KR102007249B1 - Apparatus, method and system for autonomous driving - Google Patents

Abstract

The present invention relates to an autonomous vehicle driving apparatus, a method and a system, comprising: a sensor unit for sensing a surrounding object and a driving environment of the own vehicle, and an autonomous vehicle based on moving data and driving environment information of the surrounding object detected by the sensor unit Probably analyzing the expected movement trajectory of the surrounding objects based on the control unit for generating a driving route, and the movement data of the surrounding objects received from the control unit, and analyzing the accident data corresponding to the driving environment information input from the control unit. And a controller, wherein the controller optimizes the autonomous driving route based on the predicted movement trajectory and the accident data of the surrounding object analyzed by the data analyzer.

Description

Autonomous driving device, method and system {APPARATUS, METHOD AND SYSTEM FOR AUTONOMOUS DRIVING}

The present invention is an autonomous driving device. The present invention relates to a method and a system, and more particularly, to an autonomous vehicle, a method and a system for performing autonomous driving according to an autonomous driving route generated to avoid a collision with a surrounding object.

Today's automotive industry is moving toward realizing autonomous driving with minimal driver intervention in vehicle driving. An autonomous vehicle refers to a vehicle that independently recognizes a driving route by recognizing the surrounding environment through external information sensing and processing function and drives independently using its own power.

Autonomous vehicles can drive to their destinations by preventing collisions with obstacles on the driving path and adjusting the speed and direction of the road according to the shape of the road without the driver manipulating the steering wheel, accelerator pedal or brake. have. For example, acceleration may be performed on a straight road, and deceleration may be performed on a curved road while changing a driving direction corresponding to the curvature of the road.

Such autonomous vehicles use sensor data acquired through sensors mounted on the vehicle to drive the route to the first set destination to avoid collision with surrounding vehicles, or through vehicle-to-everything (V2X) communication. Autonomous driving is performed by setting the route and modifying the originally set route. However, the autonomous driving based on the mounted sensor of the vehicle has a problem in that its precision is reduced due to the system limitation of the sensor device, and the autonomous driving path obtained through the communication is not the latest information of the communication information (non-latest map data). Due to sex, etc., the accuracy is low.

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

The present invention has been made to solve the above problems, an object of the present invention is to improve the accuracy of the autonomous driving control that occurs when performing autonomous driving only through the sensor data measured through the sensor mounted on the vehicle, The present invention provides an autonomous driving apparatus, a method, and a system for improving autonomous driving control performance by improving inaccuracy of an autonomous driving route due to non-latest information.

An autonomous vehicle according to an aspect of the present invention is a sensor unit for detecting the surrounding object and the driving environment of the own vehicle, the autonomous driving of the vehicle based on the movement data and the driving environment information of the peripheral object detected by the sensor unit Probably analyzes the expected movement trajectory of the surrounding objects based on the controller for generating a route, and the movement data of the surrounding objects received from the controller, and the accident data corresponding to the driving environment information received from the controller. And a data analyzer to analyze the controller, wherein the controller optimizes the autonomous driving route based on the predicted movement trajectory and the accident data of the surrounding object analyzed by the data analyzer.

In the present invention, the movement data of the surrounding object is object attribute data including at least one of object type, movement speed, deceleration information, lane change frequency information, and lane compliance information.

In the present invention, the data analysis unit receives the movement data of the surrounding object, and reflects the movement data reference information according to the object property to probabilistically analyze the expected movement trajectory of the surrounding object based on previously stored big data. It is characterized by.

In the present invention, the driving environment information may include at least one of driving road information, driving area information, and driving time information of the own vehicle.

In the present invention, the data analysis unit is characterized by analyzing the accident data corresponding to the driving environment information received from the controller based on the pre-stored big data reflecting the accident data for each driving environment.

In the present invention, the control unit, based on the movement data of the surrounding object and the expected movement trajectory of the peripheral object to finally determine the expected movement path of the peripheral object, and the accident data analyzed by the data analysis unit The autonomous driving path may be optimized by reflecting the estimated moving path of the surrounding object.

The invention further includes an autonomous driving drive unit that performs one or more of driving, steering and braking the autonomous vehicle such that the autonomous vehicle follows the optimized autonomous driving route.

