jnogga/droid_success

---
license: cc-by-4.0
task_categories:
- robotics
tags:
- LeRobot
- Robotic manipulation
pretty_name: DROID Success Episodes
size_categories:
- 10M<n<100M
---

## DROID Success Episodes

Successful episodes in [DROID-COMMUNITY](https://droid-dataset.github.io/). Episodes with inconsistent data or lacking language instructions were discarded, leaving ~89% of all successful episodes.

Ported from raw 1.0.1 data at full resolution to LeRobotDataset v3.0 format (1.04 TiB | 11.3k inodes) with extra annotation from [KarlP/droid](https://huggingface.co/KarlP/droid/tree/main).

<div align="center" style="margin: 16px 0;">
<video controls autoplay loop muted playsinline style="max-width: 100%; border-radius: 10px;">
<source src="https://huggingface.co/datasets/jnogga/droid_success/resolve/main/droid_example_episode.mp4" type="video/mp4">
Your browser does not support the video tag.
</video>
</div>

For a subset of episodes with more reliable camera extrinsics, see [jnogga/droid_success_high_quality](https://huggingface.co/datasets/jnogga/droid_success_high_quality).

## Updates

* 22.02.2026: Removed episodes with unexpected camera resolutions.

## Dataset Structure

The external cameras are assigned to left and right views depending on the episode. For their extrinsics, the source is given along with the corresponding metric and score.

[meta/info.json](meta/info.json):
```json
{
"codebase_version": "v3.0",
"fps": 15,
"data_files_size_in_mb": 100.0,
"video_files_size_in_mb": 200.0,
"robot_type": "franka_emika_panda_robotiq_2F-85",
"total_episodes": 53282,
"total_frames": 14153535,
"total_tasks": 53282,
"chunks_size": 1000,
"splits": {
"train": "0:53282"
},
"data_path": "data/chunk-{chunk_index:03d}/file_{file_index:03d}.parquet",
"video_path": "videos/{video_key}/chunk-{chunk_index:03d}/file_{file_index:03d}.mp4",
"features": {
"action.cartesian_position": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"action.cartesian_velocity": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"action.gripper_position": {
"dtype": "float32",
"shape": [
1
],
"names": null,
"fps": 15
},
"action.gripper_velocity": {
"dtype": "float32",
"shape": [
1
],
"names": null,
"fps": 15
},
"action.joint_position": {
"dtype": "float32",
"shape": [
7
],
"names": [
"joint_0",
"joint_1",
"joint_2",
"joint_3",
"joint_4",
"joint_5",
"joint_6"
],
"fps": 15
},
"action.joint_velocity": {
"dtype": "float32",
"shape": [
7
],
"names": [
"joint_0",
"joint_1",
"joint_2",
"joint_3",
"joint_4",
"joint_5",
"joint_6"
],
"fps": 15
},
"observation.cartesian_position": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"observation.gripper_position": {
"dtype": "float32",
"shape": [
1
],
"names": null,
"fps": 15
},
"observation.joint_position": {
"dtype": "float32",
"shape": [
7
],
"names": [
"joint_0",
"joint_1",
"joint_2",
"joint_3",
"joint_4",
"joint_5",
"joint_6"
],
"fps": 15
},
"observation.joint_velocity": {
"dtype": "float32",
"shape": [
7
],
"names": [
"joint_0",
"joint_1",
"joint_2",
"joint_3",
"joint_4",
"joint_5",
"joint_6"
],
"fps": 15
},
"wrist_camera_intrinsics": {
"dtype": "float32",
"shape": [
4
],
"names": [
"fx",
"cx",
"fy",
"cy"
],
"fps": 15
},
"wrist_camera_to_robot_extrinsics": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"left_external_camera_intrinsics": {
"dtype": "float32",
"shape": [
4
],
"names": [
"fx",
"cx",
"fy",
"cy"
],
"fps": 15
},
"left_external_camera_to_robot_extrinsics": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"left_external_camera_to_robot_source": {
"dtype": "string",
"shape": [
1
],
"names": null,
"fps": 15
},
"left_external_camera_to_robot_metric": {
"dtype": "string",
"shape": [
1
],
"names": null,
"fps": 15
},
"left_external_camera_to_robot_score": {
"dtype": "float32",
"shape": [
1
],
"names": null,
"fps": 15
},
"left_external_camera_to_robot_extrinsics_raw": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"right_external_camera_intrinsics": {
"dtype": "float32",
"shape": [
4
],
"names": [
"fx",
"cx",
"fy",
"cy"
],
"fps": 15
},
"right_external_camera_to_robot_extrinsics": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"right_external_camera_to_robot_source": {
"dtype": "string",
"shape": [
1
],
"names": null,
"fps": 15
},
"right_external_camera_to_robot_metric": {
"dtype": "string",
"shape": [
1
],
"names": null,
"fps": 15
},
"right_external_camera_to_robot_score": {
"dtype": "float32",
"shape": [
1
],
"names": null,
"fps": 15
},
"right_external_camera_to_robot_extrinsics_raw": {
"dtype": "float32",
"shape": [
7
],
"names": [
"position.x",
"position.y",
"position.z",
"quaternion.w",
"quaternion.x",
"quaternion.y",
"quaternion.z"
],
"fps": 15
},
"language_instruction_1": {
"dtype": "string",
"shape": [
1
],
"names": null,
"fps": 15
},
"language_instruction_2": {
"dtype": "string",
"shape": [
1
],
"names": null,
"fps": 15
},
"language_instruction_3": {
"dtype": "string",
"shape": [
1
],
"names": null,
"fps": 15
},
"keep_interval_index": {
"dtype": "int64",
"shape": [
1
],
"names": null,
"fps": 15
},
"frame_index": {
"dtype": "int64",
"shape": [
1
],
"names": null,
"fps": 15
},
"timestamp": {
"dtype": "float32",
"shape": [
1
],
"names": null,
"fps": 15
},
"index": {
"dtype": "int64",
"shape": [
1
],
"names": null,
"fps": 15
},
"task_index": {
"dtype": "int64",
"shape": [
1
],
"names": null,
"fps": 15
},
"episode_index": {
"dtype": "int64",
"shape": [
1
],
"names": null,
"fps": 15
},
"observation.images.left_external": {
"dtype": "video",
"shape": [
720,
1280,
3
],
"names": [
"height",
"width",
"channel"
],
"info": {
"video.height": 720,
"video.width": 1280,
"video.codec": "h264",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 15,
"video.channels": 3,
"has_audio": false
}
},
"observation.images.wrist": {
"dtype": "video",
"shape": [
720,
1280,
3
],
"names": [
"height",
"width",
"channel"
],
"info": {
"video.height": 720,
"video.width": 1280,
"video.codec": "h264",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 15,
"video.channels": 3,
"has_audio": false
}
},
"observation.images.right_external": {
"dtype": "video",
"shape": [
720,
1280,
3
],
"names": [
"height",
"width",
"channel"
],
"info": {
"video.height": 720,
"video.width": 1280,
"video.codec": "h264",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 15,
"video.channels": 3,
"has_audio": false
}
}
}
}
```

## Getting started

```py
# pip install lerobot
from lerobot.datasets.lerobot_dataset import LeRobotDataset

dataset = LeRobotDataset("jnogga/droid_success")
```

See [droid_example.ipynb](droid_example.ipynb) for a more detailed example.

## Citation

All credit goes to the original authors of DROID. If you find their work helpful, please cite

**BibTeX:**

```bibtex
@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},
}
```