A Gaussian Mixture Model Based Fast Motion Planning Method Through Online Environmental Feature Learning

Abstract

Rapidly-exploring Random Tree (RRT) and its applications for mobile robot navigation have attracted extensive interest in human-robot interaction environments. However, most current sampling-based motion planning algorithms are easy to fall into the trap space in complex and dynamic environments. In this paper, a fast motion planning algorithm based on Gaussian Mixture Model is proposed to allow robotic systems to efficiently extract feature nodes and generate cheuristic paths considering the pedestrian density and the environmental structure. Firstly, the preliminary feature nodes are obtained by training GMM, in which the covariance matrix of each feature node contains the environmental structure information. Secondly, an online feature learning method is presented to extract features during the movement of the robot by the dual-channel scale filter and the secondary distance fusion. Once the free grids can be connected to the feature nodes without any collision, a heuristic path is generated directly to guide the robot to avoid the crowds according to the proposed pedestrian matrix. For the same environment, the learned information can be reused as prior knowledge in the next path planning to further improve the efficiency of re-planning. A series of experimental studies demonstrate that our proposed method can remarkably reduce the time and enhance the success rate of navigation in trapped and narrow environments.