Vehicle and method of controlling the vehicle

Abstract

The present application relates to a kind of vehicle and the method for controlling the vehicle, the vehicle includes: sensor part, it is configured to obtain the occupancy information of the area around vehicle and the speed of vehicle;Camera, it is configured to obtain the surrounding image of vehicle;And controller, it is configured to: according to the movement of vehicle, form map information based on occupancy information;It is determined whether there is barrier in the surrounding of vehicle based on map information and surrounding image;In response to barrier existence, based on the existence of barrier and the collision probability of vehicle according to the speed of vehicle and map information, control vehicle.

Description

[0001] Cross-reference to related applications

[0002] This application claims priority and benefit to Korean Patent Application No. 10-2020-0090087, filed on July 21, 2020, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This invention relates to a vehicle that performs parking collision avoidance control during parking and a method for controlling the vehicle. Background Technology

[0004] The statements in this section are provided only as background information relating to the invention and do not constitute prior art.

[0005] Autonomous driving technology for vehicles is designed to drive vehicles autonomously by recognizing road conditions, without requiring a driver to control the brakes, steering wheel, accelerator pedal, etc.

[0006] Autonomous driving technology is a key technology for realizing intelligent vehicles. These technologies include highway driving assist (HAD) for automatically maintaining distance between vehicles; blind spot detection (BSD) that issues audible warnings when reversing by detecting surrounding vehicles; automatic emergency braking (AEB) that activates the braking system when no vehicle is detected in front; lane departure warning system (LDWS); lane maintenance assistance system (LKAS) that prevents vehicles from leaving their lanes without activating turn signals; lane maintenance assistance system (LKAS) to prevent vehicles from leaving their lanes without turn signals; advanced smart cruise control (ASCC) that maintains distance between vehicles while traveling at a specified speed; traffic jam assist (TJA); and parking collision-avoidance assist (PCA), among others.

[0007] Specifically, regarding PCA, research has been actively conducted on sensors and control logic used for side collision avoidance assist. Summary of the Invention

[0008] The present invention provides a vehicle and a method for controlling the vehicle, wherein the vehicle is able to prevent erroneous braking in a parking collision avoidance assist (PCA) system by estimating the position of obstacles using ultrasonic sensors and cameras located in the vehicle.

[0009] Other aspects of the invention will be set forth in part in the description which follows, and will be apparent in part from the description, or may be learned by practice of the invention.

[0010] One aspect of the present invention provides a vehicle, the vehicle comprising: a sensor unit configured to acquire occupancy information of an area surrounding the vehicle and the vehicle speed; a camera configured to acquire images of the vehicle's surroundings; and a controller configured to: generate map information based on the occupancy information according to the vehicle's movement; determine whether an obstacle exists around the vehicle based on the map information and the surrounding images; and control the vehicle based on the existence of the obstacle and a collision probability of the vehicle derived from the vehicle speed and the map information in response to the existence of the obstacle.

[0011] The controller can form map information by assigning a first weight to the occupancy information of a first area measured in real time and assigning a second weight greater than the first weight to the occupancy information of a second area measured previously.

[0012] The controller can generate map information by assigning a third weight to the occupancy information of a third area that corresponds to a region without obstacles.

[0013] The controller can classify each pixel in an image into one of three categories: space, low obstacle, and normal obstacle, based on the surrounding image.

[0014] The controller can be configured to: determine the collision time between the vehicle and the obstacle, and stop the vehicle when the collision probability of the vehicle exceeds a predetermined reference value and the obstacle corresponds to the normal obstacle.

[0015] The controller can be configured to stop the vehicle after a predetermined time from the detection of the obstacle when the vehicle's collision probability exceeds a predetermined reference value and the obstacle corresponds to the low obstacle.

[0016] The controller can be configured to: determine the collision time between the vehicle and the obstacle, and compare the collision time with a reference braking time corresponding to the vehicle's speed to determine the vehicle's braking moment.

[0017] The controller can determine occupancy information corresponding to obstacles and pixels included in the surrounding image, and form map information based on the covariance of the occupancy information and the covariance of the pixels.

[0018] The vehicle may further include an output device, wherein the controller may output a warning signal to the output device based on the vehicle's collision probability.

[0019] The controller can determine the probability of a vehicle collision by comparing a reference time corresponding to the vehicle's speed with the collision time between the vehicle and the obstacle.

[0020] The vehicle may further include a braking unit, wherein the controller can control the braking unit based on the vehicle's collision probability.

