real-stanfordMIT

Adaptive Compliance Policy (ACP) data

Name: Adaptive Compliance Policy (ACP) data
Creator: real-stanford
License: https://opensource.org/license/mit
Keywords: manipulation, pick_and_place, lab

A mirror of processed datasets for learning adaptive compliance policies in robotic manipulation tasks, including flip-up and vase wiping demonstrations.

Downloads38
Episodes430

Why This Matters for Physical AI

This dataset provides real robot demonstrations of contact-rich manipulation tasks that require adaptive compliance, which is essential for developing policies that can handle force feedback and environmental interactions in physical manipulation.

Technical Profile

Environment: lab
Task Types: manipulationpick_and_place
Episodes: 430
License: MIT

Part of the Adaptive Compliance Policy family

Access

View on HuggingFace Read Paper

Need custom physical AI data?

Claru builds purpose-built datasets for lab applications with dense human annotations and quality assurance.

Request a Sample Pack