KR20160136640A - Vechile auto driving system and method - Google Patents

Abstract

The present invention relates to an autonomous vehicle and, more specifically, relates to a vehicle automatic driving system and a method, wherein the system adopts an algorithm capable of utilizing navigation information for accuracy and stability of vehicle automatic driving. According to the present invention, the vehicle automatic driving system in which the algorithm is adopted and the method can improve accuracy and stability of vehicle automatic driving by considering an inside road or lanes to rocket to generate an expected driving route.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a vehicle-

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an autonomous vehicle, and more particularly, to a autonomous vehicle traveling system and method employing an algorithm capable of utilizing information of navigation for accuracy and stability of autonomous vehicle autonomous driving.

BACKGROUND ART [0002] With recent advances in technology, a large number of conventional instruments have been automated. In the field of automobiles, this trend is not an exception, and electric / electronic technology is being applied to technologies such as controlling an engine of a vehicle or detecting nearby objects to prevent accidents.

In particular, in recent years, a cruise control system has been developed to allow the driver to maintain the speed of the vehicle in accordance with the external road conditions without stepping on the brake or accelerator pedal when the driver sets the vehicle speed at a constant speed.

In recent years, a smart cruise control technology has been developed that can be decelerated or accelerated by providing a radar on the vehicle, while keeping the distance from the car ahead.

Nowadays, automobile companies are studying fully autonomous vehicles that the car finds its own way without driver intervention.

Automotive Automotive technology is largely divided into four categories: sensors, processors, algorithms, and actuators.

Sensors collect traffic signals, vehicle flows, objects and lanes instead of human eyes and ears. Vehicle-mounted video cameras, radar sensors, and position sensors replace human eyes and ears.

Processors and algorithms replace the human brain. It's a decision-making step that determines whether you want to quickly process the information gathered by the sensor, whether you want to run instantly or run, and how much to turn the steering wheel. It belongs to the top core technology.

When this decision is made, the actuator controls the vehicle in place of the human hands and feet.

Most autonomous vehicles currently under development in the industry are not 100% autonomous. It is the so-called limited autonomous vehicle in which the driver carries out intermittent intervention with the authority to monitor the traffic situation, but most of the time, in the event of an emergency, a warning is sent.

As mentioned above, one of the key points of the autonomous vehicle is that it is possible to cover specifically from the road information acquisition to the vehicle control in spite of the control algorithm, and there are few algorithms that can improve the safety and accuracy of the driving.

There are many problems in the ambiguity of algorithms such as not discriminating the applied algorithm depending on whether the road in which the vehicle is running is a road with a lane or a road without a lane.

The present invention relates to a system and a method for an autonomous vehicle that employs an algorithm capable of utilizing information of navigation for correctness and stability of autonomous driving of a vehicle.

According to an aspect of the vehicle autonomous vehicle traveling system according to the present invention,

A camera for capturing an image of the running direction of the vehicle;

An image processing processor for extracting operation environment information from an image captured by the camera;

Receiving the vehicle driving information from a plurality of sensors attached to the vehicle, receiving road information during driving of the vehicle from navigation, receiving the driving environment information from the image processing processor, and generating a predicted driving route of the vehicle An electronic control unit (ECU) for generating and outputting control commands for controlling the autonomous travel of the vehicle by detecting an object being moved and another vehicle being driven in the predicted travel route;

And a plurality of vehicle control actuators for receiving the control command and individually controlling the plurality of vehicle operation components.

Preferably,

Wherein the camera, the image processing processor and the ECU are configured in a camera module of the vehicle,

And the image processing processor and the ECU are connected by serial communication.

Preferably,

The driving environment information includes at least one of a location and driving information of a vehicle, guardrail-related information, road barrier related information, road lane information, road curb information, and roadside building information.

Preferably,

When the road lane information can be extracted from the driving environment information, the ECU generates the predicted traveling route based on the road lane information,

The estimated travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate.

Preferably,

When the road lane information can not be extracted from the driving environment information, the ECU combines the free space determined based on the driving environment information and the road information during running from the navigation, Lt; / RTI >

The estimated travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate.