[0021] Another aspect of the present invention provides a method for controlling a vehicle, the method comprising: acquiring occupancy information of the area surrounding the vehicle and the vehicle speed; acquiring an image of the vehicle's surroundings; forming map information based on the occupancy information and the vehicle's movement; determining whether an obstacle exists around the vehicle based on the map information and the surrounding image; and controlling the vehicle in response to the presence of an obstacle, based on the presence of the obstacle and a collision probability of the vehicle derived from the vehicle speed and the map information.

[0022] The process of generating map information may include: generating map information by assigning a first weight to the occupancy information of a first area measured in real time; and assigning a second weight, which is greater than the first weight, to the occupancy information of a second area measured previously.

[0023] The formation of map information may include: forming map information by assigning a third weight to the occupancy information corresponding to a third area without obstacles.

[0024] The information used to form the map may include classifying each pixel in the image as one of three types: space, low obstacles, and normal obstacles, based on the surrounding image.

[0025] Controlling the vehicle may include: determining the collision time between the vehicle and an obstacle, and stopping the vehicle when the probability of collision exceeds a predetermined reference value and the obstacle corresponds to the normal obstacle.

[0026] Controlling the vehicle may include stopping the vehicle after a predetermined time from the detection of the obstacle when the vehicle's collision probability exceeds a predetermined reference value and the obstacle corresponds to the low obstacle.

[0027] Controlling the vehicle may include: determining the collision time between the vehicle and an obstacle, and comparing the collision time with a reference braking time corresponding to the vehicle's speed to determine the vehicle's braking moment.

[0028] Forming map information may include: determining occupancy information corresponding to obstacles and pixels included in the surrounding image, and forming map information based on the covariance of the occupancy information and the covariance of the pixels.

[0029] Another aspect of the present invention provides a vehicle comprising: an ultrasonic sensor configured to acquire occupancy information of a region surrounding the vehicle based on ultrasonic signals; a wheel speed sensor configured to acquire the speed of the vehicle; a camera configured to acquire images of the vehicle's surroundings; and at least one processor configured to: assign occupancy probabilities corresponding to the occupancy information; determine the occupancy probability of a previously measured region by assigning a first weight to the occupancy information of a first region measured in real time using a time slice measurement model determined based on the vehicle's speed, assigning a second weight greater than the first weight to the occupancy information of a previously measured second region, and assigning a third weight to the occupancy information corresponding to a third region to reduce the occupancy probability of the third region; determine coordinate information corresponding to the surrounding images and the vehicle; determine an obstacle map by classifying each pixel corresponding to the occupancy information into at least one of space, low obstacles, and normal obstacles based on the covariance of map information corresponding to the occupancy information and the covariance of coordinate information based on the surrounding images; and control the vehicle based on the obstacle map.

[0030] Other applications will become apparent from the description provided herein. It should be understood that this specification and specific examples are for illustrative purposes only and are not intended to limit the scope of the invention. Attached Figure Description

[0031] To provide a good understanding of the invention, various embodiments of the invention, given by way of example, will now be described with reference to the accompanying drawings, in which:

[0032] Figure 1 To illustrate a control block diagram of a vehicle according to one embodiment of the present invention;

[0033] Figure 2 This is a schematic diagram illustrating a lateral obstacle detection area according to an embodiment of the present invention;

[0034] Figure 3 This is a schematic diagram illustrating a time-slice measurement mode according to an embodiment of the present invention;

[0035] Figures 4A to 4D This is a schematic diagram illustrating the process of forming map information according to one embodiment of the present invention;

[0036] Figure 5 This is a schematic diagram illustrating an operation for detecting obstacles based on surrounding images and map information according to an embodiment of the present invention;

[0037] Figure 6 This is a schematic diagram illustrating braking control according to one embodiment of the present invention;

[0038] Figure 7 A schematic diagram illustrating the operation of an output warning signal according to an embodiment of the present invention; and

[0039] Figure 8 This is a flowchart of one embodiment of the present invention.

[0040] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the invention in any way. Detailed Implementation

[0041] The following description is merely exemplary in nature and is not intended to limit the invention, application, or use. It should be understood that throughout the drawings, corresponding reference numerals denote the same or corresponding parts and features.

[0042] Throughout this specification, the same reference numerals denote the same elements. Not all elements of embodiments of the invention will be described, and descriptions of those known in the art or overlapping in embodiments will be omitted. Terms used throughout this specification, such as “part,” “module,” “component,” “block,” etc., can be implemented in software and / or hardware, and multiple “parts,” “modules,” “components,” or “blocks” can be implemented as a single element, or a single “part,” “module,” “component,” or “block” can include multiple elements.

