KR102539286B1 - Autonomous driving apparatus and method - Google Patents

Abstract

The present invention relates to an autonomous driving apparatus and method, and relates to a sensor unit for detecting surrounding objects including surrounding vehicles of a self-driving vehicle, a memory for storing map information, and a prediction generated based on the map information stored in the memory. A processor for controlling autonomous driving of the host vehicle according to the driving trajectory, the processor determining whether or not an expected driving trajectory of the own vehicle needs to be corrected based on a result of the sensor unit detecting vehicles around the host vehicle; , and performs trajectory-based control for controlling the autonomous driving of the own vehicle by correcting the expected driving trajectory according to the determination result, and the first driving route to the destination of the own vehicle is the second driving of the driving cluster formed by a plurality of group vehicles If it overlaps with the path, cluster following control is performed to control the autonomous driving of the host vehicle to follow the driving of the driving cluster. The sensing parameter of the sensor unit is controlled to have a value mutually dependent on the parameter, and the sensing parameter includes at least one of a field of view (FOV) and sensor output.

Description

Autonomous driving device and method {AUTONOMOUS DRIVING APPARATUS AND METHOD}

The present invention relates to an autonomous driving device and method applied to an autonomous vehicle.

Today's automotive industry is moving in the direction of implementing autonomous driving that minimizes driver intervention in driving the vehicle. An autonomous vehicle refers to a vehicle that recognizes the surrounding environment through external information detection and processing functions while driving, determines a driving path on its own, and drives independently using its own power.

Self-driving vehicles can drive to their destination by themselves, avoiding collisions with obstacles on the driving path and adjusting the vehicle speed and driving direction according to the shape of the road, without the driver manipulating the steering wheel, accelerator pedal, or brakes. there is. For example, acceleration may be performed on a straight road, and deceleration may be performed while changing a driving direction corresponding to a curvature of the road on a curved road.

In order to ensure stable driving of an autonomous vehicle, the driving environment must be accurately measured through each sensor mounted on the vehicle, and the driving condition must be continuously monitored to control the driving according to the measured driving environment. To this end, various sensors such as lidar sensors, radar sensors, ultrasonic sensors, and camera sensors are applied to autonomous vehicles as sensors for detecting surrounding objects such as surrounding vehicles, pedestrians, and fixed facilities, Data output from these sensors is used to determine information about the driving environment, for example, state information such as the location, shape, moving direction, and moving speed of surrounding objects.

Furthermore, the self-driving vehicle optimally determines the driving route and driving lane by determining and correcting the location of the vehicle using pre-stored map data, controls the driving of the vehicle so as not to deviate from the determined route and lane, and suddenly It also provides a function of performing defense and avoidance driving against an approaching vehicle or risk factors existing on the driving route.

The background art of the present invention is disclosed in Korean Patent Publication No. 10-1998-0068399 (published on October 15, 1998).

An object according to an aspect of the present invention is to selectively apply a method of controlling autonomous driving of a vehicle according to a driving trajectory to a destination and a method of following the driving of a driving cluster formed by a plurality of group vehicles, thereby providing autonomous vehicles of autonomous vehicles. It is an object of the present invention to provide an autonomous driving device and method capable of reaching a destination in the shortest time while minimizing driving control calculation load.

An object according to another aspect of the present invention is a method of varying a surrounding object sensing area according to a relative position of an autonomous vehicle with another group vehicle in a process of performing group driving by joining a driving cluster, so that each member belonging to the driving cluster It is an object of the present invention to provide an autonomous driving device and method capable of reducing total system resources required for group vehicles to sense surrounding objects.

An autonomous driving device according to an aspect of the present invention includes a sensor unit for detecting surrounding objects including vehicles around a self-driving vehicle, a memory for storing map information, and a prediction generated based on the map information stored in the memory. a processor controlling autonomous driving of the own vehicle according to a driving trajectory, wherein the processor needs to correct an expected driving trajectory of the own vehicle based on a result of the sensor unit detecting vehicles around the own vehicle; It is determined whether or not there exists a vehicle, and according to the determination result, the expected driving trajectory is corrected to perform trajectory-based control for controlling autonomous driving of the own vehicle, and the first driving path to the destination of the own vehicle is a plurality of group vehicles. When overlapping with the second driving path of the driving cluster formed by , cluster following control is performed to control autonomous driving of the host vehicle to follow the driving of the driving cluster, and the processor, when performing the cluster following control, Control the sensing parameter of the sensor unit to have a value mutually dependent on the sensing parameter of the sensor device mounted on each group vehicle, wherein the sensing parameter includes at least one of a field of view (FOV) and sensor output. It is characterized by doing.

In the present invention, when performing the trajectory-based control, the processor generates an actual driving trajectory of the surrounding vehicle based on the driving information of the surrounding vehicle detected by the sensor unit, and maps the map information stored in the memory to the map information stored in the memory. generating an expected driving trajectory of the surrounding vehicle based on the basis, and determining that the expected driving trajectory of the own vehicle needs to be corrected when a trajectory error between the actual driving trajectory and the predicted driving trajectory of the surrounding vehicle is equal to or greater than a preset threshold It is characterized by doing.

In the present invention, when the cluster following control is performed, the processor, based on the direction in which the host vehicle travels to the destination, from a convergence point where overlapping between the first and second driving routes starts, the first and performing the cluster following control until a withdrawal point at which the overlapping between the second driving routes ends.

In the present invention, the processor performs mutual switching between the trajectory-based control and the cluster following control according to whether a predefined control switching condition is satisfied, and the control switching condition is, the trajectory-based control to the cluster following control and a cluster following control switching condition for switching to , and a trajectory-based control switching condition for switching from the cluster following control to the trajectory-based control.

In the present invention, the processor determines that the cluster following control switching condition is satisfied when the own vehicle arrives at the merging point in the process of performing the trajectory-based control from the current location of the own vehicle, and It is characterized in that follow-up control is performed.

In the present invention, the processor determines that the trajectory-based control switching condition is satisfied when the host vehicle reaches the leaving point in the process of performing cluster following control from the joining point, and performs the trajectory-based control It is characterized by doing.

In the present invention, the processor determines the joining point and the leaving point for performing the cluster following control from a plurality of candidate joining points and a plurality of candidate leaving points; A time required to reach a candidate joining point from the current location, a time required for the host vehicle to reach a candidate leaving point from a candidate joining point based on the cluster following control, and a candidate leaving point based on the trajectory based control A candidate joining point and a candidate leaving point at which a total required time, which is the sum of times required to reach a destination from , are minimum, are determined as the joining point and the leaving point, respectively.

In the present invention, when the cluster following control is performed, the processor varies the surrounding object detection area of the sensor unit according to the relative position of the host vehicle to the cluster vehicles belonging to the driving cluster.

In the present invention, when performing the cluster following control, the processor classifies the driving cluster into a preceding driving group, a middle driving group, and a trailing driving group using a predefined group classification algorithm, and among the driving groups It is characterized in that a driving group to which the host vehicle belongs is determined and a surrounding object detection area of the sensor unit is varied according to a result of the determination.

In the present invention, the processor detects an object in front of the host vehicle through the sensor unit when the host vehicle belongs to the preceding driving group, and detects an object around the host vehicle in front of the host vehicle through the sensor unit when the host vehicle belongs to the middle driving group. It is characterized in that an object around the side of the own vehicle is detected, and when the own vehicle belongs to the following driving group, an object around the rear of the own vehicle is detected through the sensor unit.

In the present invention, the processor controls the sensing parameter of the sensor unit according to the sensor adjustment signal transmitted from the leader vehicle of the driving cluster, and the sensor adjustment signal controls the detection area and detection performance of surrounding objects at the level of the driving cluster. Characterized in that each cluster vehicle is generated by the leader vehicle based on the driving environment of the driving cluster and the position of each cluster vehicle within the driving cluster and transmitted to each group vehicle, so that the driving cluster can be optimized. to be

In the present invention, the processor may, when the host vehicle is in the position of a leader vehicle of the driving cluster, based on a result of detecting a surrounding object by the sensor unit and the location of each group vehicle within the driving cluster. After generating the sensor adjustment signal for each cluster vehicle belonging to the driving cluster, the signal is transmitted to each cluster vehicle.

An autonomous driving method according to an aspect of the present invention provides a sensor unit for detecting surrounding objects including vehicles around a self-driving vehicle, a memory for storing map information, and a prediction generated based on the map information stored in the memory. A method for controlling autonomous driving in an autonomous driving system including a processor controlling autonomous driving of the own vehicle according to a driving trajectory, wherein the processor performs the control of the autonomous driving based on a result of the sensor unit detecting surrounding vehicles of the own vehicle. Determining whether it is necessary to correct an expected driving trajectory of the own vehicle, and performing trajectory-based control for controlling autonomous driving of the own vehicle by correcting the expected driving trajectory according to the determination result, and the processor , When the first driving route to the destination of the own vehicle overlaps with the second driving route of the driving cluster formed by a plurality of cluster vehicles, cluster following for controlling the autonomous driving of the own vehicle to follow the driving of the driving cluster and performing control, wherein in the performing of the group follow-up control, the processor controls the sensing parameters of the sensor unit to have values mutually dependent on the sensing parameters of the sensor devices mounted on each of the group vehicles. However, the sensing parameter is characterized in that it includes at least one of a field of view (FOV) and sensor output.

