Modelling Multi-Channel Emotions Using Facial Expression and Trajectory Cues for Improving Socially-Aware Robot Navigation
Abstract
Using facial expressions and trajectory signals, we present an emotion-aware navigation algorithm for social robots. Our approach uses a combination of Bayesian-inference, CNN-based learning and the Pleasure-Arousal-Dominance model from psychology to estimate time-varying emotional behaviors of pedestrians from their faces and trajectories. For each pedestrian, these PAD characteristics are used to generate proxemic constraints. We use a multi-channel model to classify pedestrian features into four categories of emotions (happy, sad, angry, neutral). We observe an emotional detection accuracy of 85.33% in our validation results. In low-to medium-density environments, we formulate emotion-based proxemic constraints to perform socially conscious robot navigation. With Pepper, a social humanoid robot, we demonstrate the benefits of our algorithm in simulated environments with tens of pedestrians as well as in a real world setting.
Cite
Text
Bera et al. "Modelling Multi-Channel Emotions Using Facial Expression and Trajectory Cues for Improving Socially-Aware Robot Navigation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00035Markdown
[Bera et al. "Modelling Multi-Channel Emotions Using Facial Expression and Trajectory Cues for Improving Socially-Aware Robot Navigation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/bera2019cvprw-modelling/) doi:10.1109/CVPRW.2019.00035BibTeX
@inproceedings{bera2019cvprw-modelling,
title = {{Modelling Multi-Channel Emotions Using Facial Expression and Trajectory Cues for Improving Socially-Aware Robot Navigation}},
author = {Bera, Aniket and Randhavane, Tanmay and Manocha, Dinesh},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {257-266},
doi = {10.1109/CVPRW.2019.00035},
url = {https://mlanthology.org/cvprw/2019/bera2019cvprw-modelling/}
}