Apparatus and method for controlling braking force of vehicle

Abstract

Provided is an apparatus for controlling braking force of a vehicle. The apparatus includes a sensor device that obtains information about an image in front of the vehicle and travel information of the vehicle, and a controller that determines a road surface state including a left road surface state and a right road surface state based on the information about the image and the travel information, and controls a braking force of a left wheel of the vehicle and a braking force of a right wheel of the vehicle based on the left road surface state and the right road surface state of the vehicle, respectively.

Description

[0001] Cross-references to related applications

[0002] This application claims priority to Korean Patent Application No. 10-2021-0175062, filed on December 8, 2021, with the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to apparatus and methods for controlling the braking force of a vehicle. Background Technology

[0004] Generally speaking, an Automatic Emergency Braking System (AEBS) is a system that assists the driver in predicting and determining the risk of a collision with a vehicle, pedestrian, or obstacle by sensing the surrounding environment and immediately applying a braking command to automatically avoid the collision.

[0005] When a target that is predicted to collide is within the route, AEBS will apply a warning or apply braking if it is less than or equal to a predefined time-to-collision (TTC) threshold. When applying braking, AEBS calculates target values ​​for various levels of braking commands, such as partial braking and full braking.

[0006] However, the current AEBS braking target value is calculated based on the friction coefficient of asphalt roads. Therefore, since the braking distance is longer when the road surface friction coefficient is reduced according to weather or driving conditions, it is difficult to avoid a collision when braking is applied based on a fixed TTC threshold. Furthermore, when the friction coefficients of the road surfaces traversed by the left and right wheels differ, such as potholes (or puddles) or partial freezing that cause lane deviation, there is a risk of oversteer when emergency braking is applied with the same braking force. Summary of the Invention

[0007] This disclosure aims to solve the aforementioned problems in the prior art while fully maintaining the advantages achieved by the prior art.

[0008] This disclosure provides apparatus and methods for controlling the braking force of a vehicle to develop automatic braking systems and driver assistance systems for advancing fully automated driving in various road conditions, and to apply active safety and collision avoidance systems based on image and deep learning in various road conditions.

[0009] The technical problems to be solved by this disclosure are not limited to those described above, and any other technical problems not mentioned herein will be clearly understood by those skilled in the art to which this disclosure pertains based on the following description.

[0010] According to one aspect of this disclosure, an apparatus for controlling the braking force of a vehicle may include: a sensor device for obtaining information about an image of the front of the vehicle and driving information of the vehicle; and a controller for determining road conditions, including left road conditions and right road conditions, based on the information about the image and the driving information, and controlling the braking force of the left wheel and the braking force of the right wheel of the vehicle based on the left road conditions and the right road conditions of the vehicle, respectively.

[0011] In one embodiment, the controller can use a convolutional neural network (CNN) to determine the road surface conditions and the drivable area of ​​the vehicle based on information about the image.

[0012] In one embodiment, the controller can divide the image into a left image and a right image, and determine the road surface condition of each in the left and right images based on information about the images.

[0013] In one embodiment, the controller can determine the road surface condition using a deep neural network (DNN) based on driving information obtained during a predetermined time period.

[0014] In one embodiment, the controller can determine the left road surface state of the vehicle using a DNN based on driving information obtained by an acceleration sensor, a yaw rate sensor, and a left wheel speed sensor during a predetermined time period, and can also determine the right road surface state of the vehicle using a DNN based on driving information obtained by an acceleration sensor, a yaw rate sensor, and a right wheel speed sensor during a predetermined time period.

[0015] In one embodiment, the controller can compare the time to collision (TTC) based on the vehicle's left and right road conditions with a reference TTC to determine the collision risk.

[0016] In one embodiment, the controller can compare the braking amount of the left wheel and the right wheel of the vehicle based on the collision risk with the required deceleration, and can select the smaller value between the braking amount of the left wheel and the right wheel as the braking force of the left wheel and the right wheel.

[0017] According to another aspect of this disclosure, a method for controlling the braking force of a vehicle may include: obtaining information about an image of the front of the vehicle and driving information of the vehicle; determining road conditions, including left road conditions and right road conditions, based on the information about the image and the driving information; and controlling the braking force of the left wheel and the braking force of the right wheel of the vehicle based on the left road conditions and the right road conditions of the vehicle, respectively.

