Method And Apparatus for Controlling Vehicle
A hierarchical vehicle control system using upper and lower controllers with pattern recognition and context-based analysis enhances control performance by integrating environmental context and temporal patterns, addressing limitations in conventional systems.
Patent Information
- Application Number
- KR1020250059143
- Authority / Receiving Office
- KR · KR
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2026-11-16
AI Technical Summary
Conventional vehicle control systems face limitations in performing global optimization under complex driving conditions due to reliance on lower-level controllers, simple numerical indicators, and instability in machine learning-based controllers, leading to degraded control performance.
A hierarchical control structure combining an upper controller for global optimization and a lower controller for local optimization, utilizing pattern recognition and context-based analysis, with an integrated evaluation module to assess vehicle behavior and adjust steering and braking forces.
Enables stable vehicle control under complex conditions by integrating environmental context and temporal patterns, allowing for real-time adjustments and improved predictive power through MPC and machine learning-based corrections.
Smart Images

Figure PAT00024_ABST
Abstract
Description
Technology Field
[0001] The present disclosure relates to a method and apparatus for controlling a vehicle. Background Technology
[0002] The following description merely provides background information related to the present embodiment and does not constitute prior art.
[0003] Conventional vehicle control systems utilize only lower-level controllers, enabling local control of vehicle steering and braking, but they have limitations in performing global optimization. In structures using only lower-level controllers, problems of degraded control performance occurred because they could not adequately respond to changes in the external environment or complex road conditions.
[0004] In evaluating vehicle behavior as well, existing technologies had limitations in that they relied solely on simple numerical indicators or sensor data, failing to integrally reflect temporal patterns or the context of the external environment.
[0005] There were limitations even when applying Model Predictive Control (MPC) or machine learning-based controllers alone as control algorithms. MPC suffered from low prediction accuracy in non-linear or irregular environments, while machine learning exhibited instability due to a high dependence on large-scale data and a rapid deterioration in control performance in unlearned situations.
[0006] Therefore, vehicle control technology is required that can secure stable vehicle control performance even under complex driving conditions by integrally reflecting the external environment and temporal context. The problem to be solved
[0007] The main purpose of the present disclosure is to comprehensively evaluate the behavior of a vehicle using pattern recognition and context-based analysis, and to improve the control performance of the vehicle's behavior using a hierarchical control structure.
[0008] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem
[0009] According to one aspect of the present disclosure, a method for controlling a vehicle comprises: a process of analyzing the behavior of the vehicle based on learned behavior pattern data regarding the behavior of the vehicle, including one or more of a steering angle or a braking force; a process of evaluating contextual appropriateness for the behavior of the vehicle; a process in which an upper controller performs global optimization for the behavior of the vehicle based on the result of analyzing the behavior of the vehicle and the contextual appropriateness evaluation; a process in which a lower controller performs local optimization for the behavior of the vehicle based on a control value received from the upper controller; and a process of controlling the vehicle based on one or more of the steering angle or braking force optimized by the global optimization and the local optimization.
[0010] According to another aspect of the present disclosure, an apparatus for controlling a vehicle comprises: at least one memory for storing instructions; and at least one processor, wherein the at least one processor executes the instructions to analyze the behavior of the vehicle based on learned behavior pattern data regarding the behavior of the vehicle, including one or more of steering angles or braking forces, evaluates contextual appropriateness for the behavior of the vehicle, and a higher controller performs global optimization for the behavior of the vehicle based on the result of analyzing the behavior of the vehicle and the contextual appropriateness evaluation, and a lower controller performs local optimization for the behavior of the vehicle based on a control value received from the higher controller, and controls the vehicle based on one or more of the steering angles or braking forces optimized by the global optimization and the local optimization. Effects of the invention
[0011] According to one embodiment of the present disclosure, there is an effect of learning the behavioral patterns of a vehicle and evaluating the behavior of the vehicle more precisely through context-based analysis.
[0012] According to one embodiment of the present disclosure, by using both an upper controller and a lower controller, it is possible to simultaneously perform global optimization and local control, which has the effect of being possible.
[0013] According to one embodiment of the present disclosure, an upper controller sets a global goal, and a lower controller rapidly performs control of each part of the vehicle within a local scope, thereby enabling real-time control even under complex external conditions.
[0014] According to one embodiment of the present disclosure, combining an MPC-based physical model with machine learning-based nonlinear correction can have the effect of improving the predictive power and control power of the vehicle's behavior.
