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.
Highlights
Conventional industrial robots work in a safety fence, and their work trajectory is usually preset through a program
The sampling space is constructed by means of variable density resampling, and more sampling points are generated in the Gaussian component close to the obstacle, which improves the resampling speed and the success rate of path planning;
The path planned by the Gaussian Mixture Model (GMM)/Gaussian Mixture Regression (GMR)-Modified Probabilistic Roadmap (MPRM) is shown in Figure 7, and it can be seen from the figure that the GMM/GMR-MPRM can still plan a feasible path when the recurrent scene is not the same as the teaching scene
Summary
Conventional industrial robots work in a safety fence, and their work trajectory is usually preset through a program. Path planning algorithms based on sampling always start planning from the beginning, while the LfD method aims to generate task trajectories from human teaching paths. By estimating an unknown reward function from the demonstration and using the quasi-Newton strategy to learn the parameters of the reward function, Amir realized the path planning [23] These algorithms are generally based on nonlinear optimization, which may fall into local minima. The sampling space is constructed by means of variable density resampling, and more sampling points are generated in the Gaussian component close to the obstacle, which improves the resampling speed and the success rate of path planning;. According to the teaching path data, the GMM algorithm is used to obtain the Gaussian conditional distribution of the data of the teaching path, and the GMR algorithm is used to generate the task path and sampling space. The feasible space of the trajectory is used as the sampling space of the MPRM algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