[0018] In one embodiment, determining road conditions based on information about an image and driving information may include using a convolutional neural network (CNN) to determine the road conditions and the drivable area of ​​a vehicle based on information about the image.

[0019] In one embodiment, determining the road surface condition based on information about the image and driving information may include: dividing the image into a left image and a right image, and determining the road surface condition of each of the left and right images based on information about the image.

[0020] In one embodiment, determining road conditions based on information about images and driving information may include using a deep neural network (DNN) to determine road conditions based on driving information obtained during a predetermined time period.

[0021] In one embodiment, determining the road surface condition based on information about the image and driving information may include: determining the left road surface condition of the vehicle using a DNN based on driving information obtained by an acceleration sensor, a yaw rate sensor, and a left wheel speed sensor during a predetermined time period, and determining the right road surface condition of the vehicle using a DNN based on driving information obtained by an acceleration sensor, a yaw rate sensor, and a right wheel speed sensor during a predetermined time period.

[0022] In one embodiment, controlling the braking force of the left wheel and the right wheel of a vehicle based on the left and right road conditions of the vehicle, respectively, includes comparing the time to collision (TTC) based on the left and right road conditions of the vehicle with a reference TTC to determine the collision risk.

[0023] In one embodiment, controlling the braking force of the left wheel and the right wheel of a vehicle based on the left and right road conditions of the vehicle, respectively, may include: comparing the braking amount of the left wheel and the right wheel based on the collision risk with the required deceleration, and selecting the smaller value between the braking amount of the left wheel and the right wheel as the braking force of the left wheel and the right wheel, respectively. Attached Figure Description

[0024] The above and other objects, features and advantages of this disclosure will become clearer from the following detailed description given in conjunction with the accompanying drawings, in which:

[0025] Figure 1 This is a block diagram illustrating a device for controlling the braking force of a vehicle according to an embodiment of the present disclosure;

[0026] Figure 2 This is a diagram illustrating the operation of an image sensor according to an embodiment of the present disclosure;

[0027] Figure 3This is a diagram illustrating the operation of vehicle sensors according to embodiments of the present disclosure; and

[0028] Figure 4 This is a flowchart illustrating a method for controlling the braking of a vehicle according to an embodiment of the present disclosure. Detailed Implementation

[0029] In the following description, various embodiments of the present disclosure will be illustrated with reference to the accompanying drawings. However, it should be understood that this is not intended to limit the present disclosure to specific implementations, and includes various modifications, equivalents, and / or substitutions to the embodiments of the present disclosure.

[0030] It should be understood that the various embodiments of this disclosure and the terminology used therein are not intended to limit the technical features set forth herein to the particular embodiments, but rather to include various changes, equivalents or substitutions to the corresponding embodiments.

[0031] Regarding the description of the accompanying drawings, similar reference numerals may be used to refer to similar or related elements. It should be understood that the singular form of the noun corresponding to an item may include one or more things, unless the relevant context clearly indicates otherwise.

[0032] As used herein, each of the expressions “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C” and “at least one of A, B or C” may include any and all combinations of one or more of the items listed together with the corresponding expression in the expression.

[0033] Terms such as “first” and “second” or “first” and “second” can be used to simply distinguish corresponding components from other components without limiting the components in any other way (e.g., in terms of importance or order). It should be understood that if any (e.g., first) component is mentioned as being “coupled,” “coupled to,” “connected to,” or “connected to” another (e.g., second) component with or without the use of the terms “operably” or “communically”, it means that the component can be coupled to the other component directly (e.g., wired), wirelessly, or via a third component.

[0034] Figure 1 This is a block diagram illustrating a device for controlling the braking force of a vehicle according to an embodiment of the present disclosure. Figure 2 This is a diagram illustrating the operation of an image sensor according to an embodiment of the present disclosure. Figure 3 This is a diagram illustrating the operation of vehicle sensors according to an embodiment of the present disclosure.

[0035] refer to Figure 1The apparatus for controlling the braking force of a vehicle according to embodiments of the present disclosure may include an image sensor 110, a vehicle sensor 120, a radar sensor 130, a storage device 140, and a controller 150.