[0015] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing
[0016] FIG. 1 is a block diagram schematically showing the components of a vehicle control device according to one embodiment of the present disclosure. FIG. 2 is a flowchart schematically illustrating a method for controlling a vehicle according to one embodiment of the present disclosure. FIG. 3 is a flowchart illustrating a method for learning and evaluating the behavioral pattern of a vehicle according to one embodiment of the present disclosure. FIG. 4 is a flowchart illustrating a method for evaluating contextual appropriateness for the behavior of a vehicle according to one embodiment of the present disclosure. FIG. 5 is a flowchart illustrating a method for a higher-level controller of a vehicle to perform global optimization according to one embodiment of the present disclosure. FIG. 6 is a flowchart illustrating a method for a vehicle's sub-controller to perform local optimization according to one embodiment of the present disclosure. FIG. 7 is a block diagram schematically showing the configuration of a vehicle that can be used to implement the method or device described in the present disclosure. FIG. 8 is a schematic block diagram of an exemplary computing device that can be used to implement the devices and methods described in the present disclosure. Specific details for implementing the invention
[0017] Some embodiments of the present disclosure are described in detail below with reference to exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the present disclosure, if it is determined that a detailed description of related known components or functions could obscure the essence of the present disclosure, such detailed description is omitted.
[0018] In describing the components of the embodiments according to the present disclosure, symbols such as first, second, i), ii), a), b), etc., may be used. These symbols are intended only to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the symbols. When a part in the specification is described as 'comprising' or 'having' a component, this means that, unless explicitly stated otherwise, it does not exclude other components but may include additional components.
[0019] The detailed description set forth below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiment in which the present disclosure can be practiced.
[0020] FIG. 1 is a block diagram schematically showing the components of a vehicle control device according to one embodiment of the present disclosure.
[0021] Referring to FIG. 1, the vehicle control unit (10) may include a data collection module (100), a pattern analysis module (110), a context-based evaluation module (120), an integrated evaluation module (130), and a control module (140).
[0022] The data collection module (100) collects internal data related to the vehicle (hereinafter internal data) and external data related to the vehicle (hereinafter external data). The internal data may include the vehicle's speed, acceleration, steering angle, or gyroscope data. The external data may include road curvature, road surface conditions (e.g., friction coefficient or degree of wetness of the road surface), the speed and location of surrounding vehicles, or weather. The data collection module (100) may preprocess the collected data so that other modules can use it.
[0023] The pattern analysis module (110) learns the vehicle's behavior pattern based on the vehicle's temporal data using Long Short-Term Memory (LSTM). The vehicle's behavior pattern may include a stable state, an unstable state, or a dangerous state based on the stability of the behavior. For example, a stable state may refer to a state where the change in the vehicle's steering angle or angular velocity is small or constant. An unstable state may refer to a state where the rate of change in the vehicle's roll angle or steering angle increases. A dangerous state may refer to a case where the vehicle brakes abruptly or the fluctuation in the yaw angle is excessive. The pattern analysis module (110) can classify the current state of the vehicle as stable, unstable, or dangerous by comparing the vehicle's driving behavior data in real time with the learned behavior pattern data. For example, when driving on a curved road, if the vehicle's roll and yaw angular velocity exceed a certain range, it can be classified as an abnormal increase in roll. When braking suddenly while driving on a highway, if rapid deceleration and an irregular increase in yaw angular velocity are detected, it can be classified as a dangerous pattern. When braking on a slippery road surface, if the vehicle's deceleration is abnormal or the roll increases abnormally, it can be determined that the braking is unstable and classified as a dangerous pattern. The vehicle's behavior pattern can be calculated using Equation 1.
[0024]
[0025]
[0026] The context-based evaluation module (120) evaluates the suitability of the vehicle's behavior by analyzing external data. The external data may include road conditions, weather, or surrounding vehicles. The context-based evaluation module (120) calculates a suitability indicator to evaluate the suitability of the vehicle's behavior. The suitability indicator may include a road context indicator, an environmental context indicator, or a traffic context indicator. The road context indicator may indicate the suitability between the vehicle's behavior, road curvature, and road surface conditions. The environmental context indicator may indicate the suitability between the vehicle's speed, weather, and visibility. The traffic context indicator may indicate the suitability with the distance and speed difference between vehicles. The context suitability score is the sum of the road suitability, environmental suitability, and traffic suitability multiplied by their respective weights. The lower the suitability score, the more likely it is that adjustment is required for the vehicle's behavior. For example, when making a sudden stop while driving on a highway, traffic suitability can be assessed as low if the distance to the vehicle ahead is insufficient. When driving on a curved road, speeding can be assessed as excessive if the vehicle speed is faster than the curvature when comparing the road curvature. When braking on a slippery road surface, road suitability can be assessed as low if the coefficient of friction is low. The contextual suitability score can be calculated using Equation 2.
