Method and apparatus for preventing collision between unmanned moving object and worker on basis of location information

Abstract

The present invention relates to a location-based safety management system for preventing a collision between an unmanned moving object and a worker in an industrial site. In particular, the present invention includes a technology for predicting the possibility of a collision in real time and providing graded warnings through an elliptical measurement method centered on a traveling direction of an unmanned moving object and a weight-based risk analysis according to locations, speeds, and moving directions of a worker and the moving object. The present invention may enable accurate and rapid collision prevention in industrial sites, thereby ensuring the safety of workers and improving work efficiency.

Description

Method and device for preventing collisions between unmanned mobile vehicles and workers based on location information

[0001] The present invention relates to safety management in industrial sites, and more specifically, to a location information-based method and device for preventing collisions between an unmanned vehicle and a worker, which predicts the likelihood of safety accidents based on location information of the worker and the unmanned vehicle and provides step-by-step collision warning lights in order to prevent collisions and accidents between the unmanned vehicle and the worker occurring at a work site.

[0002] Recently, unmanned vehicles (e.g., autonomous robots, unmanned cranes, and automated transport vehicles) are being increasingly introduced in industrial settings to enhance automation and efficiency. These vehicles are significantly contributing to work automation, cost reduction, and productivity improvement across various sectors, including logistics, manufacturing, construction, and shipyards. However, the risk of collisions remains ever-present in work environments where unmanned vehicles and humans coexist. Such collisions can result in not only worker safety issues but also damage to production equipment and work stoppages, thereby highlighting the growing need for safety management and collision prevention systems in industrial settings.

[0003] Most existing collision avoidance technologies primarily rely on providing warnings based on the straight-line distance between the operator's location and the moving object's location. For example, they attempt to prevent accidents by providing a warning notification to the operator or reducing the object's speed when it approaches within a certain distance. However, these conventional methods have limitations in predicting actual collision risks because they fail to account for the direction of travel of the unmanned vehicle and the operator's movement path. In particular, effective collision prevention is difficult with simple distance-based warnings in situations where unmanned vehicles are moving rapidly or in complex work environments.

[0004] Therefore, for the safe operation of unmanned vehicles, a risk prediction system is required that comprehensively considers not only the distance from the operator but also the vehicle's direction of travel, speed, and the operator's direction of movement. For example, if an operator is located in a specific direction while the vehicle is moving rapidly, the risk becomes very high. Conversely, if the operator is in the opposite direction to the vehicle's movement, the risk may be relatively lower even if they are within the same distance. Thus, to more accurately assess collision risk, risk prediction that applies weights based on the direction of travel and speed is necessary, rather than simply providing warnings based on the distance between the vehicle and the operator.

[0005] Furthermore, existing positioning technologies primarily utilize GPS, RFID, or BLE to track the location of moving objects or workers in real time. While these systems enable location tracking over a relatively wide range, they may have limitations in accurate location prediction. For example, although GPS performs well outdoors, its accuracy can decrease in indoor environments due to unstable signals. Similarly, while BLE and Wi-Fi-based positioning systems can be used indoors, their accuracy may decline in enclosed spaces or environments with many obstacles.

[0006] As such, existing positioning technologies alone make it difficult to effectively manage the risk of collision between unmanned vehicles and workers in the complex environments of industrial sites. To address this, a hybrid positioning system must be introduced to enable precise location tracking both indoors and outdoors by utilizing various positioning technologies (GPS, Wi-Fi, BLE, etc.). Through this, location information must be accurately collected to suit the specific characteristics of industrial sites, and a collision avoidance system based on this data must be provided.

[0007] The present invention was devised to solve such problems and aims to ensure worker safety and maintain productivity and efficiency in industrial sites by predicting collision risks in real time in industrial sites where unmanned vehicles and workers are mixed, and by establishing a precise warning system based on this. To this end, the present invention adopts an elliptical risk area setting method considering the direction of travel of the unmanned vehicle and a risk analysis method reflecting weights to overcome the limitations of existing simple distance-based warning methods, and provides a location information-based method and device for preventing collisions between unmanned vehicles and workers that offers a more effective collision prevention solution in various environments.

