KR20250054277A - An autonomous driving system and a method for avoiding crashes by using it - Google Patents

Abstract

According to an embodiment of the present invention, a method for controlling an autonomous driving system mounted on a vehicle comprises: a step of identifying one or more object information based on sensing information around the vehicle; a step of calculating a time-series position-wise existence probability within an expected driving range area of the vehicle corresponding to the object information, and configuring an object-specific location map; a step of performing a composite operation of the time-series position-wise existence probability between the object-specific location maps, and configuring a collision map for predicting a collision probability with a vehicle within the expected driving range area of the vehicle; a step of determining a risk area based on the collision map; and a step of driving vehicle steering and speed control along a path that avoids the risk area.

Description

{AN AUTONOMOUS DRIVING SYSTEM AND A METHOD FOR AVOIDING CRASHES BY USING IT}

The present invention relates to an autonomous driving system and a collision avoidance method using the same. More specifically, the present invention relates to a system and an operating method thereof for predicting the movement of surrounding objects to avoid expected collisions and provide safe driving.

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

Autonomous vehicles can drive to their destinations on their own, avoiding collisions with obstacles along their path and adjusting their speed and direction of travel based on the shape of the road, without the driver having to operate the steering wheel, accelerator pedal, or brakes. For example, they can accelerate on a straight road and decelerate on a curved road while changing their direction of travel in response to the curvature of the road.

In order to ensure stable driving of autonomous vehicles, the driving environment must be accurately measured through each sensor mounted on the vehicle, the driving status of the vehicle must be continuously monitored, and driving must be controlled according to the measured driving environment. In addition, it is important to prevent path deviation or collision with obstacles in advance by using vehicle-to-vehicle communication or vehicle-to-infrastructure communication technology.

In the past, when an obstacle such as a vehicle or person was detected in front of an autonomous vehicle, braking control was used to avoid collision with the obstacle. That is, the risk of collision with the obstacle in front was calculated through radar and cameras, and the distance to the obstacle required to avoid collision was compared with the current distance, and if sufficient distance was not secured, a warning was issued to the driver. If the driver did not respond appropriately despite the warning, a method was used to automatically generate or assist braking force through the braking control system.

However, in a real environment where there are a large number of obstacles in the surroundings, the evasion strategy is inevitably simplified by simply calculating the distance relationship to the obstacles and avoiding them through braking control, which makes it difficult to effectively avoid complex real-world situations.

The present invention has been made to solve the above-mentioned problems, and the purpose of the present invention is to provide an autonomous driving system capable of quickly configuring a realistic and complex collision prediction situation based on probability, and thereby performing effective avoidance and recovery driving path setting, steering system operation, and braking control system operation, and a collision avoidance method using the same.

According to an embodiment of the present invention for solving the above-described problem, a method for controlling an autonomous driving system mounted on a vehicle comprises: a step of identifying one or more object information based on sensing information around the vehicle; a step of calculating a time-series position-by-position existence probability within an expected driving range area of the vehicle corresponding to the object information, and configuring an object-by-object location map; a step of performing a composite operation of the time-series position-by-position existence probabilities between the object-by-object location maps, and configuring a collision map for predicting a collision probability with a vehicle within the expected driving range area of the vehicle; a step of determining a risk area based on the collision map; and a step of driving vehicle steering and speed control along a path that avoids the risk area.

In addition, the method according to an embodiment of the present invention for solving the above-described problem can be implemented as a computer program stored in a computer-readable medium for executing the method on a computer.

In addition, according to an embodiment of the present invention for solving the above-described problem, a device includes a location map calculation unit which identifies one or more object information based on sensing information around the vehicle, calculates a time-series position-by-position existence probability within an expected driving range area of the vehicle corresponding to the object information, and configures an object-by-object position map; a collision map calculation unit which performs a composite operation of the time-series position-by-position existence probability between the object-by-object position maps, configures a collision map which predicts a collision probability with a vehicle within an expected driving range area of the vehicle, and determines a risk area based on the collision map; and an autonomous driving control unit which drives vehicle steering and speed control along a path that avoids the risk area.

According to an embodiment of the present invention, by deriving the existence probability of each time-series location within the expected driving range of surrounding objects of an autonomous vehicle based on a location map and constructing a collision map that derives the collision probability between the vehicle and objects from the derived location map, it is possible to drive the vehicle steering and speed control along a path that avoids a risk area based on the collision map.

