KR20240019656A - Method and apparatus for planning future driving speed - Google Patents

Abstract

This disclosure relates to a method and apparatus for planning future driving speed. One embodiment of the present disclosure includes obtaining a region of interest, which is a predetermined area in front of the vehicle's driving path; Detecting a nearby object around the vehicle and setting a degree of relevance of the nearby object to the vehicle based on the region of interest; determining a reference location profile based on the relevance; and determining a final location profile corresponding to the reference location profile.

Description

Method and device for planning future driving speed {METHOD AND APPARATUS FOR PLANNING FUTURE DRIVING SPEED}

The present disclosure provides a method and apparatus for planning future driving speeds.

Smartization of vehicles is rapidly progressing due to the convergence of information and communication technology and the vehicle industry. Due to smartization, vehicles are evolving from simple mechanical devices to smart cars, and in particular, autonomous driving is attracting attention as a core technology for smart cars. Autonomous driving is a technology that allows a vehicle to reach its destination on its own without the driver having to operate the steering wheel, accelerator pedal, or brakes.

Various additional functions related to autonomous driving are continuously being developed, and ways to provide a safe autonomous driving experience to both passengers and pedestrians by controlling the car by recognizing and judging the driving environment using various data and self-driving vehicles Research on how to control a vehicle when other objects are recognized is continuously required.

The above-mentioned background technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be said to be known art disclosed to the general public before filing the application for the present invention.

The purpose of the present disclosure is to provide a method and device for planning future driving speed. The problem that the present disclosure aims to solve is not limited to the problems mentioned above, and other problems and advantages of the present disclosure that are not mentioned can be understood through the following description and can be understood more clearly by the examples of the present disclosure. It will be. In addition, it will be appreciated that the problems and advantages to be solved by the present disclosure can be realized by the means and combinations thereof indicated in the patent claims.

A first aspect of the present disclosure includes obtaining a region of interest in front of the vehicle's driving path; Detecting a nearby object around the vehicle and setting a degree of relevance of the nearby object to the vehicle based on the region of interest; determining a reference location profile based on the relevance; and determining a final location profile corresponding to the reference location profile.

A second aspect of the present disclosure includes a memory storing at least one program; and a processor that operates by executing the at least one program, wherein the processor acquires an area of interest in front of the driving path of the vehicle, detects nearby objects around the vehicle, and determines the area of interest based on the area of interest. An apparatus may be provided that sets a degree of relevance of a nearby object to the vehicle, determines a reference location profile based on the degree of relationship, and determines a final location profile corresponding to the reference location profile.

A third aspect of the present disclosure may provide a computer-readable recording medium recording a program for executing the method of the first aspect on a computer.

In addition to this, another method for implementing the present invention, another device, and a computer-readable recording medium recording a program for executing the method may be further provided.

Other aspects, features and advantages in addition to those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to the problem-solving means of the present disclosure described above, driving safety can be guaranteed even in various situations by planning future driving speeds.

In addition, according to the problem solving means of the present disclosure, the traveling speed can be planned taking riding comfort into consideration.

1 to 3 are diagrams for explaining an autonomous driving method according to an embodiment.
Figure 4 is an exemplary diagram schematically showing the environment ahead of the vehicle driving path according to one embodiment.
FIG. 5 is a diagram illustrating a method of planning the driving speed of a vehicle based on prediction information about the behavior of a nearest object according to an embodiment.
FIGS. 6A and 6B are diagrams for explaining a process of deriving a corrected position profile based on the degree of relevance of a nearby object according to an embodiment.
FIGS. 7A and 7B are diagrams illustrating a process for determining a reference location profile in an environment where a plurality of nearby objects exist, according to an embodiment.
Figure 8 is an exemplary diagram showing a final location profile according to an embodiment.
Figure 9 is a flowchart of a method for planning future driving speed according to one embodiment.
Figure 10 is a block diagram of a device for planning future driving speed according to an embodiment.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments presented below, but can be implemented in various different forms, and should be understood to include all transformations, equivalents, and substitutes included in the spirit and technical scope of the present invention. do. The examples presented below are provided to make the disclosure of the present invention complete and to fully inform those skilled in the art of the scope of the invention. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented in various numbers of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or may be implemented by circuit configurations for certain functions. Additionally, for example, functional blocks of the present disclosure may be implemented in various programming or scripting languages. Functional blocks may be implemented as algorithms running on one or more processors. Additionally, the present disclosure may employ conventional technologies for electronic environment setup, signal processing, and/or data processing. Terms such as “mechanism,” “element,” “means,” and “configuration” may be used broadly and are not limited to mechanical and physical configurations.

Additionally, connection lines or connection members between components shown in the drawings merely exemplify functional connections and/or physical or circuit connections. In an actual device, connections between components may be represented by various replaceable or additional functional connections, physical connections, or circuit connections.

Hereinafter, 'vehicle' may refer to any type of transportation used to move people or objects with engine, such as a car, bus, motorcycle, kickboard, or truck.

Hereinafter, the present disclosure will be described in detail with reference to the attached drawings.

