Estimating Emotional Intensity from Body Poses for Human-Robot Interaction

TL;DR

This paper introduces a real-time method for robots to estimate human emotional intensities from body poses using local joint transformations and LSTM-RNNs, improving emotional perception in human-robot interactions.

Contribution

It presents a novel approach combining local joint transformations with LSTM-RNNs for real-time emotional intensity estimation from body poses, outperforming baseline methods.

Findings

The method outperforms baseline on test dataset.

Field tests show effective real-time emotional intensity estimation.

Robots with this method are perceived as more emotionally intelligent.

Abstract

Equipping social and service robots with the ability to perceive human emotional intensities during an interaction is in increasing demand. Most of existing work focuses on determining which emotion(s) participants are expressing from facial expressions but largely overlooks the emotional intensities spontaneously revealed by other social cues, especially body languages. In this paper, we present a real-time method for robots to capture fluctuations of participants' emotional intensities from their body poses. Unlike conventional joint-position-based approaches, our method adopts local joint transformations as pose descriptors which are invariant to subject body differences as well as the pose sensor positions. In addition, we use a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) architecture to take the specific emotion context into account when estimating emotional intensities from body poses. The dataset evaluation suggests that the proposed method is effective and performs better than baseline method on the test dataset. Also, a series of succeeding field tests on a physical robot demonstrates that the proposed method effectively estimates subjects emotional intensities in real-time. Furthermore, the robot equipped with our method is perceived to be more emotion-sensitive and more emotionally intelligent.