KR102644324B1 - Autonomous driving apparatus and method - Google Patents

Abstract

The present invention relates to an autonomous driving device and method, which includes a sensor unit that detects vehicles around a self-driving vehicle, a memory that stores map information, and a device that controls autonomous driving of the self-vehicle based on the map information stored in the memory. It includes a processor, wherein the processor generates an actual driving trajectory of the surrounding vehicle based on driving information of the surrounding vehicle detected by the sensor unit, and generates an expected driving trajectory of the surrounding vehicle based on map information stored in the memory, A reliability diagnosis of autonomous driving control for the own vehicle is performed based on the size of the trajectory error between the generated actual driving trajectory and the expected driving trajectory, or the cumulative addition amount of the trajectory error, and as a result of performing the reliability diagnosis, the autonomous driving for the own vehicle is performed. If control is determined to be unreliable, correction processing is performed on one or more of the sensor unit and map information to ensure reliability of autonomous driving control.

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 automobile industry is moving toward implementing autonomous driving that minimizes driver intervention in vehicle driving. An autonomous vehicle refers to a vehicle that recognizes the surrounding environment through external information detection and processing functions when driving, determines its own driving path, and drives independently using its own power.

Self-driving vehicles can drive to their destination on their own, preventing collisions with obstacles in the driving path and adjusting vehicle speed and driving direction according to the shape of the road, without the driver having to operate the steering wheel, accelerator pedal, or brakes. there is. For example, acceleration can be performed on a straight road, and deceleration can be performed on a curved road by changing the driving direction in response to the curvature of the 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 status of the vehicle must be continuously monitored to control 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 to detect surrounding objects such as surrounding vehicles, pedestrians, and fixed facilities. Data output from these sensors is used to determine information about the driving environment, such as status information such as the location, shape, direction of movement, and speed of surrounding objects.

Furthermore, autonomous vehicles use pre-stored map data to determine and correct the vehicle's position to optimally determine the driving path and driving lane, control the vehicle's driving so that it does not deviate from the determined path and lane, and control the vehicle's driving to prevent sudden changes in the surrounding area. It also provides functions to perform defense and avoidance operations against incoming vehicles or hazards present on the driving path.

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

The purpose of one aspect of the present invention is to provide an autonomous driving device and method for improving the driving stability and driving accuracy of an autonomous vehicle by precisely diagnosing the reliability of autonomous driving control performed on an autonomous vehicle.

An autonomous driving device according to an aspect of the present invention includes a sensor unit that detects vehicles around a self-driving host vehicle, a memory that stores map information, and controls autonomous driving of the host vehicle based on the map information stored in the memory. and a processor, wherein 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 predicts the surrounding vehicle based on the map information stored in the memory. Generates a driving trajectory, performs a reliability diagnosis of autonomous driving control for the own vehicle based on the size of the trajectory error between the generated actual driving trajectory and the expected driving trajectory, or a cumulative addition amount of the trajectory error, and determines the reliability If the autonomous driving control of the own vehicle is determined to be unreliable as a result of the diagnosis, correction processing is performed on one or more of the sensor unit and the map information to ensure reliability of the autonomous driving control. It is characterized by

In the present invention, the processor determines that autonomous driving control for the host vehicle is unreliable if a state occurs in which the size of the trajectory error is greater than a preset first threshold within a first preset threshold time. do.

In the present invention, the processor additionally performs the reliability diagnosis using the accumulated amount of the trajectory error while the size of the trajectory error is maintained below the first threshold during the first threshold time. Do it as

In the present invention, the processor, within a second threshold time preset to a value greater than the first threshold time, while the size of the trajectory error is maintained below the first threshold during the first threshold time, When a state occurs in which the accumulated trajectory error is accumulated and the accumulated addition amount is greater than or equal to a preset second threshold, autonomous driving control of the own vehicle is determined to be unreliable.

In the present invention, the sensor unit includes a plurality of sensors for detecting the surrounding vehicles, and when the processor determines that autonomous driving control for the own vehicle is unreliable, the sensor unit includes a plurality of sensors included in the sensor unit. It is characterized by performing correction processing on the sensor unit through a method of matching sensors.

In the present invention, the processor is characterized in that it performs correction processing on the map information stored in the memory by updating the map information stored in the memory using new map information received from the outside.

In the present invention, when it is determined that the autonomous driving control of the own vehicle is unreliable, the processor stores the actual driving trajectory of the surrounding vehicle in the memory, and the actual driving trajectory of the surrounding vehicle stored in the memory. It is characterized by verifying the updated map information with the new map information using .

An autonomous driving method according to an aspect of the present invention includes the steps of a processor controlling autonomous driving of a host vehicle based on map information stored in a memory, the processor controlling the driving of vehicles around the host vehicle detected by a sensor unit. generating an actual driving trajectory of the surrounding vehicle based on information, the processor generating an expected driving trajectory of the surrounding vehicle based on map information stored in the memory, the processor generating the generated actual driving trajectory Performing a reliability diagnosis of autonomous driving control for the host vehicle based on the size of the trajectory error between the trajectory and the expected driving trajectory, or a cumulative addition amount of the trajectory error, and a result of the reliability diagnosis for the host vehicle When the autonomous driving control is determined to be unreliable, the processor performs correction processing on one or more of the sensor unit and map information stored in the memory to ensure reliability of the autonomous driving control. It is characterized by:

In the present invention, performing the reliability diagnosis includes determining, by the processor, whether a state in which the size of the trajectory error is greater than or equal to a preset first threshold occurs within a first preset threshold time, and 1 If the size of the trajectory error is maintained below the first threshold for a critical time, the processor accumulates the trajectory error within a second threshold time preset to a value greater than the first threshold time. It is characterized by including the step of determining whether a state in which the cumulative addition amount is more than a preset second threshold occurs.

