GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy

2023-06-14

arXiv.org

AI Summary

Existing rope manipulation methods require extensive trial-and-error to adapt to diverse rope types, severely limiting generalization to real-world scenarios. This paper introduces the first parameter-aware, one-shot generalization framework for end-to-end rope manipulation across rope categories, requiring only a single real-world demonstration. Our method jointly integrates online rope parameter estimation—based on point-cloud density matching—with differentiable physics simulation. We design a policy network conditioned on physical parameters (e.g., bending stiffness and mass density) and enhance both in-distribution and out-of-distribution generalization via cross-distribution simulation training. Experiments demonstrate a 62% improvement in simulation success rate over baselines under in-distribution settings and a 15% gain under out-of-distribution conditions. On real robotic hardware, task success rates increase by 26%, significantly surpassing conventional approaches that rely on hundreds of demonstrations.

Abstract

Due to the inherent uncertainty in their deformability during motion, previous methods in rope manipulation often require hundreds of real-world demonstrations to train a manipulation policy for each rope, even for simple tasks such as rope goal reaching, which hinder their applications in our ever-changing world. To address this issue, we introduce GenORM, a framework that allows the manipulation policy to handle different deformable ropes with a single real-world demonstration. To achieve this, we augment the policy by conditioning it on deformable rope parameters and training it with a diverse range of simulated deformable ropes so that the policy can adjust actions based on different rope parameters. At the time of inference, given a new rope, GenORM estimates the deformable rope parameters by minimizing the disparity between the grid density of point clouds of real-world demonstrations and simulations. With the help of a differentiable physics simulator, we require only a single real-world demonstration. Empirical validations on both simulated and real-world rope manipulation setups clearly show that our method can manipulate different ropes with a single demonstration and significantly outperforms the baseline in both environments (62% improvement in in-domain ropes, and 15% improvement in out-of-distribution ropes in simulation, 26% improvement in real-world), demonstrating the effectiveness of our approach in one-shot rope manipulation.

Problem

• Rope Manipulation
• Adaptability
• Learning Framework

Innovation

• GenORM
• Parameterized Rope Deformation
• Adaptive Control Strategy