[0027]
[0028]
[0029] The integrated evaluation module (130) evaluates the behavioral state of a vehicle by combining the results of the pattern analysis of vehicle behavior and the results of the suitability evaluation. The integrated evaluation module (130) can calculate a composite indicator by adding the values obtained by multiplying the pattern risk and context suitability scores by weights that change dynamically according to driving conditions and driving situations, respectively. The composite indicator can be obtained using Equation 3.
[0030]
[0031]
[0032] The integrated evaluation module (130) can determine whether the vehicle's behavioral state is stable or dangerous based on the integrated indicator. If the pattern analysis result is normal and the contextual appropriateness score is high, it may correspond to a stable state. If the pattern analysis result is dangerous and the contextual appropriateness score is low, it may correspond to a dangerous state.
[0033] The control module (140) performs real-time control of the vehicle based on the integrated indicator calculated by the integrated evaluation module (130). If the control module (140) determines that the vehicle is in a normal state, it can maintain the vehicle's driving. If the control module (140) determines that the vehicle is in a warning state, it can provide a warning message or increase the sensitivity of the braking or steering assistance system. If the control module (140) determines that the vehicle is in a danger state, it can activate a function to stabilize the vehicle's braking or steering and limit the vehicle's speed.
[0034] The control module (140) includes a high-level controller and a low-level controller. The high-level controller analyzes global conditions regarding the vehicle's behavior. The high-level controller can analyze global patterns of the vehicle's behavior using an LSTM. The high-level controller sets global control goals. The high-level controller evaluates the suitability with external data, such as road surface conditions, road curvature, or traffic conditions, to set optimal global control goals for the vehicle's overall behavior. Model Predictive Control (MPC) is used for global optimization. The vehicle's global control goals may include the vehicle's steering angle or braking force. The high-level controller transmits target values for the braking force or steering angle to the low-level controller.
[0035] The lower controller receives target values from the upper controller. Based on the target values, the lower controller performs detailed local control for each part of the vehicle. Based on the received target values, the lower controller performs local optimization by reflecting local conditions, such as road surface friction coefficients or tire conditions. The lower controller transmits the result values, including the actual steering angle or braking force obtained using local optimization, to the upper controller.
[0036] FIG. 2 is a flowchart schematically illustrating a method for controlling a vehicle according to one embodiment of the present disclosure.
[0037] The vehicle control unit (10) collects internal and external data of the vehicle using a data collection module (100) (S200). The vehicle control unit (10) learns the vehicle's behavior pattern using a deep learning model (LSTM) based on the collected data using a pattern analysis module (110). During driving, the vehicle's behavior is evaluated by comparing the data collected in real time with the learned behavior pattern data (S202). The vehicle control unit (10) evaluates the contextual suitability of the vehicle's behavior by calculating a suitability score based on the vehicle's external data using a context-based evaluation module (120) (S204). The vehicle control unit (10) calculates an integrated index by combining the results of evaluating the vehicle's behavior and the results of evaluating contextual suitability using an integrated evaluation module (130), and determines whether the vehicle's state is stable based on the calculated integrated index (S206). The vehicle control unit (10) sets a control goal to perform global optimization using a higher-level controller, optimizes the overall behavior of the vehicle to a higher level based on the control goal, and transmits the target value to a lower-level controller (S208). The vehicle control unit (10) performs detailed control of each part of the vehicle using a lower-level controller and transmits feedback to the higher-level controller (S210).
[0038] FIG. 3 is a flowchart illustrating a method for learning and evaluating the behavioral pattern of a vehicle according to one embodiment of the present disclosure.
