Abstract: Disclosed is an unmanned platform with bionic visual multi-source information and intelligent perception. The unmanned platform is equipped with a bionic polarization vision/inertia/laser radar combined navigation module, a deep learning object detection module and an autonomous obstacle avoidance module; the bionic polarization vision/inertia/laser radar combined navigation module is configured to position and orient the unmanned platform in real time; the deep learning object detection module is configured to sense an environment around the unmanned platform according to RGB images of a surrounding environment collected by the bionic polarization vision/inertia/laser radar combined navigation module; and the autonomous obstacle avoidance module determines whether there are any obstacles around the unmanned platform during running according to the objects identified by the target, and performs autonomous obstacle avoidance in combination with the carrier navigation and positioning information.

Abstract: To obtain a global optimal navigation track, a contour line matching method based on sliding window data backtracking includes the steps of determining sliding window parameters according to the calculation performance of a real-time multi-task operating system and aided navigation precision requirements, constructing a sliding window data backtracking framework by using historical physical field value matching data, obtaining a rotation transformation matrix from an indication track point set to a closest reference point set by adopting a matrix eigenvalue and eigenvector decomposition method, and moving a sliding window and performing forward and reverse cyclic matching to achieve a global track constraint, thereby improving the matching precision and robustness.

Abstract: To obtain a global optimal navigation track, a contour line matching method based on sliding window data backtracking includes the steps of determining sliding window parameters according to the calculation performance of a real-time multi-task operating system and aided navigation precision requirements, constructing a sliding window data backtracking framework by using historical physical field value matching data, obtaining a rotation transformation matrix from an indication track point set to a closest reference point set by adopting a matrix eigenvalue and eigenvector decomposition method, and moving a sliding window and performing forward and reverse cyclic matching to achieve a global track constraint, thereby improving the matching precision and robustness.