[0008] To achieve the above objective, a method for preventing a collision between an unmanned vehicle and a worker using a location information-based collision prevention device in an industrial site according to the present invention comprises: (a) setting an elliptical area based on the current location and direction of travel of the unmanned vehicle; (b) measuring the location of the worker and monitoring the direction of travel; (c) predicting a collision risk by applying weights according to the location, speed, and direction of travel of the worker and the unmanned vehicle within the elliptical area; and (d) providing a warning notification according to a risk grade reflecting the weights when the collision risk exceeds a certain standard.

[0009] The elliptical area setting of step (a) above is formed by making the direction of movement of the unmanned vehicle the major axis and the lateral direction the minor axis.

[0010] A higher weight is applied to the major axis of the aforementioned elliptical region according to the direction of movement of the unmanned mobile vehicle.

[0011] Step (c) above predicts the possibility of a worker entering the elliptical area of ​​the unmanned vehicle and, if the worker is located within the elliptical area, provides a collision risk warning according to the risk level.

[0012]

[0013] In step (d) above, if the operator approaches within a certain distance, the path of the unmanned vehicle is reset or an avoidance path is suggested to prevent a collision.

[0014] The above step (a) includes the step of setting an elliptical measurement area based on GPS, Wi-Fi, and BLE signals according to the real-time location and direction of travel of the unmanned vehicle, and further includes the step of correcting the error of the elliptical measurement according to the indoor and outdoor location environment.

[0015] Another aspect of the present invention for achieving such an objective is a computer program stored in a non-transient storage medium for preventing collisions between an unmanned vehicle and a worker based on location information, the computer program being stored in the non-transient storage medium and comprising a command to execute by a processor the following steps: (a) setting an elliptical area based on the current location and direction of travel of the unmanned vehicle; (b) measuring the location of the worker and monitoring the direction of travel; (c) predicting a collision risk by applying weights according to the location, speed, and direction of travel of the worker and the unmanned vehicle within the elliptical area; and (d) providing a warning notification according to a risk grade reflecting the weights when the collision risk exceeds a certain standard.

[0016] Another aspect of the present invention for achieving such an objective is a device for performing a method for preventing collisions between an unmanned vehicle and a worker based on location information, comprising: (a) setting an elliptical area based on the current location and direction of travel of the unmanned vehicle; (b) measuring the location of a worker and monitoring the direction of travel; (c) predicting a collision risk by applying weights according to the location, speed, and direction of travel of the worker and the unmanned vehicle within the elliptical area; and (d) providing a warning notification according to a risk grade reflecting the weights when the collision risk exceeds a certain standard.

[0017] According to the present invention, by comprehensively analyzing various factors such as the direction of travel of an unmanned vehicle, the position and direction of movement of a worker, and speed, it is possible to accurately predict the risk of collision.

[0018] In addition, weight-based risk analysis reduces unnecessary warnings and provides alerts only in actual risk situations, thereby enhancing user convenience.

[0019] In addition, the combined positioning system enables application in both indoor and outdoor environments, and is effective for adapting to various working conditions in industrial sites.

[0020] FIG. 1 is a flowchart illustrating a method for preventing collisions between an unmanned mobile vehicle and a worker based on location information according to the present invention.

[0021] FIG. 2 is a diagram showing the configuration of a computer device equipped with a location information-based collision prevention application for an unmanned mobile vehicle and a worker according to the present invention.

[0022] FIG. 3 is a diagram showing the configuration of a composite positioning system in a location information-based collision avoidance system for an unmanned mobile vehicle and a worker according to the present invention.

[0023] FIG. 4 is a module configuration diagram showing a composite tag of a positioning collection device in a composite positioning system according to FIG. 3.

[0024] Figure 5 is a sequence flow showing the distance measurement process of FTM.

[0025] Figure 6 is a diagram showing a position estimation technique using trilateration.

[0026] Figure 7 is a diagram showing distance correction between a reference beacon-based FTM AP and a tag.

