Online Model Learning for Shape Control of Deformable Linear Objects

Abstract

Traditional approaches to manipulating the state of deformable linear objects (DLOs) -i.e., cables, ropes -rely on model-based planning. However, constructing an accurate dynamic model of a DLO is challenging due to the complexity of interactions and a high number of degrees of freedom. This renders the task of achieving a desired DLO shape particularly difficult and motivates the use of model-free alternatives, which while maintaining generality suffer from a high sample complexity. In this paper, we bridge the gap between these fundamentally different approaches and propose a framework that learns dynamic models of DLOs through trial-and-error interaction. Akin to model-based reinforcement learning (RL), we interleave learning and exploration to solve a 3D shape control task for a DLO. Our approach requires only a fraction of the interaction samples of the current state-of-theart model-free RL alternatives to achieve superior shape control performance. Unlike offline model learning, our approach does not require expert knowledge for data collection, retains the ability to explore, and automatically selects relevant experience.

Shape Control of Elastic Deformable Linear Objects for Robotic Cable Assembly

“…Han et al [ 29 ] proposed a method for estimating the deformation Jacobian matrix by combining it with function approximation technology that can control variable linear deformation objects to approach the target shape. Yang et al [ 30 ] used model‐based reinforcement learning for shape control in a task interspersed with learning and explored efficient sample‐based online dynamic learning and shape control through trial‐and‐error interactions.…”