Referring to FIG. 1, the autonomous driving device according to an embodiment of the present invention can be mounted on a vehicle to implement an autonomous vehicle 10. The autonomous driving device mounted on the autonomous vehicle 10 may include various sensors (including cameras) to collect surrounding situation information. For example, the autonomous driving device may detect the movement of the preceding vehicle 20 running in front through an image sensor and/or an event sensor mounted on the front of the autonomous vehicle 10. The self-driving device may further include sensors for detecting not only the front of the self-driving vehicle 10, but also other driving vehicles 30 running in the lane next to the self-driving vehicle 10 and pedestrians around the self-driving vehicle 10.

At least one of the sensors for collecting situational information around the autonomous vehicle may have a predetermined field of view (FoV), as shown in FIG. 1 . For example, when a sensor mounted on the front of the autonomous vehicle 10 has a field of view (FoV) as shown in FIG. 1, information detected at the center of the sensor may have relatively high importance. This may be because the information detected at the center of the sensor includes most of the information corresponding to the movement of the preceding vehicle 20.

The self-driving device processes information collected by the sensors of the self-driving vehicle 10 in real time to control the movement of the self-driving vehicle 10, while storing at least some of the information collected by the sensors in a memory device. .

Referring to FIG. 2, the autonomous driving device 40 may include a sensor unit 41, a processor 46, a memory system 47, and a vehicle body control module 48. The sensor unit 41 includes a plurality of sensors (including cameras) 42-45, and the plurality of sensors 42-45 include an image sensor, an event sensor, an illumination sensor, a GPS device, an acceleration sensor, etc. It can be included.

Data collected by sensors 42-45 may be transmitted to processor 46. The processor 46 stores the data collected by the sensors 42-45 in the memory system 47 and controls the vehicle body control module 48 based on the data collected by the sensors 42-45 to control the vehicle body control module 48. movement can be determined. The memory system 47 may include two or more memory devices and a system controller for controlling the memory devices. Each of the memory devices may be provided as one semiconductor chip.

In addition to the system controller of the memory system 47, each of the memory devices included in the memory system 47 may include a memory controller, and the memory controller may include an artificial intelligence (AI) operation circuit such as a neural network. The memory controller may generate calculation data by assigning a predetermined weight to data received from the sensors 42 - 45 or the processor 46 and store the calculation data in a memory chip.

Figure 3 is a diagram showing an example of image data acquired by sensors (including cameras) of an autonomous vehicle equipped with an autonomous driving device. Referring to FIG. 3, image data 50 may be data acquired by a sensor mounted on the front of an autonomous vehicle. Therefore, the image data 50 may include the front part 51 of the autonomous vehicle, the preceding vehicle 52 in the same lane as the autonomous vehicle, the vehicles 53 and the background 54 around the autonomous vehicle. .

In the image data 50 according to the embodiment shown in FIG. 3, the data in the area where the front part 51 and the background 54 of the autonomous vehicle appear are data that are unlikely to affect the operation of the autonomous vehicle. It can be. In other words, the front 51 and background 54 of the autonomous vehicle can be considered data with relatively low importance.

On the other hand, the distance to the preceding vehicle 52 and the lane change movement of the driving vehicle 53 may be very important factors in the safe operation of an autonomous vehicle. Accordingly, in the image data 50, data in an area including the preceding vehicle 52 and the driving vehicle 53 may have relatively high importance in the operation of the autonomous vehicle.

The memory device of the autonomous driving device may store the image data 50 received from the sensor by assigning different weights to each region. For example, a high weight is given to data in an area that includes the preceding vehicle 52 and the driving vehicle 53, and a low weight is given to data in an area where the front 51 and background 54 of an autonomous vehicle appear. can be given.

Hereinafter, operations according to various embodiments may be understood as being performed by the autonomous driving device or a processor included in the autonomous driving device.

Figure 4 is an exemplary diagram schematically showing the environment ahead of the vehicle driving path according to one embodiment.

Referring to FIG. 4, various objects 420, 430, 440, and 450, including vehicles and pedestrians, may exist in front of the driving path 410 of the vehicle 400. In order for the vehicle 400 to drive safely, the driving conditions of other vehicles 420, 430, and 440 and the behavior of the pedestrian 450 must be taken into consideration. Therefore, the device for planning future driving speed (hereinafter referred to as 'device') according to the present invention sets the range to be considered when driving the vehicle 400 as the area of interest 460 and determines the vehicle 400 based on the area of interest 460. The driving speed of (400) can be determined.

In one embodiment, the device may acquire a region of interest 460, which is a predetermined area in front of the driving path 410. The device may determine the driving speed of the vehicle 400 by considering only the objects 420, 430, and 440 included in the region of interest 460.

In one embodiment, the device acquires a longitudinal area of interest (not shown) within a specific distance 401 in front of the driving path 410 and within a specific distance 402 on both sides orthogonal to the driving path 410. It can be obtained as a lateral region of interest (not shown). For example, if the driving path 410 is a curved path rather than a straight path as shown in FIG. 4, the region of interest 460 may not have a rectangular shape, but is not limited thereto.

In one embodiment, the device may acquire a longitudinal region of interest (not shown) based on the speed of the vehicle 400. When the speed of the vehicle 400 is high, it is necessary to consider objects at a relatively long distance in front of the driving path 410, so at this time, the device can acquire a longitudinal region of interest (not shown) within a relatively long distance. In another embodiment, the device may acquire a longitudinal region of interest (not shown) within a preset distance.

