Method and vehicle for recognizing irregular static objects for road boundary identification
Patent Information
- Authority / Receiving Office
- KR · KR
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-05
- Publication Date
- 2026-08-12
Smart Images
Figure P1020250014391_ABST
Abstract
Description
Technology Field
[0001] The present disclosure relates to a method for recognizing non-standard static objects and a vehicle for identifying road boundaries, and more specifically, to a method for recognizing non-standard static objects and a vehicle that accurately provides road boundaries by estimating the intended function of continuously arranged non-standard static objects on a road. Background Technology
[0002] Recently, there has been a trend toward commercializing vehicles equipped with various features to enhance driving convenience. To this end, autonomous driving functions are being supported in vehicles. These functions are being developed to minimize driver intervention or allow the vehicle to control driving without any intervention.
[0003] The vehicle can perceive the surrounding environment acquired by various types of heterogeneous sensors and identify the situation around the vehicle based on the perceived surrounding environment. The vehicle can control the vehicle's actuators by establishing a control plan for autonomous driving that responds to the identified situation.
[0004] The perceived surrounding environment may include, for example, dynamic objects and static objects. Static objects may include roads and stationary objects around the roads. Static objects may include, for example, road safety facilities, road signs, and lanes considered for driving on the road. Road safety facilities may indicate road boundaries and may include, for example, guide posts, rubber cones, traffic barrels, and curbs.
[0005] The types and attributes of dynamic objects and other static objects can be identified by boundary regions based on object perception derived from sensor data detecting the surrounding environment. Sensor data may be output from radar sensors or lidar sensors. While the type of a single road safety facility is identified by object perception, the attributes or functions of road safety facilities arranged continuously on the road may not be clearly identified by perception through sensor data. Specifically, even by perception based on sensor data, it may not be possible to infer whether a continuous arrangement of road safety facilities possesses the attributes of a road boundary. Here, the continuously arranged road safety facilities may be a type of unstructured static object for which boundary regions identifying functions through perception cannot be identified.
[0006] Accordingly, the vehicle does not recognize the space between mutually spaced road safety facilities as a road boundary but determines it as a drivable area, which may cause errors in vehicle control. The problem to be solved
[0007] The technical problem of the present disclosure is to provide a method for recognizing non-standard static objects and a vehicle that accurately provide road boundaries by estimating the intended function of non-standard static objects arranged in a continuous manner on a road.
[0008] The technical problems to be solved in this disclosure are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this disclosure belongs from the description below. means of solving the problem
[0009] According to one aspect of the present disclosure, a method for recognizing an unstructured static object for identifying a road boundary is provided. The method for recognizing an unstructured static object comprises: generating a track area of a static object arranged in a plurality based on sensor data of a sensor that generates point cloud data; providing a prediction range spaced apart from a preceding track area; including the succeeding track area in a track list based on detection of the succeeding track area within the prediction range; and generating a road boundary object that classifies the track area as a continuous static object based on the track list containing a threshold number or more track areas.
[0010] According to another embodiment of the present disclosure, the prediction range may include an enclosed area positioned at a distance spaced apart from the preceding track area.
[0011] According to another embodiment of the present disclosure, the step of including the trailing track area in the track list may include including the trailing track area detected in the enclosed area in the track list.
[0012] According to another embodiment of the present disclosure, the prediction range includes the enclosed area spaced apart from the preceding track area by the distance within the range of allowable angles, and the allowable angle may be set to a range of predetermined angles based on the arrangement direction of the preceding track area and the succeeding track area.
[0013] According to another embodiment of the present disclosure, the threshold number may be set to three or more.
[0014] According to another embodiment of the present disclosure, The steps of providing the prediction range and including the subsequent track area in the track list can be performed sequentially for the plurality of track areas. The step of generating the road boundary object may include: a step of removing the duplicate track area from the track list based on the existence of the duplicate track area in the track list; and a step of generating the road boundary object that classifies the remaining track area into the continuous static object.
[0015] According to another embodiment of the present disclosure, After the step of providing the above prediction range, the method may further include: a step of assigning a track loss area to the prediction range based on the non-detection of the following track area within the above prediction range; a step of determining whether to detect a following track area in a prediction range spaced apart from the track loss area; a step of determining whether to detect a subsequent track area in a prediction range spaced apart from the detected following track area based on the detection of the following track area; and a step of including the following track area and the subsequent track area in the track list based on the detection of the subsequent track area.
[0016] According to another embodiment of the present disclosure, the method may further include the step of classifying the track area, the trailing track area, and the subsequent trailing track area as discontinuous static objects based on the non-detection of the trailing track area in the prediction range or the non-detection of the subsequent trailing track area in the prediction range.
[0017] According to another embodiment of the present disclosure, the static object may include an object related to a traffic safety facility.
[0018] According to another aspect of the present disclosure, a method for recognizing an unstructured static object for identifying a road boundary is provided. The method for recognizing an unstructured static object comprises: generating a track area of a static object arranged in a plurality based on sensor data of a sensor that generates point cloud data; generating linear information including a linear model based on the connection between the leading track area and the trailing track area among more than a number of track areas; and generating a road boundary object that classifies the plurality of track areas as a continuous static object based on the fact that the intermediate track area exists within the association range with the linear model and the sensor characteristics of the plurality of track areas have similarity.
[0019] According to another embodiment of the present disclosure, the sensor comprises a radar sensor or a lidar sensor, and the sensor characteristics of the radar sensor include at least one of a signal-to-noise ratio (SNR) and a radar cross section (RCS), and the sensor characteristics of the lidar sensor may include the intensity of a reflected signal.
[0020] According to another aspect of the present disclosure, a vehicle is provided for implementing the recognition of an unstructured static object for identifying a road boundary. The vehicle comprises: a sensor unit including a sensor that detects the surrounding environment as point cloud data; a memory that stores at least one instruction; and at least one processor that executes the at least one instruction stored in the memory. The at least one processor is configured to generate a track area of a static object arranged in a plurality based on sensor data of the sensor, provide a prediction range spaced apart from a preceding track area, include the succeeding track area in a track list based on detection of the following track area in the prediction range, and generate a road boundary object that classifies the track area as a continuous static object based on the track list containing a threshold number or more of track areas.