[0036] Image sensor 110 can acquire information about an image of the front of the main vehicle. Image sensor 110 may include one or more cameras. Here, the cameras may be installed in the window glass of the main vehicle, or in the front panel, interior mirror or roof panel of the main vehicle to be exposed to the outside, and may be installed in the license plate, grille or logo at the front of the main vehicle.

[0037] Vehicle sensor 120 can obtain driving information of the main vehicle. Vehicle sensor 120 may include acceleration sensor 121, yaw rate sensor 122, right wheel speed sensor 123 and left wheel speed sensor 124.

[0038] Accelerometer 121 can measure the acceleration of the main vehicle; it can sense longitudinal, lateral, and vertical acceleration. Accelerometer 121 can be a sensor that processes output signals and measures dynamic forces such as the acceleration of an object, vibration, or impact. Accelerometer 121 can be implemented as an electronic accelerometer or a voltage accelerometer. For reference, an electronic accelerometer uses the electromotive force of a magnet and coil to measure the acceleration corresponding to the amount of movement of the moving body, and a voltage accelerometer uses a piezoelectric element that receives pressure to generate a voltage to measure the acceleration corresponding to the applied pressure.

[0039] The yaw rate sensor 122 can be a sensor that detects the angular velocity of rotation of a vehicle in the vertical direction. When an alternating current (AC) voltage is applied to the vibrator, the vibrator deforms and vibrates. Ultimately, the vibrator always vibrates left and right at a constant frequency. The yaw rate sensor 122 can utilize the following principle: when the vibrator rotates at a constant angular velocity in this state, the yaw rate sensor 122 is tilted at a right angle to the direction of vibration applied by the Coriolis force, and outputs an AC voltage. For example, the yaw rate sensor 122 can be mounted in the steering wheel of the main vehicle to detect the yaw rate value in real time.

[0040] The right wheel speed sensor 123 can be installed on the inside of the right front wheel and right rear wheel of the main vehicle to detect the rotational speed of the right wheel of the main vehicle.

[0041] The left wheel speed sensor 124 can be installed on the inside of the left front wheel and left rear wheel of the main vehicle to detect the rotational speed of the left wheel of the main vehicle.

[0042] In other words, the right wheel speed sensor 123 and the left wheel speed sensor 124 can be installed in the four left and right wheels of the main vehicle, respectively, to sense the rotational speed of the wheels as a sensor and the change of magnetic lines of force in the tone wheel, and input the sensed information into the computer.

[0043] The sensing data sensed by the acceleration sensor 121, yaw rate sensor 122, right wheel speed sensor 123 and left wheel speed sensor 124 can be stored in the storage device 140.

[0044] The radar sensor 130 can acquire data about obstacles in front of the main vehicle. Acquiring this data can be achieved using only one of various devices (such as LiDAR, visible light vision, infrared sensors, or ultrasonic sensors), or a combination thereof.

[0045] The controller 150 can determine the road surface condition based on image information and driving information, and can control the braking force of the left wheel and the right wheel of the main vehicle based on the left and right road surface conditions of the main vehicle, respectively. The controller 150 may include a first convolutional neural network (CNN) 151, a second CNN 152, a first deep neural network (DNN) 153, a second DNN 154, a collision calculation device 155, a risk determination device 156, a deceleration calculation device 157, and a braking calculation device 158.

[0046] refer to Figure 2 The first CNN 151 can obtain information from image information (e.g., Figure 2 The depth-based region features (A1, B1, and C1) are extracted to determine the road surface condition, such as roughness or unevenness. The first CNN 151 can use a depth estimation network, such as a single-depth network, to extract depth information from image information.

[0047] The first CNN 151 can divide an image into a left image and a right image after the depth information has been extracted (e.g., Figure 2 The first CNN 151 can output road surface features in real time from the left image (A2, B2, and C2), and can determine the road surface state of each of the left and right images. It can also output road surface features in real time from the right image (A2, B2, and C2), such as the roughness of the road surface that the left wheel of the main vehicle will pass over, or the unevenness of the road surface such as puddles that appear when it is excavated).

[0048] The second CNN 152 can determine which part of the left image, from which the depth image was extracted by the first CNN 151, will be identified as the road surface that the left wheel can drive on, and it can also determine which part of the right image will be identified as the road surface that the right wheel can drive on. The second CNN 152 can use semantic segmentation techniques to determine the drivable area of ​​the main vehicle.