The device may obtain the intersection of the longitudinal region of interest (not shown) and the horizontal region of interest (not shown) as the region of interest 460.

In one embodiment, the device may detect nearby objects 420, 430, 440, and 450 present around the vehicle 400. The nearby objects 420, 430, 440, and 450 may be objects within the region of interest 460 or outside the region of interest 460. For example, the device may include or be separately equipped with various imaging devices or sensors such as a camera, image sensor, radar (RADAR) or LIDAR sensor, and these can be used singly or in a combined form to detect nearby objects around the vehicle ( 420, 430, 440, 450) can be used for detection. Accordingly, the detected object may correspond to not only the captured image shape but also a plurality of measurement points obtained from an image sensor, etc.

In one embodiment, the device may detect the nearest object 440. The nearest object 440 is the closest object to the vehicle 400 among nearby objects driving on the driving path 440, and refers to an object that exists inside the region of interest 460.

Meanwhile, when detecting the nearby objects 420, 430, 440, and 450, the device can also obtain prediction information on the behavior of the nearby objects. Behavior prediction information refers to information that predicts the near future behavior of an object by considering both the position and speed information of the object.

Since the position of the vehicle 400 cannot be ahead of the position of the nearest object 440, the device must consider the location and behavior of the nearest object 440 when planning the driving speed of the vehicle 400. Accordingly, when the nearest object 440 is detected, the device can plan the driving speed of the vehicle 400 based on the behavior prediction information of the nearest object 440.

In one embodiment, the device may set the degree of relevance of the nearby objects 420, 430, 440, and 450 based on the region of interest 460. The degree of relevance is a number that reflects the interconnection between the vehicle 400 and nearby objects (420, 430, 440, 450). When the device plans the driving speed, the location of nearby objects (420, 430, 440, 450) and It can be an indicator of how much behavior should be considered. For example, if the distance 421 from the driving path of a nearby object 420 is close, the location and behavior of the nearby object 420 need to be weighted and reflected when planning the driving speed, so the device The degree of relevance of the corresponding nearby object 420 can be set high.

Likewise, if the distance (not shown) from the driving path of a nearby object 450 is long, or if a nearby object 450 does not exist in the region of interest 460, the device plans the driving speed accordingly. The position and behavior of the nearby object 450 may not be considered at all or may be reflected with significantly less weight. Accordingly, if the nearby object 450 does not exist within the region of interest 460, the device may set the relevance of the nearby object 450 to 0.

Meanwhile, the device can obtain the distance 422 from the driving path by reflecting the width of the vehicle 400 and nearby objects 420, 430, 440, and 450. For example, the device may obtain the distance 422 from the driving path of the nearby object 420 by excluding the space occupied by the volume of each object itself.

When the device plans the vehicle's driving speed, it does not simply judge in a binary way whether other objects are included in the area of interest or not and decelerates/accelerates in a heterogeneous manner, but sets the degree of relationship with other objects and determines whether other objects are included or not in the area of interest. Safety and riding comfort can be improved through the process of determining how much to decelerate/accelerate based on continuous relevance.

In one embodiment, the device may set the degree of relevance to be inversely proportional to the distance from the driving path of the nearby object (420, 430, 440) when the nearby object (420, 430, 440) exists within the region of interest (460). there is. For example, since the distance (not shown) from the driving path of a specific nearby object 430 in FIG. 4 is closer than the distance 421 from the driving path of another nearby object 420, the device The relevance of the corresponding nearby object 430 may be set to be higher than that of the other nearby objects 420 so that it is inversely proportional to the distance.

In one embodiment, when the nearest object 440 is detected, the device may set the relevance of the nearest object 440 to 1. Accordingly, as described above, the driving speed of the vehicle 400 can be planned to maintain a safe distance from the nearest object 440 by maximally reflecting the position and behavior of the nearest object 440.

FIG. 5 is a diagram illustrating a method of planning the driving speed of a vehicle based on prediction information about the behavior of a nearest object according to an embodiment.

Referring to FIG. 5 , it can be assumed that the closest object 520 among the objects traveling on the driving path of the vehicle 510 exists within the region of interest. At this time, in one embodiment, the device provides a reference location profile based on at least one of the standard location profile 530 of the vehicle 510, the behavior prediction information of the nearest object 520, and the relevance of the nearest object 520. (550) can be determined.

Specifically, when the nearest object 520 exists, the device derives the corrected location profile 550 by correcting the standard location profile 530 based on the relevance or behavior prediction information of the nearest object 520, , the reference location profile 550 can be determined using the corrected location profile 550. In this embodiment according to FIG. 5 , since there is only one nearby object 520 , the corrected position profile 550 may be determined as the reference position profile 550 as is.

The position profile refers to a profile that reflects the change in displacement of an arbitrary object over time by setting the time axis and displacement axis to the x-axis and y-axis, respectively.

