Vehicle control device and method
Patent Information
- Application Number
- KR1020250023426
- Authority / Receiving Office
- KR · KR
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-24
- Publication Date
- 2026-09-01
Smart Images
Figure P1020250023426_ABST
Abstract
Description
Technology Field
[0001] The embodiments relate to a vehicle control device and a method. Background Technology
[0003] Technology that accurately estimates a vehicle's driving position and outputs lane position plays a key role in autonomous driving and advanced driver assistance systems (ADAS). To this end, technology is being applied that integrates various information collected from sensors and comprehensively analyzes lane markers (lanes), static objects (shoulder lines, median strips, etc.), and dynamic objects (moving vehicles in adjacent lanes, etc.).
[0004] To estimate the position of a vehicle based on lane marker, static object, and dynamic object data collected from sensors, an algorithm is used to evaluate and integrate the reliability of each data in real time. For example, it operates by utilizing probabilistic methodologies such as Kalman filters or Bayesian networks to fuse information obtained from multiple data sources and supplementing it with other data when specific data is temporarily unreliable.
[0005] However, if sensor data performs incorrect recognition or errors occur during data collection, a problem may arise where the vehicle's lane position is incorrectly displayed. For example, if lane paint is worn off and the lane marker is incorrectly detected, or if the movement of dynamic objects (other vehicles) is misinterpreted, there is a possibility that the vehicle's current lane position will be inaccurately determined.
[0006] Therefore, there is a need for technology that reduces the possibility of mis-output caused by incorrect perception information and estimates the driving lane based on reliable data. The problem to be solved
[0008] The technical problem that the present invention aims to solve is to provide a vehicle control device and method capable of improving driving stability by providing accurate and reliable lane determination results. means of solving the problem
[0010] According to an embodiment, a vehicle control device is provided having a transceiver; one or more processors; and a memory for storing one or more programs executed by the one or more processors, wherein the transceiver receives external object recognition information and vehicle driving information collected from a sensor unit disposed in the vehicle and receives map information from a navigation system, and the processor generates a first position candidate group of the vehicle at a first time point along the lateral direction of the driving road using the external object recognition information and the map information, predicts the behavior of each of the first position candidate group using the vehicle driving information to generate a second position candidate group of the vehicle at a second time point, calculates a matching score for each lane of the driving road according to the degree of matching between the external object recognition information and the map information at the second time point, calculates a weight for the probability that each of the second position candidates belonging to the second position candidate group is located in a specific lane based on the matching score, and determines the driving lane of the vehicle at the second time point based on the weight.
[0011] The above processor can accumulate and reflect the above weights over time.
[0012] The above processor can determine the lane where the second position candidates, which have a higher calculated weight compared to other lanes, are located as the driving lane of the vehicle.
[0013] The processor can delete a second position candidate whose weight is below a preset threshold or initialize the weight.
[0014] The processor may delete some of the multiple second position candidates located in the driving lane of the vehicle or initialize their weights.
[0015] The processor can calculate and sum a first matching score for a static object, a second matching score for a dynamic object, and a third matching score for a lane, respectively, based on the degree of matching between the external object recognition information and the map information.
[0016] The processor can calculate the first matching score by comparing the coordinates of a static object included in the object recognition information with the road boundary line coordinates included in the map information.
[0017] The processor can calculate the second matching score by comparing the coordinates of a dynamic object included in the object recognition information with the coordinates of a road boundary line and a lane included in the map information.
[0018] The processor can calculate the third matching score by comparing the lane coordinates and lane type included in the object recognition information with the road information included in the map information.
[0019] The processor can adjust the number of third position candidate groups of the vehicle at the third time point by lane based on the matching score calculated at the second time point.
[0020] According to an embodiment, a vehicle control method is provided by a computing device comprising: a transceiver; one or more processors; and a memory for storing one or more programs executed by the one or more processors, wherein the transceiver receives external object recognition information and vehicle driving information collected from a sensor unit placed in the vehicle, and receives map information from a navigation system, and the processor generates a first position candidate group of the vehicle at a first time point along the lateral direction of the driving road using the external object recognition information and the map information, predicts the behavior of each of the first position candidate group using the vehicle driving information to generate a second position candidate group of the vehicle at a second time point, calculates a matching score for each lane of the driving road according to the degree of matching between the external object recognition information and the map information at the second time point, calculates a weight for the probability that each of the second position candidates belonging to the second position candidate group is located in a specific lane based on the matching score, and determines the driving lane of the vehicle at the second time point based on the weight.
[0021] The above processor can accumulate and reflect the above weights over time.
[0022] The above processor can determine the lane where the second position candidates, which have a higher calculated weight compared to other lanes, are located as the driving lane of the vehicle.
[0023] The processor can delete a second position candidate whose weight is below a preset threshold or initialize the weight.
[0024] The processor may delete some of the multiple second position candidates located in the driving lane of the vehicle or initialize their weights.