[0021] The features briefly summarized above regarding the present disclosure are merely exemplary aspects of the detailed description of the present disclosure that follows and do not limit the scope of the present disclosure. Effects of the invention
[0022] According to the present disclosure, a method for recognizing atypical static objects and a vehicle can be provided that accurately provide road boundaries by estimating the intended function of atypical static objects arranged in a continuous manner on a road.
[0023] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below. Brief explanation of the drawing
[0024] Figure 1 is a diagram illustrating an example of a vehicle communicating with another device to transmit and receive data. FIG. 2 is a drawing showing a module constituting a vehicle according to one embodiment of the present disclosure. Figure 3 is a drawing illustrating traffic safety facilities. FIG. 4 is a diagram showing a module that constitutes a server according to the present disclosure. FIG. 5 is a flowchart relating to a method for recognizing an atypical static object for identifying a road boundary according to another embodiment of the present disclosure. Figure 6 is a diagram showing an example of searching a track area. Figure 7 is a diagram showing another example of track area navigation. Figure 8 is a diagram showing another example of track area navigation. FIG. 9 is a flowchart relating to a method for recognizing an atypical static object for identifying a road boundary according to another embodiment of the present disclosure. Figure 10 is a diagram showing another example of track area navigation. Specific details for implementing the invention
[0025] Hereinafter, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein.
[0026] In describing the embodiments of the present disclosure, if it is determined that a detailed description of known configurations or functions could obscure the essence of the present disclosure, such detailed description is omitted. Additionally, parts of the drawings unrelated to the description of the present disclosure have been omitted, and similar parts are denoted by similar reference numerals.
[0027] In the present disclosure, when a component is described as being connected, combined, or joined with another component, this may include not only a direct connection but also an indirect connection in which another component exists in between. Furthermore, when a component is described as including or having another component, this means that, unless specifically stated otherwise, it does not exclude the other component but may include an additional component.
[0028] In the present disclosure, terms such as first, second, etc. are used solely for the purpose of distinguishing one component from another component and do not limit the order or importance of the components unless specifically stated otherwise. Accordingly, within the scope of the present disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and likewise, a second component in one embodiment may be referred to as a first component in another embodiment.
[0029] In this disclosure, distinct components are intended to clearly describe their respective features and do not imply that the components are separate. That is, multiple components may be integrated to form a single hardware or software unit, or a single component may be distributed to form multiple hardware or software units. Accordingly, such integrated or distributed embodiments are included within the scope of this disclosure, even if not otherwise mentioned.
[0030] In the present disclosure, the components described in various embodiments do not necessarily mean essential components, and some may be optional components. Accordingly, embodiments consisting of a subset of the components described in one embodiment are also included within the scope of the present disclosure. Furthermore, embodiments including other components in addition to the components described in various embodiments are also included within the scope of the present disclosure.
[0031] In the present disclosure, each of the phrases such as A or B, at least one of A and B, at least one of A or B, A, B or C, at least one of A, B and C, and at least one of A, B, or C (at least one of A, B, C or combination thereof) may include any one of the items listed together in the corresponding phrase or all possible combinations thereof.
[0032] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments presented below but can be implemented in various different forms, and these embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention.
[0033] Hereinafter, with reference to FIGS. 1 and FIGS. 2, a vehicle implementing the recognition of irregular static objects for identifying road boundaries will be described.
[0034] Figure 1 is a diagram illustrating an example of a vehicle communicating with another device to transmit and receive data.
[0035] Referring to FIG. 1, the vehicle (100) may be driven based on electric energy or fossil energy. In the case of electric energy, the vehicle (100) may employ, for example, a pure battery-based vehicle driven solely by a high-voltage battery or a gas-based fuel cell as an energy source. Additionally, the fuel cell may utilize various forms of gas capable of generating electric energy, and the gas may be filled into the vehicle (100), for example, in a liquefied state. Here, the gas may be, for example, hydrogen. However, it is not limited thereto and various gases may be applied. In the case of fossil energy, the vehicle (100) may be driven based on fuel such as gasoline, diesel, or liquefied gas, and may be equipped with an internal combustion engine that drives the actuator unit (116) by the combustion of said fuel. The engine may be included in the power source unit (114) in order to provide the driving rotational force of the wheel to the wheel drive unit (118). As another example, the vehicle (100) can selectively utilize the energy of a fossil energy-based internal combustion engine and an electric battery to drive the actuator (116), and this may be a hybrid type vehicle.
[0036] A vehicle (100) may refer to a mobile device. A vehicle (100) may be a ground vehicle that travels on the ground, such as a conventional passenger or commercial vehicle, a purpose-built vehicle (PBV), etc. A vehicle (100) may be a four-wheeled vehicle, such as a passenger car, an SUV, or a small truck, or a vehicle with more than four wheels, such as a bus, a large truck, a container transport vehicle, or a heavy equipment vehicle. A vehicle (100) may be a robot in a broad sense, such as a means of transportation, and a robot may be moved using wheels, tracks, or other movement modules. The examples described in this disclosure may also be applied to robots, provided there is no technical conflict.
[0037] The vehicle (100) can be driven by being controlled by manual driving or autonomous driving through the user's driving. Autonomous driving can be implemented as semi-autonomous driving or fully autonomous driving. Fully autonomous driving can be provided as autonomous movement in which the processor (120) of the vehicle (100) fully controls the vehicle without user intervention, even when driving conditions are uncertain. Semi-autonomous driving can be provided as autonomous movement in which driver intervention is required depending on specific driving conditions. Semi-autonomous driving can be implemented so that the user performs manual driving by the processor (120) deactivating autonomous driving and transferring control to the user when the above situation occurs. According to the levels of autonomous driving defined by the Society of Automotive Engineers (SAE), semi-autonomous driving corresponds to autonomous driving levels 1 through 4, and fully autonomous driving may correspond to level 5.
[0038] Meanwhile, the vehicle (100) may communicate with other devices (200, 300) or other vehicles (400). Other devices may include, for example, a server (200) that supports various controls, state management, and driving of the vehicle (100), an ITS device (300) for receiving information from an Intelligent Transportation System (ITS), and various types of user devices. The server (200) is, for example, an external device operated by a vehicle manufacturer or provided to service driving support functions, and may receive connected data of the vehicle (100) or transmit data necessary for manual and autonomous driving. To support the driving and various services of the vehicle (100), the server (200) may transmit various information and software modules used for controlling the vehicle (100) to the vehicle (100) in response to requests and data transmitted from the vehicle (100) and user devices.