Meanwhile, the position profile of the nearby object, nearest object, and Nth surrounding object, which will be described later, is a behavior prediction profile in which the behavior prediction information of the object is expressed as a time-displacement graph, and is corrected to reflect the safety distance between the object and the vehicle. It may mean a location profile. For example, in FIG. 5, the position profile 540 of the nearest object is the behavior prediction profile 541 of the nearest object, in which the behavior prediction information of the nearest object 520 is expressed as a time-displacement graph, and the vehicle 510 It may mean a position profile corrected by reflecting the safety distance between the object 520 and the nearest object 520.

The standard location profile 530 may refer to a location profile that reflects the current driving speed of the vehicle 510. Alternatively, the standard location profile 530 may provide a desired speed for the vehicle 510 to drive (e.g., the highest limit set on the road on which the vehicle 510 is traveling) when there are no nearby objects around the vehicle 510 or no nearby objects exist within the area of interest. It may mean a position profile corresponding to a speed corresponding to a certain ratio of the speed. In other words, the standard position profile 530 may mean a position profile when the vehicle 510 drives at a desired speed.

The corrected position profile 550 refers to a position profile that corrects the standard position profile 530 by reflecting the behavior prediction information of each nearby object 520 when a nearby object 520 exists around the vehicle 510. That is, since the corrected position profile 550 corresponds to a position profile corrected by each nearby object, if there are a plurality of nearby objects excluding the nearest object, a plurality of corrected position profiles corresponding to the number of the nearby objects can be derived. there is. The method of deriving a plurality of correction position profiles will be described in detail with reference to FIGS. 7A and 7B.

The reference position profile 550 refers to a position profile obtained by correcting the standard position profile 530 by considering the behavior prediction information of all nearby objects 520 when nearby objects 520 exist around the vehicle 510. In one embodiment, the device may use all of the derived corrected location profiles 550 to determine one reference location profile 550.

In one embodiment, the device determines a standard location profile 530 of the vehicle 510 and determines a reference location profile 550 based on the standard location profile 530 and behavioral prediction information of the nearest object 520. You can. For example, the point at which the standard position profile 530 and the position profile 540 of the nearest object 520 derived from the behavior prediction information of the nearest object 520 meet When defined, the device is Up to standard position profile 530, Thereafter, the reference location profile 550 may be determined to match the location profile 540 of the nearest object 520 .

By determining the final position profile (not shown), which will be described later, with reference to the reference position profile 550 determined in this way, safe driving without collision with other objects can be made possible.

FIGS. 6A and 6B are diagrams for explaining a process of deriving a corrected position profile based on the degree of relevance of a nearby object according to an embodiment.

Figure 6a shows the process of determining a reference location profile based on the relevance, assuming that the device sets the relevance of a nearby object to 0.4.

When the device discovers a nearby object that is stationary at a certain distance laterally 20 m ahead of the current location of the vehicle, the device can obtain the location profile 611 of the nearby object as shown in the graph of FIG. 6A. At this time, the device may derive a corrected location profile 610 that corrects the standard location profile based on the relevance of the nearby object.

이라고 정의할 때 장치는 현재 시점부터

까지는 표준 위치 프로파일,

이후로는 근접 객체의 위치 프로파일(611)에 40% 근접하도록 보정 위치 프로파일(610)을 도출할 수 있다.In one embodiment, the device may derive a corrected position profile such that the standard position profile is 40% closer to the position profile 611 of a nearby object. For example, when the standard position profile meets the position profile of a nearby object.

When defined, the device starts from the current point in time.

Up to standard position profile,

Afterwards, the corrected position profile 610 can be derived to be 40% closer to the position profile 611 of the nearby object.

Since the position profile corresponds to the shape of a displacement graph with the time axis and displacement axis set to the x-axis and y-axis, respectively, the slope of the position profile is derived from the behavior prediction information of the corresponding nearby object. It means speed.

Since there is only one nearby object within the area of interest, the device can determine the derived corrected position profile 610 as the reference position profile.

Figure 6b shows the process of determining a reference location profile based on the relevance, assuming that the device sets the relevance of a nearby object to 0.8.

In one embodiment, when the device discovers a nearby object that is stationary at a certain distance laterally 20 m ahead of the current location of the vehicle, the device obtains the location profile 621 of the nearby object as shown in the graph of FIG. 6B. can do.

라고 정의할 때 장치는 현재 시점부터

까지는 표준 위치 프로파일,

이후로는 근접 객체의 위치 프로파일(621)에 80% 근접하도록 보정 위치 프로파일(620)을 도출할 수 있다.At this time, the device may derive the corrected position profile 620 so that the standard position profile is 80% closer to the position profile 621 of the nearby object. For example, when the standard position profile and the position profile 621 of a nearby object meet,

When defined, the device starts from the current point in time.

Up to standard position profile,

Afterwards, the corrected position profile 620 can be derived to be 80% closer to the position profile 621 of the nearby object.

Since there is only one nearby object within the area of interest, the device can determine the derived corrected position profile 620 as the reference position profile.

FIGS. 7A and 7B are diagrams illustrating a process for determining a reference location profile in an environment where a plurality of nearby objects exist, according to an embodiment.

The device may detect nearby objects 710, 720, and 730, including the closest object 730, within the area of interest of the vehicle 700. For convenience of explanation, the nearest object 730 is hereinafter defined as the first nearby object, and the nearby objects 710 and 720 other than the nearest object 730 are defined as the second nearby objects.