According to one aspect of the present invention, the present invention provides a trajectory-based control for controlling autonomous driving according to driving trajectory correction for each predetermined section on a route from a current location of an autonomous vehicle to a destination, and cluster following control for following the driving of a driving cluster. By performing mutual conversion, it is possible to reduce the autonomous driving control computational load of the autonomous vehicle and minimize the occupant's intervention in the vehicle's driving control in the process of reaching the destination, thereby improving the passenger's convenience and reaching the destination in the shortest time. can make it possible to reach

In addition, according to one aspect of the present invention, since the present invention operates to vary the surrounding object detection area of the sensor unit according to the relative position of the own vehicle to other cluster vehicles belonging to the driving cluster when performing cluster following control, When viewed from the level of the entire driving group, it is possible to reduce the total resource of the system required for each group vehicle belonging to the driving group to sense surrounding objects.

1 is an overall block configuration diagram of an autonomous driving control system to which an autonomous driving device according to an embodiment of the present invention can be applied.
2 is a block diagram showing a specific configuration of an autonomous driving integrated control unit in an autonomous driving device according to an embodiment of the present invention.
3 is an exemplary view showing an example in which an autonomous driving device according to an embodiment of the present invention is applied to a vehicle.
4 is an exemplary view showing an example of an internal structure of a vehicle to which an autonomous driving device according to an embodiment of the present invention is applied.
5 is an exemplary view showing an example of a set distance and a horizontal angle of view at which a lidar sensor, a radar sensor, and a camera sensor can detect a surrounding object in an autonomous driving device according to an embodiment of the present invention.
6 is an exemplary view showing an example of detecting a surrounding vehicle by a sensor unit in an autonomous driving device according to an embodiment of the present invention.
7 is an exemplary diagram showing an example in which a surrounding object detection area of a sensor unit is varied according to a location of an own vehicle in a driving cluster in an autonomous driving device according to an embodiment of the present invention.
8 and 9 are flowcharts for explaining an autonomous driving method according to an embodiment of the present invention.

Hereinafter, embodiments of an autonomous driving device and method according to the present invention will be described with reference to the accompanying drawings. In this process, the thickness of lines or the size of components shown in the drawings may be exaggerated for clarity and convenience of explanation. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, definitions of these terms will have to be made based on the content throughout this specification.

1 is an overall block diagram of an autonomous driving control system to which an autonomous driving device according to an embodiment of the present invention can be applied, and FIG. 2 is a detailed diagram of an integrated autonomous driving control unit in an autonomous driving device according to an embodiment of the present invention. It is a block diagram showing the configuration, Figure 3 is an exemplary view showing an example of the self-driving device according to an embodiment of the present invention is applied to a vehicle, Figure 4 is an autonomous driving device according to an embodiment of the present invention is applied 5 is an exemplary diagram showing an example of the internal structure of a vehicle, and FIG. 5 is a set distance and horizontal angle of view at which a lidar sensor, a radar sensor, and a camera sensor can detect a surrounding object in an autonomous driving device according to an embodiment of the present invention. 6 is an exemplary view showing an example of detecting a surrounding vehicle by a sensor unit in an autonomous driving device according to an embodiment of the present invention, and FIG. 7 is an exemplary view showing autonomous driving according to an embodiment of the present invention. It is an exemplary view showing an example in which the detection area of the sensor unit is changed according to the location of the own vehicle in the driving cluster in the device.

First, the structure and function of an autonomous driving control system to which the autonomous driving device according to the present embodiment can be applied will be described with reference to FIGS. 1 and 3 . As shown in FIG. 1 , the autonomous driving control system is used for autonomous driving control of a vehicle through a driving information input interface 101, a driving information input interface 201, a passenger output interface 301, and a vehicle control output interface 401. It can be implemented around the autonomous driving integrated control unit 600 that transmits and receives necessary data.

The autonomous driving integrated control unit 600 may obtain driving information according to a driver's manipulation of the user input unit 100 in the autonomous driving mode or the manual driving mode of the vehicle through the driving information input interface 101 . As shown in FIG. 1 as an example, the user input unit 100 includes a driving mode switch 110 and a user terminal 120 (eg, a navigation terminal installed in a vehicle, a smartphone or a tablet PC owned by a passenger). Accordingly, the driving information may include vehicle driving mode information and navigation information. For example, the vehicle's driving mode (ie, autonomous driving mode/manual driving mode, or sport mode/eco mode/safety mode) determined according to the driver's manipulation of the driving mode switch 110 Mode (Safe Mode/Normal Mode) may be transmitted to the autonomous driving integrated control unit 600 through the driving information input interface 101 as the driving information described above. In addition, navigation information such as the passenger's destination input by the passenger through the user terminal 120 and the route to the destination (the shortest route or preferred route selected by the passenger among candidate routes to the destination) is the driving information. It can be transmitted to the autonomous driving integrated control unit 600 through the input interface 101 . Meanwhile, the user terminal 120 may be implemented as a control panel (eg, a touch screen panel) that provides a user interface (UI) for a driver to input or modify information for autonomous driving control of a vehicle. , In this case, the driving mode switch 110 described above may be implemented as a touch button on the user terminal 120 .

In addition, the autonomous driving integrated control unit 600 may obtain driving information indicating a driving state of the vehicle through the driving information input interface 201 . The driving information includes the steering angle formed by the occupant operating the steering wheel, the stroke of the accelerator pedal or the brake pedal formed by depressing the accelerator or brake pedal, and vehicle speed, acceleration, yaw, pitch, and behavior formed in the vehicle. and roll, etc., and may include various information representing the driving state and behavior of the vehicle, and each of the driving information includes a steering angle sensor 210, an Accel Position Sensor (APS)/Pedal Travel Sensor (PTS) as shown in FIG. 220 , vehicle speed sensor 230 , acceleration sensor 240 , and yaw/pitch/roll sensor 250 . Furthermore, vehicle driving information may include vehicle location information, and vehicle location information may be acquired through a Global Positioning System (GPS) receiver 260 applied to the vehicle. Such driving information may be transmitted to the autonomous driving integrated control unit 600 through the driving information input interface 201 and used to control driving of the vehicle in the autonomous driving mode or the manual driving mode.

In addition, the autonomous driving integrated control unit 600 may transmit driving state information provided to the occupant in the autonomous driving mode or the manual driving mode of the vehicle to the output unit 300 through the occupant output interface 301 . That is, the autonomous driving integrated control unit 600 transmits driving state information of the vehicle to the output unit 300 so that the driver can drive the vehicle autonomously or manually based on the driving state information output through the output unit 300. The driving state information may include various information indicating the driving state of the vehicle, such as a current driving mode, a shift range, and a vehicle speed. In addition, when it is determined that a driver needs to be warned in the autonomous driving mode or manual driving mode of the vehicle along with the driving state information, the autonomous driving integrated control unit 600 outputs warning information through the occupant output interface 301 to the output unit. 300 so that the output unit 300 outputs a warning to the driver. In order to audibly and visually output such driving state information and warning information, the output unit 300 may include a speaker 310 and a display device 320 as shown in FIG. 1 . In this case, the display device 320 may be implemented as the same device as the aforementioned user terminal 120 or may be implemented as a separate and independent device.

In addition, the autonomous driving integrated control unit 600 may transmit control information for driving control of the vehicle in the autonomous driving mode or the manual driving mode of the vehicle to the lower control system 400 applied to the vehicle through the vehicle control output interface 401. there is. As shown in FIG. 1 , the sub-control system 400 for vehicle driving control may include an engine control system 410, a braking control system 420, and a steering control system 430, and an autonomous driving integrated control unit. 600 may transmit engine control information, braking control information, and steering control information as the control information to each lower control system 410 , 420 , and 430 through the vehicle control output interface 401 . Accordingly, the engine control system 410 may increase or decrease fuel supplied to the engine to control the vehicle speed and acceleration, and the braking control system 420 may control braking of the vehicle by adjusting the braking force of the vehicle. The steering control system 430 may control steering of the vehicle through a steering device applied to the vehicle (eg, a Motor Driven Power Steering (MDPS) system).

As described above, the autonomous driving integrated control unit 600 according to the present embodiment transmits driving information according to the driver's manipulation and driving information indicating the driving state of the vehicle through the driving information input interface 101 and the driving information input interface 201, respectively. obtained, driving state information and warning information generated according to the autonomous driving algorithm processed by the internal processor 610 may be transmitted to the output unit 300 through the occupant output interface 301, and the internal processor ( Control information generated according to the autonomous driving algorithm processed by 610 may be transferred to the lower control system 400 through the vehicle control output interface 401 to operate to control vehicle driving.