[0027] FIG. 8 is a conceptual diagram showing GPS-based indoor and outdoor location determination.

[0028] FIG. 9 is a drawing showing an example of danger radius correction for a large unmanned mobile vehicle.

[0029] Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings. Identical or similar components are assigned identical or similar reference numerals, and redundant descriptions thereof are omitted. In describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art may obscure the essence of the embodiments disclosed in this specification, such detailed description is omitted. The attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings; it should be understood that they include all modifications, equivalents, or substitutions that fall within the spirit and technical scope of the present invention.

[0030] Terms containing ordinal numbers, such as first, second, etc., may be used to describe various components; however, these terms are used solely for the purpose of distinguishing one component from another, and the corresponding components are not limited by these terms. A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0031] Terms such as “comprising,” “comprising,” or “having” as used herein should be understood as limiting the existence of the features, steps, components, or combinations thereof described herein, and are not intended to exclude the possibility that one or more other features, steps, components, or combinations thereof may exist or be added.

[0032] When a component is described as being "connected" or "joined" to another component, it should be understood that it may be directly connected or joined to that other component, or that there may be another component in between. On the other hand, when a component is referred to as being "directly connected" or "directly joined" to another component, it should be understood that no other component exists in between.

[0033] FIG. 1 is a flowchart illustrating a method for preventing collisions between an unmanned mobile vehicle and a worker based on location information according to the present invention.

[0034] Referring to FIG. 1, an elliptical area is established based on the current position and direction of travel of the unmanned vehicle (S100). Previously, the current position information of the unmanned vehicle was positioning information collected from a composite positioning system, which is information reflecting N positioning technologies that reflect the physical environment within the industrial site. One of the N positioning technologies is an FTM-based positioning technology, and the positioning technology is explained through FIGS. 5 to 9 as follows.

[0035] For reference, Fig. 5 is a sequence flow illustrating the distance measurement process of FTM, Fig. 6 is a diagram showing the position estimation technique using trilateration, and Fig. 7 is a diagram illustrating distance correction between a reference beacon-based FTM AP and a tag. First, the distance to the AP is measured as a result of FTM. Then, the location of the composite tag is calculated using the measured distance. A trilateration algorithm is used at this stage. Furthermore, to ensure FTM accuracy, FTM accuracy is calculated by utilizing FTM signal information or by comparing FTM coordinate information with map polygons. Next, reference beacon-based FTM positioning correction is performed considering the NLOS environment. In this case, positioning is performed by correcting the measured distance values ​​(A, A') between the AP and the Tag based on the distance between the beacon and the AP (C, C') calculated based on the reference beacon location and the AP location, and the RSSI distance between the positioning tag and the reference beacon (B, B'). Additionally, distance value correction between the AP and the Tag is performed using an RSSI distance-based correction function.

[0036] Among positioning technologies, GPS-based systems receive GPS coordinates and perform error filtering. They also improve GPS accuracy through a correction function. Correction can be performed using a Kalman filter or by optimizing the speed of GPS coordinate correction, and accuracy is achieved by using GPS satellite position information or by comparing coordinate information with map polygons. Furthermore, GPS technology performs indoor and outdoor position determination functions; indoor position determination occurs when FTM accuracy is very high or GPS accuracy is very low, while outdoor position determination occurs when FTM accuracy is very low or GPS accuracy is very high. Figure 8 is a conceptual diagram illustrating GPS-based indoor and outdoor position determination. Unlike general cargo trucks, positioning technology for large unmanned vehicles (TPs, trailers) can result in a state where positioning is impossible depending on whether cargo is loaded. To address this, tags are installed at the front and rear of the unmanned vehicle to facilitate positioning, and a correction algorithm is applied to the two collected positioning locations. Positioning accuracy can be improved through the correction of the danger radius of the large vehicle, as shown in Figure 9.