[0039] The ITS device (300) is, for example, a Road Side Unit (RSU), and the ITS device (300) can mutually exchange vehicle recognition data, driving control and status data, environment data around the vehicle, map data, etc., through V2I with the vehicle (100) to assist the user's driving of their own vehicle or support the autonomous driving of the vehicle (100). In the present disclosure, the ITS device (300) may be referred to as a traffic infrastructure device. The vehicle (100) can mutually exchange the aforementioned data through V2V with another vehicle (400) to support manual driving or autonomous driving.
[0040] The vehicle (100) can communicate with other vehicles or other devices based on cellular communication, WAVE (Wireless Access in Vehicular Environment) communication, DSRC (Dedicated Short Range Communication) or short-range communication, or other communication methods.
[0041] For example, for communication between the vehicle (100) and the server (200), ITS device (300), and other vehicles (400), a cellular communication network such as LTE, 5G, WiFi, or WAVE may be used. As another example, DSRC used in the vehicle (100) may be used for communication between vehicles. The method of communication between the vehicle (100), the server (200), the ITS device (300), other vehicles (400), and user devices is not limited to the embodiments described above.
[0042] FIG. 2 is a drawing showing a module constituting a vehicle according to one embodiment of the present disclosure.
[0043] The vehicle (100) may include a sensor unit (104), an operating unit (106), a display (108), a load device (110), and a transmitting and receiving unit (116).
[0044] The sensor unit (104) may be equipped with various types of sensors to detect various states and situations occurring in the external surrounding environment, internal system, user operation, and passenger space of the vehicle (100).
[0045] Specifically, the sensor unit (104) may be equipped with an externally oriented image sensor (104a), a lidar sensor (104b), and a radar sensor (104c), etc., to recognize dynamic and static objects existing around the vehicle (100).
[0046] The image sensor (104a) can recognize an external object as an image during the use of the vehicle (100), generate image data, and transmit the image data to the controller (120). The image sensor (104a) is installed in multiple parts of the vehicle (100) so that multiple images or multi-views of the surrounding environment of the vehicle (100) can be acquired.
[0047] The LiDAR sensor (104b) can generate point cloud data for objects around the vehicle (100) and transmit it to the controller (120). The point cloud data includes three-dimensional information of the objects, and the point cloud data may also be referred to as LiDAR data in this disclosure. In this disclosure, the LiDAR sensor (104b) is exemplified as being mounted, but in other examples, the LiDAR sensor (104b) may be omitted. The radar sensor (104c) can generate radar data by emitting electromagnetic waves of a specific frequency around the vehicle (100) to determine the presence, relative distance, speed, direction, etc. of external objects, and through the radio waves reflected from external objects. The radar data may be generated as point cloud data similar to LiDAR data. In this disclosure, the sensor generating the point cloud data may be exemplified as either the LiDAR sensor (104b) or the radar sensor (104c). Although not shown in FIG. 2, the sensor unit (104) may include an ultrasonic sensor. An ultrasonic sensor can generate ultrasonic data including the distance and speed of surrounding objects based on ultrasonic waves emitted and reflected around the vehicle.
[0048] Additionally, the sensor unit (104) may include a positioning sensor (104d) for determining the position of the vehicle (100). The positioning sensor (104d) is, for example, a GPS sensor or a GNSS sensor, but is not limited thereto. In addition, the sensor unit (104) may include an attitude sensor (not shown). The attitude sensor may, for example, detect the state of the vehicle (100) in each of its three axes, such as yaw, pitch, and roll, and output various attitude states of the vehicle based on the factors described above. The attitude sensor may be composed of, for example, an IMU sensor, a gyroscope sensor, etc.
[0049] The present disclosure describes primarily the sensors of the sensor unit (104) referenced in the description, but may additionally include sensors that detect various situations not listed herein.
[0050] The control unit (106) may be composed of a module for a user to control for driving. For example, the control unit (106) may be a steering wheel for manual driving, an automatic or manual transmission actuator, an accelerator pedal, a brake pedal, a gear shifter, etc. The control unit (106) may further be provided with an interface for the use, deactivation, and selection of detailed functions of an autonomous driving mode requested by the user, so that the user can use the autonomous driving function. The control unit (106) may be composed of a hard-type interface provided, for example, at a predetermined location inside the vehicle (100), or a soft-type interface that is touchable on a display (108) to receive various requests related to autonomous driving.
[0051] The display (108) can function as a user interface. The display (108) can be displayed by the processor (120) to output the operating status, control status, route / traffic information, remaining energy information, content requested by the driver, etc. Additionally, the display (108) is configured as a touch screen capable of detecting driver input, and can receive requests from the driver instructing the processor (120).
[0052] The load device (110) is mounted on the vehicle (100) and may be a type of non-driving electric device excluding a driving power system such as a wheel drive unit (118). The load device (114) is an auxiliary device that receives power from a power source unit (114) and may be, for example, an air conditioning system, an indicator lamp system, a lighting system, a seat system, and various devices installed on the vehicle (100).
[0053] The transceiver (116) can support mutual communication with the server (200), ITS device (300), surrounding vehicles (300), etc. The transceiver (116) may include, for example, a module for processing cellular communication, WAVE, DSRC communication, etc. In the present disclosure, the transceiver (116) can transmit data generated or stored during driving to the server (200) and receive data and software modules transmitted from the server (200). The transceiver (116) may also support communication with an electronic device carried by a passenger inside the vehicle (100). In the present disclosure, the vehicle (100) can transmit and receive data used in the method according to the present disclosure to the outside through the transceiver (116).
[0054] Additionally, the vehicle (100) may include a power source unit (114) and an actuator unit (116).
[0055] The power source unit (114) can generate and supply power and electricity used in driving power systems and non-driving power systems, such as the actuator unit (118). The non-driving power system may be, for example, a sensor unit (104), an operating unit (106), a display (108), a load device (110), and a transceiver unit (116), but is not limited thereto, and may include various components that implement sensing, interface, communication, and convenience functions, excluding components that are directly involved in driving operations.
