Wiggle and Go! System Identification for Zero-Shot Dynamic Rope Manipulation

2026-04-23

AI Summary

Dynamic rope manipulation suffers from high failure rates due to the absence of accurate physical models, and existing approaches rely heavily on extensive real-world data or trial-and-error. This work proposes a two-stage, zero-shot manipulation framework: first, a task-agnostic rope system identification module estimates physical parameters from observations; then, leveraging simulation priors and Fourier frequency-domain analysis, it drives goal-conditioned action optimization to generate control policies. The method enables seamless multi-task execution without any real-world training data. Evaluated on a real-world 3D target-hitting task, it achieves an average positioning error of only 3.55 cm—significantly lower than the baseline’s 15.34 cm—and attains a Pearson correlation coefficient of 0.95 between predicted and actual trajectory Fourier spectra.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Many robotic tasks are unforgiving; a single mistake in a dynamic throw can lead to unacceptable delays or unrecoverable failure. To mitigate this, we present a novel approach that leverages learned simulation priors to inform goal-conditioned dynamic manipulation of ropes for efficient and accurate task execution. Related methods for dynamic rope manipulation either require large real-world datasets to estimate rope behavior or the use of iterative improvements on attempts at the task for goal completion. We introduce Wiggle and Go!, a system-identification, two-stage framework that enables zero-shot task rope manipulation. The framework consists of a system identification module that observes rope movement to predict descriptive physical parameters, which then informs an optimization method for goal-conditioned action prediction for the robot to execute zero-shot in the real. Our method achieves strong performance across multiple dynamic manipulation tasks enabled by the same task-agnostic system identification module which offers seamless switching between different manipulation tasks, allowing a single model to support a diverse array of manipulation policies. We achieve a 3.55 cm average accuracy on 3D target striking in real using rope system parameters in comparison to 15.34 cm accuracy when our task model is not system-parameter-informed. We achieve a Pearson correlation coefficient of 0.95 between Fourier frequencies of the predicted and real ropes on an unseen trajectory. Project website please see https://wiggleandgo.github.io/

Problem

• dynamic rope manipulation
• zero-shot
• system identification
• robotic manipulation
• goal-conditioned control

Innovation

• zero-shot manipulation
• system identification
• dynamic rope manipulation
• learned simulation priors
• goal-conditioned control