[0037] Meanwhile, although not yet implemented, LiDAR is used as a laser technology-based crane positioning technology. LiDAR sensors capable of being utilized can detect the distance, direction, speed, temperature, material distribution, and concentration characteristics of an object by shining a laser light source onto the target. Furthermore, LiDAR sensors utilize the advantages of lasers, which can generally generate pulse signals with high energy density and short periods, to be used for more precise observation of atmospheric properties and distance measurement. For example, on the ground, simple forms of LiDAR sensor technology have been commercialized for long-distance measurement and enforcement of vehicle speed violations. Recently, however, its utility and importance are gradually increasing as it is being utilized as a core technology for laser scanners and 3D video cameras for 3D reverse engineering and future autonomous vehicles.

[0038] Here, the elliptical area setting of the S100 establishes an elliptical risk zone based on the unmanned vehicle's current location and direction of travel. By adjusting the size and shape of the risk zone according to the unmanned vehicle's direction of travel, the elliptical area setting effectively predicts the risk of collision in the direction the vehicle is moving. The direction of travel is set as the major axis of the ellipse to define a wide risk range in that direction. A high weight is applied to the major axis to prioritize consideration of potential collision risks in that direction. Conversely, the lateral direction of the unmanned vehicle is assumed to have a relatively low probability of collision and is set as the minor axis to define a narrow risk zone. This reflects the difference between the direction of travel and the lateral direction, thereby preventing unnecessary warnings. For example, if the unmanned vehicle moves quickly along a straight path, an elliptical area is formed along the major axis of the direction of travel, resulting in a wide area with a high probability of collision. Conversely, when the unmanned vehicle moves slowly, the elliptical area may become relatively smaller.

[0039] Next, the location of the worker is measured and the direction of movement of the worker is monitored (S110). This allows for determining whether the worker is in a dangerous location within an elliptical danger zone set on the unmanned vehicle. As previously explained, the worker's location is collected in real time through positioning technologies such as GPS, Wi-Fi, and BLE. This location information is used to evaluate the possibility of a collision by comparing it with the direction of travel of the unmanned vehicle. The worker's direction of movement is also predicted based on the location information. If the worker is moving in a direction that matches the direction of travel of the unmanned vehicle, the risk of a collision may increase. The worker's location and direction of movement information collected in S110 serve as key elements for calculating the collision risk and are reflected in the risk analysis along with weights in subsequent steps. Therefore, the possibility of the worker approaching the expected path of the unmanned vehicle can be determined and utilized in the risk calculation.

[0040] Then, the collision risk is precisely calculated by applying weights based on the location, speed, and direction of movement of the unmanned vehicle and the worker (S120). This provides a warning that is more precise and suitable for real-world situations than the existing method of simply providing a warning when within a certain distance.

[0041] Distance weighting is applied by setting weights based on the distance between the unmanned vehicle and the worker. The closer the distance, the higher the risk; for example, if the distance is within 5 meters, the weight is set to 2 times, and if the distance is within 10 meters, the weight is set to 1.5 times to increase the risk.

[0042] In addition, speed weighting is applied based on the speed of the unmanned vehicle. As the faster the unmanned vehicle moves, the higher the risk of collision, a weight is set based on speed to increase the risk level. For example, if the speed of the unmanned vehicle is 2 m / s or higher, the weight can be set to 1.5 times.

[0043] In addition, the application of direction-of-movement weighting assigns a weight based on the direction of movement because the risk of collision is high when a worker is located in the direction of the unmanned vehicle's movement. For example, if a worker is located in the direction of the unmanned vehicle's movement and is close to the unmanned vehicle, the weight is set to double to increase the risk.

[0044] For example, if a worker is moving within 3 meters of the direction in which the unmanned vehicle is moving and the speed of the unmanned vehicle is 2.5 m / s, a high risk is calculated by applying weights based on distance, speed, and direction of movement.

