Research on the Path Planning Algorithm of a Manipulator Based on GMM/GMR-MPRM

Abstract

Autonomous, flexible, and human–robot collaboration are the key features of the next-generation robot. Such unstructured and dynamic environments bring great challenges in online adaptive path planning. The robots have to avoid dynamic obstacles and follow the original task path as much as possible. A robust and efficient online path planning method is required accordingly. A method based on the Gaussian Mixture Model (GMM), Gaussian Mixture Regression (GMR), and the Probabilistic Roadmap (PRM) is proposed to overcome the above difficulties. During the offline stage, the GMM was used to model teaching data, and it can represent the offline-demonstrated motion and constraints. The optimal solution was encoded in the mean value, while the environmental constraints were encoded in the variance value. The GMR generated a smooth path with variance as the resample space according to the GMM of the teaching data. This representation isolated the old environment model with the novel obstacle. During the online stage, a Modified Probabilistic Roadmap (MPRM) was used to plan the motion locally. Because the GMM provides the distribution of all the feasible motion, the sampling space of the MPRM was generated by the variable density resampling method, and then, the roadmap was constructed according to the Euclidean and Probability Distance (EPD). The Dijkstra algorithm was used to search for the feasible path between the starting point and the target point. Finally, shortcut pruning and B-spline interpolation were used to generate a smooth path. During the simulation experiment, two obstacles were added to the recurrent scene to indicate the difference from the teaching scene, and the GMM/GMR-MPRM algorithm was used for path planning. The result showed that it can still plan a feasible path when the recurrent scene is not the same as the teaching scene. Finally, the effectiveness of the algorithm was verified on the IRB1200 robot experiment platform.