On the other hand, in order to ensure stable autonomous driving of the vehicle, it is necessary to continuously monitor the driving state by accurately measuring the driving environment of the vehicle and control the driving according to the measured driving environment. To this end, the autonomous driving device of the present embodiment As shown in FIG. 1 , a sensor unit 500 may be included to detect objects around the vehicle, such as surrounding vehicles, pedestrians, roads, or fixed facilities (eg, traffic lights, milestones, traffic signs, construction fences, etc.). As shown in FIG. 1 , the sensor unit 500 may include one or more of a lidar sensor 510 , a radar sensor 520 , and a camera sensor 530 to detect surrounding objects outside the vehicle.

The lidar sensor 510 transmits a laser signal to the surroundings of the vehicle and receives a signal reflected back by the object to detect surrounding objects outside the vehicle. A surrounding object located within a vertical field of view and a set vertical field of view may be detected. The lidar sensor 510 may include a front lidar sensor 511, an upper lidar sensor 512, and a rear lidar sensor 513 installed on the front, top, and rear of the vehicle, respectively, but their installation locations and the number of installations is not limited to a specific embodiment. The threshold value for determining the validity of the laser signal reflected by the object and returned may be pre-stored in the memory 620 of the autonomous driving integrated control unit 600, and the processor 610 of the autonomous driving integrated control unit 600 The laser signal transmitted through the lidar sensor 510 can determine the position (including the distance to the object), speed, and direction of movement of the object through a method of measuring the time it takes for the laser signal to be reflected by the object and return. can

The radar sensor 520 may detect surrounding objects outside the vehicle by radiating electromagnetic waves around the vehicle and receiving a signal reflected back by the object, and according to the specifications, set distance, set vertical angle of view and A surrounding object located within the set horizontal field of view range can be detected. The radar sensor 520 may include a front radar sensor 521, a left radar sensor 521, a right radar sensor 522, and a rear radar sensor 523 installed on the front, left side, right side, and rear of the vehicle, respectively. However, the installation location and number of installations are not limited to specific embodiments. The processor 610 of the autonomous driving integrated control unit 600 analyzes the power of electromagnetic waves transmitted and received through the radar sensor 520 to determine the position of the object (including the distance to the object), speed and the direction of movement can be determined.

The camera sensor 530 may detect surrounding objects outside the vehicle by capturing an image of the surroundings of the vehicle, and may detect surrounding objects located within a range of a predefined set distance, set vertical angle of view, and set horizontal angle of view according to the specification. . The camera sensors 530 may include a front camera sensor 531, a left camera sensor 532, a right camera sensor 533, and a rear camera sensor 534 installed on the front, left, right, and rear surfaces of the vehicle, respectively. However, the installation location and number of installations are not limited to specific embodiments. The processor 610 of the autonomous driving integrated control unit 600 applies predefined image processing to the image captured through the camera sensor 530, thereby determining the position of the object (including the distance to the object) and speed. and the direction of movement can be determined. In addition, an internal camera sensor 535 for capturing an image of the inside of the vehicle may be mounted at a predetermined position inside the vehicle (eg, a rear view mirror), and the processor 610 of the integrated autonomous driving control unit 600 may A guide or warning may be output to the occupant through the above-described output unit 300 by monitoring the occupant's behavior and condition based on the image acquired through the sensor 535 .

In addition to the lidar sensor 510, the radar sensor 520, and the camera sensor 530, the sensor unit 500 may further include an ultrasonic sensor 540 as shown in FIG. Various types of sensors for detecting surrounding objects may be further employed in the sensor unit 500 . 3 shows that a front lidar sensor 511 or a front radar sensor 521 is installed on the front of the vehicle, and a rear lidar sensor 513 or rear radar sensor 524 is installed on the rear of the vehicle to help understand the present embodiment. It is installed on the front camera sensor 531, left camera sensor 532, right camera sensor 533 and rear camera sensor 534 are installed on the front, left side, right side and rear side of the vehicle, respectively. , As described above, the installation position and number of installations of each sensor are not limited to a specific embodiment. 5 shows an example of a set distance and a horizontal angle of view at which the lidar sensor 510, the radar sensor 520, and the camera sensor 530 can detect a nearby object in front, and FIG. An example of detecting an object is shown. 6 is only an example of detecting a surrounding object, and the method for detecting a surrounding object is determined depending on the installation location and number of installed sensors. Depending on the configuration of the sensor unit 500 described above, surrounding vehicles and surrounding objects in an omnidirectional area of the host vehicle may be detected.

Furthermore, the sensor unit 500 detects the occupant's voice and vital signals (eg, heart rate, electrocardiogram, respiration, blood pressure, body temperature, brain wave, blood flow (pulse wave), blood sugar, etc.) It may further include a microphone and a biosensor for processing, and the biosensors include a heart rate sensor, an electrocardiogram sensor, a respiration sensor, a blood pressure sensor, a body temperature sensor, an electroencephalogram sensor, a photoplethysmography sensor, and a blood sugar sensor. This can be.

4 shows an example of the internal structure of a vehicle, and inside the vehicle, its state is controlled by manipulation of a driver or passenger of the vehicle to provide driving or convenience (eg, rest, entertainment activities, etc.) of the vehicle. Internal devices to support may be installed. These internal devices may include a vehicle seat (S) on which the occupant is seated, a lighting device (L) such as an interior light and a mood light, the above-described user terminal 120 and display device 320, an internal table, and the like. The state of the internal device may be controlled by the processor 610 .

In the case of the vehicle seat S, the angle may be adjusted by the processor 610 (or by manual manipulation of the occupant), and the vehicle seat S may be adjusted to the front row seat S1 and the rear row seat S2. , only the angle of the front row seats S1 can be adjusted. When the rear seat S2 is not provided and the front row seat S1 is divided into a seat structure and a footrest structure, the seat structure of the front row seat S1 is physically separated from the footrest structure, It may be implemented such that the angle is adjusted. In addition, an actuator (eg, a motor) for adjusting the angle of the vehicle seat S may be provided. In the case of the lighting device (L), its on/off may be controlled by the processor 610 (or by manual manipulation of the occupant), and the lighting device (L) operates a plurality of lighting units such as interior lights and mood lights. When included, each lighting unit can be independently controlled on and off. The angle of the user terminal 120 or the display device 320 may be adjusted by the processor 610 (or by manual manipulation of the passenger) according to the passenger's viewing angle, and for example, the screen is aligned with the passenger's line of sight. The angle can be adjusted so that it exists. In this case, an actuator (eg, a motor) may be provided to adjust the angles of the user terminal 120 and the display device 320 .

As shown in FIG. 1 , the autonomous driving integrated control unit 600 may communicate with the server 700 through a network. As a network method between the autonomous driving integrated control unit 600 and the server 700, various communication methods such as a wide area network (WAN), a local area network (LAN), or a personal area network (PAN) may be employed. In addition, in order to secure wide network coverage, LPWAN (Low Power Wide Area Network, a network with very wide coverage among the Internet of Things, including commercialized technologies such as LoRa, Sigfox, Ingenu, LTE-M, and NB-IOT) communication method can be employed. For example, a communication method of LoRa (having a wide coverage of up to 20Km while enabling low-power communication) or Sigfox (having a coverage of 10Km (city) to 30Km (outside the city) depending on the environment) is adopted 3GPP (3rd generation Partnership Project) release 12, 13 based LTE network technology may be employed. The server 700 may provide up-to-date map information (various map information such as 2D navigation map data, 3D remote map data, or 3D high-precision electronic map data) may be provided, and furthermore, the road It can also provide various types of information such as accident information, road control information, traffic volume information, and weather information. The autonomous driving integrated control unit 600 may update the map information stored in the memory 620 by receiving the latest map information from the server 700, and receive accident information, road control information, traffic volume information, and weather information to drive the vehicle. It can also be used for autonomous driving control.

Next, with reference to FIG. 2 , the structure and function of the autonomous driving integrated control unit 600 according to this embodiment will be described. As shown in FIG. 2 , the autonomous driving integrated controller 600 may include a processor 610 and a memory 620 .

The memory 620 may store basic information necessary for autonomous driving control of the vehicle or information generated in the process of controlling the autonomous driving of the vehicle by the processor 610. The processor 610 may store the memory 620 It is possible to control the autonomous driving of the vehicle by accessing (read, access) the information stored in ). The memory 620 may be implemented as a computer-readable recording medium so that the processor 610 can access it. Specifically, the memory 620 may include a hard drive, a magnetic tape, a memory card, a read-only memory (ROM), a random-access memory (RAM), a digital video disc (DVD), or an optical disk. It can be implemented as an optical data storage device such as

Map information required for autonomous driving control by the processor 610 may be stored in the memory 620 . The map information stored in the memory 620 may be a navigation map (digital topographic map) that provides road-level information, but a precision road map that provides lane-level road information to improve the precision of autonomous driving control; That is, it may be preferable to implement the 3D high-precision electronic map data. Accordingly, the map information stored in the memory 620 is dynamic and necessary for autonomous driving control of the vehicle, such as lanes, lane center lines, regulatory lines, road boundaries, road center lines, traffic signs, road markings, road shapes and heights, and lane widths. Static information can be provided.