[0025] The processor can calculate and sum a first matching score for a static object, a second matching score for a dynamic object, and a third matching score for a lane, respectively, based on the degree of matching between the external object recognition information and the map information.
[0026] The processor can calculate the first matching score by comparing the coordinates of a static object included in the object recognition information with the road boundary line coordinates included in the map information.
[0027] The processor can calculate the second matching score by comparing the coordinates of a dynamic object included in the object recognition information with the coordinates of a road boundary line and a lane included in the map information.
[0028] The processor can calculate the third matching score by comparing the lane coordinates and lane type included in the object recognition information with the road information included in the map information.
[0029] The processor can adjust the number of third position candidate groups of the vehicle at the third time point by lane based on the matching score calculated at the second time point. Effects of the invention
[0031] The vehicle control device and method according to the embodiment can more accurately estimate the current position and driving lane of a moving vehicle.
[0032] In addition, it can provide stable lane judgment results even when the vehicle is driving in various environments (curved roads, intersections, damaged lane paint, etc.).
[0033] This can contribute to improving the driving stability of the vehicle and the reliability of the autonomous driving system.
[0034] Furthermore, accurate and stable lane identification results can be utilized as important information for determining and controlling the movement direction and path of autonomous vehicles, which can simultaneously improve the safety and efficiency of autonomous driving.
[0035] In addition, the vehicle's lane position can be accurately estimated even in a real-time changing environment.
[0036] In addition, a lane judgment system robust to error-recognized data or noise can be implemented. Brief explanation of the drawing
[0038] 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. FIG. 3 is a data flow diagram of a vehicle control device according to an embodiment. FIGS. 4 to 10 are drawings for explaining the operation of a processor according to an embodiment. FIG. 11 is a flowchart of a vehicle control method according to an embodiment. Specific details for implementing the invention
[0039] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.
[0040] However, the technical concept of the present invention is not limited to some of the described embodiments but can be implemented in various different forms, and within the scope of the technical concept of the present invention, one or more of the components among the embodiments may be selectively combined or substituted.
[0041] In addition, terms used in the embodiments of the present invention (including technical and scientific terms) may be interpreted in a sense that is generally understood by those skilled in the art to which the present invention belongs, unless explicitly and specifically defined otherwise. Terms that are commonly used, such as terms defined in advance, may be interpreted in consideration of their meaning in the context of the relevant technology.
[0042] Furthermore, the terms used in the embodiments of the present invention are for the purpose of describing the embodiments and are not intended to limit the present invention.
[0043] In this specification, the singular form may include the plural form unless specifically stated otherwise in the text, and when described as "at least one of A and B and C (or more than one)," it may include one or more of all combinations that can be formed from A, B, and C.
[0044] In addition, terms such as first, second, A, B, (a), (b), etc. may be used when describing the components of the embodiments of the present invention.
[0045] These terms are intended merely to distinguish a component from other components and are not limited by the nature, order, sequence, etc., of the said component.
[0046] And, where it is stated that a component is 'connected', 'combined', or 'joined' to another component, this may include not only cases where the component is directly connected, combined, or joined to the other component, but also cases where it is 'connected', 'combined', or 'joined' due to another component located between the component and the other component.
[0047] Furthermore, when described as being formed or placed "above or below" each component, "above" or "below" includes not only cases where two components are in direct contact with each other, but also cases where one or more other components are formed or placed between the two components. Additionally, when expressed as "above or below," it may include the meaning of a downward direction as well as an upward direction relative to a single component.
[0048] Hereinafter, embodiments will be described in detail with reference to the attached drawings, provided that identical or corresponding components are given the same reference number regardless of the drawing symbols, and redundant descriptions thereof will be omitted.
[0050] Hereinafter, a vehicle will be described with reference to FIGS. 1 and FIGS. 2. FIG. 1 is a diagram illustrating a vehicle communicating with another device to transmit and receive data.
[0051] 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 energy generation unit (110) 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 energy from a fossil energy-based internal combustion engine and an electric battery to drive the actuator (116), and this may be a hybrid type vehicle.
[0052] 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, SUV, or small truck, or a vehicle with more than four wheels, such as a bus, large truck, container transport vehicle, or heavy equipment vehicle. Here, a ground vehicle may be referred to as including not only a vehicle that travels over land but also a vehicle that travels underground. A vehicle (100) may be a robot in a broad sense, such as a means of transportation, and the robot may be moved using wheels, tracks, or other movement modules. Although the present disclosure primarily describes ground mobility devices such as ground vehicles, the present embodiment is applicable to air mobility devices such as AAMs and aircraft, and water mobility devices such as ships and submarines, provided that it does not contradict the present disclosure.
[0053] The vehicle (100) can be driven by being controlled autonomously, and 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 (130) 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 (130) 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.
[0054] 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 provide autonomous driving services, and may receive connected data from the vehicle (100) or transmit data necessary for autonomous driving. To support autonomous 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.
[0055] 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 in driving their own vehicle or support the autonomous driving of the vehicle (100). The vehicle (100) can mutually exchange the aforementioned data through V2V with another vehicle (400) to support manual driving or autonomous driving.
