KR20240017183A - Method And Apparatus for Controlling Autonomous Driving Vehicle - Google Patents

Abstract

Disclosed is a control method for an autonomous vehicle.
According to an embodiment of the present disclosure, in a method of controlling an autonomous vehicle (hereinafter referred to as 'vehicle') driving on a narrow road, a pressure sensor disposed in the narrow road is sent from a central server before the vehicle enters the narrow road. A process of acquiring at least one of pressure distribution and pressure value of parked vehicles and obstacles on the road based on a pressure sensor; A process of calculating the type, speed information, and location information of the parked vehicle and the obstacle based on one or more of pressure distribution and pressure values of the parked vehicle and the obstacle; A process of controlling driving of the vehicle based on the type of parked vehicle and obstacle, the speed information, and the location information; When the vehicle travels on the road, storing images of the path the vehicle has taken and the surrounding space; And when an opposing vehicle traveling in a direction opposite to the driving direction of the vehicle in front of the vehicle enters the road, providing a control method for an autonomous vehicle including a process of the vehicle driving evasively based on the image. do.

Description

Control device for autonomous vehicle and its control method {Method And Apparatus for Controlling Autonomous Driving Vehicle}

This disclosure relates to a control device and method for controlling an autonomous vehicle.

The content described in this section simply provides background information for the present disclosure and does not constitute prior art.

In order to increase the safety and convenience of users driving vehicles, the development of technology for incorporating various sensors and electronic devices into vehicles is accelerating.

The autonomous driving system is a system that allows the vehicle to recognize its surroundings and vehicle status without driver intervention, and automatically drive to a designated destination.

When an autonomous vehicle drives on a narrow road that only allows one vehicle to enter, for example, an alley, situations may occur where the vehicle cannot enter the alley or the vehicle is damaged due to parked vehicles and obstacles placed within the alley. there is. Therefore, an autonomous driving system tailored to specific situations such as narrow roads is needed, rather than an autonomous driving system that operates on general roads.

An autonomous driving system is needed that can determine whether a vehicle can enter the road and respond to specific situations that occur while the vehicle is driving on an alley.

A control device and a control method for an autonomous vehicle according to an embodiment are an autonomous driving system for a vehicle that runs on a narrow road based on location information of parked vehicles and obstacles placed on the narrow road by installing a pressure sensor in the narrow road. can be implemented.

The control device and control method for an autonomous vehicle according to an embodiment can implement various scenario control systems to respond to specific situations when the vehicle is driving on a small road.

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 an embodiment of the present disclosure, in a method of controlling an autonomous vehicle (hereinafter referred to as 'vehicle') driving on a narrow road, a pressure sensor disposed in the narrow road is sent from a central server before the vehicle enters the narrow road. A process of acquiring at least one of pressure distribution and pressure value of parked vehicles and obstacles on the road based on a pressure sensor; A process of calculating the type, speed information, and location information of the parked vehicle and the obstacle based on one or more of pressure distribution and pressure values of the parked vehicle and the obstacle; A process of controlling driving of the vehicle based on the type of parked vehicle and obstacle, the speed information, and the location information; When the vehicle travels on the road, storing images of the path the vehicle has taken and the surrounding space; And when an opposing vehicle traveling in a direction opposite to the driving direction of the vehicle in front of the vehicle enters the road, providing a control method for an autonomous vehicle including a process of the vehicle driving evasively based on the image. do.

According to an embodiment of the present disclosure, an image around the road is acquired based on road information obtained from at least one of a camera, a navigation device, a communication unit, and a sensor unit, and the location of at least one obstacle and driving information of the other vehicle are acquired. acquisition department to acquire; And a control unit that controls the driving of the vehicle based on the image around the road, the location of the obstacle, and the driving information of the other vehicle, wherein the acquisition unit determines the pressure distribution and pressure value of the road received from the central server. A control device for an autonomous vehicle is provided that receives and obtains location and driving information of obstacles and other vehicles located on the road.

According to one embodiment, the control device and control method for an autonomous vehicle can implement an autonomous driving system for a vehicle driving on a road based on location information of parked vehicles and obstacles placed on the road by installing a pressure sensor in the road. There is an effect.

According to one embodiment, the control device and control method for an autonomous vehicle have the effect of implementing various control systems to respond to specific situations when the vehicle is driving on a small road.

