PurposeTraditional robot arm trajectory planning methods have problems such as insufficient generalization performance and low adaptability. This paper aims to propose a method to plan the robot arm’s trajectory using the trajectory learning and generalization characteristics of dynamic motion primitives (DMPs).Design/methodology/approachThis study aligns multiple demonstration motion primitives using dynamic time warping; use the Gaussian mixture model and Gaussian mixture regression methods to obtain the ideal primitive trajectory actions. By establishing a system model that improves DMPs, the parameters of the nonlinear function are learned based on the ideal primitive trajectory actions of the robotic arm, and the robotic arm motion trajectory is reproduced and generalized.FindingsExperiments have proven that the robot arm motion trajectory learned by the method proposed in this article can not only learn to generalize and demonstrate the movement trend of the primitive trajectory, but also can better generate ideal motion trajectories and avoid obstacles when there are obstacles. The maximum Euclidean distance between the generated trajectory and the demonstration primitive trajectory is reduced by 29.9%, and the average Euclidean distance is reduced by 54.2%. This illustrates the feasibility of this method for robot arm trajectory planning.Originality/valueIt provides a new method for the trajectory planning of robotic arms in unstructured environments while improving the adaptability and generalization performance of robotic arms in trajectory planning.
Read full abstract