[0045] Subsequently, if the collision risk exceeds a set standard, warning notifications are provided in stages according to a risk level reflecting weights (S130). This classifies the risk level based on weights and adjusts the warning intensity accordingly. If the collision risk is low, a simple warning notification is provided to the operator to allow them to pay attention. If the risk is medium, a warning notification is provided to both the operator and the unmanned vehicle, and an avoidance path in a safe direction can be suggested to the operator. Additionally, if the collision risk is very high, a strong warning is issued to avoid the unmanned vehicle's path, and the speed of the unmanned vehicle can be reduced or temporarily stopped if necessary. For example, if an operator is located in the direction of travel of the unmanned vehicle and the vehicle is moving at a high speed, the system determines the risk to be high, provides a strong warning, and guides the operator along an avoidance path.

[0046] FIG. 2 is a diagram showing the configuration of a computer device equipped with a location information-based collision prevention application between an unmanned mobile vehicle and a worker according to the present invention.

[0047] Referring to FIG. 2, the location information-based collision prevention device (100) between an unmanned mobile vehicle and a worker according to the present invention communicates with a composite positioning system (300) to collect location information in real time, analyzes the collision risk based on this information, and provides a warning suitable for the dangerous situation. The location information-based mobile vehicle and worker collision prevention system refers to a structure in which the composite positioning system (300) is further included in the location information-based mobile vehicle and worker collision prevention device (100).

[0048] A location information-based collision avoidance device (100) between an unmanned mobile vehicle and a worker comprises a processor (110), a non-volatile storage unit (120) for storing programs and data, a volatile memory (130) for storing programs currently running, a communication unit (140) for communicating with other devices, and a bus, which is an internal communication channel between these devices. Programs currently running may include device drivers, operating systems, and various applications. Although not illustrated, the electronic device includes a power supply unit such as a battery.

[0049] The processor (110) is the central processing unit of the entire system, analyzes location information and collision risk, and determines warning notifications.

[0050] The storage unit (120) stores data related to collision risk analysis, location information of workers and unmanned vehicles, weight settings, etc.

[0051] The communication unit (140) receives real-time location information through data transmission and reception with the composite positioning system (300).

[0052] The memory (130) stores programs necessary for system operation, and these programs include functional modules such as a positioning prediction application (210), a collision risk analysis application (220), and a warning notification application (230). The positioning prediction application (210) sets an elliptical area centered on the direction of travel of the unmanned vehicle and predicts the expected path of the vehicle. The collision risk analysis application (220) calculates the collision risk by applying weights based on the location of the worker within the elliptical area, the speed and direction of travel of the vehicle, etc. The warning notification application (230) provides a warning to the worker and the unmanned vehicle according to the risk level based on the weights when the collision risk exceeds a certain standard.

[0053] FIG. 3 shows the configuration of a composite positioning system (300) in a collision prevention system between an unmanned mobile vehicle and a worker based on location information according to the present invention, and FIG. 4 is a module configuration diagram showing a composite tag of a positioning collection device (310) in the composite positioning system (300) according to FIG. 3.

[0054] Referring to FIGS. 3 and 4, the composite positioning system (300) includes a positioning collection device (310) and a real-time location positioning system (320), and the positioning collection device (310) may be composed of a composite tag module as shown in FIG. 4.