1 is a functional block diagram of an autonomous driving control unit according to an embodiment of the present disclosure.
Figure 2 is a flowchart showing a control method of an autonomous vehicle according to an embodiment of the present disclosure.
FIG. 3 is a flowchart showing process S204 of FIG. 2 in detail.
FIG. 4 is a flowchart showing process S208 of FIG. 2 in detail.
Figure 5 is a flowchart showing process S408 of Figure 4 in detail.

Hereinafter, some embodiments of the present disclosure will be described in detail through illustrative 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. .

1 is a functional block diagram of an autonomous driving control unit according to an embodiment of the present disclosure.

Referring to FIG. 1, the autonomous driving control unit 100 may include some or all of a collection unit 110, a control device 120, and a driving unit 130.

The collection unit 110 includes at least one of a navigation device 112, a camera 114, a communication unit 116, and a sensor unit 118.

The navigation device 112 estimates the location of the vehicle and provides road information based on the estimated location. Specifically, the navigation device 112 may receive satellite signals using a GPS receiver included in a global navigation system (GPS) and estimate the location of the vehicle using the satellite signals.

The navigation device 112 may provide information about the road on which the vehicle is located. Road information includes at least one of road direction, road curvature, road speed limit information, road type information, number of lanes, lane-specific characteristic information, or road section-specific characteristic information. Here, road type information includes general roads, highways, unpaved roads, alleys, etc. Characteristic information for each lane includes exclusive left turn lanes, straight-only lanes, right turn-only lanes, and bus-only lanes. Information on characteristics of each area includes child protection areas, accident-prone areas, etc. The navigation device 112 can provide road information to the occupants and the control device 120. Road information can be stored as map information in the navigation device 112.

The map information may be either a navigation map or a high definition map (HD map).

A navigation map includes a node indicating a point where at least two roads meet and a link connecting the two nodes. The navigation map may include geographic information, road information, lane information, building information, or signal information.

Precision maps contain more detailed data than navigation maps. A precision map may include lane information, lane boundary information, stop line locations, traffic light locations, signal sequences, or intersection information at a very precise level. A precision map may include basic road information, surrounding environment information, detailed road environment information, or dynamic road situation information. Detailed road environment information may include static information such as terrain elevation, curvature, lanes, lane center lines, regulation lines, road boundaries, road center lines, traffic signs, road surface signs, road shape and height, and lane width. Dynamic road situation information may include traffic jams, accident sections, construction sections, etc. A precision map may include 3D road surrounding environment information, geometric information such as road shape or facility structure, and semantic information such as traffic signs or lane marks.

The camera 114 captures scenes around the vehicle as images. The camera 114 can detect traffic signs in an image and process information displayed on the traffic signs.

Specifically, the camera 114 can acquire an image from the front of the vehicle. Cameras 114 can be additionally placed on the sides and rear. The camera 114 can acquire not only the front, but also side and rear images of the vehicle.

The camera 114 may transmit acquired image information to the control device 120 or process the image information.

When the camera 114 processes image information, the camera 114 may include an image sensor and an image processing module. The camera 114 can process still images or moving images obtained by an image sensor, for example, a complementary metal-oxide-semiconductor (CMOS) or a charge-coupled device (CCD). The image processing module can process still images or moving images obtained using an image sensor, extract necessary information, and transmit the extracted information to the control device 120.

The camera 114 may perform some functions of the control device 120. The camera 114 detects the path taken by the vehicle and the situation of the narrow road from the acquired image. For example, when a vehicle enters a narrow road and there is an opposing vehicle ahead, the vehicle can drive backwards based on the path it has taken. Here, 'narrow road' means a road with a width of, for example, 3 to 5 m that can normally accommodate one vehicle. 'Narrow road' is hereinafter referred to as 'narrow road'.

The communication unit 116 can communicate with servers or other vehicles.

The communication unit 116 may receive driving information of other vehicles or may receive driving information of other vehicles using a server. When the server processes driving information of other vehicles, the communication unit 116 may receive the driving information processed by the server.

The communication unit 116 may receive path information from a central server (not shown) that receives the pressure distribution and pressure value of an object located in the path using a pressure sensor (not shown) disposed in the path. Here, the pressure distribution of the object is determined by a pressure sensor placed in the path measuring the load of the object, and the range in which the load of the object is recognized is the weight distribution. Additionally, the pressure value is the weight of the object measured by the pressure sensor placed in the furnace.

