Dynamic Manipulation of Deformable Objects using Imitation Learning with Adaptation to Hardware Constraints
On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning
Abstract (arXiv)
Imitation Learning (IL) is a promising paradigm for learning dynamic manipulation of deformable objects since it does not depend on difficult-to-create accurate simulations of such objects. However, the translation of motions demonstrated by a human to a robot is a challenge for IL, due to differences in the embodiments and the robot's physical limits. These limits are especially relevant in dynamic manipulation where high velocities and accelerations are typical. To address this problem, we propose a framework that first maps a dynamic demonstration into a motion that respects the robot's constraints using a constrained Dynamic Movement Primitive. Second, the resulting object state is further optimized by quasi-static refinement motions to optimize task performance metrics. This allows both efficiently altering the object state by dynamic motions and stable small-scale refinements. We evaluate the framework in the challenging task of bag opening, designing the system BILBO: Bimanual dynamic manipulation using Imitation Learning for Bag Opening. Our results show that BILBO can successfully open a wide range of crumpled bags, using a demonstration with a single bag. See supplementary material at https://sites.google.com/view/bilbo-bag.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 15 of its 27 references that are in the map. First posted on arXiv 19 Mar 2024.
Builds on
15 of 27 references.
References · 15
- 2021FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfoldingcited by 80
- 2020Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networkscited by 77
- 2022Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objectscited by 36
- 2020Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cablescited by 21
- 2022DextAIRity: Deformable Manipulation Can be a Breezecited by 17
- 2022AutoBag: Learning to Open Plastic Bags and Insert Objectscited by 14
- 2023Benchmarking the Sim-to-Real Gap in Cloth Manipulationcited by 14
- 2022Bag All You Need: Learning a Generalizable Bagging Strategy for Heterogeneous Objectscited by 12
- 2021Graph-based Task-specific Prediction Models for Interactions between Deformable and Rigid Objectscited by 10
- 2021Learning Visual Feedback Control for Dynamic Cloth Foldingcited by 10
- 2023Bagging by Learning to Singulate Layers Using Interactive Perceptioncited by 7
- 2023QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulationcited by 5
3 more
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation
- 2024A Comparison of Imitation Learning Algorithms for Bimanual Manipulation
- 2025Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy
- 2022A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies
- 2025Imitation Learning-Based Path Generation for the Complex Assembly of Deformable Objects
- 2025Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models
- 2024ALOHA Unleashed: A Simple Recipe for Robot Dexterity
- 2022Learning Deformable Object Manipulation from Expert Demonstrations