Robot SLAM method and system used in outdoor feature sparse environment

The invention provides a mobile robot vision inertia SLAM method and system used in an outdoor feature sparse environment. The method comprises the steps: obtaining an environment image in the outdoor feature sparse environment, carrying out the preprocessing of the environment image, and obtaining a preprocessed environment image; extracting sparse features of the preprocessed environment image through a block SIFT feature extraction algorithm; estimating the inter-frame motion of a robot through the pre-integration quantity of an inertial unit IMU, estimating the inter-frame displacement of a matching point, judging the importance of sparse features through the displacement, and calculating to obtain a visual re-projection error; obtaining an IMU error according to variance accumulation in an IMU pre-integration process; jointly constructing a loss function according to the visual re-projection error and the IMU error; and minimizing a loss function through a nonlinear optimization method, and solving pose