[0049] The first DNN 153 can determine the road surface condition of the left area of ​​the main vehicle based on the driving information obtained by the vehicle sensor 120. The first DNN 153 can receive data from the past approximately 1.5 seconds to approximately 2 seconds (e.g., corresponding to a predetermined time period) that has been learned and stored in the storage device 140, including data from the acceleration sensor 121, the yaw rate sensor 122, and the left wheel speed sensor 124, and can determine the road surface condition of the left area of ​​the main vehicle.

[0050] The second DNN 154 can determine the road condition of the right region of the main vehicle based on the driving information obtained by the vehicle sensor 120. The second DNN 154 can receive data from the past approximately 1.5 seconds to approximately 2 seconds (e.g., corresponding to a predetermined time period) that has been learned and stored in the storage device 140, including data from the acceleration sensor 121, the yaw rate sensor 122, and the right wheel speed sensor 123, and can determine the road condition of the right region of the main vehicle.

[0051] For example, when the left wheel of the main vehicle is traveling on a muddy road and the right wheel of the main vehicle is traveling on a dry road, the controller 150 can determine the road condition of the left or right region of the main vehicle due to the differences between the data measured by the acceleration sensor, yaw rate sensor and wheel speed sensor when the main vehicle is traveling on a muddy road and when the main vehicle is traveling on a dry road.

[0052] The collision calculation device 155 can calculate the time-to-collision (TTC) between the main vehicle and the obstacle based on the distance between the main vehicle and the obstacle detected by the radar sensor 130. In other words, the collision calculation device 155 can obtain the position and velocity information of the obstacle based on the information about the obstacle detected by the radar sensor 130, and can determine the relative distance and relative velocity between the main vehicle and the obstacle based on the obtained position and velocity information of the obstacle, thereby obtaining the TTC between the main vehicle and the obstacle based on the obtained relative distance and relative velocity.

[0053] The risk assessment device 156 can output the braking amounts of the left and right wheels based on the speed of the right wheel of the main vehicle via the right wheel speed sensor 123, the speed of the left wheel of the main vehicle via the left wheel speed sensor 124, the TTC calculated by the collision calculation device 155, the road surface condition output from the first CNN 151, the road surface condition of the left region of the main vehicle output from the first DNN 153, and the road surface condition of the right region of the main vehicle output from the second DNN 154, depending on the road surface condition and collision risk.

[0054] For example, there can be a TTC calculated based on the relative distance between the main vehicle and the obstacle, and there can be TTCs calculated differently based on road conditions such as wet, rough, dry, or icy conditions. Therefore, when the TTC calculated based on the relative distance between the main vehicle and the obstacle is 0.8 seconds and the TTC based on road conditions is 0.7 seconds, the risk assessment device 156 can determine the existence of a collision risk based on the road conditions. Furthermore, when the TTC is 0.7 seconds in a dry road condition, since the braking distance is longer in a wet road condition, the risk assessment device 156 can set the TTC to a higher value, such as 1.2 seconds. In this case, when the road conditions of the left and right wheels are different, for example, when the left wheel is on a dry road and the right wheel is on a wet road, the risk assessment device 156 can set different braking amounts for the left and right wheels based on the different road conditions.

[0055] The deceleration calculation device 157 can calculate the required deceleration to slow down and avoid collisions between the main vehicle and obstacles. The deceleration calculation device 157 can calculate the required deceleration, where the required deceleration [m / s] 2 ] = -(relative velocity) 2 / (2×relative distance).

[0056] At this time, although there are no obstacles in front of the main vehicle, there may be no drivable area. For example, since the main vehicle should not travel beyond a certain distance when the width of the road is less than that of the main vehicle at a certain distance in front of it, the deceleration calculation device 157 can calculate the relative distance as a certain distance that the main vehicle can travel in order to calculate the required deceleration.

[0057] The braking calculation device 158 can compare the required deceleration calculated by the deceleration calculation device 157 with the braking amounts of the left and right wheels output from the risk determination device 156, and can select the smaller value as the final braking force. In other words, the braking calculation device 158 can compare the required deceleration with the braking amount of the left wheel to select the smaller value as the final braking force of the left wheel, and can compare the required deceleration with the braking amount of the right wheel to select the smaller value as the final braking force of the right wheel. At this time, since the required deceleration, the braking amount of the left wheel, and the braking amount of the right wheel are output as negative values, if a smaller value exists, the braking force can be increased.