In the autonomous driving method according to an aspect of the present invention, the sensor unit, detecting the surrounding object and the driving environment of the own vehicle, the control unit based on the movement data and the driving environment information of the peripheral object detected by the sensor unit Generating an autonomous driving route of the own vehicle, the data analysis unit receives the movement data of the surrounding object from the control unit to probabilistically analyze the expected movement trajectory of the surrounding object, the driving environment information received from the control unit Analyzing accident data corresponding to the; and the control unit, optimizing the autonomous driving route based on the predicted movement trajectory and accident data of the surrounding objects analyzed by the data analysis unit do.

An autonomous driving system according to an aspect of the present invention is a control unit for generating an autonomous driving route of the own vehicle based on the movement data and the driving environment information of the surrounding objects of the own vehicle, the moving data of the peripheral object received from the control unit A data server configured to probabilistically analyze an expected movement trajectory of the surrounding object and to analyze accident data corresponding to the driving environment information received from the controller, and a communication unit to perform data communication between the controller and the data server The control unit may be configured to optimize the autonomous driving route based on the predicted movement trajectory and the accident data of the surrounding object analyzed by the data server.

The present invention generates an autonomous driving path in consideration of the expected movement trajectory of the surrounding vehicle analyzed through the data server together with the sensor data measured by the sensor mounted on the vehicle, and at the same time generated in an environment similar to the driving environment of the own vehicle By generating an autonomous driving route in consideration of the accident history, it is possible to overcome the limitations of the conventional sensor-based autonomous driving control and to enable autonomous driving control that can effectively avoid collision with surrounding objects.

1 is a block diagram illustrating an autonomous driving control apparatus according to an embodiment of the present invention.
2 and 3 are exemplary views illustrating a process of sensing a surrounding object and a driving environment by the sensor unit in the autonomous driving control apparatus according to an embodiment of the present invention.
4 and 5 are exemplary diagrams for explaining a process of analyzing the moving data of the object around the data analysis unit in the autonomous driving control apparatus according to an embodiment of the present invention.
6 and 7 are exemplary diagrams for explaining a process of avoiding a collision with the surrounding objects through the accident data analyzed by the data analyzer in the autonomous driving control apparatus according to an embodiment of the present invention.
8 is a flowchart illustrating an autonomous driving method according to an embodiment of the present invention.
9 is a block diagram illustrating an autonomous driving system according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings will be described an embodiment of the autonomous driving apparatus, method and system according to the present invention. In this process, the thickness of the lines or the size of the components shown in the drawings may be exaggerated for clarity and convenience of description. In addition, terms to be described below are terms defined in consideration of functions in the present invention, which may vary according to the intention or convention of a user or an operator. Therefore, definitions of these terms should be made based on the contents throughout the specification.

1 is a block diagram for explaining an autonomous driving control apparatus according to an embodiment of the present invention, Figures 2 and 3 are the sensor unit in the autonomous driving control apparatus according to an embodiment of the present invention and the surrounding environment and driving environment 4 and 5 are exemplary diagrams for explaining a process of analyzing a moving data of a nearby object in the autonomous driving control apparatus according to an embodiment of the present invention. 6 and 7 are exemplary views for explaining a process of avoiding a collision with surrounding objects through accident data analyzed by the data analyzer in the autonomous driving control apparatus according to an embodiment of the present invention.

Referring to FIG. 1, the autonomous driving control apparatus according to an embodiment of the present invention includes an interface unit 10, a positioning unit 20, a map data storage unit 30, a sensor unit 40, a control unit 50, The data analyzer 60 and the autonomous driving driver 70 may be included.

The interface unit 10 performs an input / output function for receiving a user's operation and outputs driving information of the own vehicle, and performs an input / output function such as a voice recognition device and a 3D hologram as well as a head up display (CUD), a cluster and a button. It can include all possible configurations.

The positioning unit 20 may position the current position of the own vehicle. In detail, the positioning unit 20 may receive GPS coordinates of the current location of the vehicle, that is, location information of latitude and longitude coordinates, using a satellite navigation system such as GPS.

The map data storage unit 30 stores map data for searching for a driving route and guiding the found driving route. The map data storage unit 30 may not only provide information of links of driving roads, attributes of each link, node lists of intersections of each link, but also width information of lanes, lane information, location of fixed facilities, size and shape information, and the like. It may be storing the precision map data including.

