Hierarchical Deformation Planning and Neural Tracking for DLOs in Constrained Environments

TL;DR

This paper tackles the challenge of manipulating deformable linear objects (DLOs) in constrained, obstacle-rich spaces by introducing a hierarchical deformation framework that couples global planning with neural tracking. The planning component generates a homotopic spatial path set $\mathcal{P}$ through clearance-aware pivot paths and passage-assisted deformation, then maps this to a smooth, feasible deformation sequence via a nonlinear mass-spring objective. The tracking component employs a Transformer-based deformation model within a neural model-predictive control (MPC) loop to reliably follow the planned deformation while avoiding obstacles, demonstrated across extensive simulations and real-world experiments with diverse cables. The work advances DLO manipulation by bridging efficient global planning with data-driven, long-horizon deformation dynamics, enabling robust performance in cluttered environments and showing potential for broader, multi-robot or human-robot shared manipulation tasks.

Abstract

Deformable linear objects (DLOs) manipulation presents significant challenges due to DLOs' inherent high-dimensional state space and complex deformation dynamics. The wide-populated obstacles in realistic workspaces further complicate DLO manipulation, necessitating efficient deformation planning and robust deformation tracking. In this work, we propose a novel framework for DLO manipulation in constrained environments. This framework combines hierarchical deformation planning with neural tracking, ensuring reliable performance in both global deformation synthesis and local deformation tracking. Specifically, the deformation planner begins by generating a spatial path set that inherently satisfies the homotopic constraints associated with DLO keypoint paths. Next, a path-set-guided optimization method is applied to synthesize an optimal temporal deformation sequence for the DLO. In manipulation execution, a neural model predictive control approach, leveraging a data-driven deformation model, is designed to accurately track the planned DLO deformation sequence. The effectiveness of the proposed framework is validated in extensive constrained DLO manipulation tasks.

Figures (11)

• Figure 1: (a) DLO manipulation with a bi-manual robot. (b) Real-world cables. (c) Example of constrained DLO manipulation.
• Figure 2: Pipeline of the proposed manipulation framework, unifying hierarchical deformation planning and closed-loop neural MPC tracking.
• Figure 3: (a) Passage determination and validity checking routine. (b) Valid passages (dashed lines), workspace boundaries are treated as obstacles. (c) Pivot path planning with different parameters. (d) Failed case of pivot path transferring with linear interpolation. (e-h) Overview of passage-assisted homotopic path set generation. (i) Heuristic MS model along the path set. (j) Optimized deformation sequence in a constrained workspace with four obstacles.
• Figure 4: Deformation model architecture with three components: DLO encoder, robot encoder, and DLO decoder.
• Figure 5: Deformation planning and tracking results. (a) single obstacle avoidance, (b) multiple obstacle avoidance, and (c) maze navigation tasks.