[0058] Therefore, when the road conditions for the left and right wheels differ, the braking forces of the left and right wheels can be output differently. For example, when the entire road surface is not icy and only the road surface for the left wheels is icy while that for the right wheels is not, the main vehicle may spin due to the lower friction of the left wheel caused by the ice when the same braking force is applied to control both wheels, potentially leading to an accident. Therefore, by changing the braking force of the left wheel on an icy road surface and the braking force of the right wheel on a non-icy road surface, the braking calculation device 158 can prevent the main vehicle from spinning during braking to prevent an accident.

[0059] Furthermore, controller 150 can control at least one other component (e.g., hardware or software component) of the means for controlling the braking force of the vehicle, and can perform various data processing or calculations. According to one embodiment, as at least part of the data processing or calculation, controller 150 can store commands or data received from another component (e.g., a sensor) in volatile memory, can process the commands or data stored in volatile memory, and can store the result data in non-volatile memory. According to one embodiment, controller 150 may include a main processor (e.g., a central processing unit or application processor), or an auxiliary processor (e.g., a graphics processing unit, image signal processor, sensor hub processor, communication processor) that can operate independently or in conjunction with the main processor. For example, the auxiliary processor may be configured to use lower power than the main processor or be dedicated to a specific function when controller 150 includes both the main processor and the auxiliary processor. The auxiliary processor may be implemented independently of the main processor or as part of the main processor.

[0060] In addition, storage device 140 may store instructions, control command codes, control data, or user data for controlling devices used to control the braking force of a vehicle. For example, storage device 140 may include at least one of an application program, an operating system (OS), middleware, or a device driver. Storage device 140 may include either volatile memory or non-volatile memory. Volatile memory may include dynamic random access memory (DRAM), static RAM (SRAM), synchronous DRAM (SDRAM), phase-change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (RRAM), ferroelectric RAM (FeRAM), etc. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc. Storage device 140 may also include non-volatile media such as hard disk drives (HDDs), solid-state drives (SSDs), embedded multimedia cards (eMMC), or universal flash memory (UFS).

[0061] In the following text, reference will be made to Figure 4 A method for controlling the braking force of a vehicle according to another embodiment of the present disclosure is described in detail.

[0062] Figure 4 This is a flowchart illustrating a method for controlling the braking of a vehicle according to an embodiment of the present disclosure.

[0063] The following assumes that it is used for control Figure 1 The vehicle's braking system Figure 4 The processing.

[0064] First, the first CNN 151 can obtain information from image information (e.g., Figure 2 The first CNN 151 can extract depth information from image information by extracting region features based on depth estimation from A1, B1 and C1 in the image to determine the road surface condition, such as the roughness or unevenness of the road surface, and the first CNN 151 can extract depth information from image information using a depth estimation network such as a single depth network.

[0065] Next, the first CNN 151 can divide the image from which depth information has been extracted into a left image and a right image (e.g., Figure 2In S110, the second CNN 152 determines which part of the left image (A2, B2, and C2) will be identified as the road surface condition for each of the left and right images. The first CNN 151 can output road surface features in real-time based on the left image, such as the roughness of the road surface that the left wheel of the main vehicle will traverse, or the unevenness of the road surface, such as puddles, when it is excavated. It can also output road surface features in real-time based on the right image, such as the roughness of the road surface that the right wheel of the vehicle will traverse, or the unevenness of the road surface, such as puddles, when it is excavated. In S110, the second CNN 152 can determine which part of the left image, from which the depth image has been extracted by the first CNN 151, will be identified as the road surface that the left wheel can traverse, and it can determine which part of the right image will be identified as the road surface that the right wheel can traverse, thereby using semantic segmentation techniques to determine the drivable area of ​​the main vehicle.