Accordingly, the present invention can provide an autonomous driving system capable of quickly configuring a realistic and complex collision prediction situation based on probability, and thereby performing effective avoidance driving and return driving path setting, steering system operation, and braking control system operation, and a collision avoidance method using the same.

FIG. 1 is a block diagram illustrating a system configuration according to one embodiment of the present specification.
FIG. 2 is a block diagram for explaining a location map calculation unit and its configuration according to an embodiment of the present invention.
FIG. 3 is a block diagram for explaining a collision map calculation unit and its configuration according to an embodiment of the present invention.
Figure 4 is a flowchart for explaining system operation according to an embodiment of the present invention.
Figure 5 is an exemplary diagram explaining a location map calculation process according to an embodiment of the present invention.
Figure 6 is an exemplary diagram explaining a collision map and risk area calculation process according to an embodiment of the present invention.
FIG. 7 is a flowchart illustrating system operation according to another embodiment of the present invention.
FIG. 8 is a block diagram exemplarily showing the hardware configuration of a computing device used to implement various embodiments of the present invention.

In describing the embodiments of this specification, if it is judged that a specific description of a known configuration or function may obscure the gist of the embodiments of this specification, a detailed description thereof will be omitted. In addition, in the drawings, parts that are not related to the description of the embodiments of this specification are omitted, and similar parts are given similar drawing reference numerals.

In the embodiments of this specification, when a component is said to be "connected", "coupled" or "connected" to another component, this may include not only a direct connection relationship, but also an indirect connection relationship in which another component exists in between. In addition, when a component is said to "include" or "have" another component, this does not exclude the other component unless specifically stated otherwise, but rather means that the other component can be included.

In the embodiments of this specification, the terms first, second, etc. are used only for the purpose of distinguishing one component from another component, and do not limit the order or importance between the components unless specifically stated otherwise. Therefore, within the scope of the embodiments of this specification, a first component in an embodiment may be referred to as a second component in another embodiment, and similarly, a second component in an embodiment may be referred to as a first component in another embodiment.

In the embodiments of this specification, the components that are distinguished from each other are intended to clearly explain the characteristics of each, and do not necessarily mean that the components are separated. That is, a plurality of components may be integrated to form a single hardware or software unit, or a single component may be distributed to form a plurality of hardware or software units. Accordingly, even if not mentioned separately, such integrated or distributed embodiments are also included in the scope of the embodiments of this specification.

In this specification, the network may be a concept that includes both wired and wireless networks. In this case, the network may mean a communication network in which data can be exchanged between devices and systems and between devices, and is not limited to a specific network.

The embodiments described herein may have aspects that are entirely hardware, partly hardware and partly software, or entirely software. As used herein, the terms “unit,” “device,” or “system” refer to hardware, a combination of hardware and software, or a computer-related entity such as software. For example, a unit, module, device, or system as used herein may be, but is not limited to, a running process, a processor, an object, an executable, a thread of execution, a program, and/or a computer. For example, both an application running on a computer and the computer may be a unit, module, device, or system as used herein.

In this specification, the communication method of the network is not limited, and the connection between each component may not be connected in the same network method. The network may include not only a communication method utilizing a communication network (for example, a mobile communication network, wired Internet, wireless Internet, broadcasting network, satellite network, etc.), but also short-range wireless communication between devices. For example, the network may include all communication methods by which objects can network with each other, and is not limited to wired communication, wireless communication, 3G, 4G, 5G, or other methods. For example, wired and/or networks include Local Area Network (LAN), Metropolitan Area Network (MAN), Global System for Mobile Network (GSM), Enhanced Data GSM Environment (EDGE), High Speed Downlink Packet Access (HSDPA), Wideband Code Division Multiple Access (W-CDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, Zigbee, Wi-Fi, VoIP (Voice over Internet Protocol), LTE Advanced, IEEE802.16m, WirelessMAN-Advanced, HSPA+, 3GPP Long Term Evolution (LTE), Mobile WiMAX (IEEE 802.16e), UMB (formerly EV-DO Rev. C), Flash-OFDM, iBurst and MBWA (IEEE 802.20) systems, HIPERMAN, Beam-Division Multiple Access (BDMA), Wi-MAX (World Interoperability for Microwave) The term "communication network" may refer to a communication network using one or more communication methods selected from the group consisting of, but is not limited to, wireless communication using access and ultrasonic communication.