[0039] The vehicle control unit (10) collects internal and external data of the vehicle using a data collection module (100) (S300). The collected data undergoes a preprocessing process to learn the vehicle's behavior pattern. The vehicle control unit (10) learns the vehicle's behavior pattern based on the vehicle's temporal data using an LSTM technique with a pattern analysis module (110) (S302). The vehicle's behavior pattern may include a stable state, an unstable state, or a dangerous state based on the stability of the behavior. The vehicle control unit (10) collects the vehicle's behavior data in real time while the vehicle is driving using the data collection module (100) (S304). The vehicle control unit (10) compares the vehicle's behavior data with the learned behavior pattern data to classify the current state of the vehicle as normal, warning, or dangerous (S306).
[0040] FIG. 4 is a flowchart illustrating a method for evaluating contextual appropriateness for the behavior of a vehicle according to one embodiment of the present disclosure.
[0041] The vehicle control unit (10) collects external data of the vehicle using a data collection module (100) (S400). The vehicle control unit (10) calculates a contextual suitability score based on road context indicators, environmental context indicators, and traffic context indicators using a context-based evaluation module (120) (S402). The vehicle control unit (10) evaluates the suitability of the current vehicle's behavior according to the contextual suitability score using the context-based evaluation module (120) (S404).
[0042] FIG. 5 is a flowchart illustrating a method for a higher-level controller of a vehicle to perform global optimization according to one embodiment of the present disclosure.
[0043] The upper controller calculates an integrated index using an integrated evaluation module (130) (S500). The upper controller analyzes the global pattern of the vehicle's behavior using an LSTM (S502). The upper controller evaluates the suitability with external data such as road surface conditions, road curvature, or traffic conditions to set an optimal global control goal for the vehicle's overall behavior (S504). MPC is used for global optimization. The vehicle's behavior goal may include the vehicle's steering angle or braking force. The global optimization value can be calculated using Equation 4.
[0044]
[0045]
[0046]
[0047]
[0048]
[0049]
[0050] The predicted values of the physical model can be corrected in real time using an LSTM model. The correction of the predicted values can be performed using Equation 5.
[0051]
[0052]
[0053]
[0054]
[0055] The upper controller transmits a target value, including the steering angle or braking force of the vehicle, to the lower controller (S506).
[0056] FIG. 6 is a flowchart illustrating a method for a vehicle's sub-controller to perform local optimization according to one embodiment of the present disclosure.
[0057] The lower controller receives a target value from the upper controller. The lower controller performs local detailed control for each part of the vehicle based on the target value (S600). For example, the lower controller can calculate the braking pressure required for each wheel based on the braking force target. The lower controller can control the steering motor based on the steering angle target.
[0058] The sub-controller performs local optimization based on the received target value by reflecting local conditions such as the road surface friction coefficient or tire condition (S602). The local optimization value can be calculated using Equation 6.
[0059]
[0060]
[0061]
[0062]
[0063]
[0064]
[0065] The lower controller transmits the result value, including the actual steering angle or braking force obtained using local optimization, to the upper controller (S604).
[0066] FIG. 7 is a block diagram schematically showing the configuration of a vehicle that can be used to implement the method or device described in the present disclosure.
[0067] The vehicle (70) includes one or more of a communication unit (710), a sensing unit (720), a positioning unit (730), an operation unit (740), a driving unit (750), an HMI (Human-Machine Interface, 760), a storage unit (770), or a controller (780).
[0068] The communication unit (710) can exchange signals with devices located outside and inside the vehicle (70). The communication unit (710) can exchange signals with at least one of infrastructure devices such as a server or base station, other vehicles, and terminals. To perform communication, the communication unit (710) may include at least one of a transmitting antenna, a receiving antenna, an RF (Radio Frequency) circuit capable of implementing various communication protocols, and an RF element. The communication unit (710) may include an internal communication unit and an external communication unit. The internal communication unit can transmit or receive various data using various communication protocols existing within the vehicle (70). The protocols used by the internal communication unit may include at least one of CAN (Controller Area Network), CAN FD (CAN with Flexible Data rate), Ethernet, LIN (Local Interconnect Network), and FlexRay. The communication protocols may include other protocols for communication between various devices mounted on the vehicle. The external communication unit can communicate with other vehicles, infrastructure systems, base stations, roadside devices, etc., using various communication protocols. The protocols used by the external communication unit may include Vehicle-to-Vehicle (V2V) communication, Vehicle-to-Infrastructure (V2I) communication, Vehicle-to-Network (V2N) communication, and Vehicle-to-Everything (V2X) communication, including Vehicle-to-Pedestrian (V2N) communication.The infrastructure may be, for example, a roadside unit or server that periodically transmits traffic information in conjunction with a Transportation Information System (TIS) or Intelligent Transport System (ITS).