Preferably,

The running road information includes at least one of road curvature information, road width, total number of lanes, running lane information, road type information, and vehicle position information during driving.

Preferably,

The vehicle running information includes at least one of a steering angle, a steering angular velocity, a steering torque amount, a yaw rate, a traveling speed, a turn signal, and a brake operation state.

According to one aspect of the autonomous vehicle traveling method according to the present invention,

An image pickup step of picking up an image of a traveling direction of the vehicle using a camera;

Extracting operation environment information from an image captured by the camera in an image processing processor;

A driving control method for a vehicle, comprising: receiving vehicle running information from a plurality of sensors attached to the vehicle using an electronic control unit (ECU); receiving road information during driving of the vehicle from navigation; And generates and outputs control commands for controlling the autonomous running of the vehicle by detecting an object in motion and another vehicle running in the estimated expected traveling path by receiving environmental information step;

And receiving the control command from the plurality of vehicle control actuators to individually control the plurality of vehicle operation components.

Preferably,

Wherein the camera, the image processing processor and the ECU are configured in a camera module of the vehicle,

And the image processing processor and the ECU are connected by serial communication.

Preferably,

The driving environment information includes at least one of a location and driving information of a vehicle, guardrail-related information, road barrier related information, road lane information, road curb information, and roadside building information.

Preferably,

When the road lane information can be extracted from the driving environment information, the ECU generates the predicted traveling route based on the road lane information,

The estimated travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate.

Preferably,

When the road lane information can not be extracted from the driving environment information, the ECU combines the free space determined based on the driving environment information and the road information during running from the navigation, Lt; / RTI >

The estimated travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate.

Preferably,

The running road information includes at least one of road curvature information, road width, total number of lanes, running lane information, road type information, and vehicle position information during driving.

Preferably,

The vehicle running information includes at least one of a steering angle, a steering angular velocity, a steering torque amount, a yaw rate, a traveling speed, a turn signal, and a brake operation state.

According to the vehicle autonomous vehicle traveling system and method according to the present invention, it is possible to set the traveling route by combining the information obtained by the camera and the information of the navigation, and control the driving of the vehicle, thereby achieving the safety of autonomous traveling .

The autonomous vehicle traveling system and method employing the algorithm according to the present invention can improve the accuracy and safety of autonomous traveling by generating a predicted traveling route in consideration of whether it is a back road or a lane.

1 is a schematic view of the configuration of a vehicle autonomous vehicle traveling system according to the present invention.
2 is a view schematically showing a configuration of a front camera module of a vehicle autonomous navigation system according to the present invention.
3 is a diagram illustrating communication between a navigation module and a camera module in a vehicle autonomous navigation system according to the present invention.
4 is a view schematically showing the algorithm operation of the autonomous vehicle traveling system according to the present invention.
5 is a view schematically showing a vehicle control flow of the autonomous vehicle traveling system according to the present invention.

In order to fully understand the present invention, operational advantages of the present invention, and objects achieved by the practice of the present invention, reference should be made to the accompanying drawings and the accompanying drawings which illustrate preferred embodiments of the present invention.

Hereinafter, the present invention will be described in detail with reference to the preferred embodiments of the present invention with reference to the accompanying drawings. Like reference symbols in the drawings denote like elements.

1 is a schematic view of the configuration of a vehicle autonomous vehicle traveling system according to the present invention.

The vehicle autonomous navigation system according to the present invention includes a navigation system 110, a front camera module 120, a plurality of sensors (not shown) attached to the vehicle, and a plurality of actuators 130 to 150 for controlling the operation of the vehicle .

The autonomous vehicle traveling system according to the present invention is characterized in that it applies different algorithms in consideration of the road conditions of the vehicle under running.

1) The vehicle autonomous navigation system controls the vehicle based on the lane information when the lane information of the road on which the vehicle is traveling can be extracted from the information obtained from the camera module, and 2 ) When the lane information of the road on which the vehicle is traveling can not be extracted from the information obtained from the camera module, the vehicle autonomous navigation system controls the vehicle by combining the information obtained from the camera module and the information received from the navigation.