[0056] If the vehicle (100) is driven by electric energy, the power source unit (114) may be composed of, for example, an electric battery charged from an external source, or a combination of an electric battery and a fuel cell that charges the battery. In the case of a combination of an electric battery and a fuel cell, the power source unit (114) may include a tank that stores a material used to produce power for the fuel cell, such as liquefied hydrogen. If the vehicle (100) is driven by fossil energy, the power source unit (114) may be composed of an internal combustion engine. Additionally, if the vehicle (100) is of a hybrid type, the power source unit (114) may be provided as a combination of an internal combustion engine and an electric battery.
[0057] The actuating unit (116) is equipped with at least one module that implements a driving operation, and can perform at least one driving operation such as acceleration / deceleration, lateral control such as steering, and gear shifting in response to a user request from the operating unit (106) or a request from the processor (120). Here, gear shifting can be processed by a request from a manual driving user using a gear shifter or from the processor (120) in autonomous driving.
[0058] The actuating unit (116) may be equipped with a wheel drive unit (not shown), mechanical components and electronic modules for implementing driving operations in the wheel drive unit to execute driving operations according to commands of the processor (120) by manual operation by a user or autonomous driving. If the vehicle (100) is operated on an electric energy basis, it may include an assembly for transmitting the requested driving operation to the wheel drive unit (118). If the vehicle (100) is operated on a fossil energy basis, the actuating unit (116) may be equipped with a transmission and gear module for transmitting power from an internal combustion engine.
[0059] The wheel drive unit may include a plurality of wheels, a driving force generation module for generating driving force to apply to the wheels or to transmit driving force, a braking module for decelerating the driving of the wheels, and a steering module for realizing lateral control of the wheels. When the vehicle (100) is driven based on electric energy, the driving force generation module may be composed of a motor assembly that generates driving force based on power output from an electric battery. The braking module of the electric-based vehicle (100) may further have a regenerative braking function.
[0060] Additionally, the vehicle (100) may include memory (118) and a processor (120).
[0061] The memory (118) stores applications and various data for controlling the vehicle (100), and can load applications or read and write data upon the request of the processor (120). In the present disclosure, the memory (118) may include an application that recognizes unstructured static objects on the road to identify road boundaries and drivable areas. Unstructured static objects may be static objects whose functions or attributes cannot be identified by sensor-based object recognition that detects the surrounding environment. Unstructured objects may have a collective intended function of a plurality of static objects arranged continuously on the road.
[0062] The type or class of a single static object detected by a sensor, such as a radar sensor (104c) or a lidar sensor (104b), is defined by object recognition, but the function that multiple static objects collectively perform, i.e., the function of an unstructured object, may not be identified by object recognition. This may be due to the fact that object recognition cannot estimate the overall boundary of multiple static objects.
[0063] An unstructured object may be a traffic safety facility (504) arranged continuously on a road (502), as illustrated in FIG. 3. FIG. 3 is a drawing illustrating a traffic safety facility. The traffic safety facility (504) may include, for example, guide posts, rubber cones, traffic barrels, and curbs. The individual traffic safety facility (504) illustrated in FIG. 3 may be defined by a type or class based on object recognition. The function or attribute resulting from the plurality of traffic safety facilities (504) illustrated in FIG. 3 may be a road boundary that prohibits driving across potential lines according to the continuously arranged traffic safety facilities. Simple perception processing of a radar sensor (104c) or lidar sensor (104b) cannot identify the function of an unstructured object such as the plurality of traffic safety facilities (504). In addition to the perception processing of the sensors, the application of the present disclosure may recognize an unstructured static object on the road and identify road boundaries and drivable areas.
[0064] Additionally, the memory (118) can store various information and data for object recognition. For example, the memory (118) may include a database used to generate information about objects detected by the image sensor (104a), the lidar sensor (104b), and the radar sensor (104c). The database may manage information including the type (or class) of the object and detailed data of the object.
[0065] The processor (120) can perform overall control of the vehicle (100). The processor (120) can be configured to execute applications and instructions stored in memory (118). The processor (120) can generate control instructions for components of the vehicle (100) in response to driving control requests in manual driving and autonomous driving. The components may be at least one of the various members described in FIG. 2.
[0066] The processor (120) can perform various processing to identify road boundaries based on the recognition of unstructured static objects according to the present disclosure.
[0067] For example, the processor (120) can execute a process to generate track areas of static objects arranged in multiple rows based on sensor data from a sensor that generates point cloud data. The processor (120) can execute a process to provide a predicted range separated from a preceding track area. Additionally, the processor (120) can execute a process to include a subsequent track area in a track list based on detection within the predicted range of a subsequent track area. The processor (120) can execute a process to generate road boundary objects that classify track areas as continuous static objects based on a track list containing more than a threshold number of track areas.
[0068] A static object is a target stationary object and, as described above, may include objects related to traffic safety facilities. A sensor that generates point cloud data may include, for example, at least one of a radar sensor (104c) and a lidar sensor (104b). A track area may be an area for tracking static objects generated from point cloud data using a specific model. The tracked static objects are provided on a per-object basis, and a track identifier may be assigned per track area. A track area may be data constituting track information. Track information may include, for example, a track identifier, a track area, the location of an object belonging to the area, the distance of the object, the speed of the object, the direction of the object, etc. Track information may be used to predict the state of subsequent track information and to associate acquired subsequent track information.
[0069] Track information may be generated in the space of the sensor that generates the track area, or in a fusion space formed by the fusion of at least two of the image sensor (104a), radar sensor (104b), and radar sensor (104c). Track information in the fusion space may consist of sensor-specific data or data estimated by sensor fusion. Although the space in which the track area is generated is described without being specific in this disclosure, the track area exemplified in this disclosure may be provided in any space.
[0070] In another example, the processor (120) may execute a process to generate track areas of static objects arranged in multiple rows based on sensor data from a sensor that generates point cloud data. The processor (120) may execute a process to generate linear information including a linear model based on the association between the leading track area and the trailing track area among more than the number of track areas evaluated. Additionally, the processor (120) may execute a process to determine whether the sensor characteristics of multiple track areas have similarity, in addition to the intermediate track area existing within the association range with the linear model. In response to the existence within the association range and the similarity of sensor characteristics, the processor (120) may execute a process to generate road boundary objects that classify multiple track areas as continuous static objects. In other examples, the sensors and track areas may be substantially the same as those described in the example.