[0043] It should be further understood that the term "connection" or its derivatives refer to both direct and indirect connections, with indirect connections including connections via wireless communication networks.

[0044] It should be further understood that when the terms “comprising” and / or “including” are used in this specification, they indicate the presence of the said features, values, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, values, steps, operations, elements, components and / or groups thereof, unless the context clearly indicates otherwise.

[0045] In the specification, it should be understood that when a component is referred to as being "above / below" another component, the component may be directly above / below the other component, or there may be one or more intermediate components.

[0046] Although terms such as “first,” “second,” “A,” and “B” can be used to describe various components, these terms do not limit the corresponding components, but are only used for the purpose of distinguishing one component from another.

[0047] As used in this application, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well.

[0048] The reference numerals used for method steps are for illustrative purposes only and are not intended to restrict the order of steps. Therefore, the order of writing may be achieved in other ways unless the context clearly indicates otherwise.

[0049] The working principle and implementation scheme of the present invention will be described below with reference to the accompanying drawings.

[0050] Figure 1 This is a control block diagram of a vehicle 1 according to one embodiment of the present invention.

[0051] refer to Figure 1 According to one embodiment, the vehicle 1 may include a sensor unit 100, a camera 200, an output device 400, a braking unit 300, and a controller 500.

[0052] The sensor unit 100 may include an ultrasonic sensor 110 and a wheel speed sensor 120.

[0053] The ultrasonic sensor 110 can detect the distance to an obstacle by transmitting ultrasonic waves and utilizing the ultrasonic waves reflected from the obstacle.

[0054] The sensor unit 100 can acquire occupancy information of the area surrounding the vehicle.

[0055] Occupancy information can represent information obtained by determining whether the space around a vehicle is occupied by a specific object, such as an obstacle.

[0056] Wheel speed sensors 120 are installed on each of the four wheels, including the front and rear wheels, to detect the rotational speed of the wheel by means of changes in the magnetic lines of force of the wheel and the sensor.

[0057] Camera 200 can acquire images of the vehicle's surroundings.

[0058] According to one embodiment of the present invention, the camera 200 can be positioned at the front, rear, and sides of the vehicle to acquire images.

[0059] The camera 200 mounted on a vehicle may include a charge-coupled device (CCD) camera or a complementary metal-oxide-semiconductor (CMOS) color image sensor. In this document, CCD and CMOS can refer to sensors that convert light received through the camera lens into electrical signals. Specifically, a CCD camera refers to a device that uses a charge-coupled device to convert an image into an electrical signal. Additionally, a CMOS image sensor (CIS) refers to a low-power, low-consumption image acquisition device with a CMOS structure and is used as an electronic thin film in digital devices. Generally, CCDs have higher sensitivity than CISs and are therefore widely used in vehicles, but the present invention is not limited thereto.

[0060] The braking unit 300 can control the vehicle speed based on signals from the controller.

[0061] According to one embodiment, the braking unit 300 may include a hydraulic control unit (HCU) as a hydraulic control device, a sensor for detecting wheel speed, a pedal travel switch (PTS) for detecting the state of the brake pedal being pressed, a disc brake, and a brake caliper, but the invention is not limited thereto.

[0062] The output device 400 can be configured to output a warning signal based on the probability of a collision.

[0063] According to one embodiment of the invention, the output device 400 may be configured to include a display or speaker disposed on the vehicle's instrument cluster or central dashboard.

[0064] The controller 500 can generate map information based on vehicle movement and occupancy information.

[0065] In other words, the controller 500 can acquire occupancy information based on vehicle movement and time-slice measurement patterns, and then generate map information based on this occupancy information. Details will be described below.

[0066] Map information can represent information based on occupancy information and indicate whether there are obstacles around a vehicle.

[0067] The controller 500 can determine whether there are obstacles around the vehicle based on map information and surrounding images.

[0068] In other words, the controller 500 can use occupancy information obtained by ultrasonic sensors and surrounding images obtained by cameras to determine whether there are obstacles around the vehicle.

[0069] In response to the presence of an obstacle, the controller 500 can control the brake unit 300 based on the presence of the obstacle and the probability of collision of the vehicle derived from the vehicle's speed and map information.

[0070] In other words, based on the above operation, when a collision between the vehicle and an obstacle is anticipated, the controller 500 can stop the vehicle immediately by operating the brake unit.