The communication unit 116 can output the object type, speed information, and distance information using the path information received from the central server.

The communication unit 116 may include an internal communication unit and an external communication unit.

The internal communication unit can transmit or receive using various communication protocols existing in the vehicle. Here, the communication protocol may include at least one of CAN (Controller Area Network), CAN FD (CAN with Flexible Data rate), Ethernet, LIN (Local Interconnect Network), and FlexRay. The communication protocol may include other protocols for communication between various devices mounted on the vehicle.

The external communications department includes VANET (Vehicular Ad Hoc Network) communication technology, WAVE (Wireless Access in Vehicular Environments) communication technology, DSRC (Dedicated Short Range Communication), CALM (Communication Access in Land Mobile) communication technology, and V2V (Vehicle-to-Vehicle-to-Land) communication technology. Vehicle) communication technology, V2I (Vehicle-to-Infrastructure) communication technology, V2N (Vehicle-to-Network) communication technology, WLAN (Wireless LAN) communication technology, Wi-Fi (Wireless-Fidelity) communication technology, WiBro (Wireless Broadband) ) Communication technology, LTE (Long Term Evolution) communication technology, LTE-A (Long Term Evolution-Advanced) communication, 5G communication technology, 6G communication technology, UWB (Ultra-Wide band) communication technology, ZigBee communication technology, NFC (Near) Various communication methods such as Field Communication (Field Communication) communication technology can be used.

The communication unit 116 may include at least one of a transmitting antenna, a receiving antenna, a radio frequency (RF) circuit capable of implementing various communication protocols, and an RF element.

Meanwhile, the communication unit 116 can communicate with the passenger's terminal.

The sensor unit 118 senses objects around the vehicle and senses driving information of the vehicle.

Specifically, the sensor unit 118 can sense at least one surrounding vehicle located around the vehicle. The sensor unit 118 can obtain driving information of at least one surrounding vehicle. For example, the sensor unit 118 can measure the distance between the vehicle and surrounding vehicles using a distance sensor. The sensor unit 118 uses a distance sensor to accurately collect information about surrounding vehicles, such as the location of surrounding vehicles, the distance from the vehicle to the surrounding vehicles, the direction in which the surrounding vehicles are separated from the vehicle, the direction of movement of the surrounding vehicles, or the speed of the surrounding vehicles. It can be measured easily. The sensor unit 118 can detect objects located in at least one of the front, rear, left, and right areas of the vehicle using a distance sensor.

The sensor unit 118 is a distance sensor and may use a radar sensor, a Light Detection And Ranging (LiDAR) sensor, an infrared sensor, an ultrasonic sensor, or a laser sensor.

When the sensor unit 118 uses a laser sensor, the sensor unit 118 uses a time-of-flight (TOF) or/and phase-shift method depending on the laser signal modulation method. Thus, the positional relationship between the vehicle and the object can be accurately measured.

Distance sensors can be placed in various locations in the vehicle. The distance sensor may be placed at least one of the front, rear, left, right, or ceiling of the vehicle body.

When there are a plurality of surrounding vehicles around the vehicle, the sensor unit 118 can sense the plurality of surrounding vehicles simultaneously.

Meanwhile, the sensor unit 118 can measure driving information of the vehicle.

In order to obtain driving information of the vehicle, the sensor unit 118 includes a heading sensor, a yaw sensor, a gyro sensor, a vehicle forward/reverse sensor, a wheel speed sensor, It may further include a vehicle speed sensor, vehicle body tilt sensor, battery sensor, fuel sensor, tire sensor, steering sensor, vehicle interior temperature sensor, vehicle interior humidity sensor, and door sensor.

The sensor unit 118 may further sense at least one of vehicle direction information, vehicle speed information, acceleration information, tilt information, forward/backward information, fuel information, and turn signal information.

The driving unit 130 includes at least one of an acceleration control device 132, a braking control device 134, and a steering control device 136.

The acceleration control device 132 is configured to control engine drive or motor drive of the vehicle and can accelerate the vehicle.

The braking control device 134 is configured to control braking of the vehicle and may include a controller (not shown) that controls the brakes (not shown).