[0056] 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.
[0057] 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.
[0058] FIG. 2 is a drawing showing a module constituting a vehicle according to one embodiment of the present disclosure.
[0059] The vehicle (100) may include a sensor unit (102), an operating unit (106), a display (108), a load device (114), and a transmitting and receiving unit (112).
[0060] The sensor unit (102) may be equipped with various types of detectors to detect various states and situations occurring in the external environment, internal system, user operation, and passenger space of the vehicle (100).
[0061] Specifically, the first sensor unit (102) may be equipped with an outward-facing camera (102a), a lidar sensor (1042), a radar sensor (102c), etc., to recognize dynamic and static objects existing outside the vehicle (100). The camera (102a) may recognize external objects as images during the use of the vehicle (100) to generate image data and transmit the image data to the processor (130). The lidar sensor (104b) may generate point cloud data as recognized data of external objects and transmit it to the processor (130) in order to generate three-dimensional spatial information that identifies the shape of at least the external objects. The radar sensor (102c) may generate radar data through radio waves reflected from external objects by emitting radio waves of a specific frequency around the vehicle (100) to determine the existence, relative distance, speed, direction, etc. of external objects. In the present disclosure, it is exemplified that a lidar sensor (102b) is provided, but in other examples, the lidar sensor (102b) may not be installed.
[0062] The first sensor unit (102) can generate object recognition information based on sensing data. The object recognition information may include information regarding the presence or absence of an object, location information of the object, distance information between the vehicle (100) and the object, and relative speed information between the vehicle (100) and the object. In the embodiment, the external object may be various objects related to the operation of the vehicle (100).
[0063] The second sensor unit (103) may be equipped with a positioning sensor (103a), a wheel sensor (103b), and an attitude sensor (103c) to check its own position, speed, and driving attitude. The attitude sensor (103c) may include a gyroscope sensor, an angular velocity sensor, an accelerometer sensor, etc. The attitude sensor may be an IMU (Inertial Measurement Unit) sensor and may be equipped with a 3-axis accelerometer and a 3-axis angular velocity sensor. The attitude sensor may measure the acceleration in the direction of travel (x), the acceleration in the lateral direction (y), the acceleration in the height direction (z) of the vehicle (100), and the yaw, pitch, and roll as the angular velocity of the vehicle.
[0064] The second sensor unit (103) can generate vehicle driving information based on sensing data. The vehicle driving information may be information generated based on data detected by various sensors installed inside the vehicle. For example, the vehicle driving information may include vehicle attitude information, vehicle speed information, vehicle tilt information, vehicle weight information, vehicle direction information, vehicle battery information, vehicle fuel information, vehicle tire pressure information, vehicle steering information, vehicle interior temperature information, vehicle interior humidity information, pedal position information, and vehicle engine temperature information.
[0065] Additionally, the vehicle driving information may include route information. Route information may refer to information generated based on a destination entered by the vehicle user through the control unit (106). If a destination is set, route information may refer to information in which the driving route from the current location of the vehicle to the destination is displayed on the map information. If no destination is set, route information may refer to information including the road currently being driven on by the vehicle and a future driving route including it.
[0066] 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, an accelerator pedal, a brake pedal, 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 the display (108) to receive various requests related to autonomous driving. Depending on the specifications of the autonomous driving vehicle, at least one of the steering wheel, transmission, and pedal may be omitted. As another example, the control unit (106) may be provided with a module that receives a user's control request for a load device (114) in addition to driving control.
[0067] The display (108) can function as a user interface. The display (108) can be displayed by the processor (130) 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 (130).
[0068] The load device (114) 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 an energy generating unit (110) and may be, for example, an air conditioning system, a lighting system, a seat system, and various devices installed in the vehicle (100). In the present disclosure, a cooling / heating system that cools or heats at least one of a battery, a fuel cell, an internal combustion engine, an air conditioning system, and a specific part of the vehicle (100) may be further included.
[0069] The transceiver (112) can support mutual communication with the server (200), ITS device (300), surrounding vehicles (300), etc. The transceiver (112) 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).
[0070] For example, the transmitting and receiving unit (112) can receive traffic signal information from a traffic signal controller and provide it to the processor (130). In addition, the transmitting and receiving unit (112) can receive a control signal from a traffic signal controller and provide it to the processor (130).
[0071] Additionally, the vehicle (100) may include an energy generating unit (110) and an acting unit (116).
[0072] The energy generation unit (110) 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 (102), an operating unit (106), a display (108), a load device (114), and a transceiver unit (112), 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. When the vehicle (100) is driven based on electric energy, the energy generation unit (110) 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 energy generation unit (110) 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 powered by fossil energy, the energy generation unit (110) may be composed of an internal combustion engine. Additionally, if the vehicle (100) is of the hybrid type, the energy generation unit (110) may be provided as a combination of an internal combustion engine and an electric battery.