In the present invention, the sensor unit includes a plurality of sensors for detecting the surrounding vehicles, and the step of performing the correction process involves the processor matching the plurality of sensors included in the sensor unit. Performing correction processing on the sensor unit, and performing correction processing on the map information stored in the memory by the processor updating the map information stored in the memory using new map information received from the outside. It is characterized by including.

In the present invention, the step of performing the correction process involves the processor using the actual driving trajectory of the surrounding vehicle stored in the memory at the time when autonomous driving control for the own vehicle is determined to be unreliable. It is characterized in that it further includes the step of verifying the updated map information with map information.

According to one aspect of the present invention, the present invention preferentially diagnoses the reliability of autonomous driving control using the error between the actual driving trajectory and the expected driving trajectory determined for the surrounding vehicles of the autonomous driving vehicle, and according to the diagnosis result, The driving stability and driving accuracy of an autonomous vehicle can be improved by performing correction processing on the map information stored in the sensor or memory applied to the driving vehicle to ensure the reliability of autonomous driving control.

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.
Figure 2 is a block diagram showing the specific configuration of the autonomous driving integrated control unit in the autonomous driving device according to an embodiment of the present invention.
Figure 3 is an exemplary diagram showing an example of an autonomous driving device being applied to a vehicle according to an embodiment of the present invention.
Figure 4 is an exemplary diagram showing an example of the internal structure of a vehicle to which an autonomous driving device according to an embodiment of the present invention is applied.
Figure 5 is an exemplary diagram showing an example of a set distance and horizontal angle of view at which a lidar sensor, a radar sensor, and a camera sensor can detect surrounding objects in an autonomous driving device according to an embodiment of the present invention.
Figure 6 is an exemplary diagram showing an example of a sensor unit detecting surrounding vehicles in an autonomous driving device according to an embodiment of the present invention.
7 and 8 are flowcharts for explaining an autonomous driving method according to an embodiment of the present invention.

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

Figure 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 Figure 2 is a detailed view of the autonomous driving integrated 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 example diagram showing an example of the self-driving device according to an embodiment of the present invention being applied to a vehicle, and Figure 4 is an example of the self-driving device being applied to a vehicle according to an embodiment of the present invention. It is an exemplary diagram showing an example of the internal structure of a vehicle, and Figure 5 shows the set distance and horizontal angle of view at which the lidar sensor, radar sensor, and camera sensor can detect surrounding objects in the autonomous driving device according to an embodiment of the present invention. This is an exemplary diagram showing an example, and Figure 6 is an exemplary diagram showing an example of a sensor unit detecting surrounding vehicles in an autonomous driving device according to an embodiment of the present invention.

First, the structure and function of the autonomous driving control system to which the autonomous driving device according to this embodiment can be applied will be described with reference to FIGS. 1 and 3. As shown in FIG. 1, the autonomous driving control system controls the autonomous driving of the vehicle through the driving information input interface 101, the driving information input interface 201, the passenger output interface 301, and the vehicle control output interface 401. It can be implemented centered on 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 the passenger's manipulation of the user input unit 100 in the vehicle's autonomous driving mode or manual driving mode through the driving information input interface 101. The user input unit 100 includes a driving mode switch 110 and a user terminal 120 (e.g., a navigation terminal mounted on a vehicle, a smartphone or tablet PC carried by a passenger, etc.) as shown as an example in FIG. 1. Accordingly, the driving information may include driving mode information and navigation information of the vehicle. For example, the driving mode of the vehicle determined according to the occupant's operation of the driving mode switch 110 (i.e., autonomous driving mode/manual driving mode, or Sport Mode/Eco Mode/Safety) Mode (Safe Mode/Normal Mode) can be transmitted to the autonomous driving integrated control unit 600 through the driving information input interface 101 as the above-described driving information. In addition, navigation information such as the passenger's destination and the route to the destination (such as the shortest route or preferred route selected by the passenger among candidate routes to the destination) that the passenger inputs through the user terminal 120 is the driving information. It may 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 (e.g., a touch screen panel) that provides a UI (User Interface) for the driver to input or modify information for autonomous driving control of the vehicle. , In this case, the aforementioned driving mode switch 110 may be implemented as a touch button on the user terminal 120.

Additionally, the autonomous driving integrated control unit 600 may obtain driving information indicating the driving state of the vehicle through the driving information input interface 201. Driving information includes the steering angle formed as the passenger operates the steering wheel, the accelerator pedal stroke or brake pedal stroke formed as the passenger presses the accelerator or brake pedal, and vehicle speed, acceleration, yaw, and pitch as the behavior formed in the vehicle. and roll, etc. may include various information indicating the driving state and behavior of the vehicle, and each driving information includes a steering angle sensor 210, an Accel Position Sensor (APS)/Pedal Travel Sensor (PTS), as shown in FIG. (220), it may be detected by the driving information detection unit 200 including a vehicle speed sensor 230, an acceleration sensor 240, and a yaw/pitch/roll sensor 250. Furthermore, the vehicle's driving information may include the vehicle's location information, and the vehicle's location information may be obtained through a Global Positioning System (GPS) receiver 260 applied to the vehicle. This driving information can be transmitted to the autonomous driving integrated control unit 600 through the driving information input interface 201 and used to control the driving of the vehicle in the vehicle's autonomous driving mode or manual driving mode.

Additionally, the autonomous driving integrated control unit 600 may transmit driving status information provided to the passenger in the vehicle's autonomous driving mode or manual driving mode to the output unit 300 through the passenger output interface 301. That is, the autonomous driving integrated control unit 600 transmits the vehicle's driving status information to the output unit 300, so that the occupants can select the vehicle's autonomous driving status or manual driving status based on the driving status information output through the output unit 300. The status can be checked, and the driving status information may include various information indicating the driving status of the vehicle, such as the current vehicle driving mode, shift range, and vehicle speed. In addition, when the autonomous driving integrated control unit 600 determines that a warning is required to the driver in the vehicle's autonomous driving mode or manual driving mode along with the driving status information, the autonomous driving integrated control unit 600 outputs warning information through the passenger output interface 301. It can be transmitted to 300 so that the output unit 300 outputs a warning to the driver. In order to output such driving status information and warning information audibly and visually, the output unit 300 may include a speaker 310 and a display device 320 as shown in FIG. 1 . At this time, the display device 320 may be implemented as the same device as the user terminal 120 described above, or may be implemented as a separate and independent device.

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

As described above, the autonomous driving integrated control unit 600 of this embodiment provides driving information according to the driver's operation 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. The driving status information and warning information generated according to the autonomous driving algorithm obtained and processed by the internal processor 610 can be transmitted to the output unit 300 through the occupant output interface 301, and the internal processor ( The control information generated according to the autonomous driving algorithm processed by 610) may be transmitted to the lower control system 400 through the vehicle control output interface 401 to control driving of the vehicle.

Meanwhile, 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 driving according to the measured driving environment. To this end, the autonomous driving device of this embodiment is As shown in FIG. 1, it may include a sensor unit 500 for detecting objects around the vehicle, such as surrounding vehicles, pedestrians, roads, or fixed facilities (e.g., traffic lights, signposts, 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 can detect surrounding objects outside the vehicle by transmitting a laser signal to the surroundings of the vehicle and receiving a signal that is reflected and returned by the object, and has a predefined set distance and set vertical according to its specifications. It is possible to detect surrounding objects located within the vertical field of view and setting horizontal field of view. The LiDAR sensor 510 may include a front LiDAR sensor 511, an upper LiDAR sensor 512, and a rear LiDAR sensor 513, which are installed at the front, top, and rear of the vehicle, respectively, but their installation locations and number of installations are not limited to specific embodiments. The threshold 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 Determines the location (including the distance to the object), speed, and direction of movement of the object by measuring the time when the laser signal transmitted through the lidar sensor 510 is reflected by the object and returns. You can.

The radar sensor 520 can detect surrounding objects outside the vehicle by radiating electromagnetic waves around the vehicle and receiving signals that are reflected and returned by the object, and can detect a predefined distance, a vertical angle of view, and a predefined distance according to its specifications. Surrounding objects located within the set horizontal angle of view 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, which are 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 location (including the distance to the object) and speed of the object. and direction of movement can be determined.

The camera sensor 530 can detect surrounding objects outside the vehicle by capturing images around the vehicle, and can detect surrounding objects located within a predefined range of a set distance, a set vertical angle of view, and a set horizontal angle of view according to its specifications. . The camera sensor 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 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 applies predefined image processing to the image captured through the camera sensor 530 to determine the location (including the distance to the object) and speed of the object. and direction of movement can be determined. Additionally, an internal camera sensor 535 for capturing images of the inside of the vehicle may be mounted at a predetermined location inside the vehicle (e.g., a rearview mirror), and the processor 610 of the autonomous driving integrated control unit 600 may use the internal camera. Based on the image acquired through the sensor 535, the occupant's behavior and status may be monitored and guidance or warnings may be output to the occupant through the above-described output unit 300.

In addition to the lidar sensor 510, radar sensor 520, and camera sensor 530, the sensor unit 500 may further include an ultrasonic sensor 540 as shown in FIG. 1, along with the vehicle's Various types of sensors for detecting surrounding objects may be further employed in the sensor unit 500. 3 shows that the front lidar sensor 511 or the front radar sensor 521 is installed at the front of the vehicle, and the rear lidar sensor 513 or rear radar sensor 524 is installed at the rear of the vehicle to help understand this embodiment. It is installed in, and shows an example where 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 of the vehicle, respectively. , As described above, the installation location and number of each sensor are not limited to a specific embodiment. Figure 5 shows an example of the set distance and horizontal angle of view at which the lidar sensor 510, radar sensor 520, and camera sensor 530 can detect surrounding objects in front, and Figure 6 shows each sensor's surrounding objects. An example of detecting an object is shown. Figure 6 is only an example of surrounding object detection, and the surrounding object detection method is determined depending on the installation location and number of sensors. According to the configuration of the sensor unit 500 described above, surrounding vehicles and surrounding objects in the omnidirectional area of the host vehicle can be detected.

Furthermore, the sensor unit 500 detects the occupant's voice and biosignals (e.g., heart rate, electrocardiogram, respiration, blood pressure, body temperature, brain wave, blood flow (pulse wave), and blood sugar, etc.) to determine the condition of the occupant in the vehicle. It may further include a microphone and a biometric sensor, and the biometric sensors include a heart rate sensor, electrocardiogram sensor, respiration sensor, blood pressure sensor, body temperature sensor, electroencephalogram sensor, blood flow sensor, and blood sugar sensor. This can be.

Figure 4 shows an example of the internal structure of a vehicle, and the state of the interior of the vehicle is controlled by the operation of the vehicle's occupants, such as the driver or passenger, to facilitate the occupant's driving or convenience (e.g., rest, entertainment activities, etc.). Internal devices may be installed to support it. These internal devices may include the vehicle seat (S) on which the occupants sit, lighting devices (L) such as interior lights and mood lights, the user terminal 120 and display device 320 described above, internal tables, etc. The state of the internal device may be controlled by the processor 610.

In the case of the vehicle seat (S), the angle can be adjusted by the processor 610 (or by manual operation of the passenger), and the vehicle seat (S) is divided into the front row seat (S1) and the rear row seat (S2). If configured, only the angle of the front row seat (S1) can be adjusted. In the case where the rear row 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. The angle may be implemented to be adjusted. Additionally, an actuator (eg, motor) may be provided to adjust the angle of the vehicle seat (S). In the case of the lighting device (L), its on/off may be controlled by the processor 610 (or by manual operation of the passenger), and the lighting device (L) may operate a plurality of lighting units, such as an interior light and a mood light. 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 the passenger's manual operation) according to the passenger's viewing angle, for example, the screen may be adjusted in the passenger's gaze direction. The angle can be adjusted so that there is. In this case, an actuator (eg, motor) may be provided to adjust the angle of the user terminal 120 and the display device 320.