The components described in the various embodiments do not necessarily mean that they are essential components, and some may be optional components. Accordingly, embodiments that consist of a subset of the components described in the embodiments are also included in the scope of the embodiments of the present disclosure. In addition, embodiments that include other components in addition to the components described in the various embodiments are also included in the scope of the embodiments of the present disclosure.

Hereinafter, embodiments of the present specification will be described in detail with reference to the drawings.

FIG. 1 is a drawing illustrating an example of an operating environment of a system according to an embodiment of the present specification. Referring to FIG. 1, the system according to an embodiment of the present invention is an autonomous driving system (100) of a vehicle, and includes a sensor unit (110), a location map calculation unit (120), a collision map calculation unit (130), and an autonomous driving control unit (140).

The sensor unit (110) is for measuring the driving environment when a vehicle equipped with an autonomous driving system (100) is driving, and may include, for example, a camera sensor for obtaining images of the vehicle's surroundings, a radar sensor or lidar sensor for detecting obstacles (e.g., other vehicles) surrounding the vehicle, and a GPS (Global Positioning System) for detecting the vehicle's real-time location.

However, the configuration of the sensor unit (110) is not limited to the above-described configuration, and various types of sensors known to those skilled in the art may be further included as long as they can measure the driving environment.

In addition, the autonomous driving control unit (140) is for controlling autonomous driving and collision avoidance of a vehicle equipped with an autonomous driving system (100), and can be operated in a general driving mode for controlling general driving of a vehicle equipped with an autonomous driving system (100), a collision avoidance mode for controlling collision avoidance, and a return mode for returning to the original route from the avoidance mode.

Here, the general driving mode can be implemented by employing various autonomous driving algorithms known to ordinary technicians, and a detailed description thereof is omitted.

And, according to an embodiment of the present invention, the autonomous driving control unit (140) can perform complex collision prediction and avoidance control using the location map calculation unit (120) and the collision map calculation unit (130).

More specifically, first, the location map generating unit (120) can generate an object-specific location map using the time series location-specific existence probability of each object located around the vehicle.

In addition, the collision map generating unit (130) can perform a composite prediction of the existence probability for each coordinate using the location map for each object, thereby generating a collision map that includes a risk area where collision is expected.

Accordingly, the autonomous driving control unit (140) can determine whether to enter the current vehicle's avoidance mode based on the risk area information of the collision map, and can perform control of the avoidance path, steering angle, speed, etc. in the avoidance mode to perform avoidance on a safer and more effective path, and further enables smooth return to the original path.

Meanwhile, according to one embodiment, the autonomous driving control unit (140) may be implemented with one or more CPUs (Central Processing Units) and configured to perform a driving process in a normal driving mode, a collision avoidance mode, and a return mode, and the autonomous driving control unit (140) may be connected to a driving unit (not shown) of the vehicle and may control the driving direction, steering, and speed of the vehicle. The driving unit of the vehicle may include a steering actuator for controlling the driving direction of the vehicle and an acceleration/deceleration actuator for controlling the driving speed of the vehicle.

Accordingly, the driving unit of the vehicle can control the driving direction and speed of the vehicle under the control of the autonomous driving control unit (140), thereby enabling stable driving of the vehicle equipped with the autonomous driving system (100).

Meanwhile, the autonomous driving system (100) may further include a memory, a communication module, and a transceiver in addition to a processor that processes computer program commands by performing basic arithmetic, logic, and input/output operations to perform the operations of each processing unit described above, although not shown.

Memory is a non-transitory computer-readable storage medium, and may include a permanent mass storage device such as a random access memory (RAM), a read only memory (ROM), a disk drive, a solid state drive (SSD), a flash memory, etc. Here, a non-permanent mass storage device such as a ROM, an SSD, a flash memory, a disk drive, etc. may be included in the above-described device or server as a permanent storage device separate from the memory.

The communication module may provide a function for the system (100) to communicate with other devices or electronic devices via a network, and the transceiver may be a means for interfacing with an external input/output device (not shown). For example, the communication module may perform a function of receiving autonomous driving path information of a vehicle equipped with an autonomous driving system (100) and providing it to an autonomous driving control unit (140), or transmitting sensing information of a sensor unit (110) to a control server.