[0073] The actuating unit (116) is equipped with at least one module that implements a driving operation, and can perform at least one driving operation among longitudinal control such as acceleration / deceleration and lateral control such as steering, in accordance with a user request from the operating unit (106). To perform a driving operation according to a command of the processor (130) by manual operation by the user or autonomous driving, the actuating unit (116) may be equipped with a wheel drive unit (118), mechanical components and electronic modules for implementing a driving operation in the wheel drive unit (118). When the vehicle (100) is operated based on electric energy, it may include an assembly for transmitting the requested driving operation to the wheel drive unit (118). When the vehicle (100) is operated based on fossil energy, the actuating unit (116) may be equipped with a transmission and a gear module that transmit power from an internal combustion engine.
[0074] The wheel drive unit (118) may include a plurality of wheels, a driving force generation module for generating driving force and applying it to the wheels or transmitting 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.
[0075] The navigation system (122) can provide navigation information. The navigation information may include at least one of map information, set destination information, route information based on the destination setting, information about various objects on the route, lane information, and current location information of the vehicle.
[0076] The navigation system (122) can receive information from an external device through the transmitting and receiving unit (112) and update previously stored information. According to an embodiment, the navigation system (122) may be classified as a sub-component of the operating unit (106).
[0077] Additionally, the vehicle (100) may include memory (120) and a processor (130).
[0078] The memory (120) stores applications and various data for controlling the vehicle (100), and can load applications or read and write data at the request of the processor (130).
[0079] The processor (130) can perform overall control of the vehicle (100). The processor (130) can be configured to execute applications and instructions stored in memory (120).
[0080] FIG. 3 is a diagram illustrating the operation of a vehicle control device according to an embodiment. Referring to FIG. 3, the vehicle control device (10) according to an embodiment may include a transceiver (11), a processor (12), and a memory (13). The transceiver (11), processor (12), memory (13), sensor unit (14), navigation system (15), and display (16) of FIG. 3 may each represent the same configuration as the transceiver, processor, memory, sensor unit, navigation system, and display of FIG. 2.
[0081] The transmitting and receiving unit (11) receives external object recognition information and vehicle driving information collected from the sensor unit (14) installed in the vehicle, and can receive map information from the navigation system (15).
[0082] The transmitting and receiving unit (11) can store received external object recognition information, vehicle driving information, and map information in memory (13).
[0083] In the embodiment, the external object recognition information may include information regarding the presence or absence of an object, location information of the object, distance information between the vehicle and the object, and relative speed information between the vehicle and the object. In the embodiment, the external object may be various objects related to the operation of the vehicle.
[0084] For example, external objects can include static objects, dynamic objects, and lanes.
[0085] Static objects may include lane boundaries, guardrails, signs, traffic lights, stop lines, crosswalks, shoulder lines, median strips, protective walls, etc.
[0086] Dynamic objects can include moving objects on the road, such as surrounding moving vehicles, motorcycles, and bicycles.
[0087] The lane may include lane type (solid line, dotted line, etc.), lane location, and road curvature information.
[0088] In the embodiment, the vehicle driving information may include vehicle attitude information, vehicle speed information, vehicle tilt information, vehicle weight information, vehicle direction information, vehicle battery information, vehicle fuel information, vehicle tire pressure information, vehicle steering information, vehicle interior temperature information, vehicle interior humidity information, pedal position information, and vehicle engine temperature information.
[0089] In the embodiment, the map information may include coordinate information and road boundary information.
[0090] The processor (12) can generate a first candidate position group of a vehicle at a first point in time along the lateral direction of the driving road using external object recognition information and map information. In an embodiment, the first candidate position group may include a plurality of position particles, and each position particle may be formed at a predetermined interval along the lateral axis of the road based on the driving direction of the vehicle. The plurality of position particles may be formed by overlapping each other and may be formed within a predetermined error range in the longitudinal direction. The processor (12) can form position particles to cover the entire area of the road. At this time, the processor (12) can form the position particles of the first candidate position group according to a random rule. The processor (12) can set an initial value for the weight of the position particles constituting the first candidate position group. For example, the initial value may be set to 0.5.
[0091] In the following embodiments, the location particle may refer to data visualizing the location candidates constituting each candidate group, the location particle of the first location candidate group may have the same meaning as the first location candidate, and the location particle of the second location candidate group may have the same meaning as the second location candidate.
[0092] The processor (12) can determine the driving position of the vehicle using external object recognition information, vehicle driving information and map information collected at the first time point, and can generate a first position candidate group along the same horizontal axis as the driving position.
[0093] For example, the processor (12) can determine the driving position of the vehicle using the coordinate information of the map information and generate a first position candidate group along the same horizontal axis as the driving position.
[0094] For example, the processor (12) can determine the driving position of the vehicle by supplementing the coordinate information of the map information with the IMU sensor information among the vehicle driving information, and can generate a first position candidate group along the same horizontal axis as the driving position.
[0095] For example, the processor (12) can determine the driving position of the vehicle on the road by comparing the coordinates of the vehicle on the map information with high-precision map data, and can generate a first position candidate group along the same horizontal axis as the driving position. The high-precision map data can be received from the server of FIG. 2 through the transceiver (11).
[0096] For example, the processor (12) can determine the driving position of the vehicle by correcting the coordinate information of the map information using external object recognition information and generate a first position candidate group along the same horizontal axis as the driving position.
[0097] The processor (12) can generate a second candidate group of vehicle positions at a second time point by predicting the behavior of each first candidate group of positions using vehicle driving information. The processor (12) can generate a second candidate group of positions by predicting the behavior of each position particle constituting the first candidate group of positions and predicting the position of each position particle at a second time point.
[0098] In the embodiment, the second point in time may refer to a point in time after a pre-set unit time has elapsed from the first point in time. The second point in time may be changed by setting.
[0099] For example, the processor (12) can generate a second set of candidate positions using a dead reckoning algorithm. The dead reckoning algorithm is a method for estimating the current position based on the vehicle's speed and direction change data when the vehicle's initial position is known. The processor (12) can calculate the vehicle's expected position by continuously accumulating the vehicle's travel distance and direction using the vehicle's speed, steering angle, wheel rotation count, and IMU data.
[0100] For example, the processor (12) can generate a second set of candidate positions based on line cross information. Line cross information is used to detect whether a vehicle has crossed a lane or is located near the current lane boundary through a camera or lidar sensor. This information can be used to correct the position calculated by the dead reckoning algorithm. When the processor (12) detects that the vehicle has crossed a lane or is deviating from the center of a specific lane by using road lane information, the relative distance between the vehicle's position and the lane centerline, and the vehicle's steering state, it can correct the position to the center of the lane where the vehicle should be located by integrating the lane position data into the dead reckoning-based position estimate value.
[0101] For example, the processor (12) can generate a second set of candidate locations using a map curvature information compensation technique. The road curvature information included in the map information represents the geometric characteristics of the road, and this information can reduce the error in the estimate. The processor (12) can compare the road curvature, lane width, number of lanes, and intersection information with the dead reckoning-based location estimate to determine whether the vehicle is located in a position that matches the actual road curvature. If the vehicle's location does not match the curvature, the processor (12) can re-correct the vehicle's location based on the curvature data. For example, if the dead reckoning-based location estimate on a curved road is calculated as if it were a straight road, the vehicle's location can be adjusted into a curved shape using the curvature data.
[0102] For example, the processor (12) can recognize road curvature through a camera mounted on the vehicle and incorporate it into the position estimation. The processor (12) can analyze the road curvature in real time using lane curvature information extracted from the vehicle's front camera and update the vehicle's position by comparing it with a dead reckoning-based position estimation value.
[0103] The processor (12) can generate a second set of candidate locations using at least one of the aforementioned location estimation techniques. At this time, the processor (12) can generate a second set of candidate locations by applying a combination of multiple location estimation techniques.
[0104] FIG. 4 is a diagram for explaining the operation of a processor (12) according to an embodiment. Referring to FIG. 4, for example, if there are 100 location particles in a first location candidate group, 50 of them can be used to generate a second location candidate group based on lane crossing information, and the remaining 50 can be used to generate a second location candidate group using a map curvature compensation technique. That is, the processor (12) can classify location particles into multiple groups and generate a second location candidate group by applying a different location estimation technique to each group. At this time, the processor (12) can classify location particles that are not adjacent to each other into the same group.
[0105] The position particles of the second position candidate group may have different longitudinal positions depending on the prediction technique. That is, the position particles of the first position candidate group are generated to be located on the same horizontal axis, but the position particles of the second position candidate group may be generated to have different longitudinal coordinates with a predetermined error range.
[0106] The location particles of the second location candidate group have the same weight as the location particles of the corresponding first location candidate group and can be generated in the same number.
[0107] The processor (12) can calculate a matching score for each lane of the road being driven according to the degree of matching between external object recognition information and map information at a second time point. The processor (12) can calculate and sum a first matching score for static objects, a second matching score for dynamic objects, and a third matching score for lanes, respectively, according to the degree of matching between external object recognition information and map information.
[0108] The processor (12) can calculate a first matching score by comparing the coordinates of a static object included in the object recognition information with the coordinates of a road boundary line included in the map information. The processor (12) can calculate a first matching score by comparing the coordinates of a static object classified as a road boundary line using the object recognition information while assuming a vehicle lane with the road boundary line information on the map information.
[0109] FIG. 5 is a diagram for explaining the operation of a processor (12) according to an embodiment. Referring to FIG. 5, the processor (12) can compare the coordinates of a static object classified as a road boundary line with road boundary line information on map information, assuming that the vehicle is located in the first to fourth lanes, respectively. The processor (12) can subtract a score if the road boundary line on the static object is located inside the road boundary line on map information.
[0110] For example, as shown in FIG. 5, the processor (12) can calculate the first matching score as [-50, -50, 0, -50] by assuming that all static objects are located outside the road boundaries of the map information, assigning a score of 0 to the third lane, and assigning -50 to the remaining first, second, and fourth lanes. For convenience, the first matching score is described in the form of first lane, second lane, third lane, and fourth lane, but it may be changed.
[0111] The processor (12) can calculate a second matching score by comparing the coordinates of a dynamic object included in the object recognition information with the coordinates of a road boundary line and a lane included in the map information. The processor (12) can calculate a second matching score by comparing the coordinates of a dynamic object with the coordinates of a road boundary line and a lane included in the map information while assuming a lane of a vehicle.
[0112] FIG. 6 is a diagram illustrating the operation of a processor (12) according to an embodiment. Referring to FIG. 6, the processor (12) can compare the coordinates of a dynamic object with the coordinates of a road boundary line and a lane on the map information, assuming that the vehicle is located in the first to fourth lanes, respectively. The processor (12) can add a score if the dynamic object is located inside the road boundary line and within the lane on the map information. Additionally, the processor (12) can subtract a score if the dynamic object is located outside the road boundary line on the map information.
[0113] For example, as shown in FIG. 6, the processor (12) can calculate the second matching score as [-100, 50, 50, -100] by assuming that all dynamic objects are located within the road boundary line and lane on the map information, assigning a score of 50 to the second and third lanes, and assigning -100 points to the remaining first and fourth lanes in proportion to the number of dynamic objects that have deviated from the road boundary line. For convenience, the second matching score is described in the form of first lane, second lane, third lane, and fourth lane, but it may be changed.
[0114] The processor (12) can calculate a third matching score by comparing the lane coordinates and lane type included in the object recognition information with the road information included in the map information. The processor (12) can calculate the third matching score based on whether the lane coordinates of the object recognition information match the lane coordinates of the road on the map information, and whether the lane type of the object recognition information matches the lane type on the map information, while assuming a lane of a vehicle.
[0115] FIG. 7 is a diagram for explaining the operation of a processor (12) according to an embodiment. Referring to FIG. 7, the processor (12) can compare the lane coordinates of object recognition information with the lane coordinates on the map information, assuming that the vehicle is located in the first to fourth lanes, respectively. Additionally, the processor (12) can compare the lane type of object recognition information with the lane type on the map information, assuming that the vehicle is located in the first to fourth lanes, respectively. The processor (12) can calculate a third matching score by differentially assigning lane-specific scores according to the degree of agreement between the lane coordinates and the lane type.
[0116] In the examples, lane types can be classified into blue lanes, yellow lanes, white lanes, double-line lanes, solid line lanes, dotted line lanes, etc.
[0117] For example, as shown in FIG. 7, the processor (12) may assign the highest score of 100 points when the lane coordinates and type of the object recognition information match both the lane coordinates and lane type on the map information. The processor (12) may subtract points based on the number of lanes where the lane coordinates or lane types do not match, and assign -100 points to the scores of the 1st, 2nd, and 4th lanes, thereby calculating the 3rd matching score as [-100, -100, 100, -100]. For convenience, the 3rd matching score is described in the form of the 1st, 2nd, 3rd, and 4th lanes, but it may be changed.
[0118] The processor (12) can calculate a total matching score for each lane of the road being driven by summing the first matching score to the third matching score. Referring again to the example of FIGS. 5 to 7, the processor (12) can calculate a total matching score [-250, -100, 150, -250] by vector summing the first matching score ([-50, -50, 0, -50]), the second matching score (score [-100, 50, 50, -100]), and the third matching score ([-100, -100, 100, -100]).
[0119] The processor (12) can calculate the probability that each second position candidate belonging to the second position candidate group is located in a specific lane based on the matching score.
[0120] In the embodiment, the weight is a numerical value representing the probability that each location particle constituting the second location candidate group is located in a specific lane, and may have a value from 0 to 1. As described above, in the embodiment, the weights of the location particles are all initialized to a value of 0.5.
[0121] The processor (12) can update the weight of the location particle located in the corresponding lane using the lane-specific matching score.
[0122] The processor (12) can increase the weight of the location particle of the lane where the matching score is positive in proportion to the size of the matching score.
[0123] Additionally, the processor (12) can reduce the weight of the location particle to the lane where the matching score is negative in proportion to the size of the matching score.
[0124] FIG. 8 is a diagram illustrating the operation of a processor (12) according to an embodiment. Referring to FIG. 8, the processor (12) can update the weights of position particles for each lane according to a total matching score [-250, -100, 150, -250].
[0125] The processor (12) can increase the weight of the position particle located in the third lane by a preset ratio in proportion to the matching score of 100 points.
[0126] Additionally, the processor (12) can reduce the weight of particles located in the first lane, second lane, and fourth lane by a preset ratio proportional to the size of the matching score. Accordingly, the weight of the position particles located in the first lane and fourth lane is reduced relatively more than the weight of the position particles located in the second lane.
