Other
DROID
Robot manipulation learning
Multi-view teleoperated Panda manipulation demonstrations across real households, offices and laboratories.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- Other
- Environment
- Indoor
- Data origin
- Real-world
- Sensor count
- 6
- Ground truth
- Not reported
- Calibration
- Parameters Only
- Annotations
- Available
Sensor overview
High-level sensor availability before the detailed sensor records below.
Ground truth
Reference scope, method, rate, coverage, and provenance.
Not reported
Calibration and synchronization
Reported calibration level, reproducibility signals, and supporting notes.
- Level
- Parameters Only
- Processed parameters
- Available
- Raw calibration data
- Not reported
- Calibration targets
- Not reported
Parameters only
Processed calibration parameters are reported, but raw calibration data is not reported.
Notes
Intrinsic/extrinsic stereo calibration and quality-scored post-hoc variants are supplied. April 2025 improved parameters cover 36k episodes; complete raw sessions and uniform accuracy across all episodes are not established.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
The paper headline of 76k successful demonstrations and 350 hours differs from failed-episode and later annotation/calibration products. Exact current combined episode count and total duration remain unknown.
Three stereo camera systems provide six optical views plus computed depth; robot joint/gripper state is proprioception, not an inferred number of physical encoders or navigation odometry.
Improved April 2025 calibration covers 36k episodes. Language, calibration quality and episode outcome coverage vary; synchronized streams do not establish an achieved timing-error bound.
Data collection spans varied real homes, offices and laboratories with teleoperator bias. Independent pose/geometry ground truth and full raw calibration sessions are not established.
Cameras
Camera 1
- Model
- Zed 2
- Setup
- Stereo
- Count
- 2
- Effective cameras
- 4
- Modality
- Rgb
- Resolution
- 1280 x 720
- Rate
- 15 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Two external stereo systems; depth information also supplied.
Camera 2
- Model
- Zed Mini
- Setup
- Stereo
- Count
- 1
- Effective cameras
- 2
- Modality
- Rgb
- Resolution
- 1280 x 720
- Rate
- 15 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Wrist-mounted stereo system; count represents systems, not optical heads.
IMUs
Not reported
GNSS
Not reported
LiDAR
Not reported
Radar
Not reported
Additional sensors
Other sensor
- Model
- Franka Panda / Robotiq 2F-85
- Name
- Robot proprioception and actions
- Count
- 1
- Rate
- 15 Hz
- Notes
- Joint state, end-effector state and gripper state; actions in joint and Cartesian spaces, not navigation odometry.
Annotations
Reported annotation availability and task support.
- Availability
- Available
- Format
- Natural-language task instructions and episode outcome metadata. December 2024 update supplies three instructions for 95 percent of successful episodes; coverage varies by release.
- Class count
- Not reported
Semantic segmentation
Not reported
Instance segmentation
Not reported
Object detection
Not reported
Optical flow
Not reported
Depth ground truth
Not reported
Citation
Citation key and BibTeX kept at the end of the page for reference.
@article{khazatsky2024droid,
title = {DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset},
author = {Alexander Khazatsky and Karl Pertsch and Suraj Nair and Ashwin Balakrishna and Sudeep Dasari and Siddharth Karamcheti and Soroush Nasiriany and Mohan Kumar Srirama and Lawrence Yunliang Chen and Kirsty Ellis and Peter David Fagan and Joey Hejna and Masha Itkina and Marion Lepert and Yecheng Jason Ma and Patrick Tree Miller and Jimmy Wu and Suneel Belkhale and Shivin Dass and Huy Ha and Arhan Jain and Abraham Lee and Youngwoon Lee and Marius Memmel and Sungjae Park and Ilija Radosavovic and Kaiyuan Wang and Albert Zhan and Kevin Black and Cheng Chi and Kyle Beltran Hatch and Shan Lin and Jingpei Lu and Jean Mercat and Abdul Rehman and Pannag R Sanketi and Archit Sharma and Cody Simpson and Quan Vuong and Homer Rich Walke and Blake Wulfe and Ted Xiao and Jonathan Heewon Yang and Arefeh Yavary and Tony Z. Zhao and Christopher Agia and Rohan Baijal and Mateo Guaman Castro and Daphne Chen and Qiuyu Chen and Trinity Chung and Jaimyn Drake and Ethan Paul Foster and Jensen Gao and Vitor Guizilini and David Antonio Herrera and Minho Heo and Kyle Hsu and Jiaheng Hu and Muhammad Zubair Irshad and Donovon Jackson and Charlotte Le and Yunshuang Li and Kevin Lin and Roy Lin and Zehan Ma and Abhiram Maddukuri and Suvir Mirchandani and Daniel Morton and Tony Nguyen and Abigail O'Neill and Rosario Scalise and Derick Seale and Victor Son and Stephen Tian and Emi Tran and Andrew E. Wang and Yilin Wu and Annie Xie and Jingyun Yang and Patrick Yin and Yunchu Zhang and Osbert Bastani and Glen Berseth and Jeannette Bohg and Ken Goldberg and Abhinav Gupta and Abhishek Gupta and Dinesh Jayaraman and Joseph J Lim and Jitendra Malik and Roberto Martín-Martín and Subramanian Ramamoorthy and Dorsa Sadigh and Shuran Song and Jiajun Wu and Michael C. Yip and Yuke Zhu and Thomas Kollar and Sergey Levine and Chelsea Finn},
year = {2024},
}Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy