Apparatus and method for estimating a position in an automated parking service system

Abstract

Apparatus for estimating a position in an automated parking service system, comprising: a front camera processor configured to process a front image of a vehicle; a surround view monitor (SVM) processor configured to detect a short-range lane or lane boundary and a stop line by processing a surround view image of the vehicle; a map data unit configured to store a high-resolution map; and a controller configured to download a map including an area designated as a parking zone from the map data unit when the vehicle's entry into a parking space is detected, and to correct a position measurement of the vehicle by performing map matching based on the detection and processing results of the front camera processor and the SVM processor and the parking space map of the map data unit when a starting position of an automated parking service (AVP) is detected based on the short-distance lane or lane boundary and the stop line detected by the SVM processor.

Description

Cross-Reference to Related ApplicationsThis application claims priority to Korean Application No. 10-2019-0031092 filed on Mar. 19, 2019, which is incorporated herein by reference in its entirety.BACKGROUND OF THE INVENTION1. Technical FieldEmbodiments of the present disclosure relate to an apparatus and method for estimating a position in an automated service system, and more particularly to an apparatus and method for estimating a position in an automated service system that can estimate a home position in an automated valve parking system (AVP) using a surround view monitor (SVM).2. Prior ArtIn general, an autonomous vehicle refers to a vehicle that autonomously determines a travel path by recognizing an environment using a function of detecting and processing external information when driving and independently driving using its own energy.Positioning methods used in autonomous vehicles include a global navigation positioning system (GNSS) based satellite positioning method such as a global positioning system (GPS), a differential GPS (DGPS), or network-real time kinematic (RTK), vehicle behavior based dead reckoning for correcting satellite positioning using vehicle sensors and an inertial measurement device (IMU) (for example, a vehicle speed, a steering angle, and a wheelkillometer / yaw rate / acceleration), and a map matching method in which a relative estimation of the position of a vehicle is made, comparing a precise map for autonomous driving with data from various sensors (for example, a camera, a stereo camera, an SVM camera, and a radar).Recently, automated parking service (AVP) has been developed for more convenient parking. An autonomous vehicle in which an AVP system is installed may autonomously drive without a driver, search a parking space, and perform a parking operation, or leave a parking space. Further, even a function for performing a parking operation by expanding a target parking space to an surrounding parking space in a traffic congestion area has been developed.Therefore, a position determination method for estimating a position becomes important. However, a conventional satellite positioning system has problems in that the method is very expensive because it requires a high-resolution GPS, a high-resolution radar and a high-resolution camera, that the method has a low processing speed and accuracy because it is configured with a complicated algorithm, and that the method cannot maintain its performance constantly because it is influenced by the characteristics of a road and the characteristics of surrounding geographical features.The prior art to this disclosure is disclosed in U.S. Published Patent Application No. 2018-0023961 (January 25, 2018), entitled "SYSTEMS AND METHODS FOR ALIGNING CROWDSOURD SPARSE MAP DATA.".Overview of the InventionVarious embodiments relate to providing an apparatus and method for estimating a position in an automated service system that can estimate a starting position in an automated service system (AVP) using an around view monitor (SVM) without costly equipment.According to an exemplary embodiment, an apparatus for estimating a position in an automated parking service system includes a front camera processor configured to process a front image of a vehicle, an around view monitor (SVM) processor configured to recognize a short-distance lane boundary and a stop line by processing an around view image of the vehicle, a map data unit configured to store a high-resolution map, and a controller configured to download a map having an area designated as a parking zone from the map data unit when the entry of the vehicle into a parking space is recognized, and correct a position measurement value of the vehicle, by performing map matching based on the recognition and processing results of the front camera processor and the SVM processor and the parking lot map of the map data unit when a start position of an automated parking service (AVP) is recognized based on the short-distance lane boundary and the stop line recognized by the SVM processor.According to an exemplary embodiment, the controller is configured to predict a behavior of the vehicle by dead reckoning navigation when the AVP start position is detected, and to estimate an AVP starting position of the vehicle by fusing the position measurement value of the vehicle corrected by the map matching and the predicted behavior of the vehicle.According to an exemplary embodiment, the controller includes a vehicle behavior prediction unit for predicting a behavior of the vehicle by dead reckoning navigation based on GPS information received from a GPS receiver side and a vehicle steering wheel angle, the yaw rate, and the wheel speed received from a vehicle sensor unit side.According to one exemplary embodiment, the controller has a map matching unit which is designed to carry out the map matching on the basis of lane fusion data in which a long-distance lane boundary recognized by the front camera processor and the short-distance lane boundary and the stop line recognized by the SVM processor are fused, and / or parking space map data from the map data unit and / or vehicle behavior data predicted by dead reckoning are fused for each point in time.According to an embodiment, the map matching unit is configured to calculate a position and rotation correction amount in which a distance error between sensor data and map data is minimized by using iterative closest point logic (ICP).According to one exemplary embodiment, the controller has a position fusion unit which is designed to fuse a vehicle positioning output as results of the map matching and the GPS information of a vehicle position predicted by dead reckoning navigation.According to one exemplary embodiment, the controller has a fail-safe diagnostic unit which is designed to receive the vehicle position and flags output by the position fusion unit and to carry out a fail-safe diagnosis. The fail-safe diagnosis unit is configured to perform the fail-safe diagnosis using a distribution diagram configured with estimated positioning results in which past positioning results have been projected on the current time and positioning results input at the current time.According to one exemplary embodiment, the vehicle positioning has the longitude and / or the latitude and / or the heading and / or the covariance and / or a warning / fail / safe and / or flags and / or a lane offset.According to an exemplary embodiment, a method for estimating a position in an automated parking service system includes: downloading, by a controller, a map having an area designated as a parking zone from a map data unit to store a high-resolution map when entry of a vehicle into a parking space is detected; recognizing, by the controller, a start position of an automated parking service (AVP) based on a short-range lane boundary and a stop line detected by an around view monitor processor (SVM); and correcting, by the controller, a position measurement value of the vehicle by performing map matching based on the detection and processing results of a front camera processor and the SVM processor and the parking space map of the map data unit.According to an exemplary embodiment, the method comprises predicting, by the controller, a behavior of the vehicle by dead reckoning when the AVP start position is detected, and estimating, by the controller, an AVP starting position of the vehicle by merging the position measurement value of the vehicle corrected by the map matching and the predicted behavior of the vehicle.According to an embodiment, in predicting the behavior of the vehicle, the controller predicts the behavior of the vehicle by dead reckoning based on GPS information received from a GPS receiver, and a vehicle steering wheel angle, yaw rate, and wheel speed received from a vehicle sensor unit.According to an exemplary embodiment, in the correction of the position measurement value, the controller performs the map matching based on lane fusion data in which a long-distance lane boundary recognized by the front camera processor and the short-distance lane boundary and the stop line recognized by the SVM processor are fused, and / or parking space map data from the map data unit and / or vehicle behavior data predicted by dead reckoning are fused for each time point.According to an embodiment, in correcting the position measurement value, the controller calculates a position and rotation correction amount in which a distance error between sensor data and map data is minimized by using iterative closest point logic (ICP).According to one embodiment, in estimating the AVP starting position, the controller merges vehicle positioning output as results of map matching and GPS information of a predicted vehicle position by dead reckoning navigation.According to an embodiment, the method further comprises receiving, by the controller, the vehicle position and flags output as a result of the position fusion, and performing a fail-safe diagnostic. In performing the fail-safe diagnosis, the controller performs the fail-safe diagnosis using a distribution diagram configured with estimated positioning results in which past positioning results have been projected on the current time and positioning results input at the current time.Brief Description of the DrawingsFIG. 