[0066] Next, the first DNN 153 can determine the road condition of the left area of ​​the main vehicle based on the driving information obtained through the vehicle sensor 120, and can receive data from the past approximately 1.5 seconds to approximately 2 seconds stored in the storage device 140, including data from the acceleration sensor 121, the yaw rate sensor 122, and the left wheel speed sensor 124, to determine the road condition of the left area of ​​the main vehicle. The second DNN 154 can determine the road condition of the right area of ​​the main vehicle based on the driving information obtained through the vehicle sensor 120, and can receive data from the past approximately 1.5 seconds to approximately 2 seconds stored in the storage device 140, including data from the acceleration sensor 121, the yaw rate sensor 122, and the right wheel speed sensor 123, to determine the road condition of the right area of ​​the main vehicle.

[0067] In S130, the collision calculation device 155 can calculate the time of collision (TTC) between the main vehicle and the obstacle based on the distance between the main vehicle and the obstacle detected by the radar sensor 130.

[0068] In S140, the risk determination device 156 can output the braking amount of the left and right wheels based on the speed of the right wheel of the main vehicle via the right wheel speed sensor 123, the speed of the left wheel of the main vehicle via the left wheel speed sensor 124, the TTC calculated by the collision calculation device 155, the road surface state output from the first CNN 151, the road surface state of the left region of the main vehicle output from the first DNN 153, and the road surface state of the right region of the main vehicle output from the second DNN 154, depending on the road surface state and the collision risk.

[0069] In S150, the deceleration calculation device 157 can calculate the required deceleration to slow down and avoid collisions between the main vehicle and obstacles.

[0070] In S160, the braking calculation device 158 can compare the required deceleration calculated by the deceleration calculation device 157 with the braking amount of the left wheel and the braking amount of the right wheel output from the risk determination device 156, and can select the smaller value as the final braking force.

[0071] As described above, according to embodiments of this disclosure, the means for controlling the braking of a vehicle can be an automatic braking system for promoting fully automated driving in various road conditions, as well as a driver assistance system that can apply active safety and collision avoidance systems based on images and deep learning in various road conditions, and can ensure behavioral stability through differential emergency braking when road conditions are partially different, so as to prevent accidents from occurring in severe weather conditions where the occurrence of accidents increases, thereby preventing loss of life and property.

[0072] Various embodiments of this disclosure can be implemented as software (e.g., a program or application) including instructions stored in a machine-readable storage medium (e.g., memory). For example, a machine can invoke at least one of one or more instructions stored in the storage medium and can execute the invoked instructions. This causes the machine to operate to perform at least one function according to the invoked instruction. One or more instructions may include code generated by a compiler or code executable by an interpreter.

[0073] Machine-readable storage media may be provided in the form of non-transitory storage media. Here, the term "non-transitory" simply means that the storage medium is a tangible device and does not include signals (e.g., electromagnetic waves), but this term does not distinguish between cases where data is stored semi-permanently in the storage medium and cases where data is temporarily stored in the storage medium.

[0074] According to embodiments, methods according to various embodiments disclosed herein can be included and provided in a computer program product. The computer program product can be traded as a product between a seller and a buyer. The computer program product can be distributed in the form of a machine-readable storage medium (e.g., an optical disc read-only memory (CD-ROM)) or via an app store (e.g., the Play Store). TM The computer program product may be distributed online (e.g., downloaded or uploaded) or directly between two user devices (e.g., smartphones). If distributed online, at least a portion of the computer program product may be temporarily generated or at least temporarily stored in a machine-readable storage medium (e.g., the memory of a manufacturer's server, an app store's server, or a relay server).

[0075] According to various embodiments, each component of the above-described components (e.g., a module or a program) may include a single entity or multiple entities, and some of the multiple entities may be divided and arranged in another component.

[0076] According to various embodiments, one or more of the components or operations mentioned above may be omitted, or one or more other components or operations may be added.

[0077] Alternatively or additionally, multiple components (e.g., modules or programs) can be integrated into a single component. In this case, the integrated component can still perform one or more functions of each of the multiple components in the same or similar manner as they were performed by the corresponding component of the multiple components before integration.

[0078] According to various embodiments, operations performed by a module, program, or other component may be performed sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations may be performed in a different order or omitted, or one or more other operations may be added.

[0079] This technology can be used to advance fully automated driving, including automatic braking systems and driver assistance systems in various road conditions. It can apply active safety and collision avoidance systems based on images and deep learning in various road conditions, and can ensure behavioral stability through differential emergency braking when road conditions are partially different, thereby preventing accidents in severe weather conditions where the occurrence of accidents increases, and thus preventing loss of life and property.

