The Effects of Selected Object Features on a Pick-and-Place Task: a Human Multimodal Dataset

TL;DR

This paper introduces a multimodal dataset capturing human pick-and-place movements influenced by object features, useful for studying motion kinematics, intention recognition, and motion generation in robotics.

Contribution

The dataset uniquely combines multimodal recordings of human object manipulation with varied object weights and fillings, facilitating research in motion analysis and learning in hand-object interactions.

Findings

Collected data from 15 subjects performing 1200 pick-and-place actions.

Captured multimodal data including cameras, motion capture, and inertial sensors.

Demonstrated the dataset's potential for studying object feature effects on human motion.

Abstract

We propose a dataset to study the influence of object-specific characteristics on human pick-and-place movements and compare the quality of the motion kinematics extracted by various sensors. This dataset is also suitable for promoting a broader discussion on general learning problems in the hand-object interaction domain, such as intention recognition or motion generation with applications in the Robotics field. The dataset consists of the recordings of 15 subjects performing 80 repetitions of a pick-and-place action under various experimental conditions, for a total of 1200 pick-and-places. The data has been collected thanks to a multimodal setup composed of multiple cameras, observing the actions from different perspectives, a motion capture system, and a wrist-worn inertial measurement unit. All the objects manipulated in the experiments are identical in shape, size, and appearance but differ in weight and liquid filling, which influences the carefulness required for their handling.