The autonomous driving integrated control unit 600 may communicate with the server 700 through a network as shown in FIG. 1. As a network method between the autonomous driving integrated control unit 600 and the server 700, various communication methods such as WAN (Wide Area Network), LAN (Local Area Network), or PAN (Personal Area Network) may be adopted. 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 adopted. For example, communication methods such as LoRa (which enables low-power communication and has a wide coverage of up to 20 km) or Sigfox (which has a coverage of 10 km (in the city center) to 30 km (outside the city center) depending on the environment) are adopted. 3GPP (3rd Generation) such as LTE-MTC (Machine-type Communications) (or LTE-M) with Power Saving Mode (PSM), NB (Narrowband) LTE-M, and NB IoT. Partnership Project) Release 12 and 13-based LTE network technology may be adopted. The server 700 can provide map information that maintains up-to-dateness (various map information may apply, such as 2D navigation map data, 3D remote area map data, or 3D high-precision electronic map data), and further provides road It can also provide various information such as accident information, road control information, traffic information, and weather information. The self-driving integrated control unit 600 receives the latest map information from the server 700 and can update the map information stored in the memory 620, and receives accident information, road control information, traffic volume information, and weather information to It can also be used for autonomous driving control.

Next, the structure and function of the autonomous driving integrated control unit 600 of this embodiment will be described with reference to FIG. 2. As shown in FIG. 2, the autonomous driving integrated control unit 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 may store information generated in the process of controlling the autonomous driving of the vehicle by the processor 610, and the processor 610 may store the memory 620. You can control the autonomous driving of the vehicle by accessing (read, accessing) 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 is a hard drive, magnetic tape, memory card, read-only memory (ROM), random-access memory (RAM), digital video disc (DVD), or optical disc. It can be implemented as an optical data storage device such as .

The memory 620 may store map information required for autonomous driving control by the processor 610. The map information stored in the memory 620 may be a navigation map (digital topographic map) that provides road-level information, but in order to improve the precision of autonomous driving control, a precision road map that provides lane-level road information, In other words, it may be desirable to implement it as 3D high-precision electronic map data. Accordingly, the map information stored in the memory 620 includes dynamic and Static information can be provided.

Additionally, the memory 620 may store an autonomous driving algorithm for controlling the autonomous driving of a vehicle. The autonomous driving algorithm is an algorithm (recognition, judgment and control algorithm) that recognizes the surroundings of the autonomous vehicle, determines its status, and controls the driving of the vehicle according to the judgment result. The processor 610 uses the autonomous driving algorithm stored in the memory 620. By executing driving algorithms, active autonomous driving control can be performed based on the vehicle's surrounding environment.

The processor 610 includes driving information and driving information input from the driving information input interface 101 and the driving information input interface 201, information on surrounding objects detected through the sensor unit 500, and a memory. The autonomous driving of the vehicle can be controlled based on the map information and autonomous driving algorithm stored in 620. 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. To this end, as shown in FIG. 2, the processor 610 includes a sensor processing module ( 611), a driving trajectory generation module 612, a driving trajectory analysis module 613, a driving control module 614, a trajectory learning module 615, and an occupant status determination module 616. Figure 2 shows each module as an independent block according to its function, but each module may be integrated into one module and implemented in a configuration that performs each function in an integrated manner.

The sensor processing module 611 includes driving information (i.e., the location of the surrounding vehicle) of the surrounding vehicle based on the result of detecting the vehicle surrounding the own vehicle through the sensor unit 500, and includes the location, speed and (may also include the direction of movement) can be determined. That is, the location of surrounding vehicles is determined based on the signal received through the lidar sensor 510, the location of the surrounding vehicle is determined based on the signal received through the radar sensor 520, or the camera sensor 530 The location of surrounding vehicles can be determined based on images captured through, or the location of surrounding vehicles can be determined based on signals 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 (ultrasonic signal processing Additional modules may be added to the sensor processing module 611). The method of determining the location of surrounding vehicles using the lidar sensor 510, radar sensor 520, and camera sensor 530 is not limited in implementation to a specific embodiment. In addition, the sensor processing module 611 may determine attribute information such as the size and type of surrounding vehicles as well as the location, speed, and direction of movement of surrounding vehicles. An algorithm for determining information such as and type may be predefined.

The driving trajectory generation module 612 can generate the actual driving trajectory and expected driving trajectory of surrounding vehicles, and the actual driving trajectory of the own vehicle, and for this purpose, the surrounding vehicle driving trajectory generation module 612a is used as shown in FIG. 2. and a self-vehicle driving trajectory generation module 612b.

First, the surrounding vehicle driving trajectory generation module 612a can generate the actual driving trajectory of surrounding vehicles.

Specifically, the surrounding vehicle driving trajectory generation module 612a determines the surrounding vehicle driving information (i.e., the location of the surrounding vehicle determined by the sensor processing module 611) of the surrounding vehicle detected by the sensor unit 500. Actual driving trajectories can be created. In this case, in order to generate the actual driving trajectory of the surrounding vehicle, the surrounding vehicle driving trajectory generation module 612a may refer to the map information stored in the memory 620, and the location of the surrounding vehicle detected by the sensor unit 500. The actual driving trajectory of surrounding vehicles can be generated by cross-referencing arbitrary locations on the map information stored in the memory 620. For example, when a surrounding vehicle is detected at a specific point by the sensor unit 500, the surrounding vehicle driving trace generation module 612a selects the location of the detected surrounding vehicle and a random location on the map information stored in the memory 620. By cross-referencing, the location of the surrounding vehicle currently detected on the map information can be specified, and the 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 trace generation module 612a maps and accumulates the locations of surrounding vehicles detected by the sensor unit 500 to the locations on the map information stored in the memory 620, based on the above cross-reference. The actual driving trajectory of the vehicle can be generated.

