DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909790080335872 |
|---|---|
| author | Patel, Mayank Jain, Rahul Unmesh, Asim Ramani, Karthik |
| author_facet | Patel, Mayank Jain, Rahul Unmesh, Asim Ramani, Karthik |
| contents | Understanding the motion of articulated mechanical assemblies from static geometry remains a core challenge in 3D perception and design automation. Prior work on everyday articulated objects such as doors and laptops typically assumes simplified kinematic structures or relies on joint annotations. However, in mechanical assemblies like gears, motion arises from geometric coupling, through meshing teeth or aligned axes, making it difficult for existing methods to reason about relational motion from geometry alone. To address this gap, we introduce MechBench, a benchmark dataset of 693 diverse synthetic gear assemblies with part-wise ground-truth motion trajectories. MechBench provides a structured setting to study coupled motion, where part dynamics are induced by contact and transmission rather than predefined joints. Building on this, we propose DYNAMO, a dependency-aware neural model that predicts per-part SE(3) motion trajectories directly from segmented CAD point clouds. Experiments show that DYNAMO outperforms strong baselines, achieving accurate and temporally consistent predictions across varied gear configurations. Together, MechBench and DYNAMO establish a novel systematic framework for data-driven learning of coupled mechanical motion in CAD assemblies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12430 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction Patel, Mayank Jain, Rahul Unmesh, Asim Ramani, Karthik Computer Vision and Pattern Recognition Understanding the motion of articulated mechanical assemblies from static geometry remains a core challenge in 3D perception and design automation. Prior work on everyday articulated objects such as doors and laptops typically assumes simplified kinematic structures or relies on joint annotations. However, in mechanical assemblies like gears, motion arises from geometric coupling, through meshing teeth or aligned axes, making it difficult for existing methods to reason about relational motion from geometry alone. To address this gap, we introduce MechBench, a benchmark dataset of 693 diverse synthetic gear assemblies with part-wise ground-truth motion trajectories. MechBench provides a structured setting to study coupled motion, where part dynamics are induced by contact and transmission rather than predefined joints. Building on this, we propose DYNAMO, a dependency-aware neural model that predicts per-part SE(3) motion trajectories directly from segmented CAD point clouds. Experiments show that DYNAMO outperforms strong baselines, achieving accurate and temporally consistent predictions across varied gear configurations. Together, MechBench and DYNAMO establish a novel systematic framework for data-driven learning of coupled mechanical motion in CAD assemblies. |
| title | DYNAMO: Dependency-Aware Deep Learning Framework for Articulated Assembly Motion Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.12430 |