Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience

Abstract

Manipulating deformable objects, such as fabric, is a long standing problem in robotics, with state estimation and control posing a significant challenge for traditional methods. In this paper, we show that it is possible to learn fabric folding skills in only an hour of self-supervised real robot experience, without human supervision or simulation. Our approach relies on fully convolutional networks and the manipulation of visual inputs to exploit learned features, allowing us to create an expressive goal-conditioned pick and place policy that can be trained efficiently with real world robot data only. Folding skills are learned with only a sparse reward function and thus do not require reward function engineering, merely an image of the goal configuration. We demonstrate our method on a set of towel-folding tasks, and show that our approach is able to discover sequential folding strategies, purely from trial-and-error. We achieve state-of-the-art results without the need for demonstrations or simulation, used in prior approaches. Videos available at: https://sites.google.com/view/learningtofold

References in corpus (9)

• Sim-to-Real Reinforcement Learning for Deformable Object Manipulation
• Learning Predictive Representations for Deformable Objects Using Contrastive Estimation
• Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
• Scaling data-driven robotics with reward sketching and batch reinforcement learning
• Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal
• VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation
• Learning to Manipulate Deformable Objects without Demonstrations
• Learning Robust Bed Making using Deep Imitation Learning with DART
• Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics

Cited by in corpus (7)

• FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding
• A Survey of Embodied Learning for Object-Centric Robotic Manipulation
• Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks
• ShakingBot: Dynamic Manipulation for Bagging
• VisuoSpatial Foresight for Physical Sequential Fabric Manipulation
• Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables
• Mixing Human Demonstrations with Self-Exploration in Experience Replay for Deep Reinforcement Learning