[0127] The processor (12) can accumulate and reflect weights over time. That is, the processor (12) can calculate the weight at the nth time point using the weights accumulated from the first time point to the n-1th time point (n is a natural number greater than 2).
[0128] The processor (12) can determine the driving lane of the vehicle at a second time point based on weights. The processor (12) can determine the lane where the second position candidates, which have a higher calculated weight compared to other lanes, are located as the driving lane of the vehicle.
[0129] For example, the processor (12) can sum the weights of the position particles for each lane and determine the lane with the highest sum of weights as the driving lane of the vehicle.
[0130] For example, the processor (12) can average the weights of the position particles for each lane and determine the lane with the highest average weight value as the driving lane of the vehicle.
[0131] For example, the processor (12) can compare the weight of the position particles for each lane with a preset threshold weight and determine the lane with the largest number of position particles with a weight exceeding the preset threshold weight as the driving lane of the vehicle.
[0132] The processor (12) can display the vehicle's driving lane on the display (15).
[0133] The processor (12) can delete or reset the weight of a second location candidate whose weight is below a preset threshold. The processor (12) can determine whether to delete or reset the weight by comparing the weight of the location particle with the threshold at each time point. Through this process, location particles with a very low probability of a vehicle being present are deleted, and particles of a different location are regenerated at the next time point, thereby significantly improving the accuracy of lane location estimation.
[0134] Additionally, the processor (12) may delete some of the multiple second position candidates located in the vehicle's driving lane or reset their weights. The processor (12) may decide whether to delete or reset the position particles of the vehicle's driving lane at each time step. If too many position particles are located in the driving lane, the likelihood of the lane being continuously determined as the driving lane increases due to the accumulation of weights. Therefore, if the number of position particles located in the driving lane exceeds a preset threshold, the processor (12) may delete some of the position particles or reset their weight values to prevent errors in lane position estimation caused by the accumulation of weights.
[0135] Additionally, the processor (12) can adjust the number of third position candidate groups of the vehicle at the third time point by lane based on the matching score calculated at the second time point.
[0136] FIGS. 9 and FIGS. 10 are drawings for explaining the operation of a processor (12) according to an embodiment. Referring to FIG. 9 together, the processor (12) can generate new location particles at random lane locations equal to the number of deleted location particles. Accordingly, the newly generated location particles can be generated without being based on matching scores or weights, and can be concentrated in lanes where many existing location particles are located.
[0137] Referring to FIG. 10, the processor (12) can operate to generate more location particles in the lane with a high matching score calculated at the second time point. That is, since the lane with the high matching score is likely to be the vehicle's driving lane, generating more location particles in the lane with the high matching score can improve the likelihood that the lane will be determined as the driving lane at the next time point.
[0138] At this time, the processor (12) can correct the position so that the location particle can be located inside the driving lane by using map information and external object recognition information.
[0139] In addition, in cases where the number of lanes changes, such as when entering or exiting a highway, the map information received up to a specific range ahead can be used to reflect the changed number of lanes, thereby performing position particle generation, matching score calculation, weight update, and driving lane estimation.
[0140] FIG. 11 is a flowchart of a vehicle control method according to an embodiment. Referring to FIG. 11, the transceiver receives external object recognition information and vehicle driving information collected from a sensor unit placed in the vehicle, and receives map information from a navigation system (S1101).
[0141] Next, the processor generates a first position candidate group of the vehicle at a first time point along the lateral direction of the driving road using external object recognition information and map information (S1102).
[0142] Next, the processor predicts the behavior of each of the first position candidate groups using vehicle driving information and generates a second position candidate group of the vehicle at a second time point (S1103).
[0143] Next, the processor calculates a matching score for each lane of the road being driven on, based on the degree of matching between external object recognition information and map information at a second time point. Based on the degree of matching between external object recognition information and map information, the processor calculates a first matching score for static objects, a second matching score for dynamic objects, and a third matching score for lanes, respectively, and calculates a total matching score for each lane by summing these scores (S1104).
[0144] Next, the processor calculates a weight for the probability that each second-position candidate belonging to the second-position candidate group is located in a specific lane based on the matching score. At this time, the processor updates the weight accumulated up to the previous time point with the newly calculated weight (S1105).
[0145] Next, the processor determines the driving lane of the vehicle at a second time point based on weights. The processor determines the lane where the second position candidates, which have a higher calculated weight compared to other lanes, are located as the driving lane of the vehicle (S1106).
[0146] Next, the processor displays the vehicle's driving lane on the display (S1107).
[0147] Next, the processor deletes or initializes the weights of second position candidates whose weights are below a preset threshold, and deletes or initializes the weights of some of the multiple second position candidates located in the vehicle's driving lane (S1108).
[0148] The processor can determine the vehicle's driving lane in a robust manner by using weights accumulated by repeating the aforementioned process at preset unit time points.
[0150] The term "part" as used in this embodiment refers to a software or hardware component, such as a field-programmable gate array (FPGA) or an ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Thus, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.
