COFFAIL: A Dataset of Successful and Anomalous Robot Skill Executions in the Context of Coffee Preparation

arXiv cs.RO / 4/21/2026

📰 NewsDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

The paper introduces COFFAIL, a new dataset for robot manipulation research focused on coffee preparation tasks.
COFFAIL contains both successful and anomalous robot skill execution episodes, collected using a physical robot in a kitchen environment.
The dataset covers multiple skills and includes some examples involving bimanual (two-arm) manipulation.
The authors demonstrate how COFFAIL can be used to train a robot policy via imitation learning, showing practical research value beyond data collection.

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.