Multi-task real-robot data with gaze attention for dual-arm fine manipulation

TL;DR

This paper presents a large, diverse dataset of dual-arm, fine manipulation tasks with visual attention and language instructions, and introduces a model that effectively performs precise object manipulation in real robots.

Contribution

The creation of a comprehensive dual-arm manipulation dataset with visual attention signals and the development of a robust model for fine manipulation tasks.

Findings

Model successfully performed over 7,000 real robot trials.

Dataset includes 224,000 episodes with diverse fine manipulation tasks.

Visual attention signals improved manipulation precision.

Abstract

In the field of robotic manipulation, deep imitation learning is recognized as a promising approach for acquiring manipulation skills. Additionally, learning from diverse robot datasets is considered a viable method to achieve versatility and adaptability. In such research, by learning various tasks, robots achieved generality across multiple objects. However, such multi-task robot datasets have mainly focused on single-arm tasks that are relatively imprecise, not addressing the fine-grained object manipulation that robots are expected to perform in the real world. This paper introduces a dataset of diverse object manipulations that includes dual-arm tasks and/or tasks requiring fine manipulation. To this end, we have generated dataset with 224k episodes (150 hours, 1,104 language instructions) which includes dual-arm fine tasks such as bowl-moving, pencil-case opening or banana-peeling, and this data is publicly available. Additionally, this dataset includes visual attention signals as well as dual-action labels, a signal that separates actions into a robust reaching trajectory and precise interaction with objects, and language instructions to achieve robust and precise object manipulation. We applied the dataset to our Dual-Action and Attention (DAA), a model designed for fine-grained dual arm manipulation tasks and robust against covariate shifts. The model was tested with over 7k total trials in real robot manipulation tasks, demonstrating its capability in fine manipulation.