In one embodiment, the device creates one or more corrected location profiles 711, 721 by correcting a standard location profile based on the behavior prediction information and relevance of the first proximate object and one or more second proximal objects 710, 720. It can be derived. The corrected position profiles 711 and 721 correspond to the second nearby objects 710 and 720, respectively.

, 표준 위치 프로파일(701)과 최근접 객체(730)의 위치 프로파일이 만나는 시점을

라고 정의한다.The device uses the standard position profile 701, the position profile of the second nearby object 710, and the position profile of the nearest object 730 to derive the corrected position profile 711 corresponding to the second nearby object 710. will be taken into consideration. Accordingly, the point at which the standard position profile 701 and the position profile of the second nearby object 710 meet is determined.

, the point at which the standard position profile 701 and the position profile of the nearest object 730 meet

It is defined as

까지는 표준 위치 프로파일(701),

부터

까지는 제2 근접 객체(710)의 관련도에 비례하여 제2 근접 객체(710)의 거동 예측 정보에 대응되도록 보정된 위치 프로파일,

이후로는 최근접 객체(730)의 거동 예측 정보에 대응되도록 표준 위치 프로파일(701)을 보정함으로써 보정 위치 프로파일(711)을 도출할 수 있다. 일 실시예에서, 제2 근접 객체(710)의 관련도가 0.2인 경우,

부터

까지는 제2 근접 객체(710)의 위치 프로파일에 20% 근접하도록 표준 위치 프로파일(701)을 보정하고,

이후로는 최근접 객체(730)의 위치 프로파일과 제2 근접 객체(710)의 위치 프로파일에 8:2의 비율로 대응되도록 표준 위치 프로파일(701)을 보정할 수 있다.The device is

Up to standard position profile (701),

from

A position profile corrected to correspond to the behavior prediction information of the second nearby object 710 in proportion to the degree of relevance of the second nearby object 710,

Thereafter, the corrected position profile 711 can be derived by correcting the standard position profile 701 to correspond to the behavior prediction information of the nearest object 730. In one embodiment, when the relevance of the second nearby object 710 is 0.2,

from

The standard position profile 701 is corrected to be 20% closer to the position profile of the second nearby object 710,

Afterwards, the standard position profile 701 can be corrected to correspond to the position profile of the nearest object 730 and the position profile of the second nearby object 710 at a ratio of 8:2.

, 표준 위치 프로파일(701)과 최근접 객체(730)의 위치 프로파일이 만나는 시점을

라고 정의한다.Likewise, the device may derive a corrected position profile 721 corresponding to another second nearby object 720. The point at which the standard position profile 701 and the position profile of the second nearby object 720 meet

, the point at which the standard position profile 701 and the position profile of the nearest object 730 meet

It is defined as

까지는 표준 위치 프로파일(701),

부터

까지는 제2 근접 객체(720)의 관련도에 비례하여 제2 근접 객체(720)의 거동 예측 정보에 대응되도록 보정된 위치 프로파일,

이후로는 최근접 객체(730)의 거동 예측 정보에 대응되도록 표준 위치 프로파일(701)을 보정함으로써 보정 위치 프로파일(721)을 도출할 수 있다. 일 실시예에서, 제2 근접 객체(720)의 관련도가 0.6인 경우,

부터

까지는 제2 근접 객체(720)의 위치 프로파일에 60% 근접하도록 표준 위치 프로파일(701)을 보정하고,

이후로는 최근접 객체(730)의 위치 프로파일과 제2 근접 객체(710)의 위치 프로파일에 6:4의 비율로 대응되도록 표준 위치 프로파일(701)을 보정할 수 있다.The device is

Up to standard position profile (701),

from

A position profile corrected to correspond to the behavior prediction information of the second nearby object 720 in proportion to the degree of relevance of the second nearby object 720,

Thereafter, the corrected position profile 721 can be derived by correcting the standard position profile 701 to correspond to the behavior prediction information of the nearest object 730. In one embodiment, when the relevance of the second nearby object 720 is 0.6,

from

The standard position profile 701 is corrected to be 60% closer to the position profile of the second nearby object 720,

Afterwards, the standard position profile 701 can be corrected to correspond to the position profile of the nearest object 730 and the position profile of the second nearby object 710 at a ratio of 6:4.

Referring to FIG. 7B, the device may determine a reference location profile 740 using one or more corrected location profiles 711 and 721 corresponding to the first proximal object and one or more respective second proximal objects 710 and 720. there is.

According to the embodiment of deriving the corrected position profiles 711 and 721 with reference to FIG. 7A, the arbitrary displacement value of each corrected position profile 711 and 721 is less than or equal to the arbitrary displacement value of the standard position profile 701. You can see that In this way, the device can determine the reference position profile 740 such that any displacement value of the reference position profile 740 is always less than or equal to any displacement value of each of the corrected position profiles 711 and 721.

라고 정의할 때, 장치는

,

,

및

를 기준으로 시간을 5개의 구간으로 나누고, 각 구간에서 표준 위치 프로파일(701) 및 하나 이상의 보정 위치 프로파일(711, 721)중 최소의 변위 값을 갖는 위치 프로파일과 일치하도록 참조 위치 프로파일(740)을 결정할 수 있다.In one embodiment, the point at which each corrected position profile 711 and 721 meet is

When defined, the device is

,

,

and

The time is divided into five sections based on You can decide.

