Learning Sequential Kinematic Models from Demonstrations for Multi-Jointed Articulated Objects

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gupta, Anmol, Gu, Weiwei, Patil, Omkar, Lee, Jun Ki, Gopalan, Nakul
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918015669370880
author Gupta, Anmol
Gu, Weiwei
Patil, Omkar
Lee, Jun Ki
Gopalan, Nakul
author_facet Gupta, Anmol
Gu, Weiwei
Patil, Omkar
Lee, Jun Ki
Gopalan, Nakul
contents As robots become more generalized and deployed in diverse environments, they must interact with complex objects, many with multiple independent joints or degrees of freedom (DoF) requiring precise control. A common strategy is object modeling, where compact state-space models are learned from real-world observations and paired with classical planning. However, existing methods often rely on prior knowledge or focus on single-DoF objects, limiting their applicability. They also fail to handle occluded joints and ignore the manipulation sequences needed to access them. We address this by learning object models from human demonstrations. We introduce Object Kinematic Sequence Machines (OKSMs), a novel representation capturing both kinematic constraints and manipulation order for multi-DoF objects. To estimate these models from point cloud data, we present Pokenet, a deep neural network trained on human demonstrations. We validate our approach on 8,000 simulated and 1,600 real-world annotated samples. Pokenet improves joint axis and state estimation by over 20 percent on real-world data compared to prior methods. Finally, we demonstrate OKSMs on a Sawyer robot using inverse kinematics-based planning to manipulate multi-DoF objects.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06363
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Sequential Kinematic Models from Demonstrations for Multi-Jointed Articulated Objects
Gupta, Anmol
Gu, Weiwei
Patil, Omkar
Lee, Jun Ki
Gopalan, Nakul
Robotics
Artificial Intelligence
As robots become more generalized and deployed in diverse environments, they must interact with complex objects, many with multiple independent joints or degrees of freedom (DoF) requiring precise control. A common strategy is object modeling, where compact state-space models are learned from real-world observations and paired with classical planning. However, existing methods often rely on prior knowledge or focus on single-DoF objects, limiting their applicability. They also fail to handle occluded joints and ignore the manipulation sequences needed to access them. We address this by learning object models from human demonstrations. We introduce Object Kinematic Sequence Machines (OKSMs), a novel representation capturing both kinematic constraints and manipulation order for multi-DoF objects. To estimate these models from point cloud data, we present Pokenet, a deep neural network trained on human demonstrations. We validate our approach on 8,000 simulated and 1,600 real-world annotated samples. Pokenet improves joint axis and state estimation by over 20 percent on real-world data compared to prior methods. Finally, we demonstrate OKSMs on a Sawyer robot using inverse kinematics-based planning to manipulate multi-DoF objects.
title Learning Sequential Kinematic Models from Demonstrations for Multi-Jointed Articulated Objects
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2505.06363