[0080] In addition, various effects that can be directly or indirectly determined through this disclosure may be provided.

[0081] In the foregoing, although the present disclosure has been described with reference to exemplary embodiments and accompanying drawings, the present disclosure is not limited thereto, but can be modified and altered by those skilled in the art to which the present disclosure pertains without departing from the spirit and scope of the claims to which the appended claims are made.

[0082] Therefore, the embodiments of this disclosure are not intended to limit the technical spirit of this disclosure, but are for illustrative purposes only. The scope of this disclosure should be interpreted based on the appended claims, and all technical ideas within the scope of the claims should be included within the scope of this disclosure.

Claims

1. A device for controlling the braking force of a vehicle, the device comprising: Sensor devices are configured to acquire information about the front of the vehicle and the vehicle's driving information; as well as The controller is configured to: determine road conditions, including left and right road conditions, based on information about the image and the driving information, and control the braking force of the left wheel and the braking force of the right wheel of the vehicle based on the left and right road conditions of the vehicle, respectively. Specifically, the controller compares the time-to-collision (TTC) based on the vehicle's left and right road surface states with a reference TTC to determine the collision risk. The controller compares the braking amount of the vehicle's left wheel and right wheel based on the collision risk with the required deceleration, and selects the smaller value of the braking force of the left wheel and the braking force of the right wheel based on the comparison.

2. The apparatus according to claim 1, wherein, The controller uses a convolutional neural network (CNN) to determine the road surface condition and the drivable area of ​​the vehicle based on information about the image.

3. The apparatus according to claim 2, wherein, The controller divides the image into a left image and a right image, and determines the road surface condition of each of the left and right images based on information about the images.

4. The apparatus according to claim 1, wherein, The controller determines the road surface condition using a deep neural network (DNN) based on the driving information obtained during a predetermined time period.

5. The apparatus according to claim 4, wherein, The controller determines the left road surface state of the vehicle using the DNN based on the driving information obtained by the acceleration sensor, yaw rate sensor and left wheel speed sensor during the predetermined time period, and determines the right road surface state of the vehicle using the DNN based on the driving information obtained by the acceleration sensor, yaw rate sensor and right wheel speed sensor during the predetermined time period.

6. A method for controlling the braking force of a vehicle, the method comprising: Obtain information about the image ahead of the vehicle and the vehicle's driving information; The road conditions, including the left and right road conditions, are determined based on information about the image and the driving information. as well as The braking force of the left wheel and the braking force of the right wheel of the vehicle are controlled based on the left and right road conditions of the vehicle, respectively. The method of controlling the braking force of the left wheel and the braking force of the right wheel of the vehicle based on the left and right road conditions of the vehicle, respectively, includes: The collision time-to-time (TTC) based on the vehicle's left and right road conditions is compared with a reference TTC to determine the collision risk, and The method of controlling the braking force of the left wheel and the braking force of the right wheel of the vehicle based on the left and right road conditions of the vehicle, respectively, includes: The braking amounts of the vehicle's left and right wheels, based on the collision risk, are compared with the required deceleration, and the smaller values ​​of the braking force of the left and right wheels are selected based on the comparison.

7. The method according to claim 6, wherein, Determining the road surface condition based on information about the image and the driving information includes: The road surface condition and the drivable area of ​​the vehicle are determined by a convolutional neural network (CNN) based on information about the image.

8. The method according to claim 7, wherein, Determining the road surface condition based on information about the image and the driving information includes: The image is divided into a left image and a right image, and the road surface condition of each of the left and right images is determined based on information about the images.

9. The method according to claim 6, wherein, Determining the road surface condition based on information about the image and the driving information includes: The road surface condition is determined by a deep neural network (DNN) based on the driving information obtained during a predetermined time period.

10. The method according to claim 9, wherein, Determining the road surface condition based on information about the image and the driving information includes: The DNN determines the left road surface state of the vehicle based on the driving information obtained by the acceleration sensor, yaw rate sensor and left wheel speed sensor during the predetermined time period, and determines the right road surface state of the vehicle based on the driving information obtained by the acceleration sensor, yaw rate sensor and right wheel speed sensor during the predetermined time period.

Images