Tactile-Guided Dynamic Contrastive Koopman Operator for Deformable Linear Object Manipulation

Aohua Liu, Kun Qian, Boyi Duan, Shan Luo

Keywords: Koopman operator, contrastive learning, high dimensional nonlinear systems, tactile servo

Abstract:

Strong nonlinearities and infinite degrees of freedom pose intractable challenges for the manipulation of deformable linear objects (DLOs). This paper proposes a novel modeling method based on a deep Koopman operator for nonlinear systems with high-dimensional
inputs, enabling precise tactile servo performance. Initially, a dynamic contrastive learning algorithm is proposed to approximate the Koopman operator for the unknown dynamic system in the embedded space. During the training phase, a dynamic negative sampling strategy based on a task-oriented state distance measurement is employed to ensure consistency between the distance metrics in the embedded and the original spaces. Furthermore, a Koopman-based model predictive controller is developed to compensate for modeling errors, with stability conditions explicitly outlined. Extensive experiments demonstrate that the proposed method outperforms the representative deep Koopman algorithms in modeling performance and high-dimensional tactile servoing tasks.

Submission Number: 11