1 is a block diagram illustrating an apparatus for estimating a position in an automated parking service system according to an embodiment of the present disclosure. FIG. 2 is a diagram that more specifically describes the device for estimating a position in an automated parking service system according to an embodiment of the present disclosure. FIG. 3 is a flowchart for describing a method for estimating a position in an automated parking service system according to an embodiment of the present disclosure. FIG. 4 is an exemplary diagram of an apparatus and method for estimating a position in an automated service parking system according to an embodiment of the present disclosure. FIG. 5 is a diagram for describing map matching for the apparatus and method for estimating a position in an automated parking service system according to an embodiment of the present disclosure.Detailed DescriptionHereinafter, an apparatus and a method for estimating a position in an automated parking service system according to embodiments of the present disclosure will be described with reference to the accompanying drawings. In the drawings, the thickness of lines, the sizes of components, and the like are exaggerated for convenience of description and clarity.Further, the terms to be described below are defined with respect to functions in the present disclosure, and may be different depending on practices or purposes of users or operators. The terms should therefore be defined in accordance with the contents of the entire description.Furthermore, an implementation described in this description can be realized, for example, as a method or process, a device, a software program, a data stream or signal. Although the disclosure has been discussed in the context of only a single form of implementation (e.g., discussed as only one method), an implementation having a discussed feature may also be implemented in other forms (e.g., as a device or program). The device may be implemented as suitable hardware, software, or firmware. The method may be implemented in a device, such as a processor commonly referred to as a processor device, including, for example, a computer, a microprocessor, an integrated circuit, or a programmable logic device. The processor includes a communication device such as a computer, a cellular telephone, a cellular telephone / personal digital assistant ("PDA"), and other device that facilitates the exchange of information between end users.FIG. 1 is a block diagram illustrating an apparatus for estimating a position in an automated parking service system according to an embodiment of the present disclosure. FIG. 2 is a diagram that more specifically describes the device for estimating a position in an automated parking service system according to an embodiment of the present disclosure. FIG. 5 is a diagram for describing map matching for the apparatus and method for estimating a position in an automated parking service system according to an embodiment of the present disclosure. The apparatus for estimating a position in an automated service parking system will be described below with reference to FIGS. 1, 2, and 5.As illustrated in FIG. 1, the apparatus for estimating a position in an automated parking service system according to an exemplary embodiment of the present disclosure includes a front camera processor 10, an around view monitor (SVM) processor 20, a map data unit ( 30), a GPS receiver 40, a vehicle sensor unit 50, a controller 60, and an output unit 70.As is well known in the art, some example embodiments may be illustrated in the associated drawings as functional blocks, units, sections, and / or modules. Those skilled in the art will understand that these blocks, units, and / or modules are physically implemented by electronic (or optical) circuits such as logic circuits, discrete components, processors, wired circuits, memory devices, and wired connections. When implemented by processors or other similar hardware, the blocks, units, and / or modules may be programmed and controlled by software (e.g., code) to perform various functions discussed in this specification. Further, each block, unit, and / or module may be implemented by dedicated hardware or as a combination of dedicated hardware for performing some functions and a processor (e.g., one or more programmed processors and associated circuitry) for performing other functions. Each block, unit, and / or module of some example embodiments may be physically separated into two or more interacting discrete blocks, units, and / or modules without departing from the scope of the inventive concept. Further, blocks, units, and / or modules of some example embodiments may be physically combined into more complex blocks, units, and / or modules without departing from the scope of the inventive concept.First, the present embodiment is to estimate a home position in an automated parking service system (AVP) using an SVM that facilitates parking by making it possible to see spaces surrounding the vehicle in the vehicle via cameras mounted on the front, rear, and sides of the vehicle. That is, the present embodiment relates to a vehicle position determination device, and