KR20240006753A - Vehicle control method and apparatus for preventing collision between electric scooter and vehicle - Google Patents

Abstract

Disclosed are a vehicle control method and a device for preventing a collision between an electric kickboard and a vehicle. According to one embodiment of the present disclosure, the present invention provides the steps of: obtaining information about an object around a vehicle; determining whether the object is an electric kickboard based on the information about the object being an image; issuing a control command based on the object being an electric kickboard; and controlling at least one of the speed and direction of the vehicle based on the control command.

Description

Vehicle control method and device for preventing collision between electric kickboard and vehicle {VEHICLE CONTROL METHOD AND APPARATUS FOR PREVENTING COLLISION BETWEEN ELECTRIC SCOOTER AND VEHICLE}

The present invention relates to a vehicle control method and device for preventing a collision between an electric kickboard and a vehicle. More specifically, a vehicle control method for preventing a collision with an electric kickboard by detecting the electric kickboard and controlling the speed and distance of the vehicle. and devices.

The content described below simply provides background information related to this embodiment and does not constitute prior art.

In order to increase the safety and convenience of drivers using vehicles, the development of technology that integrates various sensors and electronic devices into vehicles is accelerating. Accordingly, autonomous driving, which allows the vehicle to drive on the road on its own without driver intervention, has become possible.

Meanwhile, as the number of users of electric kickboards has rapidly increased recently and the number of electric kickboards on roads and alleys has increased, accidents related to electric kickboards are increasing. Currently, the autonomous driving system does not operate in relation to electric kickboards, so the need for an autonomous driving system to prevent collisions between electric kickboards and vehicles is increasing.

The present disclosure can recognize an electric kickboard and prevent a collision between the electric kickboard and a vehicle.

Additionally, according to one embodiment, the rear view of the electric kickboard can be recognized.

Additionally, according to one embodiment, the side image of the electric kickboard can be stored and recognized.

Additionally, according to one embodiment, the speed and direction of the vehicle can be adjusted by receiving data from the electric kickboard.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

According to the present disclosure, a vehicle control method includes obtaining information about an object around the vehicle, determining whether the object is an electric kickboard based on the information about the object being an image, and determining whether the object is an electric kickboard. Based on the kickboard, it may include issuing a control command and adjusting at least one of the speed and direction of the vehicle based on the control command.

According to the present disclosure, a vehicle control device includes an input unit that acquires information about an object around the vehicle, determines whether the object is an electric kickboard based on the information about the object being an image, and determines whether the object is an electric kickboard. Based on this, it may include an autonomous driving integrated processing unit that issues a control command, and a vehicle control output unit that adjusts at least one of the speed and direction of the vehicle based on the control command.

According to the present disclosure, there is an effect of preventing a collision between an electric kickboard and a vehicle by recognizing the electric kickboard.

Additionally, according to one embodiment, there is an effect of recognizing the back of the electric kickboard.

Additionally, according to one embodiment, there is an effect of storing and recognizing the side image of the electric kickboard.

Additionally, according to one embodiment, there is an effect of controlling the speed and direction of the vehicle by receiving data from the electric kickboard.

The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. will be.

1 is a block diagram of a vehicle control device for preventing a collision with an electric kickboard, according to an embodiment of the present disclosure.
Figure 2 is a diagram for explaining the rear view of an electric kickboard according to an embodiment of the present disclosure.
Figure 3 is a diagram for explaining a side image of an electric kickboard according to an embodiment of the present disclosure.
FIG. 4 is a diagram illustrating a process for preventing a collision with a vehicle by recognizing the rear of an electric kickboard, according to an embodiment of the present disclosure.
FIG. 5 is a diagram illustrating a process for preventing collision with a vehicle by recognizing the side of an electric kickboard, according to an embodiment of the present disclosure.
FIG. 6 is a diagram illustrating a process for preventing a collision with a vehicle by receiving data from an electric kickboard, according to an embodiment of the present disclosure.
FIG. 7 is a diagram illustrating a method for predicting the location of a vehicle based on machine learning, according to an embodiment of the present disclosure.
FIG. 8 is a diagram for explaining a vehicle control method according to an embodiment of the present disclosure.