In addition, the algorithm can be modified and applied in consideration of the width of the road.

The vehicle control actuator shown in FIG. 1 schematically illustrates the steering actuator 130, the brake actuator 140, and the accelerator actuator 150, but it is not so limited, and other components of the vehicle may also be included.

The actuator of each component in the autonomous vehicle traveling receives the control command from the front camera module 120 and controls the vehicle according to the received command.

The front camera module 120 outputs vehicle control commands generated according to a control algorithm to each actuator, and each actuator receives a control command and controls each component of the vehicle according to the received control command.

The vehicle control command will be generated with different types of parameter values depending on the control component and will be a value that changes in real time.

2 is a view schematically showing a configuration of a front camera module of a vehicle autonomous navigation system according to the present invention.

The front camera module 120 in the present invention includes a camera 210, an image processing processor 220 and an electronic control unit (ECU) 230 as mentioned above.

The image processing processor 220 and the ECU 230 are connected in a serial communication.

The front camera 210 may be a conventional CMOS (Complementary Metal Oxide Semiconductor) or a CCD (charge-coupled device) camera.

 The camera 210 images a front image in the running direction of the vehicle.

The image processing processor 220 extracts the forward driving environment information from the image captured by the camera 210. [

The forward driving environment information includes the position and running information of the front vehicle, the guard rail related information, the information related to the road outer barrier, the road lane information, the road curb information, and the building information around the road.

That is, the forward driving environment information collectively refers to the road and surrounding building information to be considered in front of the vehicle in operation.

The forward driving environment information is information that can be obtained from the image captured by the front camera.

An electronic control unit (ECU) 230 generates a predicted traveling route of the vehicle in accordance with an autonomous traveling algorithm, detects whether there is an object in motion and another traveling vehicle in the predicted traveling route, And outputs the generated control commands.

The autonomous driving algorithm in the present invention is applied differently according to the information obtained by the ECU 230. [

The ECU in the present invention is configured to: 1) receive vehicle running information from a plurality of sensors attached to the vehicle; 2) receive road information that the vehicle is driving from the navigation system 110; and 3) And receives operating environment information.

The ECU 230 generates a predicted traveling route using the received or obtained information and generates a control command for moving to the predicted traveling route to generate a plurality of vehicle control actuators .

Road information that is received from the navigation system 110 includes road curvature information on the front road during running, road width, the number of lanes all over the road, lane information during driving, road type information, and position information of the autonomous vehicle.

The forward driving environment information obtained by the image processing processor 220 and the road information during driving that are received from the navigation device 110 may be the same.

The vehicle running information received by the ECU 230 from a plurality of sensors attached to the vehicle includes a steering angle, a steering angular velocity, a steering torque amount, a yaw rate, a traveling speed, a turn signal, and a brake operation.

The vehicle running information indicates the current running information of the autonomous running vehicle, and the vehicle running information to be controlled by the control command is later when compared with the vehicle running information to be controlled by the control command.

3 is a diagram illustrating communication between a navigation module and a camera module in a vehicle autonomous navigation system according to the present invention.

Communication between the navigation device 110 and the front camera module 120 in the present invention is possible.

As described above, the front camera ECU 230 can receive the road information from the navigation system 110 and utilize it as basic information for generating a control command.

As shown in FIG. 3, when the driver inputs a destination to the navigation, the ECU 230 of the camera module determines whether or not the vehicle can travel to the input destination.

When it is determined that the ECU 230 can not travel to the input destination, the ECU 230 notifies navigation that the travel on the travel route is impossible, as shown in Fig.

The navigation unit 110, which is informed that the vehicle can not travel to the destination inputted from the ECU 230, searches for a new route to the destination and transmits the road information of the newly searched route to the ECU 230.

4 is a view schematically showing the algorithm operation of the autonomous vehicle traveling system according to the present invention.

4, the algorithm of the autonomous vehicle traveling system according to the present invention generates a predicted traveling route on a road under driving (410).

The algorithm detects (420) whether there is a moving object or a driving vehicle in the generated estimated driving route.