In addition, an autonomous driving algorithm for autonomous driving control of a vehicle may be stored in the memory 620 . The self-driving algorithm is an algorithm (recognition, judgment and control algorithm) that recognizes the surroundings of the self-driving vehicle, determines its state, and controls the driving of the vehicle according to the judgment result. It is possible to perform active autonomous driving control on the environment around the vehicle by executing the driving algorithm.

The processor 610 includes driving information and driving information input from the aforementioned driving information input interface 101 and driving information input interface 201 respectively, information on surrounding objects detected through the sensor unit 500, and memory. The autonomous driving of the vehicle may be controlled based on the map information stored in 620 and the autonomous driving algorithm. The processor 610 may be implemented as an embedded processor such as a complex instruction set computer (CISC) or reduced instruction set computer (RISC), or a dedicated semiconductor circuit such as an application specific integrated circuit (ASIC). .

In this embodiment, the processor 610 can control the autonomous driving of the own vehicle by analyzing each driving trajectory of the own vehicle and surrounding vehicles, and for this purpose, as shown in FIG. 611), a driving trajectory generating module 612, a driving trajectory analysis module 613, a driving control module 614, a trajectory learning module 615, and an occupant state determination module 616. Although FIG. 2 shows each module as an independent block according to its function, each module may be integrated into one module to integrally perform each function.

The sensor processing module 611 includes the driving information of the surrounding vehicles (ie, the location of the surrounding vehicles, and the speed and may further include a movement direction) may be determined. That is, the location of a nearby vehicle is determined based on a signal received through the lidar sensor 510, the location of a nearby vehicle is determined based on a signal received through the radar sensor 520, or the camera sensor 530 It is possible to determine the location of a surrounding vehicle based on an image captured through the image or to determine the location of a surrounding vehicle based on a signal received through the ultrasonic sensor 540 . To this end, as shown in FIG. 1 , the sensor processing module 611 may include a lidar signal processing module 611a, a radar signal processing module 611b, and a camera signal processing module 611c (ultrasound signal processing). modules may be further added to the sensor processing module 611). A method of determining the location of a surrounding vehicle by using the lidar sensor 510, the radar sensor 520, and the camera sensor 530 is not limited to a specific embodiment. In addition, the sensor processing module 611 may determine attribute information such as the size and type of the surrounding vehicle as well as the location, speed, and direction of movement of the surrounding vehicle. An algorithm for determining information such as and type may be predefined.

The driving trajectory generation module 612 may generate an actual driving trajectory and an expected driving trajectory of surrounding vehicles and an actual driving trajectory of the own vehicle. To this end, as shown in FIG. and an own vehicle driving trajectory generating module 612b.

First, the surrounding vehicle driving trajectory generation module 612a may generate an actual driving trajectory of the surrounding vehicle.

Specifically, the surrounding vehicle driving trajectory generation module 612a generates the surrounding vehicle based on driving information of the surrounding vehicle detected by the sensor unit 500 (ie, the position of the surrounding vehicle determined by the sensor processing module 611). An actual driving trajectory can be created. In this case, in order to generate an actual driving trajectory of the surrounding vehicle, the surrounding vehicle driving trajectory generation module 612a may refer to map information stored in the memory 620, and the location of the surrounding vehicle detected by the sensor unit 500 An actual driving trajectory of surrounding vehicles may be generated by cross-referencing an arbitrary location on the map information stored in the memory 620 and the map information stored in the memory 620 . For example, when a nearby vehicle is detected at a specific point by the sensor unit 500, the surrounding vehicle driving trajectory generation module 612a generates the location of the detected surrounding vehicle and an arbitrary location on map information stored in the memory 620. It is possible to specify the location of the currently detected surrounding vehicle on the map information by cross-referencing, and an actual driving trajectory of the surrounding vehicle can be generated by continuously monitoring the location of the surrounding vehicle as described above. That is, the surrounding vehicle driving trajectory generating module 612a maps the location of the surrounding vehicle detected by the sensor unit 500 to the location on the map information stored in the memory 620 based on the above cross reference and accumulates the surrounding An actual driving trajectory of the vehicle can be generated.

Meanwhile, the actual driving trajectory of the surrounding vehicle may be compared with the expected driving trajectory of the surrounding vehicle to be described later, and may be used to determine whether the map information stored in the memory 620 is inaccurate. In this case, when comparing an actual driving trajectory of a specific surrounding vehicle with an expected driving trajectory, a problem of misjudging that the map information is inaccurate despite being accurate may occur. For example, when the actual driving trajectory and the expected driving trajectory of a plurality of surrounding vehicles match, and the actual driving trajectory and the expected driving trajectory of a specific surrounding vehicle are different, only the actual driving trajectory of the specific surrounding vehicle is different from the expected driving trajectory. Comparisons can lead to misjudgement that map information is inaccurate even though it is accurate. Therefore, there is a need to determine whether the tendency of the actual driving trajectories of the plurality of surrounding vehicles deviates from the expected driving trajectory. You may. Furthermore, considering that drivers of surrounding vehicles tend to slightly move the steering wheel to the left and right during the driving process to drive on a straight path, the actual driving trajectory of surrounding vehicles may be created in a curved form rather than a straight line, which will be described later. In order to calculate an error between the predicted driving trajectories, the surrounding vehicle driving trajectory generation module 612a may generate an actual driving trajectory in a straight shape by applying a predetermined smoothing technique to the original actual driving trajectory generated in a curved shape. As the smoothing technique, various techniques such as interpolation for each position of surrounding vehicles may be employed.

Also, the surrounding vehicle driving trajectory generating module 612a may generate an expected driving trajectory of surrounding vehicles based on map information stored in the memory 620 .

As described above, the map information stored in the memory 620 may be 3D high-precision electronic map data, and thus the map information includes lanes, road center lines, regulatory lines, road boundaries, road center lines, traffic signs, road signs, and road shapes. In addition, dynamic and static information required for vehicle autonomous driving control, such as height and lane width, may be provided. Considering that vehicles generally drive in the center of the lane, it can be expected that the surrounding vehicles driving around the host vehicle will also run in the center of the lane. Therefore, the surrounding vehicle driving trajectory generating module 612a An expected driving trajectory of the vehicle may be generated as a center line of a road reflected in map information.

The own vehicle driving trajectory generating module 612b may generate an actual driving trajectory the own vehicle has traveled up to now based on the driving information of the own vehicle obtained through the aforementioned driving information input interface 201 .

Specifically, the own vehicle driving trajectory generation module 612b generates the location of the own vehicle obtained through the driving information input interface 201 (ie, the location information of the own vehicle obtained through the GPS receiver 260) and the memory 620 ), an actual driving trajectory of the own vehicle can be generated by cross-referencing an arbitrary location on the map information stored in ). For example, the current location of the own vehicle can be specified on the map information by cross-referencing the location of the own vehicle obtained through the driving information input interface 201 and an arbitrary location on the map information stored in the memory 620, As described above, an actual driving trajectory of the own vehicle may be generated by continuously monitoring the location of the own vehicle. That is, the own vehicle driving trajectory generation module 612b maps the location of the own vehicle obtained through the driving information input interface 201 to the location on the map information stored in the memory 620 based on the above cross reference and accumulates By doing so, it is possible to generate an actual driving trajectory of the own vehicle.

Also, the own vehicle driving trajectory generating module 612b may generate an expected driving trajectory along which the own vehicle should travel to a destination based on map information stored in a memory.

That is, the own vehicle driving trajectory generating module 612b stores the current location of the own vehicle obtained through the driving information input interface 201 (ie, the current location information of the own vehicle obtained through the GPS receiver 260) and the memory. An expected driving trajectory to a destination may be generated using the stored map information, and the predicted driving trajectory of the own vehicle may be generated as a center line of a road reflected in the map information stored in the memory 620, similarly to the predicted driving trajectory of surrounding vehicles. can

The driving trajectory generated by the surrounding vehicle driving trajectory generating module 612a and the own vehicle driving trajectory generating module 612b may be stored in the memory 620, and autonomous driving of the own vehicle is controlled by the processor 610 It can be used for various purposes in the process.

The driving trajectory analysis module 613 generates each driving trajectory generated by the driving trajectory generating module 612 and stored in the memory 620 (that is, the actual driving trajectory and expected driving trajectory of surrounding vehicles, and the actual driving trajectory of the own vehicle). It is possible to diagnose the reliability of the autonomous driving control for the current vehicle by analyzing the data. Diagnosis of reliability of autonomous driving control may be performed by analyzing a trajectory error between an actual driving trajectory and an expected driving trajectory of surrounding vehicles.

The driving control module 614 may perform a function of controlling autonomous driving of the own vehicle, and specifically, driving information and driving information input from the aforementioned driving information input interface 101 and driving information input interface 201, respectively. And, the information on the surrounding objects detected through the sensor unit 500 and the map information stored in the memory 620 are comprehensively used to process the autonomous driving algorithm, and control information is transmitted through the vehicle control output interface 401. In addition, the driving state information and warning information of the own vehicle are transferred to the output unit 300 through the occupant output interface 301 so that the lower control system 400 controls the autonomous driving of the host vehicle. can be made aware of. In addition, when the driving control module 614 integrally controls the autonomous driving as described above, the sensor processing module 611, the driving trajectory generating module 612, and the driving trajectory analysis module 613 analyze the own vehicle And by controlling the autonomous driving in consideration of the driving trajectory of the surrounding vehicle, it is possible to improve the precision of the autonomous driving control and improve the stability of the autonomous driving control.