[0071] The controller can generate map information by assigning a first weight to the occupancy information of the area measured in real time, and assigning a second weight, which is greater than the first weight, to the occupancy information of the previously measured area.

[0072] Specifically, regarding occupancy information acquired by ultrasonic sensors, previously measured areas are identified as having higher reliability. Therefore, when forming map information, occupancy information from previously measured areas is assigned a higher weight than occupancy information acquired in real-time or later.

[0073] The controller 500 can form map information by assigning third weights to the occupancy information corresponding to the space. That is, for each obstacle, corresponding weights can be assigned to previously measured obstacles and obstacles to be measured in real time, and unique weights can be assigned to spaces without obstacles when forming map information. The details are described below.

[0074] The controller 500 can classify each pixel in the image as at least one of space, low obstacle, and normal obstacle based on the surrounding image.

[0075] The image information acquired by camera 200 may include a set of multiple pixels, and in response to determining the presence of an obstacle, the controller may determine the type of each obstacle as a low obstacle (e.g., a barrier) and a high obstacle (e.g., a vehicle).

[0076] In addition, when there are no obstacles, the corresponding area can be defined as space.

[0077] The controller can determine the collision time between the vehicle and the obstacle. Simultaneously, the controller can determine the probability of a collision based on the collision time.

[0078] When the probability of a collision exceeds a predetermined reference value and the obstacle corresponds to a normal obstacle, the controller 500 can control the braking unit to stop the vehicle, thereby preventing a collision.

[0079] On the other hand, when the probability of a collision exceeds a predetermined reference value and the obstacle corresponds to a low obstacle, the controller 500 can control the braking unit to stop the vehicle after a predetermined time from the detection of the obstacle.

[0080] For low obstacles, the controller can be set to a longer braking time than for normal obstacles.

[0081] The controller 500 can determine the collision time between the vehicle and the obstacle, and determine the braking moment of the vehicle by comparing the collision time with a reference braking time corresponding to the vehicle's speed.

[0082] The controller 500 can determine the occupancy information corresponding to the obstacle and the pixels included in the surrounding image, and form map information based on the covariance of the occupancy information and the covariance of the pixels.

[0083] The controller 500 can output a warning signal to the output device based on the probability of a collision. The warning signal can be a visual or auditory signal, such as sound. The form or type of the warning signal is not limited.

[0084] The controller 500 can determine the probability of a collision by comparing a reference time corresponding to the vehicle's speed with the collision time between the vehicle and the obstacle.

[0085] The controller 500 may include a memory (not shown) and a processor (not shown); the memory stores data about algorithms for controlling the operation of components of the vehicle, or data representing programs of such algorithms, and the processor performs the aforementioned operations using the data stored in the memory. In this case, the memory and processor may be implemented as separate chips. Alternatively, the memory and processor may be implemented as a single chip.

[0086] At least one component can be added or omitted to correspond to Figure 1 The performance of the vehicle's components is shown. Furthermore, the relative positions of the components can be changed to correspond to the system's performance or structure.

[0087] Figure 1 Some of the components shown may represent software and / or hardware components, such as field-programmable gate arrays (FPGAs) and application-specific integrated circuits (ASICs).

[0088] Figure 2 This is a schematic diagram illustrating a lateral obstacle detection area according to one embodiment of the present invention.

[0089] refer to Figure 2 Vehicles can use ultrasonic sensors installed in the vehicle to obtain occupancy information of the area around the vehicle, and estimate the location of obstacles based on the occupancy information.

[0090] exist Figure 2 Within this, the occupancy information for regions Z2-1 and Z2-2 can be obtained.

[0091] exist Figure 2In this case, the occupancy information of area Z2-1 can be obtained while the vehicle is in motion.

[0092] In this case, based on the presence of obstacle O2, it can be determined that the corresponding area is occupied.

[0093] In addition, the controller can determine the position of the corresponding obstacle O2.

[0094] In other words, the ultrasonic sensors installed in the vehicle can obtain occupancy information for the corresponding areas Z2-1 and Z2-2.

[0095] Figure 3 This is a schematic diagram illustrating a time-slice measurement mode according to an embodiment of the present invention.

[0096] refer to Figure 3 This demonstrates the operation of estimating the shape and position of obstacles based on time-slice measurement patterns.

[0097] Specifically, the vehicle can determine the shape and position of obstacles while moving.

[0098] In other words, the vehicle can estimate the location X3 of an obstacle using a time-slice measurement mode based on ultrasonic sensors.

