Research Analyzer
← Back ICRA 2026

Fabric Dynamic Motion Modeling and Collision Avoidance with Oriented Bounding Box

Letian Li, Fuyuki Tokuda, Akira Seino, Akinari Kobayashi, Norman Tien, Kazuhiro Kosuge

PDF

AI summary

Key figure (auto-extracted from paper)
A Transformer-based model predicts fabric motion as a sequence of oriented bounding boxes, enabling reliable collision-free robot path planning for soft material transport.
Fabric transport Collision avoidance Oriented bounding box Transformer Deformable object modeling Robot motion planning

Problem

Accurately modeling dynamic fabric deformation and avoiding collisions in confined factory spaces remains challenging due to unpredictable environmental factors and complex state evolution. Traditional physical or rigid-body models fail to capture these dynamics efficiently for real-time robotic control.

Approach

The method approximates fabric state using oriented bounding boxes and employs a Transformer network to predict future box positions along a robot trajectory, allowing rapid collision checks and shortest-path selection.

Key results

  • OBB-Transformer outperforms mass-spring-damper and point cloud networks in motion prediction accuracy
  • Successfully plans collision-free trajectories in both 2D and 3D confined environments
  • Generalizes to new fabric types and sizes with minimal additional training data
  • Demonstrates reliable, scratch-free fabric transport in real-world robotic experiments

Why it matters

Provides a practical, data-driven solution for automating delicate fabric handling in garment manufacturing, reducing waste and improving production safety.

Abstract

Avoiding collision between the fabric and the obstacle is critical to transport fabric piece in the garment factory. If the fabric collides with the sharp-edged obstacle, it can be scratched or contaminated, resulting in poor product quality and increased waste. However, when we consider the fabric model, we find that current fabric models are not accurate enough for this real-world application. It is almost impossible to model the dynamic motion of the fabric with high accuracy, because its motion and deformation areaffectedbymanyhard-to-estimatefactors.Inthispaper,instead of using an accurate fabric model, we propose a new fabric motion modeling method using the proposed OBB-Transformer, which modelsthefabricmotionasatimeseriesoforientedboundingboxes (OBBs). Using OBB-Transformer, a dynamic collision avoidance method is designed to plan a robot trajectory connecting the start point and the goal point without collision between the fabric and the obstacle. The performance of the fabric dynamic motion modeling is compared between the proposed and conventional methods. Then, the collision avoidance of a piece of fabric using the proposed method is demonstrated on a real robot system in both 2D and 3D scenarios.

Index terms

Collision Avoidance Deep Learning Methods Motion and Path Planning

Related papers