The trajectory learning module 615 may perform learning or correction on the actual driving trajectory of the own vehicle generated by the own vehicle driving trajectory generating module 612b. For example, if the trajectory error between the actual driving trajectory and the predicted driving trajectory of the surrounding vehicle is greater than a preset threshold value, it is determined that the map information stored in the memory 620 is inaccurate and the actual driving trajectory of the own vehicle needs to be corrected. Accordingly, the driving trajectory of the own vehicle may be corrected by determining a lateral shift value for correcting the actual driving trajectory of the own vehicle.

The occupant condition determination module 616 may determine the occupant's condition and behavior based on the occupant's condition and biosignal detected by the aforementioned internal camera sensor 535 and the biometric sensor. The occupant's condition determined by the occupant's condition determination module 616 may be utilized in the process of controlling autonomous driving of the own vehicle or outputting a warning to the occupant.

Based on the foregoing, hereinafter, trajectory-based control that controls autonomous driving according to driving trajectory correction for each predetermined section on the route from the current location of the own vehicle to the destination and cluster following control that follows the driving of the driving cluster are mutually switched. An embodiment performed by doing so will be described.

The processor 610 of this embodiment may control autonomous driving of the own vehicle according to the driving trajectory generated by the aforementioned own vehicle driving trajectory generating module 612 based on map information stored in the memory 620 . Specifically, the processor 610 determines whether or not the driving trajectory of the own vehicle needs to be corrected based on the result of the sensor unit 500 detecting vehicles around the own vehicle, and determines the driving trajectory according to the determination result. It is possible to control the autonomous driving of the own vehicle by correcting it. Autonomous driving control according to the correction of the driving trajectory is defined as trajectory-based control in this embodiment.

In detail, the trajectory-based control is described in detail. As described above, the processor 610 (the driving trajectory generating module 612) of the present embodiment generates the surrounding vehicle based on the driving information of the surrounding vehicle detected by the sensor unit 500. An actual driving trajectory of the vehicle can be generated. That is, when a nearby vehicle is detected at a specific point by the sensor unit 500, the processor 610 cross-references the location of the detected surrounding vehicle with the location on the map information stored in the memory 620, thereby detecting current on map information. The location of the surrounding vehicle may be specified, and the actual driving trajectory of the surrounding vehicle may be generated by continuously monitoring the location of the surrounding vehicle as described above.

And, the processor 610 (the driving trajectory generation module 612) may generate an expected driving trajectory of surrounding vehicles based on the map information stored in the memory 620, in which case the processor 610 may generate An expected driving trajectory may be generated as a center line of a road reflected in map information.

Further, the processor 610 (the driving trajectory generation module 612) may generate an expected driving trajectory of the own vehicle based on the map information stored in the memory 620, in which case the processor 610 may generate the predicted driving trajectory of the own vehicle. An expected driving trajectory may be generated as a center line of a road reflected in map information.

When the actual driving trajectory and the expected driving trajectory of the surrounding vehicle and the expected driving trajectory of the host vehicle are generated, the processor 610 (the trajectory learning module 615 of the vehicle) compares the actual driving trajectory and the expected driving trajectory of the surrounding vehicle to determine the autonomous driving trajectory. It may be determined whether correction of the expected driving trajectory of the vehicle is required. Specifically, the processor 610 may determine that correction of the predicted driving trajectory of the own vehicle is necessary when a trajectory error between the actual driving trajectory and the predicted driving trajectory of the surrounding vehicle is equal to or greater than a preset threshold value. That is, as described above, if the trajectory error between the actual driving trajectory and the expected driving trajectory of the surrounding vehicle is greater than or equal to the threshold value, it may be determined that the map information stored in the memory 620 is inaccurate, and thus the map information stored in the memory 620 The predicted driving trajectory of the host vehicle generated based on the ? also needs to be corrected. In this case, the processor 610 may correct the expected driving trajectory of the host vehicle based on a comparison result between the actual driving trajectory and the expected driving trajectory of the surrounding vehicles, and for example, the The predicted driving trajectory of the own vehicle may be corrected by shifting the predicted driving trajectory of the host vehicle to the left or right by the difference. Accordingly, the processor 610 may perform trajectory-based control for controlling autonomous driving of the own vehicle according to the corrected predicted driving trajectory.

On the other hand, the processor 610, when the driving route to the destination of the host vehicle (hereinafter, the first driving route) overlaps with the driving route (hereinafter, the second driving route) of the driving cluster formed by the plurality of group vehicles, the driving of the driving group. It is also possible to control the autonomous driving of the own vehicle to follow. Control following the driving cluster is defined as cluster following control in this embodiment. A driving cluster is formed of a plurality of cluster vehicles consisting of one leader vehicle and one or more follower vehicles, and means a cluster that drives on the road while sharing driving information between vehicles through vehicle-to-vehicle communication and considering the external environment. When a plurality of driving clusters exist in Vehicle to Everything (V2X) or Vehicle to Vehicle (V2V) communication coverage based on the own vehicle, the processor 610 provides information on each driving cluster from each leader vehicle of each driving cluster (eg : Specification information of the leader vehicle, cumulative travel distance of each driving group, etc.) may be received and output through the above-described user terminal 120 to be provided to the occupant, and the occupant may check information on each driving group and follow it. You can select the driving cluster you want to do. If there is no driving cluster in the V2X or V2V communication coverage based on the own vehicle, the processor 610 may receive information on each driving cluster from a separate external server.

When the cluster following control is performed, the processor 610 determines the overlapping of the first driving route and the second driving route from the merging point where the overlap between the first driving route of the host vehicle and the second driving route of the driving cluster starts. Cluster follow-up control may be performed up to the end of the withdrawal point. That is, the processor 610 may perform cluster following control rather than trajectory-based control in an overlapping section between the driving route of the own vehicle and the driving route of the driving cluster. In this case, the processor 610 may determine a joining point and a leaving point for performing the cluster following control from the plurality of candidate joining points and the plurality of candidate leaving points before performing the cluster following control, which will be described later. .

In this embodiment, the processor 610 may switch between trajectory-based control and cluster following control according to whether a predefined control switching condition is satisfied, and the control switching condition converts from trajectory-based control to cluster following control. and a trajectory-based control switching condition for switching from cluster following control to trajectory-based control. That is, the processor 610 switches between trajectory-based control and cluster following control according to whether or not the control conversion condition according to the driving environment of the own vehicle is satisfied, thereby reducing the autonomous driving control computational load of the own vehicle and reaching the destination In the process, the occupant's intervention in driving control of the vehicle is minimized, so that the occupant's convenience is improved and at the same time, it is possible to reach the destination in the shortest time.

Referring to a configuration in which trajectory-based control and cluster following control are mutually switched depending on whether a control switching condition is satisfied, the processor 610 may first perform trajectory-based control with the current location of the own vehicle as a starting point. When the host vehicle arrives at a merging point in the process of performing trajectory-based control from the current location of the vehicle, it is determined that the flock following control transition condition is satisfied, and cluster following control may be performed.

That is, the processor 610 may perform trajectory-based control from the current location of the own vehicle to the merging point, and when the own vehicle reaches the merging point, the control of the own vehicle may be switched from the trajectory-based control to the cluster following control. . The processor 610 may output an alarm through the output unit 300 before reaching the merging point (eg, 1 km before) so that the occupants may recognize that they are merging into the driving group. When transitioning from trajectory-based control to cluster following control, the processor 610 may send a driving cluster joining request to the leader vehicle of the driving cluster and, upon receiving approval from the leader vehicle, allow the host vehicle to join the driving cluster, It is possible to allow the own vehicle to join a predetermined position within the driving cluster within a range in which the ranks of the vehicles are not disturbed.

The processor 610 may perform trajectory-based control by determining that the trajectory-based control transition condition is satisfied when the host vehicle reaches the exit point in the process of performing cluster following control from the confluence point.

That is, the processor 610 may perform cluster following control from the joining point to the leaving point, and when the own vehicle reaches the leaving point, the processor 610 may switch the control of the own vehicle from cluster following control to trajectory based control again. The processor 610 may output an alarm through the output unit 300 before reaching the departure point (eg, 1 km before) so that the occupant may recognize the withdrawal from the driving group.

Meanwhile, as described above, the processor 610 may determine a joining point and a leaving point from a plurality of candidate joining points and a plurality of candidate leaving points. Joining and exiting points can be determined based on the time required to reach them.

Specifically, the processor 610 determines the time required for the host vehicle to reach the candidate joining point from the current location based on the trajectory-based control and the time required for the own vehicle to reach the candidate joining point from the candidate joining point based on the cluster following control. A candidate joining point and a candidate leaving point at which the total required time, which is the sum of the required time and the time required to reach the destination from the candidate leaving point based on the trajectory-based control, are minimized, may be determined as the joining point and the leaving point, respectively.

