PlaNet-ClothPick : effective fabric flattening based on latent dynamic planning
Date
09/02/2024Metadata
Show full item recordAbstract
Why do Recurrent State Space Models such as PlaNet fail at cloth manipulation tasks? Recent work has attributed this to the blurry prediction of the observation, which makes it difficult to plan directly in the latent space. This paper explores the reasons behind this by applying PlaNet in the pick-and-place fabric-flattening domain. We find that the sharp discontinuity of the transition function on the contour of the fabric makes it difficult to learn an accurate latent dynamic model, causing the MPC planner to produce pick actions slightly outside of the article. By limiting picking space on the cloth mask and training on specially engineered trajectories, our mesh-free PlaNet-ClothPick surpasses visual planning and policy learning methods on principal metrics in simulation, achieving similar performance as state-of-the-art mesh-based planning approaches. Notably, our model exhibits a faster action inference and requires fewer transitional model parameters than the state-of-the-art robotic systems in this domain. Other supplementary materials are available at: https://sites.google.com/view/planet-clothpick.
Citation
Abdulrahim Kadi , H & Terzić , K 2024 , PlaNet-ClothPick : effective fabric flattening based on latent dynamic planning . in 2024 IEEE/SICE International Symposium on System Integration (SII) . , 10417545 , IEEE/SICE International Symposium on System Integration (SII) , IEEE , pp. 972-979 , 2024 16th IEEE/SICE International Symposium on System Integration , Ha Long , Vietnam , 8/01/24 . https://doi.org/10.1109/SII58957.2024.10417545 conference
Publication
2024 IEEE/SICE International Symposium on System Integration (SII)
ISSN
2474-2317Type
Conference item
Collections
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.