can measure the position of a vehicle using images captured by cameras without expensive equipment, a stop line, etc., and improve the accuracy of map matching.The front camera processor 10 may receive a front image of a vehicle from a front camera of the vehicle, and may recognize a long-distance lane boundary and a traffic sign by processing the front image of the vehicle.Further, the front camera processor 10 may include in-lane recognizers for recognizing an in-lane boundary in the front image, lane trackers for tracking a lane boundary having the same characteristic as the recognized lane boundary, and reliability calculators.The inside lane recognition devices may recognize a lane boundary in the form of a solid line or a broken line having a certain color (for example, white or yellow) in a front image.The lane trackers may track a lane boundary having the same characteristics within a predetermined margin by considering the history (or direction) of the detected lane boundary, although components (e.g., color, thickness, and shape) of the detected lane boundary do not partially maintain the same characteristics (e.g., the same line color, line thickness, and line interval).Further, the reliability calculators may calculate the ratio (i.e., the lane component matching ratio) in which the components (for example, color, thickness, and shape) of the tracked lane coincide with predetermined reference values for each component. When the lane component matching ratio is close to 100%, it means high reliability. In contrast, when the lane component matching ratio is closer to 0%, this means poor reliability. Further, the reliability calculators may predict a current lane boundary (i.e., a predicted lane boundary) using the detection of a previous lane boundary and movement information of a vehicle, and may calculate the reliability to compare the predicted lane boundary with a current lane boundary detected in the front image and increase a reliability count value (or reliability score) when a difference between the predicted lane boundary and the current lane boundary is equal to or less than a preset threshold. When the reliability count is greater than the preset threshold, the reliability calculators may determine that the corresponding lane recognition is valid (i.e., the corresponding lane boundary is a valid lane boundary).The SVM processor 20 can recognize a short-distance lane boundary and a stop line by processing an around view image of a vehicle.Further, the SVM processor 20 serves to recognize a lane in an around view image (or a composite around view image). The surround view image refers to an image obtained by composing surrounding images (for example, front, side, and rear side images) of a vehicle captured by one or more cameras in plan view or surround view form. Accordingly, the SVM processor 20 can recognize a lane boundary (i.e., a short-range lane) in an area near a vehicle.In this case, the cameras are disposed at the front, rear, left and right sides of the vehicle. In order to increase the degree of completion of the plan view or surround view image and prevent the occurrence of a photographic blind spot, additional cameras may also be disposed on the upper surfaces at the front or rear of the vehicle, i.e., at relatively higher positions than the positions of the cameras disposed at the front, rear, left and right.Further, the SVM processor 20, such as the front camera processor 10, may include in-lane recognizers, lane trackers, and reliability calculators.That is, the inside lane recognition devices can recognize an inside lane boundary in an around view image and can recognize a lane boundary in the form of a solid line or a broken line having a certain color (for example, white or yellow) in the around view image. In the present exemplary embodiment, the inside lane recognition devices can recognize, in particular, a stop line.The lane trackers may track a lane boundary having the same characteristics within a predetermined margin by considering the history (or direction) of the detected lane boundary, although components (e.g., color, thickness, and shape) of the detected lane boundary do not partially maintain the same characteristics (e.g., the same line color, line thickness, and line interval).Further, the reliability calculators may calculate the ratio (i.e., the lane component matching ratio) in which the components (for example, color, thickness, and shape) of the tracked lane coincide with predetermined reference values for each component. When the lane component matching ratio is close to 100%, it means high reliability. In contrast, when the lane component matching ratio is closer to 0%, this means poor reliability. Further, the reliability calculators may predict a current lane boundary (i.e., a predicted lane boundary) using the detection of a previous lane boundary and movement information of a vehicle, and may calculate the reliability to compare the predicted lane boundary with a current lane boundary detected in the front image and increase a reliability count value (or reliability score) when a difference between the predicted lane boundary and the current lane boundary is