The sensor unit 40 may detect a surrounding object and a driving environment of the own vehicle and transmit the detected object to the controller 50 to be described later. The sensor unit 40 may include all kinds of sensors mounted on the vehicle, and may include a camera sensor, a radar sensor, a lidar sensor, an ultrasonic sensor, or the like to detect the surrounding objects and the driving environment of the own vehicle. . 2 illustrates a process in which the sensor unit 40 detects a surrounding object and a driving environment.

When the controller 50 receives a destination from the user through the interface unit 10, the controller 50 is currently based on the current position of the own vehicle measured by the positioning unit 20 and the map data stored in the map data storage unit 30. A path from a location to a destination may be generated, and the autonomous driving of the vehicle may be controlled by controlling the autonomous driving driver 70 to be described later while driving the generated path.

In the present exemplary embodiment, the controller 50 may generate an autonomous driving route of the own vehicle based on the movement data and the driving environment information of the surrounding object detected by the sensor unit 40.

Here, the surrounding object includes all the objects moving around the own vehicle, such as a pedestrian, a bicycle, or a motorcycle, as well as the surrounding vehicle traveling around the own vehicle. The moving data of the surrounding objects includes at least one of an object type (type of an object such as a car, truck, bus, pedestrian, bicycle or motorcycle), moving speed, deceleration information, lane change frequency information, and lane compliance information. Object property data.

The driving environment information may include one or more of driving road information, driving area information, and driving time information of the own vehicle. Specifically, the driving road information may include information on road width, number of lanes, lane slope, lane curvature, road type, road pavement, tunnel status, confluence point, signage, and the like. It may include information about the surrounding natural environment, such as mountains and rivers, and the driving time information may include information about time, date, season, sun position, and the like.

That is, the controller 50 monitors the surrounding objects and the driving environment of the own vehicle through the sensor unit 40 while driving the route to the destination, and in real time, the autonomous driving route for avoiding collision with the surrounding objects in the driving environment. The autonomous driving of the own vehicle can be performed by the method of generating the vehicle.

However, as described above, when performing autonomous driving based only on a sensor mounted in a conventional vehicle, there is a problem in that autonomous driving precision decreases due to a system limitation of the sensor device. Through the probabilistic analysis of the predicted movement trajectory of the surrounding objects, the accident data corresponding to the driving environment information is analyzed and reflected in the generation of the autonomous driving route of the own vehicle.

The data analyzer 60 may probably analyze the expected movement trajectory of the surrounding object by receiving the movement data of the surrounding object from the controller 50. In this case, the data analyzer 60 may receive the movement data of the surrounding object, and may probably analyze the expected movement trajectory of the surrounding object based on previously stored big data by reflecting the moving data reference information according to the object property. .

In more detail, as described above, the movement data of the surrounding object received from the control by the data analysis unit 60 includes one or more of object type, moving speed, deceleration information, lane change frequency information, and lane compliance information. do. Referring to the example illustrated in FIG. 4, the data analyzing unit 60 may determine that the driving vehicle 1 is a vehicle that performs frequent lane changes based on the movement data of the driving vehicle 1, and the movement data of the driving vehicle 2 may be determined. Based on the movement data of the driving vehicles 3 and 4, the driving vehicle 2 may be determined to be a vehicle traveling at a constant speed in front of the own vehicle, respectively. Similarly, referring to the example illustrated in FIG. 5, the data analyzer 60 may determine that the traveling vehicle 1 is a vehicle inadvertently driving in the lane based on the movement data of the traveling vehicle 1, and the movement of the traveling vehicle 2 is performed. Based on the data, the driving vehicle 2 may be determined to be a vehicle performing frequent lane changes, and based on the movement data of the driving vehicle 3, the driving vehicle 3 may be determined to be a vehicle that is speeding in front of the own vehicle.