Hereinafter, some embodiments of the present disclosure will be described in detail using exemplary drawings. When adding reference signs to components in each drawing, it should be noted that the same components are given the same reference numerals as much as possible even if they are shown in different drawings. Additionally, in describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present disclosure, the detailed description will be omitted.

In describing the components of the embodiment according to the present disclosure, symbols such as first, second, i), ii), a), and b) may be used. These codes are only used to distinguish the component from other components, and the nature, sequence, or order of the component is not limited by the code. In the specification, when a part is said to 'include' or 'have' a certain element, this means that it does not exclude other elements, but may further include other elements, unless explicitly stated to the contrary. .

The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiments in which the present disclosure may be practiced.

1 is a block diagram of a vehicle control device for preventing a collision with an electric kickboard, according to an embodiment of the present disclosure.

Referring to FIG. 1, the input unit 110 can obtain information about the electric kickboard using a camera, ultrasonic waves, Bluetooth, radar, or navigation. Information about the electric kickboard may include a rear image, a front image, and a side image of the electric kickboard, as well as the location and speed of the electric kickboard. The input unit 110 may obtain information about the electric kickboard and transmit it to the information input processing unit 120 inside the vehicle. The vehicle internal information input processing unit 120 can process information about the electric kickboard. The vehicle internal information input processing unit 120 may transmit information about the processed electric kickboard to the autonomous driving integrated processing unit 130. The autonomous driving integrated processing unit 130 may issue a control command to the vehicle control output unit 140 using information about the processed electric kickboard.

The autonomous driving integrated processing unit 130 may determine whether the photographed object is the back of an electric kickboard and recognize the electric kickboard. The autonomous driving integrated processing unit 130 may compare the acquired image with the side image of the electric kickboard stored internally. The autonomous driving integrated processing unit 130 may determine the image acquired according to the comparison result to be a side image of the electric kickboard. Accordingly, the electric kickboard can be recognized. The autonomous driving integrated processing unit 130 may determine the expected location of the electric kickboard using the position and speed data received from the electric kickboard. A vehicle speed control command can be generated based on the estimated location of the electric kickboard and the location of the vehicle. Control commands may be transmitted to the vehicle control output unit 140. The autonomous driving integrated processing unit 130 may include a machine learning-based vehicle location prediction model. The autonomous driving integrated processing unit 130 may be equipped with a learning unit (not shown) to train a machine learning-based vehicle location prediction model in advance. The learning unit can pre-train the learning model using supervised learning, unsupervised learning, semi-supervised learning, and/or reinforcement learning. . Here, the specific method by which the learning unit trains the learning model based on the learning data is common in the field, so detailed explanation will be omitted. However, the present disclosure is not limited to these embodiments. The autonomous driving integrated processing unit 130 may include various AI-based learning models in addition to the machine learning-based vehicle location prediction model.

The vehicle control output unit 140 may transmit a control signal using the control command received from the autonomous driving integrated processing unit 130. The engine, braking, and AVN (Audio Video Navigation) can be controlled according to the corresponding control signal. Depending on the results of this control, a collision between the electric kickboard and a vehicle can be prevented.

Figure 2 is a diagram for explaining the rear view of an electric kickboard according to an embodiment of the present disclosure. Existing autonomous driving systems operate to prevent collisions with vehicles only for pedestrians. Additionally, the electric pedestrian collision prevention system does not operate when pedestrians move at a certain speed or higher. The vehicle control device according to the present disclosure can determine the rear view of the electric quick board by using the rear view of the person, whether the lower body is moving, and the wheel portion on the ground.

Referring to FIG. 2, a camera mounted on a vehicle can capture objects passing around the vehicle. The vehicle control device can detect the rear view 210 of a person from a photographed object. In the back view 210 of a person, if the lower body 220 does not move and the part 230 that touches the ground is the wheel, the photographed object may be recognized as the back of an electric kickboard.

