Abstract: The present invention relates to a sensor fusion object detection system and method of deriving the object segmentation information including segmented point segments for each object by clustering a point cloud obtained from a LIDAR sensor, deriving object recognition information for each object from an image obtained from a camera sensor, and deriving object point groups using a graph-based probability optimization technique based on a first probability as to whether each point segment calculated based on the object segmentation information and the object recognition information correspond to a particular object and a second probability as to whether two different point segments correspond to the same object and merged as one. According to the object detection system and method according to the present invention, there is an effect that it is possible to accurately detect an object having a complex shape or a large size.

Abstract: A map matching method for autonomous driving includes extracting a first statistical map from 3D points contained in 3D map data; extracting a second statistical map from 3D points of surroundings which are obtained by a detection sensor simultaneously or after the previous extracting of the statistical map; dividing the second statistical map into a vertical-object part and a horizontal-object part; and performing map matching using the horizontal-object part and/or the vertical-object part and the first statistical map.

Abstract: The present invention relates to a steering control system and method for a vehicle, and more particularly a control system and method for accurately controlling the lateral movement of an autonomous vehicle that has a non-linear steering system, e.g., a hydraulic steering system, which includes measuring wheel angles of the vehicle, calculating the actuation value for the desired wheel angle based on the measured wheel angle, and rotating the steering wheel according to the actuation value; wherein the actuation values are calculated based on a function f( ) representing the nonlinear behavior of the steering ratio depending on the position and movement direction of the steering wheel, and another function g( ) representing a response lag when the steering direction is changed.

Abstract: The present invention relates to a method for estimating a position of an ego vehicle for autonomous driving including the steps of: receiving first sensor inputs from first sensors to extract visual road information; allowing the extracted visual road information to match first map data to produce a first matching score group; receiving second sensor inputs from second sensors; allowing the received second sensor inputs to match the second map data to produce a second matching score group; checking whether the first matching score group is consistent to the second matching score group; and estimating any one of the position candidates in the position candidate group of the ego vehicle as the position of the ego vehicle according to the consistency checking result.