The steering control device 136 is configured to control the steering angle of the vehicle and may include a steering wheel (not shown), an actuator (not shown) linked to the steering wheel, and a controller (not shown) that controls the actuator.

The control device 120 may include an acquisition unit 122 and a control unit 124. The control device 120 may be implemented by at least one processor and at least one memory.

The acquisition unit 122 acquires information about the route on which the vehicle is traveling from at least one of the camera 114, the navigation device 112, and the central server. The control unit 124 assists or controls the driving of the vehicle using the driving unit 130 based on the route information. The vehicle may be controlled based on route information obtained from at least one of the camera 114, the navigation device 112, and the central server.

The acquisition unit 122 may acquire driving information of surrounding vehicles located around the vehicle. Driving information of surrounding vehicles may be received by the communication unit 116 using wireless communication or sensed by the sensor unit 118.

The control unit 124 can compare the driving information of the vehicle with the driving information of surrounding vehicles. For example, the control unit 124 may compare the average speed of the vehicle within a predetermined time period with the average speed of surrounding vehicles. As another example, the control unit 124 may use at least one of the vehicle's speed, average speed, and speed standard deviation to compare it with at least one of the speed, average speed, and speed standard deviation of surrounding vehicles.

The control unit 124 may calculate the difference between at least one element included in the vehicle's driving information and at least one element included in the average driving information of surrounding vehicles.

The control unit 124 may be an Electronic Control Unit (ECU), Micro Controller Unit (MCU), or other lower-level controller mounted on the vehicle.

The control unit 124 uses a classification model to create classes corresponding to four-wheeled vehicles, two-wheeled vehicles, pedestrians, unidentified objects, etc. can be identified.

Below, the training and structure of the classification model will be described.

The classification model is trained to classify classes corresponding to the pressure distribution value and pressure value of the object on the path. Specifically, the classification model receives pressure distribution and pressure values as input. The classification model extracts the characteristics of the input pressure distribution and pressure value. The classification model calculates probability values that the input pressure distribution and pressure value expression belong to each class based on the extracted features.

A training device (not shown) adjusts parameters such as weights and biases of the classification model so that the pressure distribution and pressure value are output with a high probability of belonging to the labeled class. A classification model is trained based on multiple pressure distributions and pressure values.

The classification model can be learned based on a supervised learning method. The supervised learning method refers to a method of training an artificial neural network based on the state in which the label for the learning data is given. The label may mean the correct answer or result value that the artificial neural network must infer when learning data is input to an artificial neural network (ANN).

According to one embodiment of the present invention, the acquisition unit 122 can acquire speed and location information of four-wheeled vehicles, two-wheeled vehicles, pedestrians, and unidentified objects using a deep neural network (DNN)-based classification model. there is.

Specifically, the classification model receives input values for pressure distribution and pressure values measured from a pressure sensor when a four-wheeled vehicle, two-wheeled vehicle, or pedestrian, etc., drives or passes on a road, and provides the corresponding speed and location information. For example, when a four-wheeled vehicle is driving on a road, a pressure sensor placed on the road can measure the weight (pressure value) of the four-wheeled vehicle applied from the four wheels (pressure distribution). The measured pressure distribution and pressure values of the four-wheeled vehicle are stored in the central server. The acquisition unit 122 may receive the pressure distribution and pressure value of the four-wheeled vehicle from the central server via the communication unit 116. The control unit 124 may estimate the speed and location information of the four-wheeled vehicle based on the pressure distribution and pressure value of the four-wheeled vehicle received by the acquisition unit 122.

The vehicle may further include an interface unit (not shown).

The Interbase unit can visually provide necessary information to passengers or receive input from passengers.

The interface unit may be a device that can exchange various sensory information such as a person's hearing, vision, and touch. For example, the interface unit may include a User Setting Mode (USM) device or a Human-Machine Interaction (HMI) device.

Figure 2 is a flowchart showing a control method of an autonomous vehicle according to an embodiment of the present disclosure.

Referring to FIG. 2, the vehicle acquires the pressure distribution and pressure value of the parked vehicle and obstacles on the road from the central server based on the pressure sensor placed in the road (S200). The vehicle acquisition unit 122 may obtain the pressure distribution and pressure values of parked vehicles and obstacles on the road from the central server via the communication unit 116. The vehicle can determine whether the width of the passage that can pass is, for example, 1.2 times or more than the overall width of the vehicle.

