COFFAIL: A Dataset of Successful and Anomalous Robot Skill Executions in the Context of Coffee Preparation
TLDR
COFFAIL is a new robot dataset for coffee preparation, featuring both successful and anomalous skill executions for learning.
Key contributions
- Introduces COFFAIL, a novel dataset for robot manipulation in coffee preparation.
- Features both successful and anomalous robot skill executions for robust learning.
- Collected using a physical robot in a kitchen environment, including bimanual tasks.
- Demonstrates dataset utility for learning robot policies via imitation learning.
Why it matters
Existing robot datasets often lack anomalous executions or focus on single skills. COFFAIL addresses this gap by providing diverse, real-world data for robust robot learning. This dataset is crucial for developing more resilient and adaptable robotic systems.
Original Abstract
In the context of robot learning for manipulation, curated datasets are an important resource for advancing the state of the art; however, available datasets typically only include successful executions or are focused on one particular type of skill. In this short paper, we briefly describe a dataset of various skills performed in the context of coffee preparation. The dataset, which we call COFFAIL, includes both successful and anomalous skill execution episodes collected with a physical robot in a kitchen environment, a couple of which are performed with bimanual manipulation. In addition to describing the data collection setup and the collected data, the paper illustrates the use of the data in COFFAIL to learn a robot policy using imitation learning.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.