The algorithm of the autonomous vehicle traveling system in the present invention is constituted by a flow of generating a predicted travel route primarily and detecting whether there is an object in the estimated travel route that is generated secondarily.

The ECU 230 in the present invention determines a free space from the forward driving environment information received from the image processing processor 220. [

In the present invention, the free space is a space through which a vehicle under travel can move, for example, can be an empty lane on the road.

The free space can be defined depending on where the vehicle is traveling, and on a lane road, it may be a certain distance from the front / rear driving vehicle to an empty lane.

The free space on the back road can be a space where the autonomous vehicle can move, taking into consideration the spacing between adjacent buildings and the spacing between the main / stopped vehicles.

In the present invention, the expected travel route may be a concept including free space. Strictly speaking, the expected travel route means the route from the present autonomous vehicle to the free space.

As mentioned above, the present invention is characterized by embodying an algorithm in an autonomous vehicle.

When the autonomous running algorithm of the present invention can acquire the lane information from the front camera, the ECU 230 of the front camera module generates the expected driving route based on the obtained lane information.

The estimated travel route generated by the ECU 230 includes an offset, a steering angle, a curvature, and a curvature change rate.

When the lane information can be obtained, the expected travel route to the determined free space will be determined as a lane, which means to extract distance information (offset), curvature and curvature change rate to the lane to be moved.

When the road lane information can not be extracted from the forward driving environment information obtained by the camera 120 (for example, the road on the back road, the one-way road, or the road width of 8 m or less) The estimated travel route is determined by combining road information received from the navigation device during traveling.

The ECU 230 determines a free space based on the information received from the image processor 220. In the case where the road width is one-way or the road width is equal to or less than a predetermined width (for example, 8 meters) The process of determining the free space based on the information received from the image processor 220 in the ECU 230 can be compared to a process of recognizing a space on an empty road that the driver wants to visually move.

When the road lane information is not available, the ECU 230 sets the offset of the predicted traveling route, the orientation angle information based on the determined free space, and the curvature and curvature change rate information is based on the information received from the navigation .

In another embodiment, when the road running is not one-way or the road width is equal to or greater than a certain width (for example, 8 meters), when the vehicle running direction is left (determined according to the route setting to the final destination set in the navigation) The offset of the estimated travel route is determined based on the free space existing on the left side of the traveling vehicle based on the determined free space (for example, when the free space determined by the ECU 230 exists in the free space on the left side and the right side) .

The orientation angle of the expected travel route will be determined based on the free space located on the left side and the curvature and curvature rate information is set based on the information received from the navigation.

The offset of the estimated travel route in the case where the vehicle running direction is the right side (determined according to the route setting to the final destination set in the navigation) is determined by the determined free space (for example, the free space determined by the ECU 230, (If there is a free space at several points) on the right side of the traveling vehicle.

The orientation angle of the expected travel route will be determined based on the free space located on the right side, and the curvature and curvature rate information is set based on the information received from the navigation.

5 is a view schematically showing a vehicle control flow of the autonomous vehicle traveling system according to the present invention.

5 schematically shows a vehicle control flow of a vehicle autonomous navigation system, and detects (520) whether there is a moving object (e.g., a person or other animal or vehicle) in the determined expected travel route. That is, it is a process of detecting whether a person or a moving vehicle exists in a predicted traveling route moving to a free space or free space before final movement to the free space determined by the ECU 230. [

If there is no person or moving vehicle, a control command is generated to control the steering, brake, and accelerator to move along the selected predicted traveling path and output to the respective actuators (540).

If there is a moving object such as a moving vehicle, the ECU 230 tries to travel using another expected travel route (avoiding route or estimated route).

The ECU 230 can generate not only one predicted travel route but also a plurality of estimated travel routes. If there is only one free space determined and there is only one estimated travel route, and the vehicle is moving on the expected travel route, the autonomous vehicle may immediately perform the braking control (550).

However, if there is another expected travel route (i.e., avoidance route), the autonomous vehicle detects 530 whether there is a moving vehicle or other moving object within the avoidance route.

