# Toward Ergonomic Risk Prediction via Segmentation of Indoor Object Manipulation Actions Using Spatiotemporal Convolutional Networks

## TL;DR

This paper introduces a novel approach for real-time ergonomic risk prediction in human-robot collaboration by segmenting object manipulation actions in RGB-D videos using spatiotemporal convolutional networks, achieving high accuracy.

## Contribution

It formulates ergonomic risk prediction as an action segmentation problem and develops a deep learning framework combining spatial and temporal convolutional networks, along with a new dataset.

## Key findings

- Achieved 87-94% F1 overlap scores on the new dataset.
- Demonstrated effective segmentation of complex manipulation actions.
- Validated approach on real-world ergonomic risk scenarios.

## Abstract

Automated real-time prediction of the ergonomic risks of manipulating objects is a key unsolved challenge in developing effective human-robot collaboration systems for logistics and manufacturing applications. We present a foundational paradigm to address this challenge by formulating the problem as one of action segmentation from RGB-D camera videos. Spatial features are first learned using a deep convolutional model from the video frames, which are then fed sequentially to temporal convolutional networks to semantically segment the frames into a hierarchy of actions, which are either ergonomically safe, require monitoring, or need immediate attention. For performance evaluation, in addition to an open-source kitchen dataset, we collected a new dataset comprising twenty individuals picking up and placing objects of varying weights to and from cabinet and table locations at various heights. Results show very high (87-94)\% F1 overlap scores among the ground truth and predicted frame labels for videos lasting over two minutes and consisting of a large number of actions.