A Dataset of Daily Interactive Manipulation

TL;DR

This paper introduces a comprehensive dataset of daily interactive manipulation tasks, capturing position, orientation, force, and torque data to aid research in robot task learning in changing environments.

Contribution

The paper provides a new dataset of 1,593 trials across 32 daily motions and pouring tasks, including helper code, to advance research in robot interactive manipulation.

Findings

Dataset enables better training of robots for daily tasks.

Includes diverse manipulation data with force and torque measurements.

Facilitates development of task-oriented robotic manipulation algorithms.

Abstract

Robots that succeed in factories stumble to complete the simplest daily task humans take for granted, for the change of environment makes the task exceedingly difficult. Aiming to teach robot perform daily interactive manipulation in a changing environment using human demonstrations, we collected our own data of interactive manipulation. The dataset focuses on position, orientation, force, and torque of objects manipulated in daily tasks. The dataset includes 1,593 trials of 32 types of daily motions and 1,596 trials of pouring alone, as well as helper code. We present our dataset to facilitate the research on task-oriented interactive manipulation.