Route search system and method for autonomous parking based on cognitive sensor

A method of searching for an autonomous parking route based on a cognitive sensor, the method comprising:

• obtaining cognitive information for determining an existence and a location of an obstacle by sensing a space around a vehicle being driven in an inside of a parking lot;
• generating a global path for the inside of the parking lot as a node map by searching for a free space, in which the vehicle is capable of being driven, based on the cognitive information and by setting a node in the free space;
• and
• generating an optimal local path from a current location of the vehicle to a destination by connecting the node set in the free space while the vehicle moves inside the parking lot;
• wherein generating the global path comprises:
• dividing the space around the vehicle;
• distinguishing between a parking space, in which the obstacle is detected, and a free space, in which the obstacle is not detected, based on the cognitive information, searching for a driving free space, which has a width at which the vehicle is capable of being driven, in the free space, and selecting the driving free space as a part of the global path;
• and
• generating a high-priority (HP) node at an end of the driving free space, and setting the HP node for the driving free space on a parking lot map indicating the inside of the parking lot so as to be stored;
• wherein generating the global path further comprises generating a low-priority (LP) connection line parallel to a principal component analysis line with respect to a space after the HP node;
• and
• wherein generating the optimal local path comprises:
• lowering a priority of the HP node, through which the vehicle passes while being driven inside the parking lot, in inverse proportion to elapsed time;
• and
• generating a path from the current location of the vehicle to the destination based on a potential field and generating a path with a high priority of the HP node through which the vehicle passes to reach the destination as a local path.

A cognitive sensor-based autonomous parking route search system, the system comprising:

• a cognitive sensor configured to obtain cognitive information for determining an existence and a location of an obstacle by sensing a space around a vehicle being driven in an inside of a parking lot;
• a global path search module configured to generate a global path for the inside of the parking lot as a node map by searching for a free space, in which the vehicle is capable of being driven, based on the cognitive information and by setting a node in the free space;
• and
• an optimal local path generation module configured to generate an optimal local path from a current location of the vehicle to a destination by connecting the node set in the free space while the vehicle moves inside the parking lot;
• wherein the global path search module comprises:
• a cell setting device configured to determine whether the obstacle is recognized for each cell by dividing the space around the vehicle detected by the cognitive sensor into a plurality of cells;
• a free space search device configured to distinguish between a parking space, in which the obstacle is detected, and a free space, in which the obstacle is not detected, based on the cognitive information, to search for a driving free space, which has a width at which the vehicle is capable of being driven, in the free space, and to select the driving free space as a part of the global path;
• and
• a high-priority (HP) node setting device configured to generate a HP node at an end of the driving free space, and to set the HP node for the driving free space on a parking lot map indicating the inside of the parking lot so as to be stored;
• wherein the global path search module further comprises:
• a principal component analysis line generation device configured to generate a principal component indicating a distribution status of a covariance calculation region set depending on a detection location of the obstacle and to generate a principal component analysis line indicating directivity of the covariance calculation region having a probability of detecting the obstacle having a specific level or more;
• a low-priority (LP) connection line generation device configured to generate an LP connection line parallel to the principal component analysis line with respect to a space after the HP node;
• an LP node setting device configured to set a point, at which the LP connection line contacts another connection line or another node, to an LP node;
• and
• wherein the optimal local path generation module comprises:
• a priority update device configured to lower a priority of the HP node, through which the vehicle passes while being driven inside the parking lot, in inverse proportion to elapsed time;
• and
• a local path generation device configured to generate a path from the current location of the vehicle to the destination based on a potential field and to generate a path with a high priority of the HP node through which the vehicle passes to reach the destination as a local path.