Semantic ORB-SLAM sensing method and device based on environmental understanding

The invention discloses a semantic ORB-SLAM sensing method and device based on environmental understanding, and the method comprises the steps: inputting a sequence frame into an ORB-SLAM front-end Tracking thread for key frame extraction, and obtaining key frame data; inputting the key frame data into an adjacent key frame graph optimization thread to perform key frame data optimization processing, and obtaining key frame data after graph optimization; calculating an error value between the key frame data after graph optimization, and generating a candidate set based on the error value; and performing closed-loop correction processing on the candidate set based on global map optimization and loop fusion, and performing synchronous positioning and map construction based on a correction result. According to the embodiment of the invention, the invention improves the remarkable effect of a robot on the environment perception, can enable the robot to obtain the higher-level cognitive information of a scene, and