equal to or less than a preset threshold. When the reliability count is greater than the preset threshold, the reliability calculators may determine that the corresponding lane recognition is valid (i.e., the corresponding lane boundary is a valid lane boundary).The short-range lane boundary may denote a lane boundary in an area recognizable in an around view image. The long-distance lane boundary may denote a lane boundary recognizable in a front image.The map data unit 30 stores a high-resolution map in which information on roads and surrounding terrain is displayed with high accuracy, and supplies the high-resolution map in response to a request from the controller 60. In the present embodiment, the map data unit 30 can store, in particular, a high-resolution (HD) map for a parking lot (i.e., an area specified as a parking zone).The GPS receiver 40 receives GPS signals from satellites and provides the GPS signals to the controller so that the position of a vehicle can be adjusted based on the current position.The vehicle sensor unit 50 indicates various sensors inside a vehicle. In the present embodiment, the vehicle sensor unit 50 may specifically include a steering wheel angle sensor, a yaw rate sensor, and a wheel speed sensor for vehicle behavior prediction.The controller 60 recognizes that a vehicle enters an area designated as a parking lot or a parking zone, and downloads a map for the corresponding area. That is, when the entry of a vehicle into a parking lot is detected, the controller 60 may download, from the map data unit 30, a map including an area designated as the parking zone.Further, the controller 60 may recognize an AVP start position based on a short-distance lane boundary and a stop line recognized by the SVM processor 20.At this time, the controller 60 may generate a single fused lane boundary (i.e., a single lane boundary that is not divided into a short-distance lane boundary and a long-distance lane boundary) by fusing a lane boundary recognized by the SVM processor 20 and a lane boundary recognized by the front camera processor 10.That is, the controller 60 may fuse lanes by lane error comparison, determine a valid lane, and generate a fused lane.The controller 60 calculates (or determines) a position error (for example, an interval between the ends of lanes in a vehicle reference coordinate system and an angle of each lane) by comparing the lane boundary recognized by the SVM processor 20 (i.e., the short-range lane boundary) and the lane boundary recognized by the front camera processor 10 (i.e., the long-range lane boundary). In this case, the vehicle reference coordinate system denotes a coordinate system indicating lateral axis coordinates X, longitudinal axis coordinates Y, and the vehicle movement direction θ corresponding to a distance travelled and the direction of a vehicle with respect to the center of the vehicle.As a result of the comparison between the two lanes (i.e., the long-distance and short-distance lanes), if this position error is within a predetermined permissibility range, the controller 60 generates a single fused lane (i.e., a single lane not divided into the short-distance lane and long-distance lanes) by fusing the two lanes (i.e., the long-distance lane and short-distance lanes). Further, as a result of the comparison between the two lanes (i.e., the long-distance and short-distance lanes), if the position error is outside a predetermined allowable range, the controller 60 does not merge the two lanes (i.e., the long-distance lane and short-distance lane) and determines a lane having relatively high reliability as a valid lane.Therefore, the controller 60 may determine that the two lanes (i.e., the long-distance lane and short-distance lane) are not valid lanes when reliability of each lane is less than a predetermined threshold. The controller 60 may generate a single fused lane boundary (i.e., a single lane boundary that is not divided into the short-range lane boundary and the long-range lane boundary) by fusing the two lanes when the reliability of each of the two lanes is equal to or higher than the predetermined threshold and the position error between the two lanes is within the predetermined permissibility range. The controller 60 may determine, among the two lanes, a lane having relatively high reliability as a valid lane when the position error between the two lanes is outside the predetermined allowable range.Further, the controller 60 includes a vehicle behavior prediction unit 62, a map matching unit 64, a position fusion unit 66, and a fail-safe diagnosis unit 68. The controller 60 may predict a behavior of a vehicle by dead reckoning navigation, correct a position measurement value of the vehicle by map matching based on the results of the recognition and processing by the front camera processor 10 and the SVM processor 20 and the parking lot map data of the map data unit 30, and finally, may estimate an AVP initial position of the vehicle by merging the predicted behavior of the vehicle and the corrected position measurement value of the vehicle.The vehicle behavior prediction unit 62 may predict a behavior of a vehicle by dead reckoning navigation based