[0071] Detailed descriptions of examples processed by the processor (120) are provided below, and processing according to one example and other examples may be performed in a manner compatible with the present disclosure.
[0072] The processor (120) is exemplified as being composed of a single processing module, as shown in FIG. 2, to execute the processing described above. As another example, the processor (120) may be composed of multiple processing modules, and the processing may be distributed and processed across multiple modules.
[0073] FIG. 4 is a diagram showing a module that constitutes a server according to the present disclosure.
[0074] The server (200) can transmit response data to the vehicle (100) in response to a request from the vehicle (100), and also transmit information to the vehicle (100) for supporting applications embedded in the vehicle (100) and vehicle driving. The server (200) may include a communication unit (202), a memory (204), and a processor (206).
[0075] The communication unit (202) transmits and receives data with an external device, supports mutual communication with the vehicle (100) in the present disclosure, and can exchange data with the vehicle (100).
[0076] The memory (204) stores programs and various data for operating the server (200), and can load programs or read and write data upon the request of the processor (206). The memory (204) can hold and manage programs for processing requests from the vehicle (100), applications embedded in the vehicle (100), and information for driving support. The memory (204) can store, for example, a database used to identify objects detected by an image sensor (104a), a lidar sensor (104b), and a radar sensor (104c), high-precision maps, and external information.
[0077] The processor (206) can perform overall control of the server (200). The server (200) can be configured to execute programs and instructions stored in memory (204). The processor (206) can execute said programs to process and respond to user requests transmitted from the vehicle (100). For example, the processor (206) can transmit, upon request from the vehicle (100), a database, high-precision maps, and external information used to identify objects detected by sensors that recognize the surrounding environment of the vehicle (100).
[0078] In the present disclosure, the processor (206) is exemplified as being composed of a single processing module. As another example, the processor (206) may be distributed among a plurality of processing modules, and the processing described above may be executed by a distributed processing model.
[0079] Hereinafter, with reference to FIG. 5, a method for recognizing an unstructured static object for identifying a road boundary according to another embodiment of the present disclosure will be described in detail. FIG. 5 is a flowchart relating to a method for recognizing an unstructured static object for identifying a road boundary according to one embodiment of the present disclosure.
[0080] In the present disclosure, the sensor generating point cloud data includes at least one of a radar sensor (104c) and a lidar sensor (104b); however, for convenience of description, the type of sensor may not be distinguished and may be described as a sensor or a point cloud sensor. If there is a matter related to an image sensor (104a), it may be described as an image sensor (104a) to distinguish it from other sensors. The method of the present disclosure is performed by a processor (120); however, for convenience of description, the processor (120) and the vehicle (100) may be described interchangeably.
[0081] Referring to FIG. 5, the processor (120) of the vehicle (100) can generate a track area including a plurality of static objects of the road detected by sensors (104b, 104c) that generate point cloud data (S105).
[0082] Track areas can be generated for static and dynamic objects on the road. In the case of static objects, track areas can be generated to include each traffic safety facility, as exemplified in FIGS. 6 through 8 and FIG. 10. Track areas can be generated, for example, by a learning-based object recognition model. Track areas are included in the aforementioned track information, and track identifiers can be assigned to each track area. Track areas are generated in a predetermined space, for example, in the space of a point cloud sensor or in a fusion space.
[0083] The processor (120) may adopt a static object of the same type that is arranged continuously on the road as a target object. The static object arranged continuously may be, for example, a traffic safety facility. A detailed description of the traffic safety facility is omitted as it is described in FIGS. 2 and FIGS. 3. The track area of the continuous static object may be arranged, for example, along the direction of travel. In the present disclosure, for convenience of explanation, a track area located relatively ahead of the direction of travel or the arrangement direction of the track area may be referred to as a leading track area to distinguish it from a track area located relatively behind. Accordingly, a track area located behind may be referred to as a trailing track area.
[0084] The processor (120) can provide a predicted range in space that is spaced apart from the preceding track area (S110).
[0085] Referring to FIG. 6(a) regarding an example of a prediction range, the prediction range may be created to include an enclosed area (508) positioned at a distance (D) spaced apart from a preceding track area (506). FIG. 6 is a diagram illustrating an example of the search of a track area. The direction in which the distance (D) is created and the enclosed area (508) may be determined, for example, based on the driving direction of the vehicle (100) or the arrangement direction of the preceding track area and the following track area identified by object recognition. FIG. 6(a) through FIG. 6(c) illustrate a plurality of static objects arranged in a straight line. The distance (D) may be set, for example, by referring to the average arrangement spacing of traffic safety facilities arranged in a straight line. For example, the size of the enclosed area (508) may be set based on the spaced position of the following track area (or the following traffic safety facility) allowed at the end of the distance (D).
[0086] FIGS. 6(b) and FIGS. 6(c) illustrate a prediction range enclosed area (508) provided when the trailing track area (512) and the subsequent trailing track area (514) illustrated in FIGS. 6(a) and FIGS. 6(b), respectively, belong to the enclosed area (508) of the prediction range. The prediction range generated based on the trailing track areas (512, 514) can be provided by applying the same distance (D) and the size of the enclosed area (508) as in the prediction range generated based on the leading track area (506).
[0087] Referring to FIG. 7(a) in relation to another example of a prediction range, the prediction range may include a surrounding area (518) spaced apart by a distance (D) from a preceding track area (516) within a range of an allowable angle (A). FIG. 7 is a diagram illustrating another example of searching for a track area.
[0088] FIGS. 7(a) through 7(c) illustrate a plurality of static objects arranged in a curved shape. The allowable angle (A) can be set to a range of a predetermined angle based on the arrangement direction of the preceding track area (516) and the following track area (518). The allowable angle (A) can be set, for example, based on the average spacing angle between the traffic safety facilities arranged in a curved shape. As another example, the allowable angle (A) can be set based on the curve shape or curvature in the area of map information corresponding to the location of the plurality of traffic safety facilities. The distance (D) can be set by referring to the average arrangement spacing of the traffic safety facilities, similar to FIG. 6. Similar to FIG. 6, the size of the enclosed area (518) can be set based on the allowable spacing position of the following track area or the following traffic safety facility allowed at the end of the distance (D).
