PROJECTSimulation to reality

Synthetic Data & Object Detection.

Building a synthetic-data pipeline and object detector for fallen boxes, with a ROS2 inference node in development.

Simulation to realityConcept illustration

Engineering projectOngoing

01 /

Project overview

Build a synthetic-data pipeline in NVIDIA Isaac Sim Replicator and train a YOLO11s detector for fallen boxes, reaching 0.99 validation mAP50–95.

Diagnose a simulation-to-real-world gap and iterate on the dataset while building a ROS2 inference node.

02 /

Project documentation will be added here.

Preview a local filePRIVATE PREVIEW

Try an image, PDF, presentation, STL model, or CAD file. Your file stays in this browser. This is a preview only; it is not uploaded or published.

Choose a file Maximum size: 50 MB. PowerPoint and CAD files open in a compatible app.