Towards More Realistic Human-Robot Conversation: A Seq2Seq-based Body Gesture Interaction System

Abstract

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.

arXiv commentAccepted by IROS 2019. Slides: https://youtu.be/zOp6tT_etQE

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• A Neural Conversational Model
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• TF.Learn: TensorFlow's High-level Module for Distributed Machine Learning