CLARU
hamzasheedi2025

MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos

A dataset of 8 hours of human play videos and simulated humanoid robot manipulation tasks across 30 objects and 8 kitchen environments, designed to enable in-context learning for humanoid robots to solve new manipulation tasks from few video examples.

Downloads110
Hours8

Why This Matters for Physical AI

MimicDroid demonstrates how large-scale human play videos can serve as scalable training data for in-context learning in humanoid robots, advancing the capability of embodied AI systems to generalize to novel manipulation tasks with minimal task-specific supervision.

Technical Profile

Modalities
rgb
Robot Embodiments
humanoid
Environment
simulationkitchen
Task Types
manipulationpick_and_placegrasping
Total Hours
8
Annotation Types
language_instructions
Part of the RoboCasa family

Access

View on HuggingFaceRead Paper

Need custom rgb data?

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

Request a Sample Pack

Related Datasets

MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos

A dataset of 8 hours of human play videos and 30 objects across 8 kitchen environments for training humanoid robots to solve manipulation tasks through in-context learning. Built on the RoboCasa simulation framework with evaluation spanning three difficulty levels.

rgb
193 downloads2025

Xperience-10M

A large-scale egocentric multimodal dataset of human experience containing 10 million interactions and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations for embodied AI, robotics, and world modeling research.

rgbaudiodepthproprioception+3
2.3M downloadsother

Open-H-Embodiment

A multi-embodiment community-driven dataset of paired kinematics and video for training AI autonomy models in surgical robotics and ultrasound applications. The dataset includes tabletop exercises, clinical procedures, and simulations of healthcare robotics tasks.

rgbproprioception
118K downloads2026cc-by-4.0

Open-H-Embodiment

A community-driven, multi-embodiment dataset of paired kinematics and video for training and evaluating AI autonomy models in surgical robotics and ultrasound applications, including tabletop exercises, clinical procedures, and healthcare robotics simulations.

rgbproprioception
76K downloads2026cc-by-4.0

LingBot-Depth Dataset

Self-curated RGB-D dataset for training masked depth modeling approaches, containing real-world indoor scenes, VLA robot manipulation tasks, and simulated data across multiple camera types and robot platforms.

rgbdepth
71K downloadsCC BY-NC-SA 4.0

PhysicalAI-Robotics-Manipulation-Kitchen-Demos

A large-scale dataset of 600 hours of human-teleoperated demonstrations across 316 different kitchen manipulation tasks, totalling 55k trajectories collected using a Franka Panda robot with an Omron mobile base.

rgbproprioception
57K downloads2025cc-by-4.0