Figure 3 is a diagram for explaining a side image of an electric kickboard according to an embodiment of the present disclosure.

Referring to FIG. 3, a camera mounted on a vehicle can capture objects passing around the vehicle. Through this shooting, the side image 310 of the electric kickboard can be converted into big data and stored in the vehicle's memory. Thereafter, the stored side image 310 of the electric kickboard may be compared with the image of the photographed object. If the comparison results determine that they are identical, the image of the captured object may be recognized as the side of the electric kickboard.

FIG. 4 is a diagram illustrating a process for preventing a collision with a vehicle by recognizing the rear of an electric kickboard, according to an embodiment of the present disclosure.

Referring to FIG. 4, the vehicle control device can detect the rear view of a person (S410). The vehicle control device can photograph objects around the vehicle using a camera. In the captured image, an object can be detected as the back of a person. In addition, when an object is detected as the back of a person in the captured image, the vehicle control device can determine whether the part of the photographed object that touches the ground without moving the lower body is a wheel (S420). If the lower body moves or the part that touches the ground is not a wheel (S420-NO), the object may be judged not to be an electric quickboard (S430). If the lower body does not move and the part that touches the ground is a wheel (S420-YES), the object may be judged to be the back of an electric quickboard (S440).

FIG. 5 is a diagram illustrating a process for preventing collision with a vehicle by recognizing the side of an electric kickboard, according to an embodiment of the present disclosure.

Referring to FIG. 5, the vehicle control device can detect objects passing to the left and right of the vehicle (S510). The vehicle control device can photograph objects around the vehicle using a camera. And, the vehicle control device can determine whether the stored side image of the electric kickboard and the detected image are the same (S520). The stored side image of the electric kickboard may correspond to what is stored in the vehicle's memory. If the stored side image of the electric kickboard and the detected image are not the same (S520-NO), the object may be determined not to be an electric kickboard (S530). If the stored side image of the electric kickboard and the detected image are the same (S520-YES), the object may be judged to be the side of the electric kickboard (S540).

FIG. 6 is a diagram illustrating a process for preventing a collision with a vehicle by receiving data from an electric kickboard, according to an embodiment of the present disclosure.

Referring to FIG. 6, the vehicle control device can receive data about the position and speed transmitted by the electric kickboard (S610). The electric kickboard may include a transceiver and Bluetooth or GPS capable of communication. The electric kickboard includes GPS or a transceiver, so it can be controlled with an app. When an electric kickboard enters a road where vehicles travel, the electric kickboard can automatically send data about its location and speed to vehicles within 20 meters around it. Whether the electric kickboard enters a road where vehicles travel can be determined through GPS. Electric kickboards can send data about their location and speed to surrounding vehicles using Bluetooth. Additionally, the vehicle control device may determine the expected location of the electric kickboard using data on the position and speed of the electric kickboard (S620). The vehicle control device can determine the expected location of the electric kickboard by analyzing data about the position and speed of the electric kickboard. Data on the position and speed of the electric kickboard can be analyzed in the autonomous driving integrated processing unit. Additionally, the vehicle control device can control the speed and direction of the vehicle by comparing the expected position of the electric kickboard with the position of the own vehicle (S630). The vehicle control device can prevent a collision between the electric kickboard and the vehicle by adjusting the speed and direction of the vehicle.

FIG. 7 is a diagram illustrating a method for predicting the location of a vehicle based on machine learning, according to an embodiment of the present disclosure. Autonomous vehicles can obtain data on dangerous vehicles ahead. Data on hazardous vehicles may include the hazardous vehicle's shape, size, distance traveled per hour, and the distance between the autonomous vehicle and the hazardous vehicle. The machine learning-based vehicle location prediction model can calculate the expected collision time using the acquired data on dangerous vehicles. Autonomous vehicles can acquire data on dangerous vehicles based on a specific range.