[0069] The sensing unit (720) can sense the state of the vehicle (70) and external objects. To sense the state of the vehicle (70), the sensing unit (720) may include one or more of an IMU (inertial measurement unit), a DMI (Distance Measuring Instrument) device, a collision sensor, a wheel sensor, a speed sensor, an inclination sensor, a weight detection sensor, a heading sensor, a position module, a vehicle forward / reverse sensor, a battery sensor, a fuel sensor, a tire sensor, a steering sensor, a temperature sensor, a humidity sensor, an ultrasonic sensor, an illuminance sensor, or a pedal position sensor. Meanwhile, the IMU (inertial measurement unit) sensor may include one or more of an acceleration sensor, a gyroscope sensor, and a magnetic sensor. The sensing unit (720) can generate state data of the vehicle based on signals generated from at least one sensor. For example, the sensing unit (720) can collect directional information such as the heading and yaw rate of the vehicle (70). The sensing unit (720) may include at least one of a camera, a radar sensor, a LiDAR (Light Detection and Ranging) sensor, an ultrasonic sensor, and an infrared sensor to detect an external object. The sensing unit (720) may measure at least one of information regarding the presence or absence of an object, location information of an object, distance information between the vehicle (70) and the object, and relative speed information between the vehicle (70) and the object.
[0070] The positioning unit (730) can generate location data of the vehicle (70). The positioning unit (730) may include at least one of a Global Positioning System (GPS), a Differential Global Positioning System (DGPS), or a Global Navigation Satellite System (GNSS). The positioning unit (730) can generate location data of the vehicle (70) based on a signal generated by at least one of a GPS, DGPS, or GNSS. The positioning unit (730) can estimate the location of the vehicle (70) based on wireless signals received from the communication unit (710). The positioning unit (730) can estimate the current location of the vehicle (70) based on previous location information, distance traveled, travel time information, speed information, or acceleration information, etc., of the vehicle (70) using an IMU or DMI. Meanwhile, based on the location information of the vehicle (70) collected by the positioning unit (730), the controller (780) can estimate the path history and predicted path of the vehicle (70).
[0071] The control unit (740) receives user input for driving. In manual mode, the vehicle (70) can be operated based on signals provided by the control unit (740). The control unit (740) may include a steering input device such as a steering wheel, an acceleration input device such as an accelerator pedal, and a brake input device such as a brake pedal.
[0072] The drive unit (750) is a device that electrically controls various drive devices within the vehicle (70). The drive unit (750) may include, for example, a powertrain drive control device, a chassis drive control device, a door / window drive control device, a safety device drive control device, a lamp drive control device, and an air conditioning drive control device. The drive unit (750) controls the movement of the vehicle (70) based on an input signal from the operating unit (740) or a control signal from the controller (780).
[0073] The HMI (760) is a device for communication between the vehicle (70) and a person (e.g., a passenger of the vehicle (70) or another vehicle). The HMI (760) can receive input from a user and provide information generated by the vehicle (70) to the user. The vehicle (70) can implement a UI (User Interface) or UX (User Experience) through the HMI (760). The HMI (760) may include input devices such as a touch panel and a microphone, and output devices such as a display device and a speaker. For example, the HMI (760) may include an internal display that outputs a screen toward the inside of the vehicle and / or an external display that outputs a screen toward the outside of the vehicle.
[0074] The storage unit (770) may store a program that enables the controller (780) to perform a method according to one embodiment of the present disclosure. For example, the program may include a plurality of instructions executable by a processor, and the method according to one embodiment of the present disclosure may be performed by executing the plurality of instructions by the processor. The storage unit (770) may be a single memory or a plurality of memories. If the storage unit (770) is composed of a plurality of memories, the plurality of memories may be physically separated. The storage unit (770) may include at least one of volatile memory and non-volatile memory. Volatile memory includes Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), etc., and non-volatile memory includes flash memory, etc. The storage unit (770) stores map information. The map information may be either a navigation map and / or a high definition map (HD map). The high definition map may be received in real time from an external device or stored in advance. Navigation maps may include geographic information, road information, lane information, building information, or traffic information. Precision maps include more detailed data compared to navigation maps. Regarding roads, precision maps may include gradient, road curvature, signage information, etc. Regarding lanes, precision maps may include lane information, lane boundary information, stop line locations, traffic light locations, signal sequences, or intersection information, etc. Precision maps may include basic road information, surrounding environment information, detailed road environment information, or dynamic road condition information. Detailed road environment information may include static information such as terrain elevation, curvature, lanes, lane centerlines, regulatory lines, road boundaries, road centerlines, traffic signs, road surface markings, road shape and height, and lane width.Dynamic road condition information may include traffic congestion, accident zones, construction zones, etc. The precision map may include information on the road surrounding environment rendered in 3D, geometric information such as road shape or facility structure, and semantic information such as traffic signs or lane markings.