[0099] The controller can predict the vehicle speed based on the vehicle speed obtained through the wheel speed sensor, and calculate the positions of the ultrasonic sensors in the map information at various times, S31 and S32.

[0100] Additionally, when an obstacle is detected while the vehicle is in motion, the controller can accumulate and store distance measurements to construct measurement vectors V31 and V32.

[0101] Additionally, the controller can predict the distance D3 from the ultrasonic sensor to the obstacle based on the vehicle's measurement vector.

[0102] Specifically, the distance between the vehicle and the obstacle can be determined based on the following matrix.

[0103] [Equation 1]

[0104]

[0105] Referring to Equation 1, h represents the operation of determining the distance between the vehicle and the obstacle based on a vector, d represents the distance between the vehicle and the obstacle, and X represents the position value of the obstacle over time.

[0106] In addition, the controller can use Equation 2 to correct the position of obstacles.

[0107] [Equation 2]

[0108] X k =X k-1 +K k (X k -h(X k-1 ))

[0109] Referring to Equation 2, the controller can obtain the nonlinear filter gain K of the ultrasonic sensor for each measurement cycle. k It also corrects the position of the obstacle estimated in the previous time step k-1 and estimates the position of the obstacle in real time based on Equation 2.

[0110] In addition, the controller can generate map information by storing the estimated location of each obstacle.

[0111] at the same time, Figure 3 The operation for determining the location of an obstacle described herein is merely one embodiment of the present invention, and there are no limitations on the operation, as long as it can improve the measurement accuracy of the obstacle's location.

[0112] Figures 4A to 4D This is a schematic diagram illustrating the process of forming map information according to one embodiment of the present invention.

[0113] When map information is generated, the controller can create an occupancy grid map. Specifically, the controller divides the area around the vehicle into cells with certain intervals, and can represent the presence of obstacles in each cell with an occupancy probability between 0 and 1.

[0114] When the ultrasonic sensor obtains the distance measurement value, the controller can determine the area occupied by the distance measurement value within the beam angle as the obstacle detection area, and determine the area from the sensor position to the position corresponding to the distance measurement value within the beam angle as the obstacle undetected area.

[0115] Additionally, when no ultrasonic sensor distance measurement is available, the controller can identify all areas indicated by the beam angle as undetected obstacle areas.

[0116] The controller can update the occupancy probability of each cell by adding a first weight or a second weight to the obstacle detection area and a third weight to the obstacle-undetected area (i.e., the spatial area).

[0117] Meanwhile, the third weight can be determined as a negative weight.

[0118] All units outside the detection range of the vehicle's ultrasonic sensors can maintain their previous occupancy probability.

[0119] refer to Figure 4A and Figure 4BThe controller assigns a first weight to the occupancy information of the area measured in real time, and assigns a second weight, which is greater than the first weight, to the occupancy information of the previously measured area, so that map information including an occupancy grid map can be formed.

[0120] Specifically, a first weight can be assigned to regions F4a and F4b measured in real time, and a second weight can be assigned to regions P4a and P4b measured previously.

[0121] The controller can reduce the reliability of obstacle detection in the real-time measured area (i.e., the untraveled area of ​​the obstacle detection area) and improve the reliability of the already traversed area.

[0122] Therefore, the second weight can be set to a value greater than the first weight.

[0123] In other words, the controller can apply the first weight to the undetected obstacle area F4a at the initial detection time to reduce the occupancy probability, thereby avoiding the obstacle being over-detected.

[0124] Additionally, refer to Figure 4B Each cell in the obstacle detection area measured in real time can be assigned a first weight, and when the measurement is completed, a second weight can be assigned, thereby updating the occupancy probability corresponding to each area.

[0125] At the same time, refer to Figure 4C and Figure 4D The controller can generate map information by assigning a third weight to the occupancy information corresponding to spaces E4c and E4d.

[0126] Specifically, the controller may over-detect obstacles due to the beam angle of the ultrasonic sensor. When an area is determined to be obstacle-free space, the controller can assign a third weight to the corresponding area.

[0127] Additionally, refer to Figure 4D The controller can use the third weight each time to reduce the occupancy probability of undetected obstacle area units, thereby deleting over-detected areas E4d.

[0128] In addition, the controller can apply predetermined adjustment parameters to each of the areas with obstacles, areas without obstacles, and areas that have not yet been determined.

[0129] When the area including the obstacle coordinates detected by the time slice measurement mode is occupied, the controller can determine the coordinates of the lateral obstacles.