If there is no driving vehicle, a control command is generated to control the steering, brake, and accelerator to move along the selected predicted traveling path and output to the respective actuators (540).

However, if there is another vehicle in motion in the avoidance path, the autonomous vehicle will generate and output a braking control command (550).

Although the embodiments described above have been described with reference to the front camera, the front image, and the front operating environment information, the present invention is not limited to this, and it is noted that the image and operating environment information obtained according to the configuration of the camera may be changed do.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention. It is.

110 Navigation
120 front camera module
130 Steering Actuator
140 Brake Actuator
150 Accelerator Actuator

Claims (14)

A camera for capturing an image of the running direction of the vehicle;
An image processing processor for extracting operation environment information from an image captured by the camera;
Receiving the vehicle driving information from a plurality of sensors attached to the vehicle, receiving road information during driving of the vehicle from navigation, receiving the driving environment information from the image processing processor, and generating a predicted driving route of the vehicle An electronic control unit (ECU) for generating and outputting control commands for controlling the autonomous travel of the vehicle by detecting an object being moved and another vehicle being driven in the predicted travel route; And
And a plurality of vehicle control actuators for receiving the control command and individually controlling a plurality of vehicle operation components. The method according to claim 1,
Wherein the camera, the image processing processor and the ECU are configured in a camera module of the vehicle,
Wherein the image processing processor and the ECU are connected in a serial communication. The method according to claim 1,
Wherein the driving environment information includes at least one of a location and a driving information of the vehicle, guardrail-related information, road barrier related information, road lane information, road curb information, and roadside surrounding building information. The method of claim 3,
When the road lane information can be extracted from the driving environment information, the ECU generates the predicted traveling route based on the road lane information,
Wherein the expected travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate. The method of claim 3,
When the road lane information can not be extracted from the driving environment information, the ECU combines the free space determined based on the driving environment information and the road information during running from the navigation, Lt; / RTI >
Wherein the expected travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate. The method according to claim 1,
Wherein the road information during running includes at least one of road curvature information, road width, total number of lanes, running lane information, road type information, and vehicle position information during driving. The method according to claim 1,
Wherein the vehicle running information includes at least one of a steering angle, a steering angular velocity, a steering torque amount, a yaw rate, a traveling speed, a turn signal, and a brake operation state. An image pickup step of picking up an image of a traveling direction of the vehicle using a camera;
Extracting operation environment information from an image captured by the camera in an image processing processor;
A driving control method for a vehicle, comprising: receiving vehicle running information from a plurality of sensors attached to the vehicle using an electronic control unit (ECU); receiving road information during driving of the vehicle from navigation; And generates and outputs control commands for controlling the autonomous running of the vehicle by detecting an object in motion and another vehicle running in the estimated expected traveling path by receiving environmental information step; And
And receiving the control command from the plurality of vehicle control actuators to individually control the plurality of vehicle operation components. The method of claim 8,
Wherein the camera, the image processing processor and the ECU are configured in a camera module of the vehicle,
Wherein the image processing processor and the ECU are connected in a serial communication. The method of claim 8,
Wherein the driving environment information includes at least one of a position and a driving information of a vehicle, guardrail-related information, road barrier related information, road lane information, road curb information, and roadside surrounding building information. The method of claim 10,
When the road lane information can be extracted from the driving environment information, the ECU generates the predicted traveling route based on the road lane information,
Wherein the expected travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate. The method of claim 10,
When the road lane information can not be extracted from the driving environment information, the ECU combines the free space determined based on the driving environment information and the road information during running from the navigation, Lt; / RTI >
Wherein the expected travel route includes at least one of an offset, a steering angle, a curvature, and a curvature change rate. The method of claim 8,
Wherein the running road information includes at least one of road curvature information during running, road width, total lane number of roads, lane information during running, road type information, and position information of the vehicle. The method of claim 8,
Wherein the vehicle running information includes at least one of a steering angle, a steering angular velocity, a steering torque amount, a yaw rate, a traveling speed, a turn signal, and a brake operation state.

Images