Deformable Object Manipulation under Partial Observability via Real-Time Full-Shape Estimation

Deformable Object Manipulation under Partial Observability via Real-Time Full-Shape Estimation

|Authors: Kosar Behnia, Ville Kyrki, Gokhan Alcan

|Venue: arXiv preprint | Year: 2026

|arXiv: 2609.10308v1

Abstract

Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, underactuated dynamics, and partial observability. In this paper, we propose cRVAE, a lightweight conditional recurrent variational autoencoder that estimates the full DO state from only partial corner-node observations during inference. The resulting model is used as the forward model in a receding-horizon optimal control framework for obstacle-aware collaborative DO manipulation. In simulation on rope and fabric, cRVAE estimates the full DO state from the available corner-node measurements alone, matching the accuracy of a parameter-identified XPBD model. At inference it uses no physical parameters as model inputs and performs no online parameter identification. It also runs approximately 350 times faster on the rope and over 1500 times faster on the fabric per forward pass, keeping horizon-based planning within the 100 ms control budget where XPBD exceeds it already at short horizons. Full-shape estimation from corner sensing at in-loop speed is what makes the model deployable on hardware, which we demonstrate on a Unitree Go2 robot.

Key Contributions

• Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, u…
• In this paper, we propose cRVAE, a lightweight conditional recurrent variational autoencoder that…
• The resulting model is used as the forward model in a receding-horizon optimal control framework …
• In simulation on rope and fabric, cRVAE estimates the full DO state from the available corner-nod…
• At inference it uses no physical parameters as model inputs and performs no online parameter iden…

Topics

• manipulation
• planning
• control

Code & Data

No code repository linked in paper metadata.

BibTeX

@article{Behnia2026_260910308v1,
  title     = {Deformable Object Manipulation under Partial Observability via Real-Time Full-Shape Estimation},
  author    = {Kosar Behnia and Ville Kyrki and Gokhan Alcan},
  year      = {2026},
  eprint    = {2609.10308v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2609.10308v1}
}