Meanwhile, the actual driving trajectories of surrounding vehicles can be compared with the expected driving trajectories of surrounding vehicles, which will be described later, and used to determine whether the map information stored in the memory 620 is inaccurate. In this case, when comparing the actual driving trajectory of a specific nearby vehicle with the expected driving trajectory, a problem may arise where the map information is misjudged as inaccurate even though it is accurate. For example, if the actual and expected driving trajectories of a number of surrounding vehicles are identical, and the actual and expected driving trajectories of a specific surrounding vehicle are different, only the actual driving trajectory of the specific surrounding vehicle is the expected driving trajectory and Comparison may lead to misjudgment that the 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 a plurality of surrounding vehicles deviates from the expected driving trajectory, and for this purpose, the surrounding vehicle driving trajectory generation module 612a generates the actual driving trajectories of a plurality of surrounding vehicles, respectively. You may. Furthermore, considering that drivers of surrounding vehicles tend to move the steering wheel somewhat to the left and right during the driving process to drive on a straight path, the actual driving trajectory of surrounding vehicles may be generated in a curved form rather than a straight line, which will be described later. In order to calculate the error between the expected driving trajectories, the surrounding vehicle driving trajectory generation module 612a may apply a predetermined smoothing technique to the original actual driving trajectory generated in a curved shape to generate an actual driving trajectory in a straight shape. As a smoothing technique, various techniques such as interpolation for each position of surrounding vehicles can be employed.

Additionally, the surrounding vehicle driving trajectory generation 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 therefore the map information includes lanes, lane center lines, regulation lines, road boundaries, road center lines, traffic signs, road surface signs, and road shapes. It can provide dynamic and static information necessary for autonomous vehicle driving control, such as height and lane width. Considering that vehicles generally drive in the center of the lane, surrounding vehicles driving around the own vehicle can also be expected to drive in the center of the lane, and therefore the surrounding vehicle driving trajectory generation module 612a The vehicle's expected driving trajectory can be generated as the lane center line reflected in map information.

The host vehicle driving trajectory generation module 612b may generate the actual driving trajectory that the host vehicle has driven to date based on the driving information of the host vehicle obtained through the driving information input interface 201 described above.

Specifically, the host vehicle driving trajectory generation module 612b includes the location of the host vehicle acquired through the driving information input interface 201 (i.e., the location information of the host vehicle acquired through the GPS receiver 260) and the memory 620. You can create the actual driving trajectory of your vehicle by cross-referencing an arbitrary location on the map information stored in ). For example, the current location of the host vehicle on the map information can be specified by cross-referencing the position of the host 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, the actual driving trajectory of the own vehicle can be generated by continuously monitoring the location of the own vehicle. That is, the host vehicle driving trajectory generation module 612b maps the position of the host vehicle obtained through the driving information input interface 201 to the position on the map information stored in the memory 620 and accumulates the position of the host vehicle based on the above cross-reference. By doing so, the actual driving trajectory of the own vehicle can be generated.

Additionally, the host vehicle driving trajectory generation module 612b may generate an expected driving trajectory along which the host vehicle should drive to the destination based on map information stored in the memory.

That is, the host vehicle driving trajectory generation module 612b stores the current location of the host vehicle acquired through the driving information input interface 201 (i.e., the current location information of the host vehicle acquired through the GPS receiver 260) and the memory. The expected driving trajectory to the destination can be generated using the stored map information, and the expected driving trajectory of the own vehicle can be generated as the lane center line reflected in the map information stored in the memory 620, like the expected driving trajectory of surrounding vehicles. You can.

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

The driving trajectory analysis module 613 analyzes each driving trajectory generated by the driving trajectory generation module 612 and stored in the memory 620 (i.e., the actual driving trajectory and expected driving trajectory of surrounding vehicles, and the actual driving trajectory of the own vehicle). Through analysis, the reliability of autonomous driving control for the current vehicle can be diagnosed. Reliability diagnosis of autonomous driving control can be carried out through the process of analyzing trajectory errors between the actual driving trajectories of surrounding vehicles and the expected driving trajectories.

The driving control module 614 can perform the function of controlling the autonomous driving of the own vehicle, and specifically, the driving information and driving information input from the driving information input interface 101 and the driving information input interface 201, respectively. The autonomous driving algorithm is processed by comprehensively using information about surrounding objects detected through the sensor unit 500 and map information stored in the memory 620, and control information is provided through the vehicle control output interface 401. This can be transmitted to the lower control system 400 to control the autonomous driving of the own vehicle, and the driving status information and warning information of the own vehicle can be transmitted to the output unit 300 through the occupant output interface 301 to the driver. can be recognized. In addition, when the driving control module 614 comprehensively controls autonomous driving as described above, the host vehicle analyzed by the above-described sensor processing module 611, driving trajectory generation module 612, and driving trajectory analysis module 613 And by controlling autonomous driving by considering the driving trajectories of surrounding vehicles, the precision of autonomous driving control can be improved and autonomous driving control stability can be improved.

The trajectory learning module 615 may learn or correct the actual driving trajectory of the host vehicle generated by the host vehicle driving trajectory creation module 612b. For example, if the trajectory error between the actual driving trajectory and the expected driving trajectory of surrounding vehicles is greater than a preset threshold, the map information stored in the memory 620 is judged to be inaccurate and correction of the actual driving trajectory of the own vehicle is determined to be necessary. Accordingly, the driving trajectory of the own vehicle can be corrected by determining the lateral shift value for correcting the actual driving trajectory of the own vehicle.

The occupant status determination module 616 may determine the occupant's status and behavior based on the occupant's status and biometric signals detected by the internal camera sensor 535 and the biometric sensor described above. The occupant's status determined by the occupant status 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 above, an embodiment of diagnosing the reliability of autonomous driving control for an autonomous vehicle will be described below.

