Abstract: A method and apparatus for controlling the flight of an Unmanned Aerial Vehicle (UAV) are provided. The method includes: determining a starting flight position where a UAV is parked currently and a nose direction of the UAV (101); starting off from the starting flight position, and flying along a straight line in the nose direction (102); and when receiving a route adjustment instruction during the flight of the UAV, adjusting an air route of the UAV according to the route adjustment instruction (103). During the flight, an operator can correct an air route via a remote control apparatus without surveying and mapping when detecting that the UAV is flying off course; and the operator can make the UAV precisely fly along a desired straight line by means of simple operations.

Abstract: A method and apparatus for controlling the flight of an Unmanned Aerial Vehicle (UAV) are provided. The method includes: determining a starting flight position where a UAV is parked currently and a nose direction of the UAV (101); starting off from the starting flight position, and flying along a straight line in the nose direction (102); and when receiving a route adjustment instruction during the flight of the UAV, adjusting an air route of the UAV according to the route adjustment instruction (103). During the flight, an operator can correct an air route via a remote control apparatus without surveying and mapping when detecting that the UAV is flying off course; and the operator can make the UAV precisely fly along a desired straight line by means of simple operations.

Abstract: Embodiments of the present invention provide a machine learning model training method, including: obtaining target task training data and N categories of support task training data; inputting the target task training data and the N categories of support task training data into a memory model to obtain target task training feature data and N categories of support task training feature data; training the target task model based on the target task training feature data and obtaining a first loss of the target task model, and separately training respectively corresponding support task models based on the N categories of support task training feature data and obtaining respective second losses of the N support task models; and updating the memory model, the target task model, and the N support task models based on the first loss and the respective second losses of the N support task models.

Abstract: A conveying apparatus includes a holding plate having a holding surface destined to face a surface of a wafer to be held; a restriction member on one end side of the holding surface adapted to contact the periphery of the wafer so as to restrict movement of the wafer; and a moving unit adapted to move the holding plate. At the holding surface, a non-contact type suction holding part is adapted to jet a fluid obliquely to the surface of the wafer to be held so as to move the wafer toward the restriction member and generate a negative pressure between the holding surface and the surface to be held, thereby holding the wafer by suction. The fluid is jetted from the suction holding part so as to abut the wafer against the restriction member, thereby positioning the wafer at a predetermined position on the holding plate.

Abstract: A conveying apparatus includes a holding plate having a holding surface destined to face a surface of a wafer to be held; a restriction member on one end side of the holding surface adapted to contact the periphery of the wafer so as to restrict movement of the wafer; and a moving unit adapted to move the holding plate. At the holding surface, a non-contact type suction holding part is adapted to jet a fluid obliquely to the surface of the wafer to be held so as to move the wafer toward the restriction member and generate a negative pressure between the holding surface and the surface to be held, thereby holding the wafer by suction. The fluid is jetted from the suction holding part so as to abut the wafer against the restriction member, thereby positioning the wafer at a predetermined position on the holding plate.