Patent classifications
G01S2015/936
Parking assist system, method, and non-transitory computer readable medium storing program
A parking assist system includes an electronic control unit configured to: estimate first extending directions of obstacles respectively located on right and left sides of a target parking space in a state where a host vehicle moves across in front of the target parking space; calculate a planned moving path based on the estimated first extending directions; as the host vehicle is guided into the target parking space, estimate second extending directions of the obstacles respectively located on the right and left sides of the target parking space while updating the second extending directions; determine whether the estimated and updated second extending directions satisfy a predetermined condition; and when the updated second extending directions satisfy the predetermined condition, update the planned moving path by using the updated second extending directions instead of the first extending directions or the second extending directions before being updated.
SENSOR-BASED PARKING SPACE SEARCHING SYSTEM AND METHOD THEREOF
A sensor-based parking space searching system and a method thereof may include a switch receiving a request for searching for a parking space from a driver, an ultrasonic sensor searching for the parking space, and a controller activating the ultrasonic sensor in response to the request for searching for the parking space, setting a speed of an ego-vehicle and a reference value for detecting an effective detecting point of the ultrasonic sensor based on a distance from an object to the ego-vehicle, which is measured by the ultrasonic sensor, and recognizing the parking space based on an output of the ultrasonic sensor.
PARKING MODE DETERMINING SYSTEM
A parking mode determining system includes a distance measurer to measure a distance to an obstacle on the side of a host vehicle; a host-vehicle position measurer to measure a position of the host vehicle; a reflected position calculator to calculate a reflected position of the transmission wave; a grouping unit to group a plurality of the reflected positions for each obstacle; an angle calculator to obtain an approximate line for each of two or more of the reflected positions adjacent to each other, and calculate an angle of inclination of the approximate line or an angle of inclination of a normal line of the approximate line; and a parking mode determiner to determine whether a parking mode is parallel parking, perpendicular parking, or angle parking on the basis of a distribution of a plurality of the angles of inclination.
Method for identifying parking spaces by means of ultrasonic sensors
The invention relates to a method for identifying parking spaces, including emitting an ultrasonic signal and receiving a reflected signal; and providing a grid which of a region having a plurality of cells. Each cell is assigned to a partial region of the region surrounding the vehicle and an occupancy value is assigned to each cell. The reflected signal is assigned to a set of cells of the grid based on a transit time of the ultrasonic signal between emission and reception. The occupancy values of the cells to which the reflected signal is allocated are increased by a specific value. An occupancy information item is determined based on the occupancy values of the cells. The signal emitting/receiving and the reflected signal assigning are repeated multiple times. Parking space identification is performed based on an occupancy status of the cells specified using the occupancy information item determination.
Parking assist apparatus
Provided is a parking assist apparatus capable of appropriately guiding a self-vehicle into a parking space even when accuracy of estimation of a corner position of each object located at a position adjacent to the parking space is low. Parking-space information, which is estimated by detecting the corner position of each of the objects sandwiching the parking space while the parking space is being searched, is sequentially corrected by using a reflection-point position on each of objects, which is detected while the self-vehicle is being guided into the parking space. Guiding assistance processing to the parking space is performed by using the corrected parking-space information.
PARKING ASSIST SYSTEM, METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM STORING PROGRAM
A parking assist system includes an electronic control unit configured to: estimate first extending directions of obstacles respectively located on right and left sides of a target parking space in a state where a host vehicle moves across in front of the target parking space; calculate a planned moving path based on the estimated first extending directions; as the host vehicle is guided into the target parking space, estimate second extending directions of the obstacles respectively located on the right and left sides of the target parking space while updating the second extending directions; determine whether the estimated and updated second extending directions satisfy a predetermined condition; and when the updated second extending directions satisfy the predetermined condition, update the planned moving path by using the updated second extending directions instead of the first extending directions or the second extending directions before being updated.
METHOD FOR CLASSIFYING OBJECTS
A method for classifying objects into object classes on the basis of information of an ultrasonic sensor of a vehicle, including receiving multiple detections of a vehicles's ultrasonic sensor. Items of position information and directional information are assigned to each detection. The position information indicates a reflection location where an ultrasonic sensor's signal was reflected and the directional information indicates a direction along which the ultrasonic signal propagates between the reflection location and ultrasonic sensor. The method includes forming detection clusters based on the received detections, with one cluster including multiple detections; calculating statistical distribution information of the position information and the directional information of the detections assigned to the respective cluster; and classifying an object into an object class based on the statistical distribution information of the position information and the directional information of the clusters.