Abstract: Provided is a mobile manipulator for performing a target motion, which includes a base unit configured to perform a positional shift and having a rail in some section thereof, and an arm unit including multi-joints and configured to perform a positional shift on the rail in consideration of a center of gravity when performing a target motion. The arm unit performs the target motion through adaptive neural network-based compensation control.

Abstract: Provided is an invention capable of securing versatility and precision in admittance control and enabling target force control on a surface of an object having a different property, in which a mutual contact force-based compensation method is used in the existing admittance control method to output a target force. To this end, the present disclosure provides a compensation algorithm that changes according to a mutual contact force with an object having a different physical property and mass-spring-damper parameters using data acquired while controlling a force input from a robot is provided. In addition, the present disclosure automatically performs tuning on coefficients related to a factor of a robot force control based on data obtained by executing a mutual contact force-based compensation in the conventional admittance control.

Abstract: A method and an apparatus for recognition a position and generating a path for autonomous driving of a mobile robot in an orchard environment are provided. The method converts three-dimensional (3D) point cloud data for the orchard environment into a 2D grid map, obtains a position of the mobile robot by performing local scan matching and global scan matching on the 2D grid map, and extracts a tree from the 2D grid map based on occupancy of each grid of the 2D grid map. Then, an effective line based on center points of extracted trees is obtained, a destination based on the obtained effective line is generated, and a driving path according to the generated destination and the position of the mobile robot is generated.

Abstract: A method and an apparatus for recognition a position and generating a path for autonomous driving of a mobile robot in an orchard environment are provided. The method converts three-dimensional (3D) point cloud data for the orchard environment into a 2D grid map, obtains a position of the mobile robot by performing local scan matching and global scan matching on the 2D grid map, and extracts a tree from the 2D grid map based on occupancy of each grid of the 2D grid map. Then, an effective line based on center points of extracted trees is obtained, a destination based on the obtained effective line is generated, and a driving path according to the generated destination and the position of the mobile robot is generated.