on GPS information received from the GPS receiver 40 side and a vehicle steering wheel angle, the yaw rate, and the wheel speed received from a vehicle sensor unit 50.Further, the map matching unit 64 may perform map matching based on lane fusion data in which a long-distance lane boundary recognized by the front camera processor 10 and the short-distance lane boundary and the stop line recognized by the SVM processor 20 are fused, and / or parking space map data from the map data unit 30 and / or dead reckoning predicted vehicle behavior data for each time point.At this time, the map matching unit 64 may calculate a position and rotation correction amount in which a distance error between sensor data and map data is minimized by using iterative closest point logic (ICP). The ICP logic is a method of registering current data with the existing data set, and is a method of finding an association based on the next data points, moving and rotating current data based on the association, and adding the current data to the existing data set.An amount for correcting a position T and a rotation (R) may be calculated, for example, with reference to the following equation and FIG. 5.Further, the position fusion unit 66 may fuse vehicle positioning output as results of map matching and the GPS information of the vehicle position predicted by dead reckoning.In this case, the position fusion unit 66 may be implemented like the method for fusing lanes recognized by the SVM processor 20 and the front camera processor 10, but may fuse position measurements using another method.The controller 60 includes the fail-safe diagnosis unit 68 for receiving a vehicle position and flags output from the position fusion unit 66, and performing a fail-safe diagnosis. The fail-safe diagnosis unit 68 may perform fail-safe diagnosis using a distribution diagram configured with estimated positioning results in which past positioning results have been projected on the current time and positioning results input at the current time.In the present exemplary embodiment, the vehicle positioning can have the longitude and / or the latitude and / or the heading and / or the covariance and / or a warning / fail / safe and / or flags and / or a lane offset.That is, in the present embodiment, the output unit 70 can output the results of the diagnosis of the fail-safe diagnosis unit 69. In this case, the output unit 70 may output the results of the fail-safe diagnosis of the vehicle position information.In the present embodiment, an autonomous driving system may perform sensor fusion positioning based on map matching, and may perform fail-safe diagnosis for improving the reliability of the system and enabling calculation (or calculation or estimation) of robust and stable positioning information in a process of performing sensor fusion positioning. Further, the fail-safe diagnosis in the present embodiment does not require additional hardware because it is an analytical redundancy-based fault diagnosis, but the disclosure is not limited thereto.Referring to FIG. 2, the present embodiment may basically include a performance core for performing a process of fusing a position measurement value corrected by map matching and the predicted results of vehicle behavior, and a safety core for performing fail-safe diagnosis of a vehicle position fused in the performance core.In the performance core, the front camera processor 10 and the SVM processor 20 may perform sensor value processing, and the map data unit 30 may download and manage a map. Further, the GPS receiver 40 in the security core may perform GPS signal processing.Further, in the controller 60, the map matching unit 64 and the position fusion unit 66 may be included in the performance core, and the vehicle behavior prediction unit 62 and the fail-safe diagnosis unit 68 may be included in the safety core, but the disclosure is not limited thereto.In other words, the performance core receives lanes and a stop line from an SVM, and receives lanes and a traffic sign from a front camera. Further, the performance core may process detection data, i.e., sensor values received from the SVM and the front camera. In other words, the controller 60 may merge recognition data from the SVM and the front camera, download the HD map of a parking zone, and perform map matching. In this case, the controller 60 may perform map matching using GPS signals, vehicle travel path information predicted by dead reckoning, and GPS information. Further, the controller may fuse a vehicle positioning (or position) corrected by the map matching and a position value based on the GPS information, and may finally estimate a home position in the automated service parking system by performing a fail-safe diagnosis of the fused results.FIG. 3 is a flowchart for describing a method for estimating a position in an automated parking service system according to an embodiment of the present disclosure. FIG. 4 is an exemplary diagram of an apparatus and method for estimating a position in an automated service parking system according to an embodiment of the present disclosure. The method for estimating a position in an automated service parking system will be