English

Improving Human Motion Prediction Through Continual Learning

Robotics 2021-07-02 v1 Computer Vision and Pattern Recognition

Abstract

Human motion prediction is an essential component for enabling closer human-robot collaboration. The task of accurately predicting human motion is non-trivial. It is compounded by the variability of human motion, both at a skeletal level due to the varying size of humans and at a motion level due to individual movement's idiosyncrasies. These variables make it challenging for learning algorithms to obtain a general representation that is robust to the diverse spatio-temporal patterns of human motion. In this work, we propose a modular sequence learning approach that allows end-to-end training while also having the flexibility of being fine-tuned. Our approach relies on the diversity of training samples to first learn a robust representation, which can then be fine-tuned in a continual learning setup to predict the motion of new subjects. We evaluated the proposed approach by comparing its performance against state-of-the-art baselines. The results suggest that our approach outperforms other methods over all the evaluated temporal horizons, using a small amount of data for fine-tuning. The improved performance of our approach opens up the possibility of using continual learning for personalized and reliable motion prediction.

Keywords

Cite

@article{arxiv.2107.00544,
  title  = {Improving Human Motion Prediction Through Continual Learning},
  author = {Mohammad Samin Yasar and Tariq Iqbal},
  journal= {arXiv preprint arXiv:2107.00544},
  year   = {2021}
}