[0089] FIGS. 7(b) and FIGS. 7(c) illustrate a prediction range enclosed area (518) provided when the trailing track area (522) and the subsequent trailing track area (524) illustrated in FIGS. 7(a) and FIGS. 7(b), respectively, belong to the enclosed area (518) of the prediction range. The prediction range generated based on the trailing track areas (520, 522, 524) can be provided by applying the same allowable angle (A), distance (D), and size of the enclosed area (518) as applied in the prediction range generated based on the leading track area (506).
[0090] Referring again to FIG. 5, the processor (120) can determine whether a trailing track area is detected in the predicted range (S115)
[0091] FIG. 6(a), relating to the detection of a candidate track area, illustrates that a trailing track area (510) is determined to belong to the enclosed area (508) of the prediction range. FIG. 6(b) and FIG. 6(c) illustrate the detection of a trailing track area within the enclosed area (508) when the trailing track area (512) and the subsequent trailing track area (514), respectively illustrated in FIG. 6(a) and FIG. 6(b), are arranged within the enclosed area (508).
[0092] FIG. 7(a), relating to the detection of a candidate track area, illustrates that a trailing track area (520) is determined to be located within the enclosed area (518) of the prediction range. FIG. 7(b) and FIG. 7(c) illustrate the detection of a trailing track area within the enclosed area (518) when the trailing track area (520) and the subsequent trailing track area (522), respectively illustrated in FIG. 7(a) and FIG. 7(b), are located within the enclosed area (518).
[0093] Referring again to FIG. 5, when a trailing track area is detected in the predicted range, the processor (120) can include the track identifier of the trailing track area in the track list (S120).
[0094] According to the example of FIG. 6(a), the track identifier of the trailing track area (510) detected in the enclosed area (508) of the prediction range can be registered in the track list together with the track identifier of the leading track area (506). According to the example of FIG. 7(a), the track identifier of the trailing track area (520) detected in the enclosed area (518) of the prediction range can be registered in the track list together with the track identifier of the leading track area (516). The track identifiers of the leading track areas (506, 516) can be registered in the track list at step S110 or S120.
[0095] The processor (120) can determine whether the track list contains track identifiers of track areas greater than or equal to a threshold number (S125).
[0096] To identify the functions of multiple static objects, for example, road boundary functions, the threshold number may be set to, for example, three or more. The threshold number may be the number required to identify the functions of unstructured objects.
[0097] If the track list does not contain more than a threshold number of track identifiers, the processor (120) can perform the processes from step S110 to step S120. According to the example of FIG. 6(a), a preceding track area (506) and a succeeding track area (510) are registered in the track list, so the track list may have two track identifiers. In this case, the processor (120) can process the processes from step S110 to step S120 related to the detection of the subsequent succeeding track area (512) exemplified in FIG. 6(b). According to the example of FIG. 7(a), a preceding track area (516) and a succeeding track area (522) are registered in the track list, so the track list may have two track identifiers. In this case, the processor (120) can process the processes from step S110 to step S120 related to the detection of the subsequent succeeding track area (522) exemplified in FIG. 7(b).
[0098] In step S125, if the track list contains more than a threshold number of track identifiers, the processor (120) can determine whether the condition for stopping the search related to the detection of the subsequent trailing track area is satisfied (S130).
[0099] The condition for stopping the search may be a stopping condition based on step S145 or step S150 described below. The stopping condition based on step S145 may be that a subsequent track area is not detected in the prediction range after the allocation of the track loss area according to step S140. The stopping condition based on step S150 may be that a subsequent track area is detected in step S145, but a subsequent track area is not detected in the prediction range.
[0100] If there is a subsequent trailing track area or if the condition for stopping the search is not satisfied, the processor (120) can perform the processes from step S110 to step S130.
[0101] As illustrated in FIG. 6(c), the processor (120) can process steps S110 through S130 related to the detection of a subsequent trailing track area (514). As illustrated in FIG. 7(c), the processor (120) can process steps S110 through S130 related to the detection of a subsequent trailing track area (524).
[0102] In step S130, if the condition for stopping the search is satisfied, the processor (120) removes track identifiers of duplicate track areas from a list of multiple accumulated tracks, creates a road boundary object that classifies the remaining track identifiers into continuous static objects, and can control the vehicle (100) based on the road boundary object (S135).
[0103] As illustrated in FIGS. 6 and 7, detection of track regions within a prediction range is performed sequentially for each track region, and the track list may have more than a threshold number of track identifiers. As a result, the subsequent track identifier of the track list generated first may be the same as the preceding track identifier of the track list generated subsequently. The processor (120) can check the track identifiers of each track list, retain one track identifier, and remove duplicate track identifiers.
[0104] The processor (120) can group remaining track identifiers into continuous static objects to create road boundary objects as unstructured static objects. The processor (120) can recognize multiple traffic safety facilities as road boundary objects and, based on the road boundary objects, determine the road boundary area and drivable area of the road. Based on the track identifiers, the processor (120) can create a boundary line connecting continuous static objects or a boundary area including all static objects. The road boundary object can be created to include the boundary line or boundary area together with the track identifiers. The processor (120) can control the driving of the vehicle (100) based on the road boundary area and drivable area estimated from multiple traffic safety facilities by the road boundary objects.
[0105] Meanwhile, referring to FIG. 5, if the trailing track area is not detected in the predicted range separated from the leading track area in step S115, the processor (120) may assign a track loss area (530) that estimates the loss of static objects to the predicted range (S140).
[0106] As illustrated in FIG. 8(a), a trailing track area may not be detected in the enclosed area (528) of the predicted range separated from the leading track area (526). FIG. 8 is a diagram illustrating another example of track area exploration. FIG. 8 shows a plurality of static objects, for example, a plurality of traffic safety facilities, arranged in a direction different from FIG. 6 and 7, so that the track areas may also be created in a direction different from FIG. 6 and 7. FIG. 8 illustrates that the track areas are arranged in a straight line, and if the track areas are arranged in a curved line, the predicted range may include an enclosed area based on an allowable angle and distance, as illustrated in FIG. 7.