[0151] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims. Explanation of the symbols
[0153] 10: Vehicle control unit 100: Vehicle 102: First sensor unit 103: Second sensor unit 106: Control Panel 16, 108: Display 110: Load device 11, 112: Transmitter / Receiver 114: Energy generation unit 116: Actuating part 118: Wheel drive unit 13, 120: Memory 15, 122: Navigation system 12, 130: Processors
Claims
Claim 1 A vehicle control device comprising: a transceiver; one or more processors; and a memory for storing one or more programs executed by the one or more processors, wherein the transceiver receives external object recognition information and vehicle driving information collected from a sensor unit disposed in the vehicle, and receives map information from a navigation system; wherein the processor generates a first position candidate group of the vehicle at a first time point along the lateral direction of the driving road using the external object recognition information and the map information, predicts the behavior of each of the first position candidate group using the vehicle driving information to generate a second position candidate group of the vehicle at a second time point, calculates a matching score for each lane of the driving road according to the degree of matching between the external object recognition information and the map information at the second time point, calculates a weight for the probability that each of the second position candidates belonging to the second position candidate group is located in a specific lane based on the matching score, and determines the driving lane of the vehicle at the second time point based on the weight. Claim 2 In claim 1, the processor is a vehicle control device that accumulates and reflects the weights over time. Claim 3 In paragraph 2, the processor is a vehicle control device that determines the lane where the second position candidates, which have a higher calculated weight compared to other lanes, are located as the driving lane of the vehicle. Claim 4 In paragraph 2, the processor is a vehicle control device that deletes a second position candidate whose weight is below a preset threshold or initializes the weight. Claim 5 In paragraph 2, the processor is a vehicle control device that deletes some of the multiple second position candidates located in the driving lane of the vehicle or initializes the weights. Claim 6 A vehicle control device according to claim 1, wherein the processor calculates and sums a first matching score for a static object, a second matching score for a dynamic object, and a third matching score for a lane, respectively, according to the degree of matching between the external object recognition information and the map information. Claim 7 In claim 6, the vehicle control device calculates the first matching score by comparing the coordinates of a static object included in the object recognition information with the coordinates of a road boundary line included in the map information. Claim 8 In claim 6, the vehicle control device calculates the second matching score by comparing the coordinates of a dynamic object included in the object recognition information with the coordinates of a road boundary line and a lane included in the map information. Claim 9 In claim 6, the vehicle control device calculates the third matching score by comparing the lane coordinates and lane type included in the object recognition information with the road information included in the map information. Claim 10 In claim 1, the processor is a vehicle control device that adjusts the number of third position candidate groups of the vehicle at the third time point by lane based on the matching score calculated at the second time point. Claim 11 A vehicle control method performed by a computing device comprising: a transmitting and receiving unit; one or more processors; and a memory for storing one or more programs executed by said one or more processors, wherein the transmitting and receiving unit receives external object recognition information and vehicle driving information collected from a sensor unit disposed in the vehicle, and receives map information from a navigation system, and the processor generates a first position candidate group of said vehicle at a first time point along the lateral direction of the driving road using said external object recognition information and said map information, predicts the behavior of said first position candidate group using said vehicle driving information to generate a second position candidate group of said vehicle at a second time point, calculates a matching score for each lane of the driving road according to the degree of matching between said external object recognition information and said map information at the second time point, calculates a weight for the probability that each second position candidate belonging to the second position candidate group is located in a specific lane based on said matching score, and determines the driving lane of said vehicle at the second time point based on said weight. Claim 12 In claim 11, the above processor is a vehicle control method that accumulates and reflects the above weights over time. Claim 13 In claim 12, the above-described processor determines the lane where the second position candidates, which have a higher weight calculated compared to other lanes, are located as the driving lane of the vehicle. Claim 14 A vehicle control method according to claim 12, wherein the processor deletes a second position candidate whose weight is below a preset threshold or initializes the weight. Claim 15 A vehicle control method according to claim 12, wherein the processor deletes some of the multiple second position candidates located in the driving lane of the vehicle or initializes the weights. Claim 16 A vehicle control method according to claim 11, wherein the processor calculates and sums a first matching score for a static object, a second matching score for a dynamic object, and a third matching score for a lane, respectively, according to the degree of matching between the external object recognition information and the map information. Claim 17 A vehicle control method according to claim 16, wherein the processor calculates the first matching score by comparing the coordinates of a static object included in the object recognition information with the coordinates of a road boundary line included in the map information. Claim 18 A vehicle control method according to claim 16, wherein the processor calculates the second matching score by comparing the coordinates of a dynamic object included in the object recognition information with the coordinates of a road boundary line and a lane included in the map information. Claim 19 A vehicle control method according to claim 16, wherein the processor calculates the third matching score by comparing the lane coordinates and lane type included in the object recognition information with the road information included in the map information. Claim 20 A vehicle control method according to claim 11, wherein the processor adjusts the number of third position candidate groups of the vehicle at the third time point by lane based on the matching score calculated at the second time point.