FIG. 2 is a block diagram for explaining more specifically a location map calculation unit and its configuration according to an embodiment of the present invention, and FIG. 3 is a block diagram for explaining more specifically a collision map calculation unit and its configuration according to an embodiment of the present invention.

First, referring to FIG. 2, the location map generating unit (120) includes an object identification unit (121), a time series location-based existence probability determining unit (123), and a map data mapping processing unit (125).

The object identification unit (121) identifies object information for each object located in the vicinity based on sensing information measured by the sensor unit (110). Here, the object information may include type information, current location information, speed information, acceleration information, and movement trajectory information of each object.

Accordingly, the time series location-specific existence probability determination unit (123) calculates existence probability information within the expected location area of each object based on object information.

Here, the time series location-based existence probability determination unit (123) can calculate existence probability information of each object within a predetermined expected driving range area based on at least one of the type information, current location information, speed information, acceleration information, and movement trajectory information of the aforementioned object, centered on a vehicle equipped with an autonomous driving system (100).

Here, the driving expected range area can be determined based on at least one of the driving direction, driving speed, driving acceleration, and driving trajectory of the vehicle equipped with the autonomous driving system (100), and can be determined as a range area of a two-dimensional or three-dimensional coordinate system in which the vehicle is expected to drive for a certain period of time.

Accordingly, the time series position-by-position existence probability determination unit (123) can determine the time series position-by-position existence probability of each identified object according to object information within the driving expected range area determined in relation to the movement of the vehicle.

The existence probability by time series location is calculated based on probability, so as time passes, the locations become more dispersed and the existence probability by location decreases. It is desirable to calculate it so that the sum of the existence probabilities within the current expected driving range area becomes 100%, i.e. 1.

And, the map data mapping processing unit (125) performs mapping processing for the map on which the vehicle is currently driving and the autonomous driving path by mapping the time series location-specific existence probability determination information of the time series location-specific existence probability determination unit (123) to the map data on which the vehicle is currently driving, thereby configuring a location map accordingly. Here, the size of the expected driving range area can be set to be the same as the size of the driving map of the current vehicle, so that the location map mapping process can be configured quickly and easily.

In addition, the location map data, to which the existence probability information by time series location is mapped, can be used for collision map calculation, avoidance mode determination, avoidance path calculation, and return path calculation, which will be described below.

And, referring to FIG. 3, the collision map generating unit (130) includes a location map acquisition unit (131) for each surrounding object, a composite existence probability calculation unit (133), and a risk area determination unit (135) to generate a collision map from a location map.

First, the location map acquisition unit (131) for each surrounding object acquires a location map that has been mapped by the location map calculation unit (120) and classifies and identifies each object around the vehicle.

And, the composite existence probability calculation unit (133) can determine the composite existence probability for each location corresponding to the current vehicle's driving map by performing a composite operation between the existence probability determination information for each time series location of each location map. Here, it is preferable that the composite operation utilizes a multiplication operation between existence probabilities, and ultimately, a collision probability value that predicts the collision probability for each location can be derived as the probability that each object exists overlappingly.

Accordingly, the risk area determination unit (135) configures a collision map by mapping a collision probability value that predicts the collision probability to map data, and determines a risk area composed of an area in the collision map where the collision probability is greater than a threshold value.

Accordingly, the autonomous driving control unit (140) identifies the risk area determined by the risk area determination unit (135) based on the collision map, predicts a collision situation of a vehicle corresponding to the risk area based on the collision probability, and, if a collision is predicted, performs evasive driving on a route that can most effectively avoid it.

In addition, the autonomous driving control unit (140) may determine whether to enter the avoidance mode based on an overlap comparison between the risk area and the current autonomous driving path. In addition, the autonomous driving control unit (140) may determine an avoidance route to a section where it is easiest to return to the current autonomous driving path based on a comparison between the current autonomous driving path and the risk area, and after avoidance driving, return driving to the current autonomous driving path may be performed based on a return route for re-entering the normal mode from the avoidance path.

Figure 4 is a flowchart for explaining system operation according to an embodiment of the present invention.

Referring to FIG. 4, the autonomous driving system (100) according to an embodiment of the present invention identifies one or more object information based on sensing information sensed by the sensor unit (110) (S101).