As described above, the processor 610 (driving trajectory generation module 612) of this embodiment can generate the actual driving trajectory of the surrounding vehicle based on the driving information of the surrounding vehicle detected by the sensor unit 500. there is. That is, when a surrounding 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 to detect the current location on the map information. The location of surrounding vehicles can be specified, and the actual driving trajectory of surrounding vehicles can be generated by continuously monitoring the locations of surrounding vehicles as described above.

In addition, the processor 610 (driving trajectory generation module 612) may generate an expected driving trajectory of a surrounding vehicle based on the map information stored in the memory 620. In this case, the processor 610 may generate an expected driving trajectory of the surrounding vehicle. The expected driving trajectory can be created as the lane center line reflected in map information.

When the actual driving trajectory and the expected driving trajectory of the surrounding vehicle are generated, the processor 610 (the driving trajectory analysis module 613) determines the size of the trajectory error between the actual driving trajectory and the expected driving trajectory of the surrounding vehicle, or the accumulation of the trajectory error. Based on the added amount, a reliability diagnosis of autonomous driving control for the own vehicle can be performed.

Specifically, a state in which there is a trajectory error between the actual driving trajectory and the expected driving trajectory of a surrounding vehicle may correspond to a state in which the autonomous driving control being performed on the own vehicle is unreliable. That is, the existence of an error between the actual driving trajectory generated based on the driving information of surrounding vehicles detected by the sensor unit 500 and the expected driving trajectory generated based on the map information stored in the memory 620 means that the surrounding This means that the vehicle is not driving along the center line of the lane expected to drive on the map information, which may indicate that surrounding vehicles have been incorrectly detected by the sensor unit 500, or that the map information stored in the memory 620 is inaccurate. It means that there is a possibility of doing so. That is, even though the surrounding vehicles are actually driving along the expected driving trajectory, there is a possibility that there is an error in the actual driving trajectory of the surrounding vehicle due to an abnormality in the sensor unit 500, and the map information stored in the memory and the status of the road currently being driven are possible. There is a possibility of discrepancy (e.g., when the lane is shifted to the left or right compared to the map information stored in memory due to construction or road redevelopment of the road currently being driven, and surrounding vehicles are driving along the shifted lane). Two possibilities may exist. Accordingly, the processor 610 may perform a reliability diagnosis of autonomous driving control for the own vehicle based on the size of the trajectory error between the actual driving trajectory and the expected driving trajectory, or the cumulative addition amount of the trajectory error. Additionally, as described above, in order to consider the overall driving tendency of surrounding vehicles, the trajectory error between the actual driving trajectories and the expected trajectories of a plurality of surrounding vehicles may be considered, rather than the actual driving trajectory of any specific surrounding vehicle.

To describe in detail the process by which the processor 610 performs a reliability diagnosis based on the trajectory error between the actual driving trajectory and the expected driving trajectory of the surrounding vehicle, first, the processor 610 determines the trajectory error within a first preset threshold time. If a state in which the size is greater than or equal to a preset first threshold occurs, autonomous driving control for the own vehicle may be determined to be unreliable.

Here, the first critical time refers to a preset time to diagnose the reliability of autonomous driving control, and the reference point is when the comparison between the actual driving trajectory and the expected driving trajectory of surrounding vehicles by the processor 610 is initiated. This can be. Specifically, the process in which the processor 610 generates the actual and expected driving trajectories of surrounding vehicles and calculates the trajectory error to diagnose the reliability of autonomous driving control involves the resources of the memory 620 and the calculation of the processor 610. It may be executed periodically according to a preset judgment cycle to reduce load (thereby, the actual driving trajectory and expected driving trajectory of surrounding vehicles stored in the memory 620 may be periodically deleted according to the judgment cycle). In this case, if a state occurs in which the size of the trajectory error is greater than the first threshold before the first threshold time elapses from the start of one cycle, the processor 610 may determine that autonomous driving control is unreliable. The size of the first threshold time is a value smaller than the time section size of the above-mentioned judgment cycle, and may be designed in various ways according to the designer's intention and stored in the memory 620, and the first threshold value may also vary depending on the designer's intention. It may be designed and stored in the memory 620.

Additionally, the processor 610 may additionally perform reliability diagnosis using the accumulated amount of the trajectory error while the magnitude of the trajectory error is maintained below the first threshold during the first critical time. That is, even if the size of the trajectory error remains below the first threshold during the first threshold time, if the cumulative value of the trajectory error maintained below the first threshold is more than a certain value, the surrounding vehicle Since it corresponds to a state of driving for a certain period of time while deviating from the expected driving trajectory, the processor 610 additionally performs a reliability diagnosis using the cumulative amount of trajectory error to check whether autonomous driving control of the own vehicle can be trusted. It can be judged precisely.

In this case, the processor 610 accumulates the trajectory error within a second threshold time preset to a value greater than the first threshold time while the size of the trajectory error is maintained below the first threshold during the first threshold time. If a state occurs in which the accumulated addition amount (i.e., the accumulated value of trajectory errors within one cycle) is greater than or equal to a preset second threshold, autonomous driving control for the own vehicle may be determined to be unreliable. Here, the second threshold time may be pre-stored in the memory 620 as a value greater than the first threshold time and smaller than the time section size of the above-mentioned judgment cycle, and the second threshold value may also be designed in various ways according to the designer's intention. and may be stored in the memory 620.

If it is determined that the autonomous driving control of the own vehicle is unreliable through the above-mentioned process, the processor 610 detects a point where the own vehicle can stop nearby (e.g. : The lower control system 400 can be controlled to move to the shoulder, rest area, etc.), and then the processor 610 stores the map stored in the sensor unit 500 and the memory 620 to ensure the reliability of autonomous driving control. Correction processing may be performed on one or more of the information.