Accordingly, the data analyzer 60 may probabilistically analyze the expected movement trajectory of the surrounding object based on the movement data of the surrounding object received from the controller 50. In this case, the data analyzer 60 may determine the object property. According to the movement data reference information, the estimated movement trajectory of the surrounding objects can be probabilisticly analyzed based on the previously stored big data. Big data is collected according to object properties (ie, object type, moving speed, acceleration / deceleration information, lane change frequency information, lane compliance information), and the movement trajectory of the surrounding object is calculated from the moving data of one surrounding object. Refers to a database of reference information for prediction. Accordingly, the data analyzer 60 may probabilistically analyze the expected movement trajectory of the surrounding object by applying a probability analysis technique through big data to the movement data of the surrounding object.

On the other hand, in consideration of the computational load of the big data-based probability analysis process, the data analysis unit 60 is implemented as a data server 60 that communicates with the host vehicle outside the host vehicle as shown in FIGS. 4 and 5. May be

In addition, the data analyzer 60 may analyze accident data corresponding to the driving environment information received from the controller 50. At this time, the data analysis unit 60 may analyze the accident data corresponding to the driving environment information received from the controller 50 based on the previously stored big data by reflecting the accident data for each driving environment.

More specifically, as described above, the driving environment information input from the control by the data analyzer 60 includes one or more of driving road information, driving area information, and driving time information. Referring to the example illustrated in FIG. 6, when the host vehicle is traveling on a curved road, the data analyzer 60 may perform the curved road as shown in FIG. 6A based on the driving environment information received from the controller 50. The accident data may be extracted from the big data. Accordingly, the autonomous vehicle may generate an autonomous driving route as shown in FIG. 6 (b) to avoid collision with the driving vehicle 1. In addition, referring to the example illustrated in FIG. 7, when the host vehicle is traveling at a complicated confluence point, the data analyzer 60 may perform the same operation as shown in FIG. 7A based on the driving environment information received from the controller 50. Accident data at the confluence point can be extracted from the big data. Accordingly, the autonomous vehicle can generate an autonomous driving route as shown in FIG. 7B to avoid collision with the driving vehicle 1.

Accordingly, the data analysis unit 60 may extract accident data corresponding to the driving environment information received from the control unit 50 from the big data. Big data refers to a database of reference information for predicting accidents that can occur in the driving environment of a vehicle by collecting accident data for each driving environment. Accordingly, the data analysis unit 60 extracts the accident data corresponding to the driving environment information by analyzing the similarity between the driving environment information received from the control unit 50 and the accident data for each driving environment collected in the big data, and controls the control unit 50. ) Can be delivered.

In summary, the big data of the data analyzer 60 collects the moving data according to the object property and functions as a database of reference information for predicting the moving trajectory of the surrounding object from the moving data of the surrounding object. Accident data is collected for each driving environment and functions as a database of reference information for predicting accidents that may occur in the driving environment of the own vehicle, and the data analysis unit 60 predicts the movement movement and the surrounding environment of the surrounding objects through the big data. The controller 50 may optimize the autonomous driving route by analyzing and transmitting the accident data corresponding to the control unit 50.

The controller 50 finally determines the expected movement path of the surrounding object based on the movement data of the surrounding object and the expected movement trajectory of the surrounding object, and estimates the movement of the surrounding object based on the accident data analyzed by the data analyzer 60. Reflect on the route to optimize the autonomous driving route.

That is, the controller 50 may calculate the surroundings based on the movement data of the surrounding objects currently monitored in real time through the sensor unit 40 and the expected movement trajectories of the surrounding objects stochastically analyzed by the data analyzer 60. By finally determining the expected movement path of the object and reflecting the accident data analyzed by the data analysis unit to the expected movement path of the surrounding object, it predicts the possibility of accident in the current driving environment of the own vehicle and collides with the surrounding object. The autonomous driving route can be optimized to avoid the problem.

The autonomous driving driver 70 may perform one or more of driving, steering and braking the own vehicle to follow the optimized autonomous driving route through the above-described process. That is, the autonomous driving driver 70 may be controlled by the controller 50 to follow the optimized autonomous driving path to perform at least one of driving, steering and braking of the own vehicle. To this end, as shown in FIG. 1, the autonomous driving drive unit 70 includes a drive system 71 for driving an internal combustion engine, motor driven power steering (MDPS), active front steering (ARS), rear wheel steering (RWS), and the like. The same steering system 73 and a braking system 75 such as Autonomous Emergency Braking (AEB) and Anti Lock Brake System (ABS) can be included.