Here, the object information may include at least one of type information, location information, speed information, acceleration information, and trajectory information identified for each object, and may be used to produce time-series movement prediction information of the object predicted according to the characteristics of each object.

Thereafter, the autonomous driving system (100) calculates the existence probability for each time series location corresponding to the identified object information and constructs a location map for each object (S103).

As described above, the object-specific location map can represent the time-series existence probability for each object location corresponding to the expected driving range area of the vehicle.

And, the autonomous driving system (100) configures a collision map based on the existence probability of each location through a composite operation of the location maps of the currently identified surrounding objects (S105).

Here, the collision map can be predicted as a collision probability based on the composite existence probability of each object of each location map mapped in response to the driving map data of the current vehicle as described above, and can be calculated based on the driving path of the current vehicle.

Accordingly, the autonomous driving system (100) determines a risk area based on a collision map (S107), determines a time-series autonomous driving path position of the vehicle as a path that avoids the risk area (S109), and performs steering and speed control driving according to the determined path position (S111).

Figure 5 is an exemplary diagram explaining a location map calculation process according to an embodiment of the present invention.

The features of the location map calculation process according to an embodiment of the present invention will be described in more detail with reference to FIG. 5.

First, the location map calculation unit (120) according to an embodiment of the present invention, when calculating a location map for each object's existence probability corresponding to time series t1, t2, and t3, can replace the existence probability of each location with 0 in areas with an existence probability lower than a certain value within the expected driving range of the vehicle, and perform probability filtering so that only areas with an existence probability higher than a certain value retain the value. This enables the amount of data processing in subsequent stages to be reduced by removing areas with extremely low actual occurrence probabilities in advance.

In addition, the location map calculation unit (120) may, when calculating the existence probability of each object by time-series position in the location map, identify the type of the object in advance and determine the existence probability distribution by time-series position differently according to the identified type. This is because driving parameters such as the degree of turning, maximum speed, and acceleration may be different for each object type. For example, when comparing the case where the surrounding object is a vehicle and the case where it is a kickboard, the kickboard has a lower speed and acceleration but can turn more freely, so it can be seen that even if the position and speed of the two are the same at the present time, the existence probabilities by position after time t may be different from each other.

However, since calculating the existence probability considering the type of an object arithmetically based on rules can increase the amount of computation and complexity, it may be desirable for the location map calculation unit (120) according to the embodiment of the present invention to configure a pre-learned artificial intelligence learning model to predict the time-series existence probability distribution by object type, and calculate an existence probability distribution suitable for each object type. As an artificial intelligence learning model for this purpose, various artificial neural network models using CNN, RNN, DNN, etc. can be used, and for learning, associative learning between the identification data by object type and the location movement data of the corresponding object during actual driving can be performed in advance using a machine learning method.

Figure 6 is an exemplary diagram explaining a collision map and risk area calculation process according to an embodiment of the present invention.

Referring to FIG. 6, the autonomous driving control unit (140) according to an embodiment of the present invention can individually extract time-series risk areas (101) from the collision map generated by the collision map generating unit (130) according to each time t1, t2, t3, and t4, and control the autonomous driving path and speed in a time-series manner so that the autonomous driving can return to a position where the return to the existing autonomous driving path is most effective while avoiding the risk area (101) most efficiently.

At this time, the autonomous driving control unit (140) can process autonomous driving control so that the magnitude of the instantaneous acceleration of the autonomous vehicle and the rate of change in the steering angle over time are below a certain value within the avoidance and recovery driving section corresponding to the risk area (101). This is to secure the stability and comfort of autonomous driving by preventing excessively sudden braking or the steering wheel from turning sharply momentarily.

FIG. 7 is a flowchart illustrating system operation according to another embodiment of the present invention.

Referring to FIG. 7, the autonomous driving control unit (140) according to an embodiment of the present invention can perform avoidance mode entry, avoidance path driving, and return control based on the aforementioned collision map. To this end, the overlap ratio between the current autonomous driving path and the collision map-based risk area can first be compared (S201).

And, the autonomous driving control unit (140) enters avoidance mode when the overlap ratio is greater than the threshold (S203).

Thereafter, the autonomous driving control unit (140), in avoidance mode, identifies a risk area avoidance path with the highest similarity to the current first autonomous driving path (S205).