까지는 표준 위치 프로파일(701),

부터

까지 및

부터

까지의 구간에서는 최소의 변위 값을 갖는 보정 위치 프로파일(711),

부터

까지 및

이후로의 구간에서는 최소의 변위 값을 갖는 보정 위치 프로파일(721)과 일치하도록 참조 위치 프로파일(740)을 결정할 수 있다.Specifically, the device is

Up to standard position profile (701),

from

until and

from

In the section up to, a correction position profile 711 with the minimum displacement value,

from

until and

In the subsequent section, the reference position profile 740 may be determined to match the correction position profile 721 with the minimum displacement value.

Referring to the above-described embodiments, a method for a device to determine a reference location profile will be described assuming that a closest object (a first nearby object) and one or more second nearby objects are detected within a region of interest. For convenience of explanation, the second proximate object is redefined as the first peripheral object, second peripheral object, ??, Nth peripheral object in the order of proximity from the front of the vehicle, and Nth peripheral object. The corrected position profile corresponding to the surrounding object is defined as the Nth corrected position profile. At this time, N is a natural number corresponding to the number of second nearby objects.

From the point where the position profile of the Nth nearby object and the standard position profile meet, the device corrects it to correspond to the behavior prediction information of the Nth nearby object in proportion to the degree of relevance of the Nth nearby object, and the position profile and standard position of the nearest object. From the point where the profiles meet, the Nth corrected position profile can be derived by correcting it to correspond to the behavior prediction information of the nearest object.

In addition, the device provides one or more points in time when the position profile of the Nth surrounding object and the standard position profile meet and one or more times when the Nth corrected position profile meets (if N is 1, there is no point where the Nth corrected position profile meets) ) to determine a reference position profile to match the position profile with the minimum displacement value among the standard position profile, one or more N-th corrected position profiles, and the position profile of the nearest object in each section. You can.

In one embodiment, when the nearest object is not detected within the area of interest, the device determines the behavior of the N-th nearby object in proportion to the relevance of the N-th nearby object from the point where the location profile of the N-th nearby object meets the standard location profile. The Nth corrected position profile can be derived by correcting it to correspond to the prediction information.

In addition, one or more times when the position profile of the Nth surrounding object and the standard position profile meet and one or more times when the Nth corrected position profiles meet (if N is 1, there is no point when the Nth corrected position profile meets). The reference location profile may be determined to match the location profile with the minimum displacement value among the standard location profile and one or more N-th corrected location profiles in each of a plurality of sections dividing the time domain as a reference.

Figure 8 is an exemplary diagram showing a final location profile according to an embodiment.

In one embodiment, the device may determine a final location profile 820 that corresponds to the reference location profile 810.

The final position profile 820 refers to a position profile indicating the final driving speed at which the vehicle 800 will actually drive.

In one embodiment, the device may calculate the cost function based on the derived reference location profile 810. The cost function is a function that represents the relationship between variables related to cost derived from the location profile where the vehicle 800 will drive. Variables related to cost can be known through each term of the cost function.

In one embodiment, the device includes an error cost corresponding to the displacement difference from the reference position profile 810, an acceleration cost corresponding to the acceleration of the vehicle 800, and an acceleration change corresponding to the jerk of the vehicle. The cost function can be calculated based on the cost.

The error cost corresponds to a cost based on the difference between the reference location profile 810 and the location profile where the vehicle 800 will drive. Since the reference position profile 810 is the minimum position profile for driving without colliding with nearby nearby objects, as the difference increases, the safety of driving is affected. Therefore, error costs can be related to driving safety.

The acceleration cost corresponds to the cost due to acceleration derived from the position profile at which the vehicle 800 will drive. A large acceleration means rapid acceleration and deceleration, so acceleration costs can be related to not only driving safety but also riding comfort.

The acceleration change cost corresponds to the cost due to the acceleration and acceleration of the vehicle 800. Acceleration corresponds to a cost that represents the change in acceleration over time. When the vehicle 800 drives, an instantaneous impact is generated due to a change in acceleration, and the greater the acceleration, the lower the riding comfort due to the instantaneous impact. Therefore, the cost of acceleration change can be related to ride comfort.

In one embodiment, the device may determine the location profile that minimizes the cost function as the final location profile. For example, the device may perform an iterative calculation to find a position profile that minimizes the cost function, and the solution derived from the calculation may be determined as the final position profile.

Meanwhile, the device can determine a reference location profile and a final location profile for a predetermined time. The predetermined time refers to a specific time to plan the driving speed and may be a predetermined time or a time that changes based on the driving speed of the vehicle, the number of nearby objects, etc. For example, the device can guarantee driving stability by setting a long predetermined time because the larger the number of nearby objects, the greater the traffic volume and the more complex the driving speed plan.

Figure 9 is a flowchart of a method for planning future driving speed according to one embodiment.

The method for planning future driving speed shown in FIG. 9 is related to the previously described embodiments, so even if the content is omitted below, the content described above can also be applied to the method of FIG. 9.

The operations shown in FIG. 9 can be executed by the above-described autonomous driving device. Specifically, the operations shown in FIG. 9 may be executed by a processor included in the above-described autonomous driving device.