8 is a flowchart illustrating an autonomous driving method according to an embodiment of the present invention.

Referring to FIG. 8, the autonomous driving method according to an embodiment of the present invention will be described. First, the sensor unit 40 detects a surrounding object and a driving environment of the own vehicle (S10). The sensor unit 40 may detect a surrounding object and a driving environment of the own vehicle through a camera sensor, a radar sensor, a lidar sensor, or an ultrasonic sensor mounted on the vehicle.

Subsequently, the controller 50 generates an autonomous driving route of the own vehicle based on the movement data and the driving environment information of the surrounding object detected by the sensor unit 40 (S20). Here, the movement data of the surrounding object means object attribute data including at least one of object type, moving speed, deceleration information, lane change frequency information, and lane compliance information, and the driving environment information is a driving road of the own vehicle. It may include one or more of information, driving region information, and driving time information.

Subsequently, the data analyzer 60 receives the movement data of the surrounding objects from the controller 50 and probabilistically analyzes the expected movement trajectories of the surrounding objects, and the accident data corresponding to the driving environment information received from the controller 50. Analyze (S30). In step S30, the data analyzer 60 receives the movement data of the surrounding object, and reflects the movement data reference information according to the object property to probabilistically analyze the expected movement trajectory of the surrounding object based on the prestored big data. The accident data corresponding to the driving environment may be reflected to analyze the accident data corresponding to the driving environment information received from the controller 50 based on the previously stored big data.

Subsequently, the controller 50 optimizes the autonomous driving route based on the predicted movement trajectory and the accident data of the surrounding object analyzed by the data analyzer 60 (S40). In operation S40, the controller 50 finally determines an expected movement path of the surrounding object based on the movement data of the surrounding object and the expected movement trajectory of the surrounding object, and analyzes the accident data analyzed by the data analyzer 60. It is possible to optimize the autonomous driving route by reflecting on the expected movement route of.

Subsequently, the controller 50 controls one or more of driving, steering and braking of the own vehicle such that the own vehicle follows the optimized autonomous driving path in step S40 (S50).

Meanwhile, in consideration of the load on big data-based data operations as described above, the data analyzer 60 may be implemented as a data server 60 that communicates with the host vehicle outside the host vehicle as shown in FIG. 9. It may be.

In this case, the interface unit 10, the positioning unit 20, the map data storage unit 30, the sensor unit 40, the control unit 50, and the autonomous driving drive unit 70 are mounted on the host vehicle and the data server ( 60 communicates with the host vehicle outside the host vehicle, and a communication unit 80 for communicating with the host vehicle and the data server 60 may be mounted in the host vehicle. The communication unit 80 may communicate with a vehicle to vehicle (V2V) and vehicle to infra (V2I) as well as the data server 60. The map data stored in the map data storage unit 30 may be updated through the latest map data provided from the infrastructure outside the own vehicle through the communication unit 80, thereby maintaining the latestness.

As such, the present embodiment generates an autonomous driving route in consideration of the expected movement trajectory of the surrounding vehicle analyzed through the data server together with the sensor data measured by the sensor mounted on the vehicle, and at the same time similar to the driving environment of the own vehicle. By generating an autonomous driving route in consideration of the accident history occurring in the environment, it is possible to overcome the limitations of the conventional sensor-based autonomous driving control and to enable autonomous driving control that can effectively avoid collision with surrounding objects.

Although the present invention has been described with reference to the embodiments shown in the drawings, it is merely exemplary and various modifications and equivalent other embodiments are possible to those skilled in the art. I will understand. Therefore, the true technical protection scope of the present invention will be defined by the claims below.