That is, the processor 610 may identify a plurality of candidate joining points where the overlap between the first and second driving routes starts, and identify a plurality of candidate exit points where the overlap between the first and second driving routes ends; Among the plurality of candidate joining points and candidate leaving points confirmed as described above, a candidate joining point and a candidate leaving point at which a total time required to reach a destination is minimized may be determined as the joining point and the leaving point. Furthermore, when determining joining points and leaving points, the processor 610 may further consider ease of joining and leaving, such as a degree of congestion or an accident risk of each candidate joining point and candidate leaving point.

In the above, the configuration in which trajectory-based control and cluster following control are mutually switched at the own vehicle level has been described, and along with the above-described configuration, this embodiment requires to sense surrounding objects in the driving cluster level that performs cluster driving. We present a configuration that reduces the total resource of the system to be

Specifically, when the processor 610 performs cluster following control after the host vehicle joins the driving cluster, the surrounding object detection area of the sensor unit 500 according to the relative position of the own vehicle to the cluster vehicles belonging to the driving cluster. can be varied.

That is, since a plurality of group vehicles belonging to the driving cluster drive under the same driving environment, rather than detecting all objects around each group vehicle through a sensing device mounted thereon, each group vehicle within the driving cluster A method of separating the surrounding object detection area according to the location of the surrounding object detection area, detecting the surrounding object only for the corresponding surrounding object detection area, and then sharing the detection result among group vehicles may be more efficient in terms of reducing system resources of each group vehicle. In order to realize the separation of the surrounding object detection area at the driving cluster level as described above, the processor 610 of the present embodiment detects the surrounding objects of the sensor unit 500 according to the relative position of the own vehicle to the cluster vehicles belonging to the driving cluster. It can operate to change the area.

In order to implement a function of varying the surrounding object detection area of the sensor unit 500 according to the relative position of the host vehicle within the driving cluster, the processor 610 performs a cluster following control using a predefined group classification algorithm. The driving group is classified into a preceding driving group, a middle driving group, and a trailing driving group by using, and a driving group to which the host vehicle belongs is determined among each driving group, and the surrounding object detection area of the sensor unit 500 is determined according to the determination result. can be variable. A group classification algorithm for classifying a driving cluster into a leading driving group, a middle driving group, and a trailing driving group can be implemented through various design methods. It can be implemented as an algorithm that identifies and calculates the longitudinal (i.e., driving direction) length of the driving cluster using the identified location, and then divides into a plurality of driving groups based on the calculated longitudinal length.

If the driving group is classified into a plurality of driving groups, the processor 610 may determine a driving group to which the host vehicle belongs among the driving groups and change the surrounding object detection area of the sensor unit 500 according to the determination result. Specifically, the processor 610 detects surrounding objects in front of the host vehicle (defined as including the front side) through the sensor unit 500 when the host vehicle belongs to the preceding driving group (ie, the sensor unit ( 500) is changed to the front area), and when the vehicle belongs to the middle driving group, the sensor unit 500 detects the surrounding objects on the side of the vehicle (ie, the sensor unit 500 The surrounding object detection area is changed to the side area), and when the own vehicle belongs to the following driving group, the surrounding object behind the own vehicle (defined as including the rear side) may be detected through the sensor unit 500. (That is, the surrounding object detection area of the sensor unit 500 may be changed to the rear area).

The fact that the surrounding object detection area of the sensor unit 500 is changed to the front area means a sensor for detecting the front area (ie, front lidar sensor 511, front radar sensor 521, front camera sensor 531) is necessarily activated and other sensors may be selectively activated according to the driving environment, and that the surrounding object detection area of the sensor unit 500 is changed to the lateral area means that the sensor for detecting the lateral area (ie, the left This may mean that the radar sensor 522, the right radar sensor 522, the left camera sensor 532, and the right camera sensor 533) are necessarily activated and other sensors are selectively activated according to the driving environment. If the surrounding object detection area of 500 is changed to the rear area, the sensors for detecting the rear area (ie, the rear lidar sensor 513, the rear radar sensor 524, and the rear camera sensor 534) must be activated. and other sensors may be selectively activated according to the driving environment.

Furthermore, as shown in FIG. 7 , considering the case where a plurality of group vehicles are group driving on one lane, only the leader vehicle and the last vehicle correspond to the preceding driving group and the trailing driving group, and the middle driving group may correspond to clustered vehicles located between the leader vehicle and the last vehicle, and a group classification algorithm for classifying such a preceding driving group, a middle driving group, and a following driving group may be predefined by a designer. In the example of FIG. 7 , the surrounding object detection area of the sensor unit 500 of the host vehicle becomes the front area and the side area when the host vehicle belongs to the preceding driving group (ie, the leader vehicle), and belongs to the middle driving group. When the vehicle belongs to the following driving group (ie, the last vehicle), it becomes the rear area and the side area.

When the function of the processor 610 as described above is applied to each cluster vehicle belonging to a driving cluster, each cluster vehicle varies the surrounding object detection area of the sensor unit 500 mounted on each vehicle according to its location within the driving cluster. it works to make it happen. Accordingly, cluster vehicles belonging to the preceding driving group detect surrounding objects in front of the driving cluster, cluster vehicles belonging to the middle driving group detect surrounding objects on the side of the driving cluster, and cluster vehicles belonging to the trailing driving group. detects surrounding objects behind the driving cluster. Therefore, since the surrounding object detection for the front, left and right sides, and rear of the driving cluster is shared by each group vehicle belonging to the driving cluster, the total resource of the system required for detecting the surrounding object at the driving cluster level is reduced. you can make huge savings.

Meanwhile, when performing cluster following control, the processor 610 varies the surrounding object detection area of the sensor unit 500 according to the relative position of the own vehicles in the driving cluster, and the processor 610, respectively, installed in each cluster vehicle. The sensing parameter of the sensor unit 500 may be controlled to have a value mutually dependent on the sensing parameter of the sensor device, wherein the sensing parameter includes at least one of a field of view (FOV) of the sensor and a sensor output. can be defined

Having a mutually dependent relationship between the sensing parameters of the sensor unit 500 of the own vehicle and the sensing parameters of the sensor devices of each group vehicle is a means for optimizing the detection area and detection performance for surrounding objects at the driving cluster level. function as Specifically, since the own vehicle and other group vehicles form one driving cluster and travel, the surrounding object detection area by the sensor unit 500 of the own vehicle and the surrounding object detection area of the sensor device of other group vehicles may overlap. Conversely, even when driving in one driving cluster, if the distance between the own vehicle and other cluster vehicles is long, surrounding objects can be detected through the sensor unit 500 of the own vehicle and the sensor devices of other cluster vehicles. A blind area may exist. As described above, when each surrounding object detection area of the sensor device between the sensor unit 500 of the own vehicle and other group vehicles overlaps, unnecessary consumption of power and resources is caused when viewed from the driving cluster level. The angle of view needs to be controlled so that the overlapping range of the angle of view of the sensor unit 500 of the own vehicle and the sensor devices of other group vehicles is minimized. Also, as described above, even when a blind spot exists, it is necessary to control the view angle to remove the blind spot by expanding the view angle of one or more of the sensor unit 500 of the own vehicle and the sensor devices of other group vehicles.

Furthermore, the importance of detection of surrounding objects may change depending on the driving environment. Conversely, in a driving environment where the risk of accidents is low because there are few other vehicles around the driving cluster and fixed facilities such as guardrails or median barriers continuously exist, the importance of detection for surrounding objects is relatively high. can be said to be low. When a nearby object is detected using only a constant sensor output without considering the importance of detecting the surrounding object according to the driving environment, the detection of the surrounding object having a high importance may be missed, and the surrounding object having a low importance may be detected by a high sensor. It can also be detected through the output, which may cause unnecessary power consumption of the vehicle.

In order to solve the above problem, the processor 610 according to the present embodiment is configured to have a value interdependent with the sensing parameters of the sensor devices mounted on each group vehicle, that is, among the sensing parameters of the sensor unit 500, that is, the angle of view and sensor output. You can control more than one. At this time, the processor 610 may control the sensing parameter of the sensor unit 500 according to the sensor adjustment signal transmitted from the leader vehicle of the driving cluster, and the sensor adjustment signal detects surrounding objects at the level of the driving cluster. It is defined as a signal generated for each group vehicle by the leader vehicle based on the driving environment of the driving cluster and the position of each cluster vehicle within the driving cluster and transmitted to each cluster vehicle so that the area and detection performance can be optimized. can

From the point of view of the leader vehicle, the driving environment of the driving group (e.g., whether there are many other vehicles around the driving group, or the current Whether the driving point corresponds to a point where accidents frequently occur) can be identified, and the location of each grouped vehicle can be identified based on V2V communication. Accordingly, the leader vehicle may generate a sensor adjustment signal for each group vehicle to optimize the detection area and detection performance of surrounding objects at the driving cluster level. Each group vehicle can receive the sensor adjustment signal assigned to it from the leader vehicle and adjust one or more of the angle of view and sensor output of the sensor device equipped with it. Upon reception, one or more of the angle of view of the sensor unit 500 and the sensor output may be adjusted.