Referring to FIG. 7, in relation to embodiment 1, a dangerous vehicle traveling in front of the autonomous vehicle may change to the left lane. Accordingly, the right rear and side parts of the dangerous vehicle may be included in the specific range. Autonomous vehicles can obtain data on dangerous vehicles changing to the left lane in front. Data on dangerous vehicles can be acquired over time. Through the data of the dangerous vehicle, the expected collision time between the autonomous vehicle and the dangerous vehicle can be calculated. Here, the dangerous vehicle can be replaced by an electric kickboard.

Regarding embodiment number 2, a dangerous vehicle may drive in front of the autonomous vehicle. Accordingly, the entire rear part of the dangerous vehicle may be included in a certain range. Autonomous vehicles can obtain data on dangerous vehicles driving in front. Data on dangerous vehicles can be obtained over time. Through the data of the dangerous vehicle, the expected collision time between the autonomous vehicle and the dangerous vehicle can be calculated. Here, the dangerous vehicle can be replaced by an electric kickboard.

Regarding embodiment number 3, the autonomous vehicle can make a left turn. A dangerous vehicle can also turn left in front of an autonomous vehicle turning left. Accordingly, the right rear and side parts of the dangerous vehicle may be included in the specific range. Autonomous vehicles can acquire data on dangerous vehicles turning left in front. Data on dangerous vehicles can be acquired over time. Through the data of the dangerous vehicle, the expected collision time between the autonomous vehicle and the dangerous vehicle can be calculated. Here, the dangerous vehicle can be replaced by an electric kickboard. However, the present disclosure is not limited to these embodiments. Autonomous vehicles can acquire data on dangerous vehicles changing to the right lane in front and dangerous vehicles turning right in front.

FIG. 8 is a diagram for explaining a vehicle control method according to an embodiment of the present disclosure.

Referring to FIG. 8, the vehicle control device can obtain information about objects around the vehicle (S810). Information about the object may be obtained based on at least one of a camera, Bluetooth, navigation, ultrasonic waves, and radar. Additionally, the vehicle control device may determine whether the object is an electric kickboard based on the fact that the information about the object is an image (S820). The expected position of the electric kickboard may be calculated based on the fact that the information about the object is at least one of the position and speed of the electric kickboard. A control command is issued by comparing the expected position of the electric kickboard with the position of the vehicle, and at least one of the speed and direction of the vehicle may be adjusted based on the control command. The expected location of the electric kickboard can be calculated using a learning model. The learning model may correspond to a machine learning-based vehicle location prediction model.

Determining whether an object is an electric kickboard can correspond to detecting the back of a person within the image of the object, determining whether the part that touches the ground without the person's lower body moving is a wheel, and determining whether the object is the back of an electric kickboard. there is. Alternatively, determining whether an object is an electric kickboard may correspond to comparing the image of the object with a stored side image of the electric kickboard and determining whether the object is the side of the electric kickboard based on the comparison result. Additionally, the vehicle control device may issue a control command based on the fact that the object is an electric kickboard (S830). Additionally, the vehicle control device may adjust at least one of the speed and direction of the vehicle based on the control command (S840).

Each component of the device or method according to the present invention may be implemented as hardware or software, or may be implemented as a combination of hardware and software. Additionally, the function of each component may be implemented as software and a microprocessor may be implemented to execute the function of the software corresponding to each component.

Various implementations of the systems and techniques described herein may include digital electronic circuits, integrated circuits, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), computer hardware, firmware, software, and/or these. It can be realized through combination. These various implementations may include being implemented as one or more computer programs executable on a programmable system. The programmable system includes at least one programmable processor (which may be a special purpose processor) coupled to receive data and instructions from and transmit data and instructions to a storage system, at least one input device, and at least one output device. or may be a general-purpose processor). Computer programs (also known as programs, software, software applications or code) contain instructions for a programmable processor and are stored on a "computer-readable medium."

Computer-readable recording media include all types of recording devices that store data that can be read by a computer system. These computer-readable recording media are non-volatile or non-transitory such as ROM, CD-ROM, magnetic tape, floppy disk, memory card, hard disk, magneto-optical disk, and storage device. It may be a medium, and may further include a transitory medium such as a data transmission medium. Additionally, the computer-readable recording medium may be distributed in a computer system connected to a network, and the computer-readable code may be stored and executed in a distributed manner.