In step 910, the device may acquire a region of interest in front of the vehicle's driving path.

In one embodiment, an area within a specific distance in front of the driving path may be acquired as a longitudinal area of interest, and an area within a specific distance on both sides orthogonal to the driving path may be acquired as a lateral area of interest.

In one embodiment, the device may obtain the intersection of the longitudinal region of interest and the horizontal region of interest as the region of interest.

In step 920, the device may detect a nearby object around the vehicle and set the degree of relevance of the nearby object to the vehicle based on the region of interest.

In one embodiment, when a nearby object does not exist within the area of interest, the device sets the degree of relevance to 0, and when a nearby object exists within the region of interest, the device sets the degree of relevance based on the distance from the driving path of the nearby object. You can set it.

At step 930, the device may determine a reference location profile based on relevance.

In one embodiment, the device may determine a standard position profile that reflects the vehicle's current travel speed.

In one embodiment, the device may detect the nearest object, which is the closest object that exists on the driving path inside the region of interest, among nearby objects.

In one embodiment, the device derives a corrected location profile by correcting a standard location profile based on the relevance of the nearby object when the nearest object is not detected, and the behavior of the nearest object when the nearest object is detected. A corrected location profile can be derived by correcting the standard location profile based on the prediction information.

In one embodiment, the device may use the calibrated location profile to determine a reference location profile.

In one embodiment, the proximity object may include a first proximity object that is the closest proximity object existing on a driving path within the region of interest and one or more second proximity objects that are different from the first proximity object.

In one embodiment, the device determines a standard location profile of the vehicle and corrects the standard location profile based on at least one of the relevance of the one or more second proximate objects and the behavior prediction information of the first proximate object, 2 One or more corrected position profiles corresponding to each nearby object can be derived, and a reference position profile can be determined using the one or more corrected position profiles.

In one embodiment, the device may derive a corrected position profile by correcting the standard position profile to correspond to the running speed of the nearby object in proportion to the degree of relevance of the nearby object.

In one embodiment, the device may derive a corrected position profile by correcting the standard position profile to correspond to the running speed of the nearest object.

In one embodiment, the device may derive the corrected position profile such that any displacement value in the corrected position profile is less than or equal to any displacement value in the standard position profile.

In one embodiment, the device can determine the reference location profile such that any displacement value in the reference location profile is less than or equal to any displacement value in the corrected location profile.

In one embodiment, the reference location profile may be a location profile for a period of time.

At step 940, the device can determine a final location profile that corresponds to the reference location profile.

In one embodiment, the device may calculate a cost function based on a reference location profile.

In one embodiment, the device may determine the location profile that minimizes the cost function as the final location profile.

In one embodiment, the cost function may be calculated based on an error cost corresponding to the difference from the reference position profile, an acceleration cost corresponding to the acceleration of the vehicle, and an acceleration change cost corresponding to the acceleration of the vehicle.

In one embodiment, the final location profile may be a location profile for a certain amount of time.

Figure 10 is a block diagram of a device for planning future driving speed according to an embodiment.

Referring to FIG. 10, the device 1000 may include a communication unit 1010, a processor 1020, and a DB 1030. In the device 1000 of FIG. 10, only components related to the embodiment are shown. Accordingly, those skilled in the art can understand that other general-purpose components may be included in addition to the components shown in FIG. 10.

The communication unit 1010 may include one or more components that enable wired/wireless communication with an external server or external device. For example, the communication unit 1010 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiver (not shown). In one embodiment, the communication unit 1010 can receive traffic information and use it to recognize crosswalks on the driving route.

The DB 1030 is hardware that stores various data processed within the device 1000, and can store programs for processing and control of the processor 1020.

The DB 1030 is a random access memory (RAM) such as dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD- It may include ROM, Blu-ray or other optical disk storage, a hard disk drive (HDD), a solid state drive (SSD), or flash memory.

The processor 1020 controls the overall operation of the device 1000. For example, the processor 1020 can generally control the input unit (not shown), display (not shown), communication unit 1010, DB 1030, etc. by executing programs stored in the DB 1030. The processor 1020 can control the operation of the device 1000 by executing programs stored in the DB 1030.

The processor 1020 may control at least some of the operations of the autonomous driving device described above with reference to FIGS. 1 to 9 .

The processor 1020 includes application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, and microcontrollers. It may be implemented using at least one of micro-controllers, microprocessors, and other electrical units for performing functions.

In one embodiment, device 1000 may be a mobile electronic device. For example, the device 1000 may be implemented as a smartphone, tablet PC, PC, smart TV, personal digital assistant (PDA), laptop, media player, navigation, device equipped with a camera, and other mobile electronic devices. Additionally, the device 1000 may be implemented as a wearable device such as a watch, glasses, hair band, or ring equipped with communication functions and data processing functions.

In another embodiment, device 1000 may be an electronic device embedded in a vehicle. For example, the device 1000 may be an electronic device that is inserted into a vehicle through tuning after the production process. In this case, the locations of the device 1000 and the above-described vehicle (or autonomous vehicle) may be the same.

