To achieve the ability for fulfilling the new task based on the learning form demonstration(LfD),a framework was proposed to represent the policy,imitation learning and optimization for robot intelligent trajectory planning was conducted,based on Gaussian mixture regression and policy improvement with path integral strategy(GMR-PI2).Meanwhile,self-reconstruction of the basis function and search of the weight coefficient of the policy expression were performed in two spaces alternately to conquer above probl...
| 
推荐 
点击下列相关研究机构和相关文献作者，可以直接查到这些机构和作者被《中国知识资源总库》收录的其它文献，使您全面了解该机构和该作者的研究动态和历史。