[0130] Additionally, the controller can remove over-detected initial obstacle coordinates from the time-slice measurement mode by comparing map information.

[0131] Based on the above operations, the controller can generate a more accurate map of the area surrounding the vehicle by using ultrasonic sensors, acquiring occupancy information while changing time, and processing the data.

[0132] at the same time, Figures 4A to 4D The operation described herein is merely one embodiment of the present invention, and there are no limitations on the operation of using ultrasonic sensors to generate map information with improved accuracy.

[0133] Figure 5 This is a schematic diagram illustrating an operation for detecting obstacles based on surrounding images and map information according to an embodiment of the present invention.

[0134] Specifically, a camera installed in the vehicle acquires images of the vehicle's surroundings, and these images may include space and obstacles.

[0135] At the same time, the controller can determine the areas of space, normal obstacles (vehicles, pedestrians and posts) and low obstacles (curb and parking barriers) within the image.

[0136] Specifically, under the assumption of a flat road surface, the controller can use the relationship between the image coordinate system and the vehicle coordinate system to measure the coordinates of the image recognition target (i.e., the obstacle).

[0137] In addition, the controller can divide the area around the vehicle into multiple radial units and determine the coordinates of the space farthest from the vehicle in each unit as the spatial recognition result S5.

[0138] On the other hand, the controller can output the coordinates of the obstacle closest to the vehicle in each unit as the obstacle recognition result.

[0139] According to one embodiment of the invention, the controller can determine occupancy information corresponding to obstacles and pixels included in the surrounding image, and can form map information based on the covariance of the occupancy information and the covariance of the pixels.

[0140] In other words, the controller can perform coordinate correction by using a combination of image recognition coordinates generated from images of the vehicle's surroundings identified by the camera and map information from the ultrasonic sensors.

[0141] Specifically, the controller can acquire coordinate information V5 from the surrounding image and map information U5 from the ultrasonic sensor, and generate a combination of coordinates that are closest to each other among the coordinates that overlap between the covariance VC5 of coordinate information V5 and the covariance UC5 of map information U5.

[0142] The controller can use the coordinates V5 from image recognition and the coordinates U5 from the ultrasonic sensor map information as measurement values, and use their respective covariances VC5 and UC5 as measurement covariance to correct the obstacle coordinates O5.

[0143] When the coordinates of an obstacle are not located in space, the controller can determine an obstacle map. In this operation, normal obstacles and low obstacles in the map information can be separated from each other.

[0144] Specifically, the controller can classify obstacles using map information determined from surrounding images into normal obstacles (vehicles, pedestrians, and posts) and low obstacles (curb and parking barriers). Furthermore, this operation allows for the creation of an obstacle map. The controller can then adjust the braking timing based on the obstacle classification described above. Details will be described below.

[0145] Figure 6 This is a schematic diagram illustrating braking control in one embodiment of the present invention.

[0146] Figure 6 The operation described herein illustrates a practical implementation that combines the above operation with the expected time to collision (TTC) between the vehicle and the obstacle.

[0147] The controller can determine the collision time between the vehicle and the obstacle, and determine the probability of a collision based on the collision time.

[0148] In addition, when the probability of a collision exceeds a predetermined reference value and the obstacle corresponds to a normal obstacle, the controller can control the braking unit to bring the vehicle to an immediate stop.

[0149] Meanwhile, when the obstacle corresponds to a low obstacle, the controller can control the braking unit to stop the vehicle after a predetermined time from when the obstacle is detected.

[0150] The controller can determine the collision time between the vehicle and the obstacle, and compare the collision time with a reference braking time corresponding to the vehicle's speed to determine the braking moment of the brake unit.

[0151] refer to Figure 6 In the area surrounding the vehicle, a parking barrier LO6 is located behind the vehicle and its rear wheels. The controller can generate map information based on ultrasonic sensors installed in the vehicle.

[0152] In addition, the controller uses cameras to identify the space, the target vehicle O6, and the parking barrier L06.

[0153] The controller can determine the collision time based on the vehicle's speed and map information.

[0154] According to one implementation plan, the reference braking time for a vehicle with a speed of 3 kph can be determined to be 0.8 seconds.

[0155] At the same time, according to an implementation plan, in Figure 6 In the process, the collision time between the vehicle and the target vehicle O6 was determined to be 0.9 seconds, and the collision time between the vehicle and the parking barrier L06 was determined to be 0.78 seconds.

