Abstract: A deep learning-based method for recognizing continuous shovel loading positions in an autonomous loader includes: acquiring laser point cloud data representing surface topography of a stockpile, and processing the laser point cloud data to obtain shovel-loading region features of the stockpile; constructing a model of an actuating mechanism for a loader, performing simulation force analysis on the model of the actuating mechanism and the shovel-loading region features of the stockpile, to obtain shovel-loading position features of the stockpile; analyzing and evaluating the shovel-loading position features of the stockpile to obtain an optimal shovel-loading position feature of the stockpile; and constructing a detection model, acquiring an image of the stockpile to be identified simultaneously, inputting the image of the stockpile to be identified into the detection model for processing, and detecting and adjusting a shovel-loading position of the loader based on the image processing results and the optimal