[0055] The positioning collection equipment (310) of the composite positioning system (300) is a device that generates radio waves as an element for estimating location and providing safety alerts, and includes a composite tag attached to a mobile unmanned vehicle or a worker. For example, it can be installed inside a mobile unmanned vehicle such as a forklift or transporter, and the area where danger is expected can be notified by a warning sound, a warning light, or a navigation application. It is configured to be small enough to be attached to a worker's work helmet, and the area where danger is expected can be notified by a warning sound or vibration. Meanwhile, essential products such as an anchor for indoor positioning, a laser measuring device for a crane (one of the unmanned vehicles), and a drone for image collection can be configured as options. The safety alert in the composite positioning system (300) consists of a positioning tag device and a positioning anchor product. In particular, the positioning anchor is configured with a USB connector so that it can be connected to an existing WiFi AP, allowing the use of an existing AP without installing a separate AP. That is, the tag can determine whether there is movement by performing WiFi FTM, receiving GPS, and using an inertial sensor that detects movement. Wi-Fi FTM performance by the positioning collection equipment (310) refers to the transmission and reception of radio waves between a tag and a Wi-Fi AP (not shown), which is a real-time location positioning system (320). That is, the tag can provide radio wave strength, GPS reception information, and direction of movement, which are radio wave transmission and reception signals, to the real-time location positioning system (320) through the AP. Accordingly, the composite positioning system (300) is a positioning system that reflects the physical environment within an industrial site and utilizes N positioning technologies. For example, in the case of outdoor environments, it may be a system that resolves GPS error problems by applying map matching technology, secures positioning accuracy with RTT-based FTM technology effective in NLOS environments in indoor environments, and applies proximity movement determination technology by applying BLE technology.Thus, positioning selection requires comprehensive outdoor and indoor positioning technology due to the characteristics of unmanned vehicles and operators; therefore, positioning is performed using a composite location tag capable of applying N combined positioning technologies such as GPS, FTM, and BLE. In outdoor areas, since positioning errors occur due to the industrial environment when relying solely on GPS signals, position correction technology based on map matching utilizing network data is applied to minimize GPS errors. For indoor areas, a composite positioning engine equipped with FTM (Fine Time Measurement) technology based on RTT (Round Trip Time) information can be applied in accordance with the IEEE 802.11.mc standard, which offers relatively high positioning performance and compatibility with commercial Wi-Fi APs (802.a / b / n). Additionally, for large unmanned vehicles, positioning with a single GPS unit results in significant errors due to the vehicle's characteristics; therefore, positioning engine technology capable of calculating merged position values ​​by installing two GPS units is applied.

[0056] The positioning prediction application (210) can receive positioning information from the composite positioning system (300). Of course, a data interface device (not shown), etc., can receive this and appropriately transmit it to the positioning prediction application (210). The data interface device can act as a buffer in the process of transmitting positioning information to the positioning prediction application (210). The positioning prediction application (210) performs hybrid positioning of the tag using FTM radio signals, movement direction information, and GPS measurement information, and performs positioning prediction by determining indoor / outdoor based on GPS information and classifying it as identified / non-identified according to the attributes of the positioning information. For example, because the content of the data regarding whether a worker is identified or non-identified is different, the positioning prediction technology is applied differently. That is, if identified, movement data linked to the work plan of the identified target can be analyzed by AI to predict movement patterns and movement paths, and if non-identified, the expected movement radius is predicted based on movement speed and direction. Here, if the attribute of the positioning information of the identified target is identified, it is possible to predict the location while reflecting the work plan while predicting AI-based location movement. Meanwhile, in the case of non-identification, positioning is predicted based on real-time location. Then, an elliptical area is established centered on the predicted direction of travel of the unmanned vehicle, and the expected path of the vehicle is predicted.

[0057] The collision risk analysis application (220) is linked with the positioning prediction application and analyzes the real-time risk level using weights based on spatial, situational, and worker safety indices when positioning is predicted according to positioning information. That is, the collision risk is calculated by applying weights based on the location of the worker within the elliptical area, the speed and direction of travel of the moving object. At this time, the analysis may also be performed according to case-by-case avoidance scenarios based on accident case analysis. For example, accident cases can be classified into collisions, impacts, and crushing between unmanned moving objects, or between an unmanned moving object and a worker. Here, unmanned moving objects include cranes, transporters, forklifts and forklifts, trailers, and cargo trucks operated at industrial sites, and cargo trucks entering and exiting from the outside are also included in the analysis cases. When the risk level is analyzed, collision prevention information is provided by the warning notification application (230). If the collision risk level exceeds a certain standard, a warning is provided to the worker and the moving object according to the risk grade based on the weights. For example, for mobile objects with defined routes, such as transporters and large trailers, notification services can be provided to enable alerts regarding hazardous areas and avoidance guidance via navigation applications. Furthermore, in environments where workers, such as forklifts or operators, work in close proximity alerts are provided through real-time location prediction between the mobile object and the operator. For other cargo vehicles entering from the outside, route guidance services based on hazardous area warnings and avoidance routes are provided by downloading a navigation application. For instance, based on identified mobile object locations and AI predictions, virtual fences or virtual signals are introduced around hazardous areas to alert mobile objects and operators approaching potential collision zones, or long-distance avoidance and alert information is provided via navigation applications, offering routes to avoid hazardous areas.In addition, for close-range avoidance between a worker, such as a forklift, and a moving object, BLE technology is used to provide close-range avoidance and notification information that offers a danger warning alert when the object or worker approaches within a specific distance (1m to 2m). Furthermore, BLE switching OTA (Over the Air) information for close-range avoidance notifications can also be provided depending on the stage of entry of the moving object and the worker into the danger zone.

