Abstract:
Disclosed herein are an apparatus and method for automatically parking a vehicle. The apparatus for automatically parking a vehicle includes a location/heading information provision unit and a parking algorithm computation unit. The location/heading information provision unit calculates the corrected distances of movement of first and second wheels of the vehicle from the time at which parking is started using a plurality of correction factors that are calculated during a movement in any one of forward and rearward headings and during determination of a parking space, and calculates the changes in a heading and location of the vehicle using the corrected distances of movement. The parking algorithm computation unit generates a vehicle control signal intended to automatically park the vehicle in the parking space based on the changes in the heading and location of the vehicle.
Abstract:
Disclosed herein is an apparatus and method for providing location and heading information of an autonomous driving vehicle on a road within a housing complex. The apparatus includes an image sensor installed on an autonomous driving vehicle and configured to detect images of surroundings depending on motion of the autonomous driving vehicle. A wireless communication unit is installed on the autonomous driving vehicle and is configured to receive a Geographic Information System (GIS) map of inside of a housing complex transmitted from an in-housing complex management device in a wireless manner. A location/heading recognition unit is installed on the autonomous driving vehicle, and is configured to recognize location and heading of the autonomous driving vehicle based on the image information received from the image sensor and the GIS map of the inside of the housing complex received via the wireless communication unit.
Abstract:
Disclosed herein are an object recognition apparatus of an automated driving system using error removal based on object classification and a method using the same. The object recognition method is configured to train a multi-object classification model based on deep learning using training data including a data set corresponding to a noise class, into which a false-positive object is classified, among classes classified by the types of objects, to acquire a point cloud and image data respectively using a LiDAR sensor and a camera provided in an autonomous vehicle, to extract a crop image, corresponding to at least one object recognized based on the point cloud, from the image data and input the same to the multi-object classification model, and to remove a false-positive object classified into the noise class, among the at least one object, by the multi-object classification model.