The vehicle calculates the type, speed information, and location information of the parked vehicle and obstacle based on the pressure distribution and pressure value of the parked vehicle and obstacle (S202). Based on the pressure distribution and pressure values of parked vehicles and obstacles on the road that the acquisition unit 122 acquires from the communication unit 116, the control unit 124 can calculate the type, speed information, and location information of the object. Here, objects may include four-wheeled vehicles, two-wheeled vehicles, pedestrians, and unidentified objects.

The control unit 124 can use the learned classification model to calculate the type, speed information, and location information of any one of four-wheeled vehicles, two-wheeled vehicles, pedestrians, and unidentified objects.

The driving of the vehicle is controlled based on the type, speed information, and location information of parked vehicles and obstacles (S204). The control unit 124 can calculate the type, speed information, and location information of parked vehicles and obstacles, and control autonomous driving of the vehicle traveling on the road based on the calculated values. Process S204 is explained in detail in FIG. 3.

When a vehicle drives on a road, images of the vehicle's path and surrounding space are stored (S206). The path taken while driving can be saved from the time the vehicle enters the road. In one embodiment of storing the path taken by the vehicle, a pressure sensor disposed in the path measures the load of the vehicle applied from a plurality of wheels (not shown) of the vehicle, and sets the measured pressure range and pressure value to the center. It can be sent to the server. The central server transmits information about the applied pressure range to the vehicle while the vehicle is driving, and the vehicle can estimate the path taken based on the information about the pressure range. In another embodiment, the vehicle may use the navigation device 112 to estimate the route the vehicle has taken. The navigation device 112 may receive satellite signals using a GPS receiver included in a global navigation system (GPS) and estimate the location of the vehicle using the satellite signals.

In another embodiment of storing images of the surrounding space when a vehicle is driving on a road, images of the front, sides, and rear of the vehicle are captured using the camera 114, and the surrounding area of the road is based on the captured images. Environmental information can be obtained.

If an opposing vehicle exists in front of the vehicle, the vehicle performs evasive driving based on the image (S208). If an opposing vehicle exists in front of the vehicle while the vehicle is driving on the road, the vehicle uses the image of the path taken and the surrounding space of the road obtained from at least one of the camera 114, the navigation device 112, and the central server. You can explore avoidance spaces within the path.

When the acquisition unit 122 receives the pressure distribution and pressure values of the two-wheeled vehicle and the pedestrian in front of the vehicle via the communication unit 116, the control unit 124 calculates location information of the two-wheeled vehicle and the pedestrian. Based on the calculated location information, when the vehicle is closer than a preset distance to the location of a two-wheeled vehicle or pedestrian, a warning signal is sent to the driver and the vehicle can be controlled to enter manual mode. .

When the acquisition unit 122 receives the pressure distribution and pressure value of an unidentified object in front of the vehicle via the communication unit 116, the control unit 124 immediately sends a warning signal to the driver and stops the vehicle. It can be controlled to be in manual mode. Process S208 is explained in detail in FIG. 4.

FIG. 3 is a flowchart showing process S204 of FIG. 2 in detail.

Referring to FIG. 3, it is determined whether the width through which the vehicle can pass is greater than or equal to a preset width compared to the overall width of the vehicle (S300). Before a vehicle enters a road, the vehicle can receive route information from the central server. The central server can store information about objects on the corridor based on pressure sensors placed in the corridor. The central server transmits the stored route information to the vehicle, and the vehicle can determine whether to enter the route based on the transmitted route information.

In process S300, if it is determined that the width through which the vehicle can pass is less than or equal to the preset width compared to the overall width of the vehicle, the vehicle searches for another route (S302).

In process S300, if it is determined that the width through which the vehicle can pass is greater than or equal to the preset width compared to the overall width of the vehicle, it is determined whether the other vehicle located in the road is driving (S304). By receiving the pressure distribution and pressure value from the central server, the vehicle can determine whether a preceding or opposing vehicle is driving on the road before entering the road. Here, the preceding vehicle refers to a vehicle traveling in the same direction as the vehicle, and the opposing vehicle refers to a vehicle traveling in the opposite direction of the vehicle. The vehicle can receive the pressure distribution and pressure value from the central server and receive speed information and location information about the vehicle traveling on the road.

