📊

Dataset

Real Robot Data

Name: Real Robot Data
Creator: Hoshipu
License: Apache-2.0

by Hoshipu hoshipu/real_robot_data

Free2AITools Nexus Index

59.3

S: Semantic 50

Query-time baseline · scored live at search

A: Authority 62

P: Popularity 54

R: Recency 99

Q: Quality 50

Tech Context

Vital Performance —

Source →

Data Integrity 59.3 FNI Score

- Size

- Rows

- Tokens

Dataset Information Summary
Entity Passport
Registry ID	hoshipu/real_robot_data
License	Apache-2.0
Provider	huggingface

📜

Cite this dataset

Academic & Research Attribution

BibTeX

@misc{hf_dataset_hoshipu_real_robot_data,
  author = {Hoshipu},
  title = {Real Robot Data Dataset},
  year = {2026},
  howpublished = {\url{https://huggingface.co/datasets/Hoshipu/real_robot_data}},
  note = {Accessed via Free2AITools.}
}

APA Style

Hoshipu. (2026). Real Robot Data [Dataset]. Free2AITools. https://huggingface.co/datasets/Hoshipu/real_robot_data

🔬Technical Deep Dive

Full Specifications [+]

⚖️ Free2AITools Nexus Index V2.0

Methodology How FNI works

Semantic (S) 50

Query-time baseline · scored live at search

Authority (A) 62

Popularity (P) 54

Recency (R) 99

Quality (Q) 50

💬 Index Insight

FNI V2.0 for Real Robot Data: Authority (A:62), Popularity (P:54), Recency (R:99), Quality (Q:50). Semantic (S) is a query-time baseline scored live at search.

Free2AITools Nexus Index

Data Sources / Provenance

HuggingFace API GitHub Metadata Arxiv Citation DB Methodology

Open data Updated: Live data

⬇️

Downloads

52,658

🎯 Task Categories

robotics

👁️ Data Preview

📊

Row-level preview not available for this dataset.

Schema structure is shown in the Field Logic panel when available.

🔗 Explore Full Dataset ↗

🧬 Field Logic

🧬

Schema not yet indexed for this dataset.

Dataset Specification

Real Robot Manipulation Dataset

Tabletop manipulation tasks recorded on a UR5e with a Robotiq 2F-140 gripper. Most tasks use two Intel RealSense cameras (fixed base + wrist-mounted); the newest hide_block_with_cup task adds a third (opposite-side counter view). All recordings at 20 Hz.

Tasks

Folder	Eps	Cameras	Instruction
`put_blocks_in_plate`	100	2	Pick two blocks from the table and place them on the plate.
`remove_blocks_from_plate`	100	2	Pick two blocks off the plate and place them on the table.
`hide_blocks_with_bowl`	100	2	Pair the two blocks together and cover them with the bowl.
`remove_blocks_under_bowl`	100	2	Uncover the hidden blocks and spread the three objects out.
`hide_blocks_with_cup`	100	2	Cover each block with an upside-down cup.
`put_blocks_on_cup`	100	2	Lift each cup off a block and stack the block on top of the cup.
`put_blocks_down`	100	2	Take the blocks off the cups and place them on the table.
`hide_block_with_cup`	120	3	Cover the block with the upside-down cup. (eps 1-66 light, 67-120 dark)

Each task folder includes a task_instruction.json with the full task spec (objects, pick/place strategies, gripper modes, workspace bounds).

hide_block_with_cup specifics: single-task variant (1 cup + 1 block). Recording captures only the cup-pick + cup-place motion; the inter-episode object randomization is not recorded. A 3rd camera (camera3, oppo-countertop) was added for this task. Per-episode meta.json includes a lighting field ("light" or "dark") — the room lighting changed at episode 67.

Layout

text

/
    1.hdf5  ...  100.hdf5     # per-episode trajectories (images + state)
    meta/
        1/meta.json  ...  100/meta.json   # per-episode ground truth
    task_instruct

Social Proof

HuggingFace Hub

52.7KDownloads

Hub Discussions

🤗 Data Source: Hugging Face ↗

🔄 Updated daily

Source summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Dataset Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: hf-dataset--hoshipu--real_robot_data
slug: hoshipu--real_robot_data
source: huggingface
author: Hoshipu
license: Apache-2.0
tags: task_categories:robotics, license:apache-2.0, size_categories:100k<n<1m, region:us, real-robot, manipulation, ur5e, imitation-learning

⚙️ Technical Specs

architecture: null
params billions: null
context length: null
pipeline tag

📊 Engagement & Metrics

downloads: 52,658
stars: null
forks: null

Data indexed from public sources. Updated daily.