determination unit 35 further determines, based on the location of the accident site, whether the accident occurred in a hazardous materials handling area (step S33). If the accident determination unit 35 determines that the accident occurred in a hazardous materials handling area, the unmanned aerial vehicle 2 equipped with an emergency kit for hazardous materials flies to the accident site (step S34).

[0069] Furthermore, if necessary, the notification unit 26 of the unmanned aircraft 2 may emit a notification sound through a speaker or display notification text or images using a projector to notify those around the manned transport vehicle 1 of the accident.

[0070] Then, the accident processing control from steps S21 to S34 is repeatedly performed to sequentially determine whether the manned transport vehicle 1 has been involved in an accident and to record accident images.

[0071] Although preferred embodiments of the present invention have been described above, the configuration of the present invention is not limited to these embodiments. For example, it can be modified as follows.

[0072] In the above embodiment, the accident determination unit 35 determined the presence or absence of an accident sound based on the loudness, pitch, and timbre of the sound. However, it may also be configured to determine the presence or absence of an accident sound based on the sound waveform, spectral analysis, frequency band, distribution of frequency components, amount of frequency change, etc.

[0073] Furthermore, the accident determination unit 35 may be configured to determine whether the manned transport vehicle 1 has been involved in an accident more reliably by incorporating information about obstacles detected by an ultrasonic sensor (such as the presence or absence of obstacles and the distance to the obstacles) on the manned transport vehicle 1, rather than simply determining whether the manned transport vehicle 1 has been involved in an accident based solely on the sound data of the surroundings of the manned transport vehicle 1 acquired by the sound collection unit 12.

[0074] Furthermore, the accident determination unit 35 may be configured to determine whether the manned transport vehicle 1 has been involved in an accident not solely based on the sound data of the surroundings of the manned transport vehicle 1 acquired by the sound collection unit 12, but by also taking into account the information detected by the acceleration sensor (such as the vehicle's tilt, vibration, and impact) when the manned transport vehicle 1 is equipped with an acceleration sensor, thereby more reliably determining whether the manned transport vehicle 1 has been involved in an accident.

[0075] The effects of the present invention will be explained.

[0076] In a transport system S comprising a manned transport vehicle 1 and an unmanned aerial vehicle 2, the manned transport vehicle 1 includes a position detection unit 10 for detecting the vehicle's position and a sound collection unit 12 for collecting sound around the vehicle. The unmanned aerial vehicle 2 includes a shooting unit 25 for photographing the area around the aircraft and an accident determination unit 35 that determines whether or not the manned transport vehicle 1 has had an accident based on the sound collected by the sound collection unit 12. The flight control unit 21 controls the unmanned aerial vehicle 2 to fly to the accident site when the manned transport vehicle 1 has had an accident. The unmanned aerial vehicle 2 is configured to photograph the accident site with the shooting unit 25.

[0077] Therefore, by equipping the manned transport vehicle 1 with a sound collection unit 12, it is not necessary to mount an expensive on-board camera on the manned transport vehicle 1, and the equipment mounted on the manned transport vehicle 1 can be made inexpensive and simple. In addition, since the unmanned aerial vehicle 2 records the accident scene with its camera unit 25, it is possible to record the entire accident scene not only from the front but also from above.

[0078] The accident determination unit 35 includes a collection unit 350 that collects training data based on the relationship between characteristic data regarding the characteristics of normal sounds when the manned transport vehicle 1 is driving and performing cargo handling operations and accident sounds when the manned transport vehicle 1 is involved in an accident; a learning model generation unit 351 that performs machine learning from the training data collected by the collection unit 350 and generates and stores a learning model through machine learning; an acquisition unit 355 that uses a sound collection unit to acquire characteristic sound data of the surroundings of the manned transport vehicle 1 at predetermined intervals; a prediction unit 352 that inputs the characteristic sound data of the surroundings of the manned transport vehicle 1 acquired from the acquisition unit 355 into the learning model generated by the learning model generation unit 351 to predict from the learning model whether or not it is an accident sound; and a decision unit 353 that determines whether or not to fly the unmanned aerial vehicle 2 to the accident site based on the prediction unit 352.

