Towards More Realistic Human-Robot Conversation: A Seq2Seq-based Body Gesture Interaction System
This work addresses the challenge of making human-robot conversations more natural and engaging for users, though it is incremental as it adapts existing seq2seq methods to a specific domain.
The paper tackles the problem of enabling robots to exhibit realistic body gestures during human-robot conversations by developing a seq2seq-based system that synthesizes gestures from 12 upper-body keypoints, achieving improvements demonstrated through metrics like MSE and cosine similarity on a test dataset and implementation on a virtual avatar and physical robot.
This paper presents a novel system that enables intelligent robots to exhibit realistic body gestures while communicating with humans. The proposed system consists of a listening model and a speaking model used in corresponding conversational phases. Both models are adapted from the sequence-to-sequence (seq2seq) architecture to synthesize body gestures represented by the movements of twelve upper-body keypoints. All the extracted 2D keypoints are firstly 3D-transformed, then rotated and normalized to discard irrelevant information. Substantial videos of human conversations from Youtube are collected and preprocessed to train the listening and speaking models separately, after which the two models are evaluated using metrics of mean squared error (MSE) and cosine similarity on the test dataset. The tuned system is implemented to drive a virtual avatar as well as Pepper, a physical humanoid robot, to demonstrate the improvement on conversational interaction abilities of our method in practice.