In process S304, if it is determined that the other vehicle located in the lane is not driving, it may be determined that the other vehicle is stopped in the lane. If it is determined that the other vehicle is stopped on the road, the vehicle searches for another route.

In process S304, if it is determined that the other vehicle located in the lane is driving, the vehicle waits to enter the lane until the other vehicle traveling in the lane exits the lane (S306). The vehicle can receive speed information and location information of the other vehicle traveling on the road from the central server and determine whether the other vehicle is driving on the road.

FIG. 4 is a flowchart showing process S208 of FIG. 2 in detail.

Referring to FIG. 4, it is determined whether an opposing vehicle has entered in front of the vehicle (S400). While the vehicle is driving on the road, it can determine whether an opposing vehicle is entering in front. Pressure distribution and pressure value can be received from the central server to determine whether the opposing vehicle has entered, and the camera 114 can be used to obtain image information about the opposing vehicle in front to determine whether the opposing vehicle has entered.

In process S400, when it is determined that an opposing vehicle has entered in front of the vehicle, the vehicle advances to a preset distance from the opposing vehicle (S402). If the vehicle enters the road ahead of the opposing vehicle, the vehicle advances to a distance of, for example, 3 m (meters) ahead of the opposing vehicle.

It is determined whether the opposing vehicle moves out of the way within a preset time (S404). After the vehicle moves forward to a distance of, for example, 3 m from the opposing vehicle and stops, it is determined whether the opposing vehicle remains stopped for, for example, more than 10 seconds.

In process S404, if it is determined that the opposing vehicle will get out of the way within a preset time, it is determined whether the width of the road that can be passed is more than the preset width compared to the overall width of the vehicle (S406). When an opposing vehicle moves backwards and escapes the lane or avoids driving behind a parked vehicle or obstacle in the lane, the vehicle can determine whether the width of the lane that can pass is, for example, 1.1 times or more than the overall width of the vehicle.

In processes S404 and S406, if it is determined that the opposing vehicle does not get out of the way within the preset time or the width of the road that can be passed is determined to be less than the preset width compared to the overall width of the vehicle, the vehicle displays the image of the road that it has passed. Based on this, drive to avoid opposing vehicles (S408). Process S408 is explained in detail in FIG. 5.

Figure 5 is a flowchart showing process S408 of Figure 4 in detail.

Referring to FIG. 5, it is determined whether there is an avoidance space in the path taken (S500). If it is determined that the opposing vehicle does not get out of the way within the preset time, or if the width of the road that can be passed is determined to be less than the preset width compared to the overall width of the vehicle, the vehicle uses the camera 114 and the navigation device 112. You can search for avoidance spaces using images of the path you have taken and the surrounding space.

In process S500, if it is determined that there is an avoidance space in the path taken by the vehicle, the vehicle moves to the avoidance space, makes way for the opposing vehicle, and escapes the path (S502). If it is determined that there is an avoidance space in the path taken by the vehicle using the camera 114, the vehicle can be driven into the avoidance space to make way for the oncoming vehicle in front.

In process S500, if it is determined that there is no avoidance space in the path taken by the vehicle, the vehicle travels backwards based on the path taken by the vehicle, makes way for the opposing vehicle, and escapes the path (S504). The vehicle can travel backwards along the previous route using the navigation device 112. When the vehicle re-enters the road by driving backwards on the path it has taken, the vehicle can perform process S300 of FIG. 3.

According to one embodiment, the control device 120 and its control method for an autonomous vehicle are an autonomous driving system for a vehicle that runs on a road based on location information of parked vehicles and obstacles placed in the road by installing a pressure sensor in the road. There is an effect that can be implemented.

According to one embodiment, the control device 120 and its control method for an autonomous vehicle have the effect of implementing various control systems to respond to specific situations when the vehicle 100 drives on a small road.

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 modified and modified in various ways 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 this embodiment, and those skilled in the art will be able to make various modifications and variations without departing from the essential characteristics of this 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.