described below with reference to FIGS. 3 and 4.First, as illustrated in FIG. 3, in the method for estimating a position in an automated parking service system according to an exemplary embodiment of the present disclosure, the controller 60 recognizes that a vehicle enters a parking space (S 10).In this case, the controller 60 may recognize that the vehicle enters a parking lot by receiving a vehicle position from the GPS receiver 40, but the disclosure is not limited to such a method.Further, when the entry of the vehicle into a parking lot is detected, the controller 60 downloads, from the map data unit 30 in which a high-resolution (HD) map is stored, a map having an area designated as the parking zone (S 20).When it is detected that the vehicle has been parked at an AVP start position (S 30), the controller 60 further determines whether an AVP start area has been detected by the SVM processor 20 (S 40).That is, when the vehicle parks at the AVP start position as illustrated in FIG. 4( a), the controller 60 may recognize the AVP parking position based on a curved lane boundary and a stop line recognized by the SVM processor 20 as illustrated in FIG. 4( b).When an AVP start range is not detected by the SVM processor 20, the controller 60 may return to step S 30 and perform AVP start position parking. The AVP start position parking may be performed by a user. The controller 60 may recognize that the vehicle has parked at the AVP start position by receiving, from the infrastructure installed in the parking lot, GPS information or a signal indicating that the vehicle has parked.Further, the controller 60 sets a position as an output value of the AVP start position (S 50).That is, as illustrated in FIG. 4( c), the controller 60 may set the position based on the AVP start range recognized by the SVM processor 20 as the output value of the AVP start position.Further, the controller 60 corrects the AVP start position as illustrated in FIG. 4(D) (S 60).At this time, the controller 60 may predict a behavior of the vehicle by dead reckoning navigation, and may correct a position measurement value of the vehicle by map matching based on the results of the recognition and processing by the front camera processor 10 and the SVM processor 20 for recognizing a long-distance lane boundary and a traffic sign and on the parking lot map of the map data unit 30.Further, the controller 60 may finally estimate an AVP starting position of the vehicle by fusing the corrected position measurement of the vehicle and the predicted behavior of the vehicle.In this case, the controller 60 may predict the behavior of the vehicle by dead reckoning navigation based on the GPS information received from the GPS receiver 40 side and a steering wheel angle, the yaw rate, and the wheel speed of the vehicle received from the vehicle sensor unit 50 side. Further, the controller 60 may perform map matching based on lane fusion data in which a long-distance lane boundary recognized by the front camera processor 10 and the short-distance lane boundary and the stop line recognized by the SVM processor 20 are fused, and / or parking space map data from the map data unit 30 and / or dead reckoning predicted vehicle behavior data for each time point.In the present embodiment, the controller 60 may calculate a position and rotation correction amount in which a distance error between sensor data and map data is minimized by using iterative closest point logic (ICP).In one embodiment, the controller 60 may merge a vehicle position output as results of map matching and the GPS information of a vehicle position predicted by dead reckoning navigation.Finally, the controller 60 may receive a vehicle position and flags output as results of the position fusion and perform a fail-safe diagnosis (S 70).In this case, the controller 60 may perform the fail-safe diagnosis using a distribution diagram configured with estimated positioning results in which past positioning results have been projected on the current time and positioning results input at the current time. In this case, the vehicle position may include the longitude and / or the latitude and / or the heading and / or the covariance and / or a warning / fail / safe and / or flags and / or a lane offsetAs described above, the apparatus and method for estimating a position in an automated service system according to an exemplary embodiment of the present disclosure may perform map matching without expensive equipment and estimate a home position regardless of the inside and the outside by estimating the home position in an automated service system (AVP) using an around view monitor (SVM), and improve the map matching accuracy by an increased detection distance accuracy (i.e., correction accuracy) by performing measurements near geographical features.While preferred embodiments of the invention have been disclosed for illustrative purposes, it will be apparent to those skilled in the art that various modifications, additions and substitutions are possible, without departing from the scope of the invention as defined in the appended claims.The true technical scope of the disclosure is therefore defined by the following claims.