[0075] The controller (780) may include at least one core capable of executing instructions. The controller (780) may execute instructions stored in the storage unit (770). The controller (780) may include a single processor or multiple processors.
[0076] FIG. 8 is a block diagram showing an exemplary computing device that can be used to implement the devices and methods described in the present disclosure.
[0077] The computing device (80) may include some or all of memory (800), a processor (820), storage (840), an input / output interface (860), and a communication interface (880). The computing device (80) may structurally and / or functionally include at least a part of the vehicle (70). The computing device (80) may be a stationary computing device such as a desktop computer, a server, an AI accelerator, etc., as well as a mobile computing device such as a laptop computer, a smartphone, etc. The computing device (80) may include any specialized hardware accelerator capable of processing operations on an artificial intelligence model in an efficient manner. For example, the computing device (80) may include a graphic processing unit (GPU), a tensor processing unit (TPU), or a neural processing unit (NPU).
[0078] The memory (800) may store a program that enables the processor (820) to perform a method or operation according to various embodiments of the present disclosure. For example, the program may include a plurality of instructions executable by the processor (820), and the aforementioned method(s) or operation(s) may be performed by executing the plurality of instructions by the processor (820).
[0079] The memory (800) may be a single memory or multiple memories. In this case, information necessary to perform a method or operation according to various embodiments of the present disclosure may be stored in a single memory or divided and stored in multiple memories. If the memory (800) is composed of multiple memories, the multiple memories may be physically separated.
[0080] The memory (800) may include at least one of volatile memory and non-volatile memory. Volatile memory includes Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), and non-volatile memory includes flash memory.
[0081] The processor (820) may include at least one core capable of executing at least one instruction. The processor (820) may execute instructions stored in memory (800). The processor (820) may be a single processor or multiple processors.
[0082] Storage (840) retains stored data even when power supplied to the computing device (80) is cut off. For example, storage (840) may include non-volatile memory and may include storage media such as magnetic tape, optical disk, and magnetic disk.
[0083] A program stored in storage (840) can be loaded into memory (800) before being executed by the processor (820). Storage (840) can store a file written in a programming language, and a program generated from the file by a compiler, etc., can be loaded into memory (800). Storage (840) can store data to be processed by the processor (820) and / or data processed by the processor (820).
[0084] The input / output interface (860) may provide an interface with input devices such as a keyboard, mouse, etc. and / or output devices such as a display device, printer, etc. The user may use an input device to trigger the execution of a program by the processor (820) and / or use an output device to check the processing results of the processor (820).
[0085] The communication interface (880) may provide access to an external network. For example, a computing device (80) may communicate with other devices (e.g., a vehicle (70)) using the communication interface (880). The communication interface (880) may include 10Base-T1S Ethernet and a wireless communication module (Wi-Fi, 5G).
[0086] Various embodiments of the systems and techniques described herein may be realized as digital electronic circuits, integrated circuits, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being implemented as one or more computer programs executable on a programmable system. A programmable system comprises a storage system, at least one input device, and at least one programmable processor (which may be a special-purpose processor or a general-purpose processor) coupled to receive data and instructions from and transmit data and instructions to at least one output device. Computer programs (which are also known as programs, software, software applications, or code) include instructions for the programmable processor and are stored on a "computer-readable recording medium."
[0087] Computer-readable recording media include all types of recording devices in which data that can be read by a computer system is stored. Such computer-readable recording media may be non-volatile or non-transitory media such as ROM, CD-ROM, magnetic tape, floppy disk, memory card, hard disk, magneto-optical disk, and storage device, and may also include transitory media such as data transmission media. Additionally, computer-readable recording media may be distributed across networked computer systems, and computer-readable code may be stored and executed in a distributed manner.
