Estimating Emotional Intensity from Body Poses for Human-Robot Interaction
This addresses the need for robots to perceive emotional intensities from body language, an overlooked aspect in social and service robotics, though it is incremental as it builds on existing pose-based approaches.
The paper tackles the problem of estimating emotional intensity from body poses for human-robot interaction, presenting a method that uses local joint transformations and LSTM-RNNs, which performs better than baselines in dataset evaluations and is effective in real-time field tests on a physical robot.
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.