Calvin ABC D: Robotics Dataset Converted for LeRobot Framework

Calvin ABC D is a robotics dataset converted from the original Calvin dataset by CollisionCode. The conversion enables seamless training with modern imitation learning pipelines like Diffusion Policy, ACT, and VLA models within the LeRobot framework. The dataset page was last updated on March 30, 2026.

Use Cases

• Train imitation learning agents based on the dataset's compatibility with Diffusion Policy.
• Develop VLA models based on the dataset's formatting for the starVLA framework.
• Benchmark ACT algorithms based on the dataset's conversion for modern imitation learning pipelines.

Strengths

• Formatted for compatibility with the starVLA framework.
• Enables training with modern imitation learning pipelines like Diffusion Policy, ACT, and VLA models.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Original Dataset: Calvin

Collection Method

Converted using RoboTron-Mani... tool.

Freshness

Last updated 2026-03-30 02:04:32; freshness should be verified.