[0079] The accident determination unit 35 can accurately determine whether or not an accident sound is present by using a learning model generated by machine learning.

[0080] The accident determination unit 35 is configured to determine whether or not an accident involves personal injury, and if it is determined to be an accident involving personal injury, the unmanned aircraft 2 equipped with a first-aid kit is configured to fly to the accident site.

[0081] In this way, in the event of an accident involving injuries, an unmanned aerial vehicle (UAV) equipped with a first-aid kit can be flown to the accident site to provide rapid first aid to the injured.

[0082] The accident determination unit 35 is configured to determine whether or not an accident is a personal injury accident, and if it is determined to be a personal injury accident, it is configured to dispatch an ambulance to the accident scene.

[0083] In this way, by ensuring that ambulances can quickly arrive at the scene of an accident involving injuries, it becomes possible to provide prompt first aid to the injured or transport them to a hospital.

[0084] The accident determination unit 35 is configured to determine whether or not an accident is a fire accident, and when it is determined to be a fire accident, the unmanned aircraft 2 equipped with a fire extinguishing kit is configured to fly to the accident site.

[0085] This allows for the rapid extinguishing of fires in the event of a fire, by having a drone equipped with a firefighting kit fly to the scene.

[0086] The accident determination unit 35 is configured to determine whether or not the accident occurred in a hazardous materials handling area. If it is determined that the accident occurred in a hazardous materials handling area, the unmanned aerial vehicle 2 equipped with an emergency kit for hazardous materials is configured to fly to the accident site.

[0087] This allows for rapid action to be taken in accordance with the type of hazardous material in an accident that occurs in a hazardous materials handling area. For hazardous materials that are likely to cause a fire, an unmanned aerial vehicle (UAV2) equipped with a fire extinguishing kit can fly to the accident site. For hazardous materials that are likely to have adverse effects on human health, an UAV2 equipped with a first-aid kit can fly to the accident site.

[0088] The unmanned aerial vehicle 2 is equipped with a notification unit 26 that informs those in the vicinity of the accident site that an accident has occurred.

[0089] This allows for the rapid notification of an accident to those in the vicinity of the accident site, enabling people nearby to quickly deal with the situation. [Explanation of Symbols]

[0090] S Conveyor System 1 Manned guided vehicle 2 Unmanned aircraft 10 Position detection unit 12 Sound collection section 21 Flight Control Unit 25 Photography Department 26 Hochi Department 30 Storage section 35 Accident Judgment Department 350 Collection Department 351 Learning Model Generation Unit 352 Prediction Section 353 Decision Section 355 Acquisition Department 356 training data ID Input Data OD output data

Claims

1. In a transport system equipped with a manned transport vehicle and an unmanned aerial vehicle, The aforementioned manned transport vehicle is A position detection unit that detects the vehicle's position, The vehicle comprises a sound collection unit that collects sound from the surrounding area, The aforementioned unmanned aircraft, The camera crew takes pictures of the area around the aircraft, The system includes an accident determination unit that determines whether or not the manned transport vehicle has been involved in an accident based on the sound collected by the sound collection unit, and a flight control unit that controls the manned transport vehicle to fly to the accident site when an accident occurs. The aforementioned unmanned aerial vehicle is configured to photograph the accident site with its camera unit. A transport system characterized by the following features.

2. The accident determination unit is configured to determine whether or not the accident is a fire accident, and when it is determined to be a fire accident, the unmanned aerial vehicle equipped with a fire extinguishing kit is configured to fly to the accident site. The transport system according to feature 1.

3. The accident determination unit is configured to determine whether or not the accident occurred in a hazardous materials handling area. When it is determined that the accident occurred in a hazardous materials handling area, the unmanned aerial vehicle equipped with an emergency kit for hazardous materials is configured to fly to the accident site. The transport system according to feature 1.

4. The aforementioned unmanned aerial vehicle is equipped with a notification unit that alerts the surrounding area to the accident site that an accident has occurred. The transport system according to feature 1.

Images