[0107] The failure to detect a trailing track area may be due, for example, to the loss or damage of a traffic safety facility, resulting in the failure to generate a track area of the traffic safety facility. If a trailing track area is not detected, the processor (120) may assign a track loss area (530) to the enclosed area (528) of the prediction range, as illustrated in FIG. 8(a).
[0108] Referring again to FIG. 5, the processor (120) can determine whether to detect a trailing track area in a predicted range spaced apart from the track loss area (530) (S145).
[0109] As illustrated in FIG. 8(b), the processor (120) can identify whether a trailing track area (532) exists in a predicted range enclosed area (528) spaced apart by a distance (D) from a track loss area (530).
[0110] Referring to FIG. 5, when a trailing track area (532) is detected, the processor (120) can determine whether to detect a subsequent trailing track area (534) in a predicted range enclosed area (528) spaced apart from the detected trailing track area (532), as illustrated in FIG. 8(c) (S150).
[0111] When a subsequent trailing track area (534) is detected, the processor (120) proceeds to step S120 to include the trailing track area (532) and the subsequent trailing track area (534) in the track list.
[0112] Meanwhile, if a trailing track area is not detected within the predicted range in step S145, or if a subsequent trailing track area is not detected within the predicted range in step S150, the processor (120) may determine that the search suspension condition according to step S130 is satisfied. When the search or detection of track areas is suspended, the processor (120) may classify the preceding track area, the trailing track area, and the subsequent trailing track area as discontinuous static objects. A discontinuous static object may refer to an object that does not have a function resulting from the set of each track area, such as a road boundary function. The space between each track area of a discontinuous static object is not recognized as a road boundary but may be recognized as another area, such as a drivable area.
[0113] The search method of the track area of FIGS. 6 and FIGS. 7 described above is compatible to the extent that it is not technically incompatible, and the prediction range for search can be set in various ways.
[0114] Hereinafter, with reference to FIG. 9, a method for recognizing irregular static objects for identifying road boundaries according to another embodiment of the present disclosure will be described in detail. FIG. 9 is a flowchart relating to a method for recognizing irregular static objects for identifying road boundaries according to another embodiment of the present disclosure. The embodiment of FIG. 9 can be used for track areas (or traffic safety facilities) arranged in an irregular shape compared to FIG. 6 to FIG. 8.
[0115] The processor (120) of the vehicle (100) can generate a track area including a plurality of static objects of the road detected by sensors (104b, 104c) that generate point cloud data (S205). This step may be substantially the same as step S105.
[0116] The processor (120) can generate linear information including a linear model based on the connection between the leading track area and the trailing track area among more than the number of track areas evaluated (S210).
[0117] To identify the functions of multiple static objects, such as road boundary functions, the number of evaluations may be three or more. As exemplified in FIG. 10(a), the number of evaluations is set to three, and a linear model (546) can be generated based on the connection between the leading track area (540) and the trailing track area (544). FIG. 10 is a diagram illustrating another example of track area exploration. The linear model (546) can be established as a linear function connecting the leading track area (540) and the trailing track area (544).
[0118] Referring to FIG. 9, the processor (120) can determine whether the intermediate track region exists within the range associated with the linear model (546) (S215).
[0119] As illustrated in FIG. 10(a), if an intermediate track area (542) between the leading track area (540) and the trailing track area (544) exists within a pre-set association range from a linear model (546) of a first-order function, the processor (120) can determine that the intermediate track area (542) has proximity to the linear model (546).
[0120] Referring to FIG. 9, if the intermediate track area (542) exists within the range associated with the linear model (546), the processor (120) can determine whether the sensor characteristics of the plurality of track areas (540 to 544) have similarity within the characteristic range (S220).
[0121] As described above, the sensor may be a radar sensor (104c) or a lidar sensor (104b). If the sensor associated with the track area is a radar sensor (104c), the sensor characteristics may include at least one of the signal-to-noise ratio (SNR) and the radar cross section (RCS). If the sensor is a lidar sensor (104b), the sensor characteristics may include the intensity of the reflected signal of the laser reflected from the object.
[0122] Track information associated with each track area may further include sensor characteristics. If the sensor characteristics according to the example described above provided in each track information fall within a preset characteristic range, the processor (120) may determine that the sensor characteristics of a plurality of track areas have similarity within the characteristic range.
[0123] When the sensor characteristics of multiple track areas have similarities, the processor (120) includes the track identifiers of the leading track area, the middle track area, and the trailing track area, respectively, in the track list, and can manage linear information from step S210, such as a linear function model, in conjunction with the track areas of the list (S225).
[0124] The processor (120) can determine whether the interruption condition of the search related to the subsequent trailing track area is satisfied (S230).
[0125] The search cessation condition may include, for example, that there is no trailing track area in the enclosed area of the distance and allowable angle range exemplified in FIGS. 6 and 7, or in the enclosed area based on a distance greater than said distance.
[0126] If the condition for stopping the search is not satisfied, the processor (120) may perform the process from step S210 to step S230. As illustrated in FIG. 10(b), the processor (120) may designate the leading track area and the trailing track area as track area (542) and track area (550), respectively, and repeat the process from step S210 to S230 for the track areas (542, 544, 550).
[0127] When the condition for stopping the search is satisfied, the processor (120) removes track identifiers of duplicate track areas from a list of multiple accumulated tracks, creates a road boundary object that classifies the remaining track identifiers into continuous static objects, and can control the vehicle (100) based on the road boundary object (S235).
[0128] The road boundary object may be created to include a boundary line (548) connecting the classified track areas exemplified in FIG. 10(b), along with a classified track identifier. Step S235 may be substantially the same as Step S135.
[0129] The exemplary methods of the present disclosure described above are expressed as a series of operations for clarity of explanation, but this is not intended to limit the order in which the steps are performed, and if necessary, each step may be performed simultaneously or in a different order. To implement the method according to the present disclosure, additional steps may be included in addition to the steps exemplified, steps excluding some steps and including the remaining steps, or steps excluding some steps and including additional steps.
[0130] The various embodiments of the present disclosure are not intended to list all possible combinations but to describe representative aspects of the present disclosure, and the matters described in the various embodiments may be applied independently or in combination of two or more.