Then, the autonomous driving control unit (140) performs autonomous driving driving control along the identified risk area avoidance path (S207).

Meanwhile, the autonomous driving control unit (140) enters the return mode when the vehicle drives along the avoidance path more than a threshold value or moves away from the danger zone more than a threshold value (S209).

Here, the autonomous driving control unit (140) may not directly enter the return mode, but may output a user interface for entering the return mode and enter the return mode according to user input.

And, the autonomous driving control unit (140), in the return mode, performs return control to a specific point on the first autonomous driving path that is closest to the current location.

According to the driving control of the autonomous driving control unit (140) as described above, the driving vehicle can predict the probability of collision based on the collision map and avoid it, and the avoidance route can be determined as the optimal route for returning to the most efficient route. In addition, the steering and acceleration/deceleration parameters for safely driving on this route can be determined, thereby providing overall passenger convenience and stability during the avoidance and return process.

Hereinafter, an exemplary computing device (500) in which the methods described in various embodiments of the present invention are implemented will be described with reference to FIG. 8. For example, the computing device (500) of FIG. 8 may be the autonomous driving system (100) of FIG. 1.

Figure 8 is an exemplary hardware configuration diagram showing a computing device (500).

As illustrated in FIG. 8, the computing device (500) may include one or more processors (510), a bus (550), a communication interface (570), a memory (530) for loading a computer program (591) executed by the processor (510), and a storage (590) for storing the computer program (591). However, only components related to the embodiment of the present invention are illustrated in FIG. 8. Therefore, a person skilled in the art to which the present invention pertains may recognize that other general components may be included in addition to the components illustrated in FIG. 8.

The processor (510) controls the overall operation of each component of the computing device (500). The processor (510) may be configured to include at least one of a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphics Processing Unit), or any other type of processor well known in the art of the present invention. In addition, the processor (510) may perform operations for at least one application or program for executing a method/operation according to various embodiments of the present invention. The computing device (500) may include one or more processors.

The memory (530) stores various data, commands, and/or information. The memory (530) can load one or more programs (591) from the storage (590) to execute methods/operations according to various embodiments of the present invention. An example of the memory (530) may be RAM, but is not limited thereto.

The bus (550) provides a communication function between components of the computing device (500). The bus (550) may be implemented as various types of buses such as an address bus, a data bus, and a control bus.

The communication interface (570) supports wired and wireless Internet communication of the computing device (500). The communication interface (570) may also support various communication methods other than Internet communication. To this end, the communication interface (570) may be configured to include a communication module well known in the technical field of the present invention.

Storage (590) can non-temporarily store one or more computer programs (591). Storage (590) can be configured to include a volatile memory such as a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention pertains.

The computer program (591) may include one or more instructions implementing methods/operations according to various embodiments of the present invention.

For example, the computer program (591) may include instructions for performing an operation of identifying one or more object information based on sensing information around the vehicle, an operation of calculating a time-series position-wise existence probability within an expected driving range area of the vehicle corresponding to the object information and constructing an object-wise location map, an operation of performing a composite operation of the time-series position-wise existence probability between the object-wise location maps and constructing a collision map that predicts a collision probability with a vehicle within the expected driving range area of the vehicle, an operation of determining a risk area based on the collision map, and an operation of driving the vehicle's steering and speed control along a path that avoids the risk area.

When the computer program (591) is loaded into the memory (530), the processor (510) can perform methods/operations according to various embodiments of the present invention by executing one or more of the instructions.

The embodiments described above may be implemented at least in part as computer programs and recorded on a computer-readable recording medium. A computer-readable recording medium on which a program for implementing the embodiments is recorded includes all kinds of recording devices that store data that can be read by a computer. Examples of the computer-readable recording medium include ROMs, RAMs, CD-ROMs, magnetic tapes, optical data storage devices, etc. In addition, the computer-readable recording medium may be distributed over network-connected computer systems, so that computer-readable codes can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present embodiments may be easily understood by a person skilled in the art to which the present embodiments belong.

The above-described specification has been described with reference to the embodiments illustrated in the drawings, but this is merely exemplary, and those skilled in the art will understand that various modifications and variations of embodiments are possible from this. However, such modifications should be considered to be within the technical protection scope of the present specification. Accordingly, the true technical protection scope of the present specification should be determined to include other implementations, other embodiments, and those equivalent to the patent claims by the technical idea of the appended claims.