If the host vehicle is in the position of the leader vehicle of the driving cluster, the above-described operation of the leader vehicle may be performed by the host vehicle, that is, the host vehicle may perform the detection result of the surrounding object by the sensor unit 500 and the driving Sensor adjustment signals may be generated for each group vehicle belonging to the driving cluster based on the location of each group vehicle within the cluster, and then transmitted to each group vehicle.

Furthermore, the configuration in which the surrounding object detection area of the sensor unit 500 is varied according to the relative position of the host vehicle within the aforementioned driving group and the configuration in which the sensing parameter of the sensor unit 500 is controlled by the sensor adjustment signal are They may be combined in a complementary manner. That is, sensing of the sensor unit 500 by the sensor adjustment signal transmitted from the leader vehicle in a state where the surrounding object detection area of the sensor unit 500 is changed according to the relative position of the own vehicle to the group vehicles belonging to the driving cluster. An embodiment in which parameters are controlled may be implemented, whereby the detection area and detection performance for surrounding objects at the driving cluster level may be maximized.

8 and 9 are flowcharts for explaining an autonomous driving method according to an embodiment of the present invention.

Referring to FIG. 8 , in an autonomous driving method according to an embodiment of the present invention, a processor 610 corrects an expected driving trajectory of the own vehicle based on a result of the sensor unit 500 detecting vehicles around the own vehicle Step S100 of determining whether it is necessary to do so, and performing trajectory-based control for controlling autonomous driving of the host vehicle by correcting the expected driving trajectory according to the determination result, and When the first driving route overlaps with the second driving route of a driving cluster formed by a plurality of group vehicles, a step S200 of performing cluster following control for controlling autonomous driving of own vehicles to follow the driving of the driving cluster may be included. there is. In this case, the processor 610 may switch and perform steps S100 and S200 depending on whether a predefined control conversion condition is satisfied.

In step S100, the processor 610 generates an actual driving trajectory of the surrounding vehicle based on the driving information of the surrounding vehicle detected by the sensor unit 500, and calculates the driving trajectory of the surrounding vehicle based on the map information stored in the memory 620. An expected driving trajectory is generated, and when the trajectory error between the actual driving trajectory and the predicted driving trajectory of the surrounding vehicle is greater than or equal to a preset threshold value, it is determined that the predicted driving trajectory of the own vehicle needs to be corrected. Accordingly, the processor 610 performs trajectory-based control for controlling autonomous driving of the own vehicle according to the corrected expected driving trajectory.

In step S200, based on the driving direction of the host vehicle to the destination, cluster following control from the merging point where the overlap between the first and second travel routes starts to the exit point where the overlap between the first and second travel routes ends. do

Referring to FIG. 9 for a configuration in which trajectory-based control and cluster following control are switched depending on whether or not a control switching condition is satisfied, the processor 610 performs trajectory-based control from the current location of the host vehicle ( S10) When the host vehicle reaches the convergence point (S20), it is determined that the flock following control transition condition is satisfied and cluster following control is performed (S30), and the host vehicle is performed in the process of performing cluster following control from the confluence point (S30). When this withdrawal point is reached (S40), it is determined that the condition for switching to the trajectory-based control is satisfied, and the trajectory-based control is performed (S50).

The processor 610 determines a joining point and a leaving point for performing cluster following control from a plurality of candidate joining points and a plurality of candidate leaving points, and in order to minimize the time required for the own vehicle to reach the destination, step S200. The time required for the own vehicle to reach the candidate joining point from the current position based on the trajectory-based control, the time required for the own vehicle to reach the candidate joining point from the candidate joining point based on the swarm following control, and the trajectory based Based on the control, a candidate joining point and a candidate leaving point at which a total required time, which is the sum of times required to reach a destination from a candidate leaving point, are minimized are determined as the joining point and the leaving point, respectively.

Meanwhile, in step S200, the processor 610 classifies the driving group into a preceding driving group, a middle driving group, and a following driving group using a predefined group classification algorithm, and determines a driving group to which the own vehicle belongs among each driving group. Accordingly, the surrounding object detection area of the sensor unit 500 may be varied according to the determination result. Specifically, the processor 610 detects surrounding objects in front of the host vehicle through the sensor unit 500 when the host vehicle belongs to the preceding driving group, and detects the sensor unit 500 when the host vehicle belongs to the middle driving group. Objects around the side of the own vehicle are detected through the sensor unit 500, and when the vehicle belongs to the following driving group, objects around the rear of the own vehicle can be detected through the sensor unit 500.

In addition, in step S200, the processor 610 may control the sensing parameters of the sensor units 500 to have mutually dependent values with the sensing parameters of the sensor devices mounted on each group vehicle. Specifically, the processor 610 may control the sensing parameter of the sensor unit 500 according to the sensor adjustment signal transmitted from the leader vehicle of the driving cluster, and the sensor adjustment signal is a detection area for surrounding objects at the level of the driving cluster. and a signal generated by the leader vehicle for each group vehicle based on the driving environment of the driving cluster and the position of each cluster vehicle within the driving cluster and transmitted to each group vehicle so that detection performance can be optimized. there is. If the own vehicle is in the position of the leader vehicle of the driving cluster, the processor 610 determines the driving cluster based on the result of the detection of surrounding objects by the sensor unit 500 and the position of each group vehicle in the driving cluster. Sensor adjustment signals may be respectively generated for each clustered vehicle belonging to and then transmitted to each clustered vehicle.

As described above, in this embodiment, the trajectory-based control for controlling autonomous driving according to the driving trajectory correction for each predetermined section on the route from the current location of the autonomous vehicle to the destination and the cluster following control for following the driving of the driving cluster are mutually switched and performed. By doing so, it is possible to reduce the autonomous driving control computational load of the autonomous vehicle and minimize the occupant's intervention in the vehicle's driving control in the process of reaching the destination, thereby improving the convenience of the occupants and making it possible to reach the destination in the shortest time. can do.

In addition, since the present embodiment operates to vary the surrounding object detection area of the sensor unit according to the relative position of the own vehicle to other cluster vehicles belonging to the driving cluster when performing cluster following control, the level of all cluster vehicles during cluster driving is operated. As seen from , the total resource of the system required for each cluster vehicle belonging to the driving cluster to sense surrounding objects can be reduced.

Although the present invention has been described with reference to the embodiments shown in the drawings, it should be noted that this is only exemplary and various modifications and equivalent other embodiments are possible from those skilled in the art to which the technology pertains. will understand Therefore, the true technical protection scope of the present invention should be defined by the claims below.

100: user input unit 101: driving information input interface
110: driving mode switch 120: user terminal
200: driving information detector 201: driving information input interface
210: steering angle sensor 220: APS/PTS
230: vehicle speed sensor 240: acceleration sensor
250: yaw/pitch/roll sensor 260: GPS receiver
300: output unit 301: occupant output interface
310: speaker 320: display device
400: sub-control system 401: vehicle control output interface
410: engine control system 420: braking control system
430: steering control system 500: sensor unit
510: lidar sensor 511: front lidar sensor
512: upper lidar sensor 513: rear lidar sensor
520: radar sensor 521: front radar sensor
522: left radar sensor 523: right radar sensor
524: rear radar sensor 530: camera sensor
531: front camera sensor 532: left camera sensor
533: right camera sensor 534: rear camera sensor
535: internal camera sensor 540: ultrasonic sensor
600: autonomous driving integrated control unit 610: processor
611: sensor processing module 611a: lidar signal processing module
611b: radar signal processing module 611c: camera signal processing module
612: driving trajectory generation module 612a: surrounding vehicle driving trajectory generation module
612b: own vehicle driving trajectory generation module 613: driving trajectory analysis module
614: driving control module 615: trajectory learning module
616: occupant state determination module 620: memory
700: server

