Guardado en:
Detalles Bibliográficos
Autores principales: Jacob, Jayadeep, Zhang, Wenzheng, Warren, Houston, Borges, Paulo, Bandyopadhyay, Tirthankar, Ramos, Fabio
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.17085
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909974153658368
author Jacob, Jayadeep
Zhang, Wenzheng
Warren, Houston
Borges, Paulo
Bandyopadhyay, Tirthankar
Ramos, Fabio
author_facet Jacob, Jayadeep
Zhang, Wenzheng
Warren, Houston
Borges, Paulo
Bandyopadhyay, Tirthankar
Ramos, Fabio
contents Manipulating clusters of deformable objects presents a substantial challenge with widespread applicability, but requires contact-rich whole-arm interactions. A potential solution must address the limited capacity for realistic model synthesis, high uncertainty in perception, and the lack of efficient spatial abstractions, among others. We propose a novel framework for learning model-free policies integrating two modalities: 3D point clouds and proprioceptive touch indicators, emphasising manipulation with full body contact awareness, going beyond traditional end-effector modes. Our reinforcement learning framework leverages a distributional state representation, aided by kernel mean embeddings, to achieve improved training efficiency and real-time inference. Furthermore, we propose a novel context-agnostic occlusion heuristic to clear deformables from a target region for exposure tasks. We deploy the framework in a power line clearance scenario and observe that the agent generates creative strategies leveraging multiple arm links for de-occlusion. Finally, we perform zero-shot sim-to-real policy transfer, allowing the arm to clear real branches with unknown occlusion patterns, unseen topology, and uncertain dynamics. Website: https://sites.google.com/view/dcmwap/
format Preprint
id arxiv_https___arxiv_org_abs_2507_17085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deformable Cluster Manipulation via Whole-Arm Policy Learning
Jacob, Jayadeep
Zhang, Wenzheng
Warren, Houston
Borges, Paulo
Bandyopadhyay, Tirthankar
Ramos, Fabio
Robotics
Machine Learning
Manipulating clusters of deformable objects presents a substantial challenge with widespread applicability, but requires contact-rich whole-arm interactions. A potential solution must address the limited capacity for realistic model synthesis, high uncertainty in perception, and the lack of efficient spatial abstractions, among others. We propose a novel framework for learning model-free policies integrating two modalities: 3D point clouds and proprioceptive touch indicators, emphasising manipulation with full body contact awareness, going beyond traditional end-effector modes. Our reinforcement learning framework leverages a distributional state representation, aided by kernel mean embeddings, to achieve improved training efficiency and real-time inference. Furthermore, we propose a novel context-agnostic occlusion heuristic to clear deformables from a target region for exposure tasks. We deploy the framework in a power line clearance scenario and observe that the agent generates creative strategies leveraging multiple arm links for de-occlusion. Finally, we perform zero-shot sim-to-real policy transfer, allowing the arm to clear real branches with unknown occlusion patterns, unseen topology, and uncertain dynamics. Website: https://sites.google.com/view/dcmwap/
title Deformable Cluster Manipulation via Whole-Arm Policy Learning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2507.17085