In this case, the processor 610 may perform correction processing on the sensor unit 500 by matching a plurality of sensors included in the sensor unit 500. That is, if a state occurs in which the size of the trajectory error is greater than the first threshold within the first threshold time, or a state occurs in which the accumulated amount of the trajectory error is greater than the second threshold within the second threshold time, the sensor unit ( Since there is a possibility that the surrounding vehicle was incorrectly detected by the sensor processing module 611 (there is a possibility that the location of the surrounding vehicle was incorrectly determined by the sensor processing module 611), the processor 610 operates the sensor unit 500 In order to ensure normal operation, correction processing for the sensor unit 500 can be performed by matching a plurality of sensors included in the sensor unit 500. As a method of matching a plurality of sensors, a plurality of After initializing the sensor, a method of performing calibration between heterogeneous sensors (i.e., lidar sensor 510, radar sensor 520, and camera sensor 530) may be adopted, and calibration is performed, for example, between each sensor. This can be performed through a process of adjusting the internal parameters of each sensor (510, 520, and 530) so that the positions of the objects determined based on the results of detecting the same object by (510, 520, and 530) are the same. Furthermore, a follow-up process can be performed to verify whether a plurality of sensors are matched through the calibration performed on the sensor unit 500. For example, the lidar sensor 510 and radar that detected the same object after performing calibration If the positions of surrounding vehicles determined according to each output value from the sensor 520 and the camera sensor 530 do not match (for example, the scatter diagram between the positions of surrounding vehicles determined based on each sensor 510, 520, and 530 If it is above the threshold, it can be determined that the plurality of sensors are not aligned), and it is determined that correction for the sensor unit 500 is impossible (e.g., failure of the sensor unit 500 itself), and the processor 610 You can turn off the autonomous driving mode for .

In addition, if the processor 610 determines that the autonomous driving control of the own vehicle is unreliable, the processor 610 stores the actual driving trajectory of the surrounding vehicle in the memory 620 and new map information received from the outside (i.e., the server ( Correction processing is performed on the map information stored in the memory 620 by updating the map information stored in the memory 620 using new map information transmitted from 700, and the actual driving of surrounding vehicles stored in the memory 620 is performed. You can use the trajectory to verify updated map information with new map information.

Specifically, the processor 610 stores the actual driving trajectory of surrounding vehicles in the memory 620 at the time when autonomous driving control for the own vehicle is determined to be unreliable, and then sends the map information stored in the memory 620 to the server. It can be updated with new map information received from (700). At this time, before using the updated map information (i.e., new map information transmitted from the server 700) for autonomous driving control, the processor 610 uses the actual driving trajectory of surrounding vehicles stored in the memory 620 to create a new map information. The updated map information can be verified with map information. In this case, the actual driving trajectory of surrounding vehicles stored in the memory 620 and the expected driving trajectory generated based on the updated map information (i.e., reflected in the updated map information) The updated map information can be verified by comparing the lane center line (e.g., the actual driving trajectory of the surrounding vehicle stored in the memory 620 and the expected driving generated based on the updated map information). If the trajectory error between trajectories is less than a preset threshold, the updated map information can be judged to be reliable). The above process is meaningful as a process of verifying whether the updated map information accurately reflects the condition of the road currently being driven.

If the sensor unit 500 and the updated map information are verified through the above correction process, the processor 610 performs normal autonomous driving control, and if the sensor unit 500 or the updated map information is not verified, the processor 610 610 turns off the autonomous driving mode of the vehicle and outputs guidance and warnings to the occupants that driving in the manual driving mode is necessary through the output unit 300.

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

When explaining the autonomous driving method according to an embodiment of the present invention with reference to FIG. 7, first, the processor 610 controls autonomous driving of the host vehicle based on map information stored in the memory 620 (S100).

Thereafter, the processor 610 generates the actual driving trajectory of the surrounding vehicle based on the driving information of the surrounding vehicle detected by the sensor unit 500 during the autonomous driving process of the own vehicle (S200).

Next, the processor 610 generates an expected driving trajectory of surrounding vehicles based on the map information stored in the memory 620 (S300).

Subsequently, the processor 610 determines the reliability of autonomous driving control for the own vehicle based on the size of the trajectory error between the actual driving trajectory and the expected driving trajectory of the surrounding vehicle generated in steps S200 and S300, or the cumulative addition amount of the trajectory error. Perform diagnosis (S400).

If the autonomous driving control of the own vehicle is determined to be unreliable in step S400, the processor 610 uses at least one of the map information stored in the sensor unit and memory to detect surrounding vehicles to ensure the reliability of the autonomous driving control. Perform correction processing for (S500).

Meanwhile, as shown in FIG. 8, in step S400, the processor 610 determines whether a state in which the size of the trajectory error is greater than or equal to a preset first threshold occurs within a preset first threshold time (S410).

If the size of the trajectory error remains below the first threshold during the first threshold time, the processor 610 accumulates the trajectory error within a second threshold time preset to a value greater than the first threshold time. It is determined whether a state in which the cumulative addition amount is greater than or equal to a preset second threshold occurs (S420).

If a state occurs in step S410 in which the size of the trajectory error is greater than or equal to the first threshold within the first threshold time, or a state occurs in step S420 in which the accumulated amount of the trajectory error is greater than or equal to the second threshold within the second threshold time, the processor 610 ) determines that the autonomous driving control of the own vehicle is unreliable and performs step S500. In step S410, the size of the trajectory error is maintained below the first threshold during the first critical time, and in step S420, the size of the trajectory error is maintained for the second critical time. If a state in which the cumulative amount of trajectory error is greater than or equal to the second threshold does not occur, the processor 610 performs normal autonomous driving control (S600).

Meanwhile, as shown in FIG. 8, in step S500, the processor 610 performs correction processing on the sensor unit 500 by matching a plurality of sensors included in the sensor unit 500 (S510).

