Dataset Viewer
id
stringclasses 9
values | images
dict | conversations
listlengths 2
2
|
---|---|---|
10332_final_part1
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz9WbAsSXYYiJ(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
11699_middle_part2
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz9WbBl2XUYiK(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
26655_final_part2
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz9WYwlWXYgiJ(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
10332_final_part2
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz9WbAsSXYYiJ(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
21032_final_part0
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz96bNkyXUfCP(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
10332_final_part0
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz9WbAsSXYYiJ(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
21032_final_part2
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz96bNkyXUfCP(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
11699_middle_part0
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz9WbBl2XUYiK(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
11699_middle_part1
| {"observation_images_chest":["iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAIAAAC6s0uzAAEAAElEQVR4nOz9WbBl2XUYiK(...TRUNCATED) | [{"from":"human","value":"Here are the observations of cameras on a robot in the given time sequence(...TRUNCATED) |
Condition Checking Dataset
This dataset contains condition checking conversations for robotics applications, with embedded base64 images from multiple camera viewpoints.
Dataset Structure
Data Fields
id
: Unique identifier for each sampleimages
: Dictionary containing base64-encoded images from multiple camera viewpointsconversations
: List of conversation turns (human question + assistant answer)
Camera Viewpoints
The dataset includes images from 5 camera viewpoints:
observation_images_chest
observation_images_left_eye
observation_images_left_wrist
observation_images_right_eye
observation_images_right_wrist
Each sample contains approximately 30 images total (6 per camera).
Sample Structure
{
"id": "frame_index_position_part",
"images": {
"camera_key": ["base64_image_1", "base64_image_2", ...],
...
},
"conversations": [
{
"from": "human",
"value": "Here are the observations... condition: (object is grasped) ..."
},
{
"from": "gpt",
"value": "True"
}
]
}
Usage
from datasets import load_dataset
# Load the dataset
dataset = load_dataset("jeffshen4011/condition-checking-dataset")
# Access a sample
sample = dataset["train"][0]
print(f"Question: {sample['conversations'][0]['value'][:100]}...")
print(f"Answer: {sample['conversations'][1]['value']}")
print(f"Number of camera views: {len(sample['images'])}")
Dataset Statistics
- Training samples: 9
- Camera viewpoints: 5
- Images per sample: ~30
- Image format: Base64-encoded PNG
- Task type: Binary classification (True/False)
Applications
This dataset is designed for:
- Training vision-language models for robotics condition checking
- Multi-modal reasoning tasks
- Robot state verification
- Visual question answering in manipulation contexts
Citation
If you use this dataset, please cite:
@dataset{condition_checking_dataset,
title={Condition Checking Dataset for Robotics},
author={Research Team},
year={2025},
url={https://huggingface.co/datasets/jeffshen4011/condition-checking-dataset}
}
- Downloads last month
- 70
Task
: Visual condition checking (True/False questions about robot states)
Modality
: Multi-modal (text + images)
Domain
: Robotics manipulation tasks
Format
: Conversational format suitable for VLM training
Size of downloaded dataset files:
11.5 MB
Size of the auto-converted Parquet files:
11.5 MB
Number of rows:
12