[0131] In addition, various embodiments of the present disclosure may be implemented by hardware, firmware, software, or a combination thereof. In the case of implementation by hardware, it may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), general processors, controllers, microcontrollers, microprocessors, etc.
[0132] The scope of the present disclosure includes software or machine-executable instructions (e.g., operating system, application, firmware, program, etc.) that enable an operation according to a method of various embodiments to be executed on a device or computer, and a non-transitory computer-readable medium on which such software or instructions, etc. are stored and executable on a device or computer.
Claims
Claim 1 A method for recognizing an unstructured static object for identifying road boundaries, comprising: generating a track area of a static object arranged in a plurality based on sensor data of a sensor that generates point cloud data; providing a prediction range spaced apart from a preceding track area; including the subsequent track area in a track list based on detection in the prediction range of the subsequent track area; and generating a road boundary object that classifies the track area as a continuous static object based on the track list containing a threshold number or more of track areas. Claim 2 A method for recognizing an unstructured static object according to claim 1, wherein the prediction range includes an enclosed area positioned at a distance spaced apart from the preceding track area. Claim 3 A method for recognizing an unstructured static object according to claim 2, wherein the step of including the subsequent track area in the track list includes including the subsequent track area detected in the enclosed area in the track list. Claim 4 A method for recognizing an unstructured static object according to claim 2, wherein the prediction range includes the enclosed area spaced apart from the preceding track area by the distance from the preceding track area within the range of an allowable angle, and the allowable angle is set to a range of a predetermined angle based on the arrangement direction of the preceding track area and the succeeding track area. Claim 5 A method for recognizing unstructured static objects according to claim 1, wherein the threshold number is set to 3 or more. Claim 6 A method for recognizing an unstructured static object according to claim 1, wherein the step of providing the prediction range and the step of including the subsequent track area in the track list are performed sequentially for the plurality of track areas, and the step of generating the road boundary object comprises: the step of removing the duplicate track area from the track list based on the existence of the duplicate track area in the track list; and the step of generating the road boundary object that classifies the remaining track area as the continuous static object. Claim 7 A method for recognizing an unstructured static object according to claim 1, further comprising: a step of, after the step of providing the prediction range, assigning a track loss area to the prediction range based on the non-detection of the subsequent track area in the prediction range; a step of determining whether to detect a subsequent track area in a prediction range spaced apart from the track loss area; a step of determining whether to detect a subsequent track area in a prediction range spaced apart from the detected subsequent track area based on the detection of the subsequent track area; and a step of including the subsequent track area and the subsequent track area in the track list based on the detection of the subsequent track area. Claim 8 A method for recognizing an unstructured static object, further comprising the step of classifying the track area, the trailing track area, and the subsequent trailing track area as discontinuous static objects based on the non-detection of the trailing track area in the prediction range or the non-detection of the subsequent trailing track area in the prediction range in claim 7. Claim 9 A method for recognizing an unstructured static object according to claim 1, wherein the static object includes an object related to a traffic safety facility. Claim 10 A method for recognizing an unstructured static object for identifying road boundaries, comprising: a step of generating a track area of a static object arranged in a plurality based on sensor data of a sensor that generates point cloud data; a step of generating linear information including a linear model based on the connection between the leading track area and the trailing track area among track areas greater than or equal to the number of evaluations; and a step of generating a road boundary object that classifies the plurality of track areas as a continuous static object based on the fact that the intermediate track area exists within the range associated with the linear model and the sensor characteristics of the plurality of track areas have similarity. Claim 11 A method for recognizing an atypical static object according to claim 10, wherein the sensor comprises a radar sensor or a lidar sensor, the sensor characteristics of the radar sensor comprise at least one of a signal-to-noise ratio (SNR) and a radar cross section (RCS), and the sensor characteristics of the lidar sensor comprise the intensity of a reflected signal. Claim 12 A vehicle for implementing recognition of unstructured static objects for identifying road boundaries, comprising: a sensor unit including a sensor that detects the surrounding environment as point cloud data; a memory that stores at least one instruction; and at least one processor that executes the at least one instruction stored in the memory, wherein the at least one processor is configured to generate a track area of static objects arranged in a plurality based on sensor data of the sensor, provide a prediction range spaced apart from a preceding track area, include the succeeding track area in a track list based on detection in the prediction range of a succeeding track area, and generate a road boundary object that classifies the track area as a continuous static object based on the track list containing a threshold number or more of track areas. Claim 13 In claim 12, the vehicle, wherein the prediction range includes a spaced-apart encirclement area positioned at a distance spaced from the preceding track area. Claim 14 A vehicle according to claim 13, wherein the inclusion of the trailing track area into the track list comprises including the trailing track area detected in the enclosed area into the track list. Claim 15 A vehicle according to claim 13, wherein the predicted range includes the enclosed area spaced apart from the preceding track area by the distance within the range of permissible angles, and the permissible angle is set to a range of predetermined angles based on the alignment direction of the preceding track area and the succeeding track area. Claim 16 In claim 12, the vehicle, wherein the threshold number is set to three or more. Claim 17 A vehicle according to claim 12, wherein the provision of the prediction range and the inclusion of the subsequent track area into the track list are performed sequentially for the plurality of track areas, and the creation of the road boundary object comprises creating the road boundary object that removes the duplicate track area from the track list based on the existence of a duplicate track area in the track list and classifies the remaining track area into the continuous static object. Claim 18 A vehicle according to claim 12, wherein, after providing the prediction range, the at least one processor is further configured to assign a track loss area to the prediction range based on the non-detection of the trailing track area in the prediction range, determine whether to detect a trailing track area in a prediction range spaced apart from the track loss area, determine whether to detect a subsequent trailing track area in a prediction range spaced apart from the detected trailing track area based on the detection of the trailing track area, and include the trailing track area and the subsequent trailing track area in the track list based on the detection of the subsequent trailing track area. Claim 19 A vehicle according to claim 18, wherein the at least one processor is further configured to classify the track area, the trailing track area, and the subsequent trailing track area as discontinuous static objects based on the non-detection of the trailing track area in the prediction range or the subsequent trailing track area in the prediction range. Claim 20 In claim 12, the static object is a vehicle including an object related to a traffic safety facility.