Abstract
In this paper, we propose a biologically inspired framework for robot learning based on demonstrations. The dynamic movement primitive (DMP), which is motivated by neurobiology and human behavior, is employed to model a robotic motion that is generalizable. However, the DMP method can only be used to handle a single demonstration. To enable the robot to learn from multiple demonstrations, the DMP is combined with the Gaussian mixture model (GMM) to integrate the features of multiple demonstrations, where the conventional GMM is further replaced by the fuzzy GMM (FGMM) to improve the fitting performance. Also, a novel regression algorithm for FGMM is derived to retrieve the nonlinear term of the DMP. Additionally, a neural network-based controller is developed for the robot to track the generated motions. In this network, the cerebellar model articulation controller is employed to compensate for the unknown robot dynamics. The experiments have been performed on a Baxter robot to demonstrate the effectiveness of the proposed methods.
Highlights
I N THE recent decades, robots have been widely applied in both industrial manufacturing and the daily life of individuals
Considering the nonlinearity of the demonstrations, the conventional Gaussian mixture model (GMM) is replaced by the fuzzy GMM (FGMM) to improve the fitting performance, which is based on the generalized single Gaussian model (SGM)
The tracking errors are reduced into the interval [−0.035, 0.035] with the compensation torques generated by the neural network as is shown in Fig. 11(d) and (e), where the effect caused by the unknown dynamics and the dynamic environment is compensated for
Summary
I N THE recent decades, robots have been widely applied in both industrial manufacturing and the daily life of individuals. The GMR has been utilized to construct the DS model called the stable estimator of DSs for stable motions [20] Inspired by these works and further considering the fitting performance of the GMM, the fuzzy GMM (FGMM) [25] is employed to fuse the features of multiple demonstrations into the nonlinear term of the DMP in this paper, which has been proposed to improve the learning efficiency of the active curve axis GMM [26] and has shown better nonlinearity fitting performance than the conventional GMM. Most of this papers on this subject have only concentrated on the motion modeling without considering the performance of the dynamics controller; this paper accounts for these two aspects to develop a more complete robot LfD framework.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Transactions on Cognitive and Developmental Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.