In another embodiment, the device 1000 may be a server located outside the vehicle. A server may be implemented as a computer device or a plurality of computer devices that communicate over a network to provide commands, codes, files, content, services, etc. The server may receive data necessary to optimize the trajectory of the vehicle from devices mounted on the vehicle, and optimize the trajectory of the vehicle based on the received data.

In another embodiment, the process performed in the device 1000 may be performed by at least some of a mobile electronic device, an electronic device embedded in the vehicle, and a server located outside the vehicle.

Embodiments according to the present invention may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. At this time, the media includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROM. , RAM, flash memory, etc., may include hardware devices specifically configured to store and execute program instructions.

Meanwhile, the computer program may be designed and configured specifically for the present invention, or may be known and available to those skilled in the art of computer software. Examples of computer programs may include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

According to one embodiment, methods according to various embodiments of the present disclosure may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. The computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or through an application store (e.g. Play StoreTM) or between two user devices. It may be distributed in person or online (e.g., downloaded or uploaded). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

Unless there is an explicit order or statement to the contrary regarding the steps constituting the method according to the invention, the steps may be performed in any suitable order. The present invention is not necessarily limited by the order of description of the above steps. The use of any examples or illustrative terms (e.g., etc.) in the present invention is merely to describe the present invention in detail, and unless limited by the claims, the scope of the present invention is limited by the examples or illustrative terms. It doesn't work. Additionally, those skilled in the art will recognize that various modifications, combinations and changes may be made depending on design conditions and factors within the scope of the appended claims or their equivalents.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the scope of the claims are within the scope of the spirit of the present invention. It will be said to belong to

Claims (11)

In the method of planning driving speed,
Obtaining an area of interest in front of the vehicle's driving path;
Detecting a nearby object around the vehicle and setting a degree of relevance of the nearby object to the vehicle based on the region of interest;
determining a reference location profile based on the relevance; and
Method comprising: determining a final location profile corresponding to the reference location profile. According to claim 1,
The reference location profile and the final location profile are,
A method, which is a location profile for a predetermined period of time. According to claim 1,
The step of acquiring the region of interest is,
acquiring an area within a specific distance in front of the driving path as a longitudinal area of interest, and acquiring an area within a specific distance on both sides orthogonal to the driving route as a lateral area of interest; and
Method comprising: obtaining an intersection of the longitudinal region of interest and the horizontal region of interest as the region of interest. According to claim 1,
The step of setting the degree of relevance is,
If the nearby object does not exist within the region of interest,
setting the degree of relevance to 0;
If the nearby object exists within the region of interest,
The method further comprising: setting the degree of relevance based on the distance from the driving path of the nearby object. According to claim 1,
The step of determining the reference location profile is,
determining a standard position profile reflecting the current driving speed of the vehicle;
Detecting a nearest object, which is the closest object existing on the driving path inside the region of interest, among the nearby objects;
If the nearest object is not detected,
deriving a corrected location profile by correcting the standard location profile based on the relevance of the nearby object;
When the nearest object is detected,
Deriving a corrected position profile by correcting the standard position profile based on motion prediction information of the nearest object; and
Method comprising: determining the reference location profile using the corrected location profile. According to claim 1,
The nearby object is,
A first proximity object that is the closest object existing on the driving path inside the region of interest and one or more second proximity objects that are different from the first proximity object,
The step of determining the reference location profile is,
determining a standard location profile for the vehicle;
By correcting the standard location profile based on at least one of the relevance of the one or more second proximity objects and the behavior prediction information of the first proximity object, one or more corrected location profiles corresponding to each of the one or more second proximity objects A step of deriving; and
Method comprising: determining the reference location profile using the one or more corrected location profiles. According to claim 5,
Deriving the corrected location profile based on the degree of relevance of the nearby object includes,
Comprising: deriving the corrected position profile by correcting the standard position profile to correspond to the running speed of the nearby object in proportion to the degree of relevance of the nearby object,
Deriving the corrected position profile based on the behavior prediction information of the nearest object includes,
A method comprising: deriving the corrected position profile by correcting the standard position profile to correspond to the running speed of the nearest object. According to claim 5,
The step of deriving the corrected position profile is,
A step of deriving the corrected position profile such that a random displacement value of the corrected position profile is less than or equal to a random displacement value of the standard position profile,
The step of determining the reference location profile is,
Determining the reference position profile such that any displacement value of the reference position profile is less than or equal to a random displacement value of the corrected position profile. According to claim 1,
The step of determining the final location profile is,
calculating a cost function based on the reference location profile;
Including determining a location profile that minimizes the cost function as the final location profile,
The cost function is calculated based on an error cost corresponding to the difference from the reference position profile, an acceleration cost corresponding to the acceleration of the vehicle, and an acceleration change cost corresponding to the acceleration and acceleration of the vehicle. How to. In the device for planning driving speed,
a memory in which at least one program is stored; and
A processor that operates by executing the at least one program;
The processor,
Obtain the area of interest ahead of the vehicle's driving path,
Detecting nearby objects around the vehicle, and setting the degree of relevance of the nearby objects to the vehicle based on the region of interest,
Determine a reference location profile based on the relevance,
Apparatus for determining a final location profile corresponding to the reference location profile. A computer-readable recording medium recording a program for executing the method of claim 1 on a computer.

Images