Claims (24)

a sensor unit that detects surrounding objects including surrounding vehicles of the own vehicle in autonomous driving;
a memory for storing map information; and
A processor controlling autonomous driving of the host vehicle according to an expected driving trajectory generated based on map information stored in the memory;
the processor,
Based on the result of the sensor unit detecting vehicles around the host vehicle, it is determined whether it is necessary to correct the expected driving trajectory of the own vehicle, and based on the determination result, the predicted driving trajectory is corrected to determine the Perform trajectory-based control to control autonomous driving;
Cluster following control for controlling the autonomous driving of the own vehicle to follow the driving of the driving cluster when the first driving route to the destination of the own vehicle overlaps with the second driving route of the driving cluster formed by a plurality of group vehicles. to perform,
the processor,
When performing the cluster following control, the sensing parameters of the sensor units are controlled to have values mutually dependent on the sensing parameters of the sensor devices mounted on each cluster vehicle, and the sensing parameters are field of view (FOV) and Include one or more of the sensor outputs;
The control of the sensing parameter includes view angle reduction control to reduce an overlapping range of view angles of the sensor unit of the own vehicle and sensor devices of other group vehicles, or view angle expansion control to remove blind spots. , autonomous driving devices.
According to claim 1,
When the processor performs the trajectory-based control,
An actual driving trajectory of the surrounding vehicle is generated based on the driving information of the surrounding vehicle detected by the sensor unit, an expected driving trajectory of the surrounding vehicle is generated based on the map information stored in the memory, and An autonomous driving device characterized in that it is determined that the expected driving trajectory of the own vehicle needs to be corrected when a trajectory error between an actual driving trajectory and an expected driving trajectory is equal to or greater than a preset threshold.
According to claim 1,
When the processor performs the cluster follow-up control,
Based on the direction in which the host vehicle travels to the destination, the cluster following control from a merging point where the overlapping between the first and second driving routes starts to a leaving point where the overlapping between the first and second driving routes ends Autonomous driving device, characterized in that for performing.
According to claim 3,
The processor converts and performs the trajectory-based control and the cluster following control according to whether a predefined control switching condition is satisfied,
The control switching condition includes a cluster following control switching condition for switching from the trajectory based control to the cluster following control, and a trajectory based control switching condition for switching from the cluster following control to the trajectory based control. autonomous driving device.
According to claim 4,
the processor,
In the process of performing the trajectory-based control from the current location of the own vehicle, when the own vehicle reaches the merging point, it is determined that the flock following control conversion condition is satisfied and the cluster following control is performed. autonomous driving device.
According to claim 5,
the processor,
and performing the trajectory-based control by determining that the trajectory-based control conversion condition is satisfied when the host vehicle reaches the exit point in the process of performing cluster following control from the confluence point. .
According to claim 6,
the processor,
determining the joining point and the leaving point for performing the cluster following control from a plurality of candidate joining points and a plurality of candidate leaving points;
A time required for the own vehicle to reach a candidate joining point from a current location based on the trajectory-based control, a time required for the own vehicle to reach a candidate joining point from a candidate joining point based on the swarm following control, and , Based on the trajectory-based control, determining a candidate joining point and a candidate leaving point at which a total required time, which is the sum of times required to reach a destination from a candidate leaving point, is minimized as the joining point and the leaving point, respectively. autonomous driving device.
According to claim 1,
When the processor performs the cluster follow-up control,
The autonomous driving device of claim 1 , wherein a surrounding object detection area of the sensor unit is varied according to a relative position of the host vehicle to the cluster vehicles belonging to the driving cluster.
According to claim 8,
When the processor performs the cluster follow-up control,
The driving group is classified into a preceding driving group, a middle driving group, and a trailing driving group using a predefined group classification algorithm, and a driving group to which the own vehicle belongs is determined among the driving groups, and the sensor unit according to the determination result. An autonomous driving device characterized by varying a surrounding object detection area.
According to claim 9,
the processor,
When the own vehicle belongs to the preceding driving group, an object around the front of the own vehicle is detected through the sensor unit, and when the own vehicle belongs to the middle driving group, an object around the side of the own vehicle is detected through the sensor unit. and, when the host vehicle belongs to the following driving group, detects an object around the rear of the host vehicle through the sensor unit.
According to claim 1,
the processor,
The sensing parameter of the sensor unit is controlled according to a sensor adjustment signal transmitted from the leader vehicle of the driving cluster, and the sensor adjustment signal is used to optimize the detection area and detection performance of surrounding objects at the level of the driving cluster. The autonomous driving device according to claim 1 , wherein each group vehicle is generated by the leader vehicle based on a group driving environment and a position of each group vehicle within the driving group and transmitted to each group vehicle.
According to claim 11,
the processor,
When the own vehicle is in the position of the leader vehicle of the driving cluster, each cluster belonging to the driving cluster is classified based on a result of detecting a surrounding object by the sensor unit and the position of each group vehicle within the driving cluster. The autonomous driving device characterized in that the sensor adjustment signal is respectively generated for each vehicle and then transmitted to each group vehicle.
A sensor unit for detecting surrounding objects including surrounding vehicles of the own vehicle in autonomous driving, a memory for storing map information, and autonomous driving of the own vehicle according to an expected driving trajectory generated based on the map information stored in the memory A method for controlling autonomous driving in an autonomous driving system including a controlling processor, comprising:
The processor determines whether it is necessary to correct the expected driving trajectory of the own vehicle based on a result of the sensor unit detecting vehicles around the own vehicle, and corrects the expected driving trajectory according to the determination result performing trajectory-based control for controlling autonomous driving of the own vehicle; and
The processor controls the autonomous driving of the own vehicle to follow the driving of the driving cluster when the first driving route to the destination of the own vehicle overlaps with the second driving route of the driving cluster formed by a plurality of group vehicles. Including; performing cluster follow-up control to
In the step of performing the cluster following control, the processor,
Control a sensing parameter of the sensor unit to have a value mutually dependent on a sensing parameter of a sensor device mounted on each group vehicle, wherein the sensing parameter includes at least one of a field of view (FOV) and sensor output,
The control of the sensing parameter includes view angle reduction control to reduce an overlapping range of view angles of the sensor unit of the own vehicle and sensor devices of other group vehicles, or view angle expansion control to remove blind spots. Characterized in that, an autonomous driving method.
According to claim 13,
In the step of performing the trajectory-based control, the processor,
An actual driving trajectory of the surrounding vehicle is generated based on the driving information of the surrounding vehicle detected by the sensor unit, an expected driving trajectory of the surrounding vehicle is generated based on the map information stored in the memory, and An autonomous driving method characterized in that it is determined that the expected driving trajectory of the own vehicle needs to be corrected when a trajectory error between an actual driving trajectory and an expected driving trajectory is equal to or greater than a preset threshold.
According to claim 13,
In the step of performing the cluster following control, the processor,
Based on the direction in which the host vehicle travels to the destination, the cluster following control from a merging point where the overlapping between the first and second driving routes starts to a leaving point where the overlapping between the first and second driving routes ends Autonomous driving method characterized in that for performing.
According to claim 15,
The processor converts and performs the trajectory-based control and the cluster following control according to whether a predefined control switching condition is satisfied,
The control switching condition includes a cluster following control switching condition for switching from the trajectory based control to the cluster following control, and a trajectory based control switching condition for switching from the cluster following control to the trajectory based control. How to do autonomous driving.
According to claim 16,
the processor,
In the process of performing the trajectory-based control from the current location of the own vehicle, when the own vehicle reaches the merging point, it is determined that the flock following control conversion condition is satisfied and the cluster following control is performed. How to do autonomous driving.
According to claim 17,
the processor,
When the host vehicle reaches the exit point in the process of performing cluster following control from the joining point, the autonomous driving method characterized in that the trajectory-based control is performed by determining that the trajectory-based control conversion condition is satisfied. .
According to claim 18,
In the step of performing the cluster following control, the processor,
determining the joining point and the leaving point for performing the cluster following control from a plurality of candidate joining points and a plurality of candidate leaving points;
A time required for the own vehicle to reach a candidate joining point from a current location based on the trajectory-based control, a time required for the own vehicle to reach a candidate joining point from a candidate joining point based on the swarm following control, and , Based on the trajectory-based control, determining a candidate joining point and a candidate leaving point at which a total required time, which is the sum of times required to reach a destination from a candidate leaving point, is minimized as the joining point and the leaving point, respectively. How to do autonomous driving.
According to claim 13,
In the step of performing the cluster following control, the processor,
and varying a surrounding object detection area of the sensor unit according to a relative position of the host vehicle to the cluster vehicles belonging to the driving cluster.
According to claim 20,
In the step of performing the cluster following control, the processor,
The driving group is classified into a preceding driving group, a middle driving group, and a trailing driving group using a predefined group classification algorithm, and a driving group to which the own vehicle belongs is determined among the driving groups, and the sensor unit according to the determination result. Autonomous driving method characterized by varying the surrounding object detection area
According to claim 21,
In the step of performing the cluster following control, the processor,
When the own vehicle belongs to the preceding driving group, an object around the front of the own vehicle is detected through the sensor unit, and when the own vehicle belongs to the middle driving group, an object around the side of the own vehicle is detected through the sensor unit. and detecting an object around the rear of the own vehicle through the sensor unit when the own vehicle belongs to the following driving group.
According to claim 13,
In the step of performing the cluster following control, the processor,
The sensing parameter of the sensor unit is controlled according to a sensor adjustment signal transmitted from the leader vehicle of the driving cluster, and the sensor adjustment signal is used to optimize the detection area and detection performance of surrounding objects at the level of the driving cluster. The autonomous driving method according to claim 1 , wherein each group vehicle is generated by the leader vehicle based on a group driving environment and a position of each group vehicle within the driving group and transmitted to each group vehicle.
According to claim 23,
In the step of performing the cluster following control, the processor,
When the own vehicle is in the position of the leader vehicle of the driving cluster, each cluster belonging to the driving cluster is classified based on a result of detecting a surrounding object by the sensor unit and the position of each group vehicle within the driving cluster. The autonomous driving method characterized in that the sensor adjustment signal is respectively generated for each vehicle and then transmitted to each group vehicle.

Images