In the flowchart/timing diagram of this specification, each process is described as being executed sequentially, but this is merely an illustrative explanation of the technical idea of an embodiment of the present disclosure. In other words, a person skilled in the art to which an embodiment of the present disclosure pertains may change the order described in the flowchart/timing diagram and execute one of the processes without departing from the essential characteristics of the embodiment of the present disclosure. Since the above processes can be applied in various modifications and variations by executing them in parallel, the flowchart/timing diagram is not limited to a time series order.

The above description is merely an illustrative explanation of the technical idea of the present embodiment, and those skilled in the art will be able to make various modifications and variations without departing from the essential characteristics of the present embodiment. Accordingly, the present embodiments are not intended to limit the technical idea of the present embodiment, but rather to explain it, and the scope of the technical idea of the present embodiment is not limited by these examples. The scope of protection of this embodiment should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be interpreted as being included in the scope of rights of this embodiment.

Claims (14)

Obtaining information about objects around the vehicle;
Determining whether the object is an electric kickboard based on the information about the object being an image;
issuing a control command based on the object being an electric kickboard; and
A vehicle control method comprising adjusting at least one of speed and direction of the vehicle based on the control command. According to paragraph 1,
Calculating an expected position of the electric kickboard based on the fact that the information about the object is at least one of the position and speed of the electric kickboard;
Comparing the expected location of the electric kickboard and the location of the vehicle;
issuing a control command based on the comparison result; and
A vehicle control method comprising adjusting at least one of speed and direction of the vehicle based on the control command. According to paragraph 1,
The step of determining whether the object is an electric kickboard is:
Detecting the back of a person in the image of the object;
determining whether the part that touches the ground without the person's lower body moving is a wheel; and
A vehicle control method comprising determining whether the object is the rear of the electric kickboard. According to paragraph 1,
The step of determining whether the object is an electric kickboard is,
Comparing the image of the object with a stored side image of the electric kickboard; and
Based on the comparison result, a vehicle control method comprising determining whether the object is a side of the electric kickboard. According to paragraph 1,
A vehicle control method in which information about the object is obtained based on at least one of a camera, Bluetooth, navigation, ultrasonic waves, and radar. According to paragraph 2,
A vehicle control method in which the expected position of the electric kickboard is calculated using a learning model. According to clause 6,
The learning model is a vehicle control method that is a machine learning-based vehicle location prediction model. An input unit that obtains information about objects around the vehicle;
An autonomous driving integrated processing unit that determines whether the object is an electric kickboard based on the information about the object being an image and issues a control command based on the fact that the object is an electric kickboard; and
A vehicle control device comprising a vehicle control output unit that adjusts at least one of speed and direction of the vehicle based on the control command. According to clause 8,
The autonomous driving integrated processing unit,
Calculate the expected position of the electric kickboard based on the fact that the information about the object is at least one of the position and speed of the electric kickboard,
Compare the expected location of the electric kickboard with the location of the vehicle,
A vehicle control device that issues a control command based on the comparison result. According to clause 8,
The autonomous driving integrated processing unit,
Determine whether the object is an electric kickboard,
Detect the back of a person within the image of the object,
Determine whether the part that touches the ground without the person's lower body moving is a wheel,
A vehicle control device that determines whether the object is the back of the electric kickboard. According to clause 8,
The autonomous driving integrated processing unit,
Determine whether the object is an electric kickboard,
Compare the image of the object with the stored side image of the electric kickboard,
A vehicle control device that determines whether the object is a side of the electric kickboard, based on the comparison result. According to clause 8,
A vehicle control device in which information about the object is obtained based on at least one of a camera, Bluetooth, navigation, ultrasonic waves, and radar. According to clause 9,
A vehicle control method in which the expected position of the electric kickboard is calculated using a learning model. According to clause 13,
The learning model is a vehicle control method that is a machine learning-based vehicle location prediction model.

Images