SurgSync: Multi-modal dVRK Dataset for Surgical Robotics

A multi-modal dataset collected using the da Vinci Research Kit (dVRK). The dataset was created by jackzhy and a subset has been incorporated into NVIDIA's PhysicalAI-Robotics-Open-H-Embodiment collection. It was last updated on June 3, 2026.

Use Cases

• Training multi-modal AI models based on synchronized sensor data from a surgical robot.
• Developing robotic control policies based on real-world dVRK teleoperation data.
• Benchmarking imitation learning algorithms based on expert demonstration data.
• Researching human-robot interaction in surgical settings based on collected telemetry.

Strengths

• Dataset is multi-modal, likely containing synchronized data streams.
• It has been recognized and incorporated into a major industry dataset collection (NVIDIA's PhysicalAI-Robotics-Open-H-Embodiment).
• A dedicated toolkit with processing pipelines and documentation is available on GitHub.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

jackzhy on Hugging Face, with a subset redistributed by NVIDIA.

Collection Method

Collected using the da Vinci Research Kit (dVRK), likely through teleoperation.

Freshness

Last updated 2026-06-03 02:49:51; freshness should be verified.