[0156] On the other hand, Figure 6 In the case of the target vehicle O6, the risk of collision is low due to its position, so emergency braking is not required. On the other hand, there is a risk of collision with the parking barrier L06, but the parking barrier L06 is classified as a low obstacle behind the rear wheels, so the braking timing can be delayed.

[0157] According to one implementation plan, in Figure 6 In the context of the system, the reference braking time corresponding to a vehicle speed of 3 kph is 0.8 seconds, but in... Figure 6 Since the parking brake L06 is located near the rear wheels, the reference braking time can be determined to be 0.74 seconds. Therefore, the controller needs to perform braking control after 0.74 seconds.

[0158] However, since the parking barrier L06 is classified as a low obstacle, the controller determines the collision time with the parking barrier L06 to be 0.78 seconds, and the controller can apply the brakes to the vehicle 0.04 seconds later than the reference braking time.

[0159] at the same time, Figure 6 The implementation schemes including collision time described herein are merely examples for illustrating the operation of the invention, and various modifications can be applied to collision time and its applications.

[0160] Figure 7 This is a schematic diagram illustrating the operation of an output warning signal according to an embodiment of the present invention.

[0161] The controller can determine the probability of a collision by comparing a reference time corresponding to the vehicle's speed with the collision time between the vehicle and the obstacle.

[0162] In addition, the controller can output a warning signal when the probability of a collision exceeds a predetermined reference value.

[0163] According to one embodiment of the invention, a warning signal can be output from a display located in the instrument cluster. According to the embodiment, the warning signal can be output via message M7 (e.g., "Rear Collision Risk").

[0164] On the other hand, there are no restrictions on the form or type of the output warning signal.

[0165] Figure 8 This is a flowchart of one embodiment of the present invention.

[0166] refer to Figure 8 The vehicle can activate the parking collision avoidance assist system (step 1001).

[0167] In addition, the vehicle can obtain occupancy information from ultrasonic sensors and acquire surrounding images from cameras (step 1002).

[0168] At the same time, the controller can generate map information based on the weighted occupancy information (step 1003).

[0169] Additionally, the controller can identify obstacles based on the generated map information and surrounding images (step 1004). Obstacle identification may include determining whether an obstacle exists and determining the type of obstacle.

[0170] On the other hand, when an obstacle exists (step 1005) and the probability of collision between the vehicle and the obstacle exceeds a reference value (step 1006), the controller can perform braking by determining different braking times of the vehicle based on the type of obstacle (step 1007).

[0171] Furthermore, the disclosed embodiments can be implemented as a recording medium storing computer-executable instructions. These instructions can be stored as program code, and when executed by a processor, can generate program modules to perform the operations of the disclosed embodiments. The recording medium can be implemented as a computer-readable recording medium.

[0172] Computer-readable recording media include various recording media that store instructions that can be decoded by a computer, such as read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0173] It is evident from the above that by using ultrasonic sensors and cameras installed in the vehicle to estimate the position of obstacles, the vehicle and the methods of controlling the vehicle can prevent erroneous braking in the Parking Collision Avoidance Assist (PCA) system.

[0174] Although exemplary embodiments of the invention have been described for illustrative purposes, those skilled in the art will understand that various modifications, additions, and substitutions can be made without departing from the scope and spirit of the invention. Therefore, exemplary embodiments of the invention are not described for limiting purposes.

Claims

1. A vehicle comprising: The sensor unit is configured to acquire occupancy information of the area surrounding the vehicle and the vehicle's speed; A camera configured to acquire images of the vehicle's surroundings; as well as The controller is configured as follows: Map information is generated based on vehicle movement and occupancy information; Determine whether there are obstacles around the vehicle based on map information and surrounding images; Classify each pixel in the surrounding image into one of three categories: space, low obstacle, or normal obstacle; The probability of a vehicle collision is determined based on its speed and map information. In response to the presence of an obstacle, the vehicle's braking is controlled based on the collision probability and the type of obstacle, such that when the collision probability exceeds a predetermined reference value, the vehicle stops at a time that varies depending on whether the obstacle corresponds to a low obstacle or a normal obstacle.

2. The vehicle according to claim 1, wherein, The controller is configured to form the map information by assigning a first weight to the occupancy information of a first area measured in real time, and assigning a second weight greater than the first weight to the occupancy information of a second area measured previously.

3. The vehicle according to claim 2, wherein, The controller is configured to generate map information by assigning a third weight to occupancy information corresponding to a third region without obstacles.

4. The vehicle according to claim 1, wherein, The controller is configured to: determine the collision time between the vehicle and the obstacle, and stop the vehicle when the collision probability of the vehicle exceeds a predetermined reference value and the obstacle corresponds to a normal obstacle.