Claims (12)

In a control method of an autonomous driving system installed in a vehicle,
A step of identifying one or more object information based on sensing information around the vehicle;
A step of calculating the existence probability for each time series location within the expected driving range of the vehicle corresponding to the object information, thereby constructing a location map for each object;
A step of constructing a collision map that predicts the probability of collision with a vehicle within the expected driving range of the vehicle by performing a composite operation of the existence probability by time series location between the above object-specific location maps;
A step of determining a risk area based on the above collision map; and
A step of driving vehicle steering and speed control along a path that avoids the above risk area is included.
A control method for an autonomous driving system. In the first paragraph,
The steps for configuring the above location map are:
A step of calculating existence probability information for each time series location within the expected driving range of each object based on at least one of object type information, current location information, speed information, acceleration information, and trajectory information included in the above object information.
A control method for an autonomous driving system. In the second paragraph,
The steps for configuring the above location map are:
A step of mapping the existence probability information by time series location within the driving expected range area of each object to the driving map data of the vehicle.
A control method for an autonomous driving system. In the second paragraph,
The steps for configuring the above location map are:
Within the expected driving range of the vehicle, a step is included in which the existence probability of an object at a location where the existence probability of the object is below a certain value is replaced with 0.
A control method for an autonomous driving system. In the second paragraph,
The steps for configuring the above location map are:
A step of calculating existence probability information by time series location differently for each object type by applying driving parameters differently for each object type identified from the object information.
A control method for an autonomous driving system. In paragraph 5,
The step of calculating the existence probability information for each time series location differently for each object type is as follows:
It includes a step of calculating a time series location-specific existence probability distribution suitable for each object type based on a pre-learned artificial intelligence learning model.
The above artificial intelligence learning model is built based on association learning between object type-specific identification data and the object's location movement data during actual driving.
A control method for an autonomous driving system. In the first paragraph,
The step of driving the above vehicle steering and speed control is,
A step of comparing the overlap ratio between the current first autonomous driving path and the above risk area; and
If the above overlapping ratio is greater than the threshold, a step of entering the avoidance mode is included.
A control method for an autonomous driving system. In Article 7,
The step of driving the above vehicle steering and speed control is,
In the above avoidance mode, the method further includes identifying a risk zone avoidance path having the highest similarity to the current first autonomous driving path, and performing autonomous driving driving control according to the identified risk zone avoidance path.
A control method for an autonomous driving system. In Article 8,
The step of driving the above vehicle steering and speed control is,
A step of entering a return mode when the vehicle drives along the evasion path more than a threshold or moves away from the danger zone more than a threshold; and
In the above return mode, the step of performing return control to a specific point on the first autonomous driving path closest to the current location is further included.
A control method for an autonomous driving system. In Article 9,
In the above avoidance mode and the above return mode, the magnitude of the instantaneous acceleration of the vehicle and the rate of change of the steering angle over time are controlled to be below a certain value.
A control method for an autonomous driving system. In autonomous driving systems installed in vehicles,
A location map generating unit that identifies one or more object information based on sensing information around the vehicle, calculates a time-series location-specific existence probability within an expected driving range of the vehicle corresponding to the object information, and constructs a location map for each object;
A collision map generating unit that performs a composite operation of the existence probability by time series location between the above object-specific location maps to predict the collision probability with a vehicle within the expected driving range of the vehicle, and determines a risk area based on the collision map; and
Including an autonomous driving control unit that drives vehicle steering and speed control along a path that avoids the above-mentioned risk area.
Autonomous driving system. processor;
A memory that loads a computer program to be executed by said processor; and
Including storage for storing the above computer program,
The above computer program,
An operation of identifying one or more object information based on sensing information around the vehicle;
An operation of constructing a location map for each object by calculating the existence probability for each time series location within the expected driving range of the vehicle corresponding to the object information.
An operation of constructing a collision map that predicts the probability of collision with a vehicle within the expected driving range of the vehicle by performing a composite operation of the existence probability of each time series location between the above object-specific location maps.
An operation for determining a risk area based on the above collision map, and
Includes instructions for performing actions to drive vehicle steering and speed control along a path that avoids the above-mentioned risk area.
Computing device.

Images