10: interface unit
20: positioning part
30: map data storage unit
40: sensor unit
50: control unit
60: data analysis unit, data server
70: autonomous driving drive unit
71: drive system
73: steering system
75: braking system
80: communication unit
90: external vehicle / infrastructure

Claims (15)

Sensor unit for sensing the surrounding objects and the driving environment of the own vehicle;
A controller configured to generate an autonomous driving route of the own vehicle based on movement data and driving environment information of the surrounding object sensed by the sensor unit; And
A data analysis unit probabilistically analyzing an expected movement trajectory of the surrounding object based on the movement data of the surrounding object received from the controller, and analyzing accident data corresponding to the driving environment information received from the controller; Including,
The controller optimizes the autonomous driving route based on the predicted movement trajectory and the accident data of the surrounding object analyzed by the data analyzer,
The movement data of the surrounding object is object attribute data including one or more of an object type, a moving speed, deceleration acceleration information, lane change frequency information, and lane compliance information.
The data analysis unit receives the movement data of the surrounding object, probably analyzes the expected movement trajectory of the surrounding object based on previously stored big data by reflecting the movement data reference information according to an object property,
The driving environment information includes one or more of driving road information, driving area information, and driving time information of the own vehicle,
The data analysis unit analyzes the accident data corresponding to the driving environment information received from the controller based on the previously stored big data reflecting the accident data for each driving environment,
The controller may determine the expected movement path of the surrounding object based on the movement data of the surrounding object and the expected movement trajectory of the surrounding object, and estimate the accident data analyzed by the data analyzer. The autonomous driving device, characterized in that to optimize the autonomous driving route reflected in the movement route.
delete delete delete delete delete The method of claim 1,
And an autonomous driving driver configured to perform at least one of driving, steering, and braking the autonomous vehicle such that the autonomous vehicle follows the optimized autonomous driving route.
A sensor unit for sensing a surrounding object and a driving environment of the own vehicle;
Generating, by the controller, an autonomous driving route of the own vehicle based on the movement data and the driving environment information of the surrounding object sensed by the sensor unit;
A data analysis unit receiving probable movement data of the surrounding objects from the controller and probably analyzing an expected movement trajectory of the surrounding objects, and analyzing accident data corresponding to the driving environment information received from the controller; And
Optimizing, by the controller, the autonomous driving route based on an expected movement trajectory and accident data of the surrounding object analyzed by the data analyzer;
Including,
The movement data of the surrounding object is object attribute data including one or more of an object type, a moving speed, deceleration acceleration information, lane change frequency information, and lane compliance information.
In the analyzing, the data analysis unit,
Receives movement data of the surrounding object, and reflects the movement data reference information according to the object property, and probabilistically analyzes the expected movement trajectory of the surrounding object based on previously stored big data,
The driving environment information includes one or more of driving road information, driving area information, and driving time information of the own vehicle,
In the analyzing, the data analysis unit,
Analyze the accident data corresponding to the driving environment information received from the controller based on the pre-stored big data by reflecting the accident data for each driving environment,
In the optimizing step, the control unit,
Based on the movement data of the surrounding object and the expected movement trajectory of the surrounding object, the expected movement path of the surrounding object is finally determined, and the accident data analyzed by the data analyzer is reflected in the expected movement path of the surrounding object. And optimizing the autonomous driving route.
delete delete delete delete delete The method of claim 8,
And controlling, by the control unit, at least one of driving, steering, and braking the autonomous vehicle so that the autonomous vehicle follows the optimized autonomous driving route.
A controller configured to generate an autonomous driving route of the own vehicle based on the movement data and the driving environment information of the surrounding objects of the own vehicle;
A data server probabilistically analyzing an expected movement trajectory of the surrounding object based on the movement data of the surrounding object received from the controller, and analyzing accident data corresponding to the driving environment information received from the controller; And
And a communication unit performing data communication between the control unit and the data server.
The controller optimizes the autonomous driving route based on the predicted movement trajectory and the accident data of the surrounding object analyzed by the data server,
The movement data of the surrounding object is object attribute data including one or more of an object type, a moving speed, deceleration acceleration information, lane change frequency information, and lane compliance information.
The data server receives moving data of the surrounding object, probably analyzes an expected movement trajectory of the surrounding object based on previously stored big data by reflecting moving data reference information according to an object property.
The driving environment information includes one or more of driving road information, driving area information, and driving time information of the own vehicle,
The data server analyzes the accident data corresponding to the driving environment information received from the controller based on the previously stored big data reflecting the accident data for each driving environment,
The control unit may finally determine an expected movement path of the surrounding object based on the movement data of the surrounding object and the expected movement trajectory of the surrounding object, and predict the movement of the surrounding object by analyzing the accident data analyzed by the data server. The autonomous driving system, characterized in that to optimize the autonomous driving route reflected in the route.

Images