[0058] As described above, although the present invention has been explained by limited embodiments and drawings, the present invention is not limited thereto, and it is obvious that various modifications and variations are possible within the scope of the technical spirit of the present invention and the equivalent scope of the claims described below by those skilled in the art to which the present invention belongs.

Claims

1. As a method for a location information-based collision avoidance device to prevent collisions between an unmanned mobile vehicle and a worker in an industrial site, (a) A step of setting an elliptical area based on the current position and direction of travel of the unmanned vehicle; (b) a step of measuring the worker's position and monitoring the direction of movement; (c) a step of predicting the collision risk by applying weights according to the position, speed, and direction of travel of the worker and the unmanned vehicle within the elliptical area; and, (d) If the above collision risk level exceeds a certain standard, providing a warning notification according to the risk level reflecting the above weights A location information-based collision prevention method between an unmanned mobile vehicle and a worker, including 2. In Claim 1, The elliptical region setting of step (a) above is formed by making the direction of movement of the unmanned vehicle the major axis and the lateral direction the minor axis. A location information-based collision prevention method for unmanned vehicles and workers characterized by the following.

3. In Claim 1, Applying a higher weight to the major axis of the elliptical region according to the direction of movement of the unmanned mobile body A location information-based collision prevention method for unmanned vehicles and workers characterized by the following.

4. In Claim 1, Step (c) above predicts the possibility of a worker entering the elliptical area of ​​the unmanned vehicle and provides a collision risk warning according to a risk level when the worker is located within the elliptical area. A location information-based collision prevention method for unmanned vehicles and workers characterized by the following.

5. In Claim 1, In step (d) above, when the operator approaches within a certain distance, the path of the unmanned vehicle is reset or an avoidance path is suggested to prevent a collision. A location information-based collision prevention method for unmanned vehicles and workers characterized by the following.

6. In Claim 1, The above step (a) includes the step of setting an elliptical measurement area based on GPS, Wi-Fi, and BLE signals according to the real-time location and direction of travel of the unmanned vehicle, and further includes the step of correcting the error of the elliptical measurement according to the indoor and outdoor location environment. A location information-based collision prevention method for unmanned vehicles and workers characterized by the following.

7. A computer program stored on a non-transient storage medium for preventing collisions between an unmanned mobile vehicle and a worker based on location information, It is stored on a non-transient storage medium, and by a processor, (a) A step of setting an elliptical area based on the current position and direction of travel of the unmanned vehicle; (b) a step of measuring the worker's position and monitoring the direction of movement; (c) a step of predicting the collision risk by applying weights according to the position, speed, and direction of travel of the worker and the unmanned vehicle within the elliptical area; and, (d) If the above collision risk level exceeds a certain standard, providing a warning notification according to the risk level reflecting the above weights A computer program stored on a non-transient storage medium for performing a collision avoidance method between an unmanned mobile vehicle and a worker based on location information, which includes a command to cause to be executed.

8. A device for performing a method to prevent collisions between an unmanned mobile vehicle and a worker based on location information, (a) A step of setting an elliptical area based on the current position and direction of travel of the unmanned vehicle; (b) a step of measuring the worker's position and monitoring the direction of movement; (c) a step of predicting the collision risk by applying weights according to the position, speed, and direction of travel of the worker and the unmanned vehicle within the elliptical area; and, (d) If the above collision risk level exceeds a certain standard, providing a warning notification according to the risk level reflecting the above weights A location information-based collision avoidance device for unmanned vehicles and workers that enables the operation of

Images