Claims

An apparatus for estimating a position in an automated service parking system, comprising: a front camera processor configured to process a front image of a vehicle; an around view monitor (SVM) processor configured to recognize a short-range lane boundary and a stop line by processing an around view image of the vehicle; a map data unit configured to store a high-resolution map; A controller configured to download a map having an area designated as a parking zone from the map data unit when the entry of the vehicle into a parking space is detected, and correct a position measurement value of the vehicle by performing map matching based on the detection and processing results of the front camera processor and the SVM processor and the parking space map of the map data unit when a start position of an automated parking service (AVP) is detected based on the short-range lane boundary and the stop line detected by the SVM processor.The apparatus of claim 1, wherein the controller is configured to: predict a behavior of the vehicle by dead reckoning navigation when the AVP start position is detected, and estimate an AVP start position of the vehicle by fusing the position measurement of the vehicle corrected by the map matching and the predicted behavior of the vehicle.The apparatus according to claim 1, wherein the controller comprises a vehicle behavior prediction unit for predicting a behavior of the vehicle by dead reckoning navigation based on GPS information received from a GPS receiver side and a vehicle steering wheel angle, the yaw rate, and the wheel speed received from a vehicle sensor unit side.The apparatus according to claim 1, wherein the controller includes a map matching unit configured to perform the map matching based on lane fusion data in which a long-distance lane boundary recognized by the front camera processor and the short-distance lane boundary and the stop line recognized by the SVM processor are fused, and / or parking lot map data from the map data unit and / or vehicle behavior data predicted by dead reckoning for each time point.The apparatus according to claim 4, wherein the map matching unit is configured to calculate a position and rotation correction amount in which a distance error between sensor data and map data is minimized by using iterative closest point logic (ICP).The apparatus according to claim 1, wherein the controller comprises a position fusion unit configured to fuse a vehicle positioning output as results of map matching and the GPS information of a vehicle position predicted by dead reckoning navigation.The apparatus according to claim 6, wherein: the controller includes a fail-safe diagnosis unit configured to receive the vehicle position and flags output from the position fusion unit and perform a fail-safe diagnosis, and the fail-safe diagnosis unit is configured to perform the fail-safe diagnosis using a distribution diagram configured with estimated positioning results in which past positioning results have been projected on the current time and positioning results input at the current time.Device according to Claim 6, in which the vehicle position has the longitude and / or the latitude and / or the heading and / or the covariance and / or a warning / fail / safe and / or flags and / or a lane offset.A method for estimating a position in an automated service parking system, the method comprising: downloading, by a controller, a map having an area designated as a parking zone from a map data unit to store a high resolution map when entry of a vehicle into a parking space is detected; recognizing, by the controller, a start position of an automated service parking (AVP) based on a short-distance lane boundary and a stop line detected by an around view monitor processor (SVM); and correcting, by the controller, a position measurement value of the vehicle by performing map matching based on the detection and processing results of a front camera processor and the SVM processor and the parking space map of the map data unit.The method of claim 9, further comprising: predicting, by dead reckoning, a behavior of the vehicle when the AVP start position is detected, by the controller; and estimating, by the controller, an AVP starting position of the vehicle by merging the vehicle position measurement corrected by the map matching and the predicted behavior of the vehicle.The method of claim 10, wherein the controller predicts the behavior of the vehicle by dead reckoning based on GPS information received from a GPS receiver and a vehicle steering wheel angle, yaw rate, and wheel speed received from a vehicle sensor unit.The method according to claim 9, wherein the controller, in the position measurement value correction, performs the map matching based on lane fusion data in which a long-distance lane boundary recognized by the front camera processor and the short-distance lane boundary and the stop line recognized by the SVM processor are fused, and / or parking space map data from the map data unit and / or vehicle behavior data predicted by dead reckoning for each time point.The method of claim 12, wherein the controller calculates, in the correction of the position measurement value, a position and rotation correction amount in which a distance error between sensor data and map data is minimized by using iterative closest point logic (ICP).The method of claim 9, wherein the controller, in estimating the AVP starting position, merges vehicle positioning output as results of map matching and GPS information of a predicted vehicle position by dead reckoning navigation.The method of claim 14, further comprising receiving, by the controller, the vehicle position and flags output as a result of the position fusion, and performing a fail-safe diagnosis, wherein, in performing the fail-safe diagnosis, the controller performs the fail-safe diagnosis using a distribution diagram configured with estimated positioning results in which past positioning results have been projected on the current time and positioning results input at the current time.

Images