ROOM

A Physics-Based Continuum Robot Simulator for Photorealistic Medical Datasets Generation

2026 IEEE International Conference on Robotics and Automation (ICRA)

arXiv GitHub YouTube MIT

From CT Scan to Bronchoscopy

Six automated stages transform a patient chest CT into photorealistic endoscopy data.

CT scan volume sweep
Stage 1 · Extract

CT Scan

High-resolution chest CT with sub-millimeter slices. DICOM series are automatically extracted, filtered, and converted to NIfTI volumes.

Airway segmentation sweep
Stage 2 · Segment

Airway Segmentation

The segmentation pipeline isolates the bronchial tree from the CT volume. Quality scoring validates anatomical coverage, airway volume, and craniocaudal extent.

3D mesh spinning
Stage 3 · Reconstruct

3D Mesh

Marching cubes surface extraction, Taubin smoothing, and decimation. Normals flipped inward for endoscopic camera rendering.

Skeleton spinning
Stage 4 · Skeleton

Medial Axis

Centerline graph extraction maps branch points, endpoints, and traversal paths for camera trajectory generation.

Bronchoscopy navigation
Stage 5 · Render

Photorealistic Bronchoscopy

Blender Cycles path tracing with dual-LED endoscope lighting, volumetric fog, wet tissue materials, and domain randomization.

Simulator
Stage 6 · Simulate

Real-Time Simulator

PyBullet physics with automatic trachea detection, collision response, and camera poses that transfer directly to Blender.

Key Components

PyBullet Simulator

Continuum robot simulation with collision physics, PS5 controller, automatic trachea detection via ray-cast diameter, and MCP integration.

Blender Rendering

Cycles path tracing with dual-LED lighting, volumetric fog, wet tissue materials, and domain randomization. Multi-GPU parallel rendering.

CT Pipeline

End-to-end automation from DICOM through segmentation, meshing, skeleton extraction, and scene creation. Quality scoring at each stage.

Citation

@inproceedings{esposito2026room,
  title={{ROOM}: A Physics-Based Continuum Robot Simulator
         for Photorealistic Medical Datasets Generation},
  author={Esposito, Salvatore and Mattamala, Mat{\'\i}as
          and Rebain, Daniel and Zhang, Francis Xiatian
          and Dhaliwal, Kevin and Khadem, Mohsen
          and Ramamoorthy, Subramanian},
  booktitle={2026 IEEE International Conference on
             Robotics and Automation (ICRA)},
  year={2026}
}

Salvatore Esposito · Matias Mattamala · Daniel Rebain · Francis Xiatian Zhang · Kevin Dhaliwal · Mohsen Khadem · Subramanian Ramamoorthy

University of Edinburgh · University of British Columbia · ICRA 2026