110: Collection department
120: Control device
130: driving unit

Claims (14)

In the control method of an autonomous vehicle (hereinafter referred to as “vehicle”) driving on a narrow road,
Before a vehicle enters the road, one of the pressure distribution and pressure value of parked vehicles and obstacles on the road is based on a pressure sensor placed in the road from the central server. The process of acquiring an ideal;
A process of calculating the type, speed information, and location information of the parked vehicle and the obstacle based on one or more of pressure distribution and pressure values of the parked vehicle and the obstacle;
A process of controlling driving of the vehicle based on the type of parked vehicle and obstacle, the speed information, and the location information;
When the vehicle travels on the road, storing images of the path the vehicle has taken and the surrounding space; and
When an opposing vehicle traveling in the opposite direction to the driving direction of the vehicle enters the road in front of the vehicle, the vehicle performs evasive driving based on the image.
A control method for an autonomous vehicle including. According to claim 1,
The process of controlling the driving of the vehicle based on the type of parked vehicle and obstacle, the speed information, and the location information,
A control method for an autonomous vehicle including the process of determining whether the width through which the vehicle can pass is greater than or equal to a preset width compared to the overall width of the vehicle. According to clause 2,
The process of determining whether the width through which the vehicle can pass is greater than or equal to a preset width compared to the overall width of the vehicle,
A control method for an autonomous vehicle including the process of determining whether an opposing vehicle located in the lane is driving when it is determined that the width through which the vehicle can pass is greater than a preset width compared to the overall width of the vehicle. According to claim 2 or 3,
A control method for an autonomous vehicle that searches for another route when it is determined that the width through which the vehicle can pass is less than a preset width or when it is determined that the other vehicle located in the road is not driving. According to clause 3,
The process of determining whether the other vehicle located on the road is driving is,
When it is determined that the other vehicle located in the road is driving, a control method for an autonomous vehicle comprising controlling the vehicle to wait for entry into the road until the other vehicle exits the road. According to claim 1,
The process of the vehicle avoiding driving based on the image is,
A control method for an autonomous vehicle comprising the step of determining whether the vehicle advances to a preset distance from the opposing vehicle and the opposing vehicle makes way for the vehicle within a preset time. According to clause 6,
The process of determining whether the opposing vehicle makes way for the vehicle within a preset time is,
When the opposing vehicle makes way for the vehicle within a preset time, control of an autonomous vehicle including the process of determining whether the width of the road through which the vehicle can pass is greater than or equal to the preset width compared to the overall width of the vehicle. method. According to claim 6 or 7,
If it is determined that the opposing vehicle does not make way for the vehicle within a preset time, or if the width of the road through which the vehicle can pass is smaller than the preset width compared to the entire width of the vehicle, the road is based on the image of the road. A control method for an autonomous vehicle including the process of driving to avoid an opposing vehicle. According to clause 8,
The process of driving to avoid the opposing vehicle based on the image of the road is,
A control method for an autonomous vehicle including the process of determining whether there is an avoidance space that can avoid the oncoming vehicle among the path along which the vehicle has passed and the surrounding space. According to clause 9,
In the process of determining whether there is an avoidance space in which the vehicle can avoid the opposing vehicle among the passed path and the surrounding space,
When it is determined that there is no avoidance space among the passed path and the surrounding space, a control method for an autonomous vehicle comprising controlling the vehicle to reverse the passed path to make way for the opposing vehicle. According to claim 1,
The process of calculating the type, speed information, and location information of the parked vehicle and obstacle based on the pressure distribution and pressure value of the parked vehicle and obstacle,
A control method for an autonomous vehicle using a classification model trained to output classes for objects on a path. According to claim 11,
The classification model is,
The pressure distribution and pressure value for the object are labeled and stored,
A control method for an autonomous vehicle including pressure distribution and pressure values of one or more of four-wheeled vehicles, two-wheeled vehicles, pedestrians, and unidentified objects. According to claim 12,
When the vehicle receives the pressure distribution and pressure value of one or more of the two-wheeled vehicle, pedestrian, and unidentified object from the central server, the vehicle is controlled to be in manual mode,
A control method for an autonomous vehicle that transmits a warning signal to the driver when the pressure distribution and pressure value of the unidentified object are received. An acquisition unit that acquires an image around the route based on route information acquired from at least one of a camera, a navigation device, a communication unit, and a sensor unit, and acquires the location of at least one obstacle and driving information of the other vehicle; and
A control unit that controls the driving of the vehicle based on the image around the road, the location of the obstacle, and the driving information of the other vehicle,
The acquisition unit is a control device for an autonomous vehicle that receives the pressure distribution and pressure value of the path received from a central server to obtain the location and driving information of obstacles and other vehicles located in the path.