Backend
Learning the Dynamics of Deformable Linear Objects Through Coupled Oscillators for Bimanual Robotic Manipulation
arXiv cs.RO0 views
arXiv:2611.23563v1 Announce Type: new Abstract: Many learning-based approaches for deformable linear objects (DLOs) rely on simplified deformation models that neglect dynamic effects and the mechanical response of the objects, limiting their applicability to lightweight, compliant objects and slow motions. Inspired by recent advances in learning physically structured dynamics with coupled oscillator networks (CONs), we propose $\Phi$-CON for learning force-driven DLO dynamics. The model combines a floating-base coupled oscillator network (FBCON), whose latent potential energy depends only on the DLO's shape, with a learned affine diffeomorphism $\Phi$ between observed positions along the DLO and latent coordinates. Its shape dynamics are stable by construction, and its Lagrangian structure yields explicit expressions for kinetic and potential energy. We exploit this structure to design a model-based proportional-derivative (PD) controller that compensates for the learned potential forces, thereby establishing closed-loop stability guarantees and ensuring convergence. We evaluate the approach on four simulated DLOs and a real bimanual robot setup. In simulation, $\Phi$-CON achieves prediction accuracy comparable to neural ordinary differential equation (NODE) models and Lagrangian neural networks (LNNs), with $97.2\%$ and $90.2\%$ fewer parameters, respectively. Relative to a model-free PD baseline, the proposed controller reduces mean endpoint regulation error by $97.5$-$99.7\%$ in simulation and achieves a mean per-target reduction of $27.9\%$ across both endpoints in real-world experiments, demonstrating the importance of explicitly accounting for the mechanical response of stiff and heavy objects.
Source:https://arxiv.org/abs/2611.23563PreviousRESCUE Jumper: A Centimeter-Scale Rolling and Jumping Robot for Search and RescueNextPanini- Feasible Grammar For Robot Designs
Related posts
Worth Another Look:Constrained World-Model Planning for Visual Inspection
0arXiv cs.RO
Dual-Actuation Emulation of Scaled Relative Orbital Dynamics on a Free-Flyer
0arXiv cs.RO
JEPA Dots: Dual-Latent World Model for Language-Guided Robot Control
0arXiv cs.RO
Modelling the human-exoskeleton interaction interface - Benchmarking MuJoCo's deformable model
0arXiv cs.RO
Facet-SLAM: Real-Time Triangle Splatting SLAM
0arXiv cs.RO
10 Copy-Paste AI Prompts That Automate 2 Hours of Daily Work in 2027
0dev.to AI