5. The vehicle according to claim 1, wherein, The controller is configured to stop the vehicle after a predetermined time since the obstacle was detected when the vehicle's collision probability exceeds a predetermined reference value and the obstacle corresponds to a low obstacle.

6. The vehicle according to claim 5, wherein, The controller is configured to: determine the collision time between the vehicle and the obstacle, and compare the collision time with a reference braking time corresponding to the vehicle's speed to determine the vehicle's braking moment.

7. The vehicle according to claim 1, wherein, The controller is configured to: determine occupancy information corresponding to obstacles and pixels included in the surrounding image, and form map information based on the covariance of the occupancy information and the covariance of the pixels.

8. The vehicle according to claim 1, further comprising an output device, in, The controller is configured to output a warning signal to the output device based on the vehicle's collision probability.

9. The vehicle according to claim 1, wherein, The probability of a vehicle collision is determined by comparing a reference time corresponding to the vehicle's speed with the time of collision between the vehicle and the obstacle.

10. The vehicle according to claim 1, further comprising a braking unit, in, The controller is configured to control the braking system based on the vehicle's collision probability.

11. A method for controlling a vehicle, the method comprising: The sensor unit acquires occupancy information of the area surrounding the vehicle and the vehicle's speed. Images of the vehicle's surroundings are captured by a camera; The controller generates map information based on vehicle movement and occupancy information; The controller determines whether there are obstacles around the vehicle based on map information and surrounding images; The controller classifies each pixel in the surrounding image into one of three categories: space, low obstacle, or normal obstacle. The controller determines the probability of a vehicle collision based on the vehicle's speed and map information; In response to the presence of an obstacle, the vehicle's braking is controlled based on the collision probability and the type of obstacle, such that when the collision probability exceeds a predetermined reference value, the vehicle stops at a time that varies depending on whether the obstacle corresponds to a low obstacle or a normal obstacle.

12. The method according to claim 11, wherein, The information used to create the map includes: The first weight is assigned to the occupancy information of the first region measured in real time; A second weight, greater than the first weight, is assigned to the occupancy information of the previously measured second region.

13. The method according to claim 12, wherein, The map information includes: assigning a third weight to the occupancy information of the third area corresponding to the area without obstacles.

14. The method according to claim 11, wherein, Vehicle control includes: Determine the time of collision between the vehicle and the obstacle; The vehicle is stopped when the probability of collision exceeds a predetermined reference value and the obstacle corresponds to a normal obstacle.

15. The method according to claim 11, wherein, Vehicle control includes: When the vehicle's collision probability exceeds a predetermined reference value and the obstacle corresponds to a low obstacle, the vehicle is stopped after a predetermined time from when the obstacle was detected.

16. The method according to claim 15, wherein, Vehicle control includes: determining the collision time between the vehicle and the obstacle, and comparing the collision time with a reference braking time corresponding to the vehicle's speed to determine the vehicle's braking moment.

17. The method according to claim 11, wherein, The information used to create the map includes: Determine the occupancy information corresponding to the obstacle and the pixels included in the surrounding image; Map information is formed based on the covariance of occupancy information and the covariance of pixels.

18. A vehicle comprising: An ultrasonic sensor configured to acquire occupancy information of the area surrounding the vehicle based on ultrasonic signals; Wheel speed sensors, configured to acquire the speed of the vehicle; A camera configured to acquire images of the vehicle's surroundings; as well as At least one processor, configured as follows: The allocation corresponds to the occupancy probability of the occupancy information; By utilizing a time-slice measurement mode based on vehicle speed, a first weight is assigned to the occupancy information of the first region measured in real time, a second weight greater than the first weight is assigned to the occupancy information of the second region measured previously to determine the occupancy probability of the second region, and a third weight is assigned to the occupancy information of the third region corresponding to the region without obstacles to reduce the occupancy probability of the third region. Determine the coordinate information corresponding to the surrounding images and vehicles; Based on the covariance of map information based on occupancy information and the covariance of coordinate information based on surrounding images, each pixel corresponding to the occupancy information is classified into one of space, low obstacle, or normal obstacle to determine the obstacle map. The probability of a vehicle collision is determined based on its speed and map information. The vehicle's braking is controlled based on the collision probability and the type of obstacle in the obstacle map, so that when the collision probability exceeds a predetermined reference value, the vehicle stops at a time that varies depending on whether the obstacle corresponds to a low obstacle or a normal obstacle.

Images