[0088] Although the flowcharts and timing diagrams in this specification describe each process as being executed sequentially, this is merely an illustrative explanation of the technical concept of one embodiment of the present disclosure. In other words, a person skilled in the art to which one embodiment of the present disclosure belongs may modify and adapt the flowcharts and timing diagrams in various ways, such as changing the order described in the flowcharts and timing diagrams or executing one or more of the processes in parallel, without departing from the essential characteristics of one embodiment of the present disclosure; therefore, the flowcharts and timing diagrams are not limited to a chronological order.
[0089] The above description is merely an illustrative explanation of the technical concept of the present embodiment, and a person skilled in the art to which the present embodiment belongs would be able to make various modifications and variations within the scope of the essential characteristics of the present embodiment. Accordingly, the present embodiments are intended to explain, not limit, the technical concept of the present embodiment, and the scope of the technical concept of the present embodiment is not limited by these embodiments. The scope of protection of the present embodiment shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present embodiment.
Claims
Claim 1 A method for controlling a vehicle, comprising: a process of analyzing the behavior of the vehicle based on learned behavior pattern data regarding the behavior of the vehicle, including one or more of steering angles or braking forces; a process of evaluating contextual appropriateness for the behavior of the vehicle; a process in which an upper controller performs global optimization for the behavior of the vehicle based on the result of analyzing the behavior of the vehicle and the contextual appropriateness evaluation; a process in which a lower controller performs local optimization for the behavior of the vehicle based on control values received from the upper controller; and a process of controlling the vehicle based on one or more of the steering angles or braking forces optimized by the global optimization and the local optimization. Claim 2 In claim 1, the learned behavioral pattern data is data obtained by collecting internal data related to the vehicle and external data related to the vehicle, and learning a stable behavioral pattern or a dangerous behavioral pattern based on the rate of change of steering angle or braking force. Claim 3 A method according to claim 1, wherein the process of analyzing the behavior of the vehicle based on learned behavior pattern data of the vehicle comprises: a process of collecting internal data and external data of the vehicle in real time; and a process of classifying the current behavior state of the vehicle by comparing the collected data with the learned behavior pattern data. Claim 4 A method according to claim 1, wherein the process of evaluating contextual appropriateness for the behavior of the vehicle comprises: a process of collecting external data including one or more of a road context index, an environment context index, or a traffic context index based on the driving of the vehicle; and a process of calculating an appropriateness score based on the external data. Claim 5 A method according to claim 1, wherein the process of performing global optimization of the behavior of the vehicle based on the result of the upper controller analyzing the behavior of the vehicle and the contextual appropriateness evaluation comprises: a process of calculating an integrated index using the risk based on the analysis result of the behavior of the vehicle and the contextual appropriateness; a process of setting a control target for steering or braking of the vehicle based on the integrated index; and a process of transmitting a control target value to the lower controller. Claim 6 A method according to claim 1, wherein the process of performing local optimization for the behavior of the vehicle based on a control value received by the lower controller from the upper controller comprises: a process of performing detailed control for each zone of the vehicle; and a process of transmitting information about the state of each zone of the vehicle to the upper controller. Claim 7 A device for controlling a vehicle, comprising: at least one memory for storing instructions; and at least one processor, wherein the at least one processor executes the instructions to analyze the behavior of the vehicle based on learned behavior pattern data regarding the behavior of the vehicle, including one or more of steering angles or braking forces, evaluates contextual appropriateness for the behavior of the vehicle, performs global optimization for the behavior of the vehicle based on the result of the analysis of the behavior of the vehicle by an upper controller and the contextual appropriateness evaluation, performs local optimization for the behavior of the vehicle by a lower controller based on a control value received from the upper controller, and controls the vehicle based on one or more of the steering angles or braking forces optimized by the global optimization and the local optimization. Claim 8 A device according to claim 7, for evaluating contextual suitability for the behavior of the vehicle, which collects external data including one or more of a road context index, an environment context index, or a traffic context index based on the driving of the vehicle, and calculates a suitability score based on the external data. Claim 9 A device according to claim 7, wherein the upper controller calculates an integrated index using the risk level and context suitability based on the analysis result of the vehicle's behavior, sets a control target for steering or braking of the vehicle based on the integrated index, and transmits the control target value to the lower controller to perform global optimization of the vehicle's behavior. Claim 10 In claim 7, the lower controller performs detailed control for each zone of the vehicle and transmits information about the state of each zone of the vehicle to the upper controller to perform local optimization.
