Intelligent planning system and method for optimal path in complex three-dimensional space

Abstract

The application relates to the technical field of artificial intelligence, and discloses an optimal path intelligent planning system and method for a complex three-dimensional space, which comprises the following steps: acquiring CT image data of a patient before surgery, using a GNN graph neural network to extract the spatial relationship between a tumor and a blood vessel in a three-dimensional anatomical model, generating a dynamic adjacency matrix, and outputting multiple surgical candidate paths from a chest cavity entrance to a tumor core; using an improved NSGA-II algorithm to optimize the multiple surgical candidate paths to obtain initial surgical path control instructions; using a rapid collision detection model based on an AABB hierarchical bounding box and a GJK algorithm to calculate the position and invasion depth of an end effector of a surgical robot in real time, obtaining a collision detection result, generating target surgical path control instructions according to the collision detection result and the net contact force, effectively shortening the surgical path planning time to the order of minutes, and greatly improving the path safety margin compared with a traditional method.

Images