Improved rrt path planning method for robot-assisted puncture based on sac-based guided sampling

Abstract

This invention discloses an improved RRT path planning method for robot-assisted puncture based on SAC-guided sampling, comprising: reconstructing a three-dimensional model of the actual physiological structure of the human chest and abdomen based on CT images to obtain the three-dimensional model of the actual physiological structure of the human chest and abdomen as obstacles for subsequent path planning; establishing a reinforcement learning environment based on the obstacles, including setting a state space, action space, and reward function; training a SAC-guided sampling model for flexible needle path planning based on the obstacles using the SAC algorithm in the reinforcement learning environment; optimizing the target parameters of the SAC-guided sampling model based on the obstacles; and using the parameter-optimized SAC-guided sampling model to sample in the improved RRT path planning based on a hybrid sampling strategy to obtain feasible paths. By using a hybrid sampling strategy, a balance is achieved between the global search capability of uniform sampling and the local optimization capability of non-uniform guided sampling, thereby improving the adaptability and planning efficiency of the algorithm in complex scenarios.

Images