If the sensor unit 500 is verified in step S510 (i.e., matching between a plurality of sensors is achieved), the processor 610 uses the new map information received from the outside (server 700) to store the memory 620. Update the map information stored in (S520).

Then, the processor 610 verifies the updated map information in step S520 using the actual driving trajectories of surrounding vehicles stored in the memory 620 at the time when autonomous driving control is determined to be unreliable in step S400 (S530) .

If the sensor unit 500 is verified in step S510 and the updated map information is verified in step S530, the processor 610 performs normal autonomous driving control (S600). On the other hand, if the sensor unit 500 is not verified in step S510 or the updated map information is not verified in step S530, the processor 610 turns off the autonomous driving mode of the own vehicle (S700). In step S700, the processor 610 may output guidance and a warning to the passenger that driving in a manual driving mode is necessary through the output unit 300.

In this way, in this embodiment, the reliability of autonomous driving control is first diagnosed using the error between the actual driving trajectory and the expected driving trajectory determined for the surrounding vehicles of the autonomous vehicle, and the sensors applied to the autonomous vehicle according to the diagnosis result. Alternatively, the driving stability and driving accuracy of the autonomous vehicle can be improved by performing correction processing on the map information stored in the memory to ensure reliability of autonomous driving control.

The present invention has been described with reference to the embodiments shown in the drawings, but these are merely illustrative, and those skilled in the art will recognize that various modifications and other equivalent embodiments can be made therefrom. You will understand. Therefore, the true technical protection scope of the present invention should be determined by the scope of the patent claims below.

100: User input unit 101: Driving information input interface
110: Driving mode switch 120: User terminal
200: Driving information detection unit 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: passenger 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 status determination module 620: Memory
700: Server

Claims (11)

A sensor unit that detects vehicles around the self-driving vehicle;
Memory to store map information; and
A processor that controls autonomous driving of the own vehicle based on map information stored in the memory,
The processor,
Generating an actual driving trajectory of the surrounding vehicle based on the driving information of the surrounding vehicle detected by the sensor unit,
Generates an expected driving trajectory of the surrounding vehicle based on map information stored in the memory,
Performing a reliability diagnosis of autonomous driving control for the host vehicle based on the size of a trajectory error between the generated actual driving trajectory and the expected driving trajectory, or a cumulative addition amount of the trajectory error,
If, as a result of performing the reliability diagnosis, it is determined that autonomous driving control for the own vehicle is unreliable, correction processing is performed on one or more of the sensor unit and the map information to ensure reliability of the autonomous driving control. do,
The processor,
If a state in which the size of the trajectory error is greater than or equal to a preset first threshold occurs within a preset first threshold time, autonomous driving control for the own vehicle is determined to be unreliable,
The processor,
An autonomous driving device, characterized in that the reliability diagnosis is additionally performed using the accumulated amount of the trajectory error while the magnitude of the trajectory error is maintained below the first threshold during the first threshold time.
delete delete According to paragraph 1,
The processor,
In a state where the size of the trajectory error is maintained below the first threshold during the first threshold time, the trajectory error is accumulated and integrated within a second threshold time preset to a value greater than the first threshold time. An autonomous driving device characterized in that when a state occurs in which the cumulative addition amount is greater than a preset second threshold, autonomous driving control for the own vehicle is determined to be unreliable.
According to paragraph 1,
The sensor unit includes a plurality of sensors for detecting the surrounding vehicles,
The processor,
An autonomous driving device characterized in that, when autonomous driving control of the own vehicle is determined to be unreliable, correction processing for the sensor unit is performed by matching a plurality of sensors included in the sensor unit.
According to paragraph 1,
The processor,
An autonomous driving device characterized in that it performs correction processing on the map information stored in the memory by updating the map information stored in the memory using new map information transmitted from the outside.
According to clause 6,
The processor,
If the autonomous driving control of the own vehicle is determined to be unreliable, the actual driving trajectory of the surrounding vehicle is stored in the memory, and the actual driving trajectory of the surrounding vehicle stored in the memory is used to provide the new map information. An autonomous driving device characterized by verifying updated map information.
A processor controlling autonomous driving of the own vehicle based on map information stored in a memory;
generating, by the processor, an actual driving trajectory of the surrounding vehicle based on driving information of the vehicle surrounding the own vehicle detected by a sensor unit;
generating, by the processor, an expected driving trajectory of the surrounding vehicle based on map information stored in the memory;
performing, by the processor, a reliability diagnosis of autonomous driving control for the own vehicle based on the size of a trajectory error between the generated actual driving trajectory and the expected driving trajectory, or a cumulative addition amount of the trajectory error; and
When it is determined that autonomous driving control for the own vehicle is unreliable as a result of performing the reliability diagnosis, the processor selects one of the sensor unit and map information stored in the memory to ensure reliability of the autonomous driving control. performing correction processing for abnormalities;
Including,
The step of performing the reliability diagnosis is,
determining, by the processor, whether a state in which the size of the trajectory error is greater than or equal to a preset first threshold occurs within a preset first threshold time; and
If the size of the trajectory error is maintained below the first threshold during the first threshold time, the trajectory error is accumulated and integrated by the processor within a second threshold time preset to a value greater than the first threshold time. An autonomous driving method comprising: determining whether a state in which the cumulative addition amount is greater than or equal to a preset second threshold occurs.
delete According to clause 8,
The sensor unit includes a plurality of sensors for detecting the surrounding vehicles,
The step of performing the correction process is,
performing, by the processor, correction processing on the sensor unit by matching a plurality of sensors included in the sensor unit; and
An autonomous driving method comprising: performing correction processing on the map information stored in the memory by the processor updating the map information stored in the memory using new map information received from an external source.
According to clause 10,
The step of performing the correction process is,
Verifying, by the processor, map information updated with the new map information using the actual driving trajectory of the surrounding vehicle stored in the memory at the time when autonomous driving control of the own vehicle is determined to be unreliable; An autonomous driving method comprising:

Images