Enhanced task parameterized dynamic movement primitives by GMM to solve manipulation tasks

Abstract

Purpose

Under the development trend of intelligent manufacturing, the unstructured environment requires the robot to have a good generalization performance to adapt to the scene changes. The purpose of this paper aims to present a learning from demonstration (LfD) method (task parameterized [TP]-dynamic movement primitives [DMP]-GMR) that combines DMPs and TP-LfD to improve generalization performance and solve object manipulation tasks.

Design/methodology/approach

The dynamic time warping algorithm is applied to processing demonstration data to obtain a more standard learning model in the proposed method. The DMPs are used to model the basic trajectory learning model. The Gaussian mixture model is introduced to learn the force term of DMPs and solve the problem of learning from multiple demonstration trajectories. The robot can learn more local geometric features and generalize the learned model to unknown situations by adding task parameters.

Findings

An evaluation criterion based on curve similarity calculated by the Frechet distance was constructed to evaluate the model’s interpolation and extrapolation performance. The model’s generalization performance was assessed on 2D virtual data sets, and first, the results show that the proposed method has better interpolation and extrapolation performance than other methods.

Originality/value

The proposed model was applied to the axle-hole assembly task on real robots, and the robot’s posture in grasping and placing the axle part was taken as the task parameter of the model. The experiment results show that The proposed model is competitive with other models.

Citation

Li, J., Cong, M., Liu, D. and Du, Y. (2023), "Enhanced task parameterized dynamic movement primitives by GMM to solve manipulation tasks", Robotic Intelligence and Automation, Vol. 43 No. 2, pp. 85-95. https://doi.org/10.1108/RIA-07-2022-0199