A novel curved gaussian mixture model and its application in motion skill encoding

Chen, Disi; Li, Gongfa; Zhou, Dalin; Ju, Zhaojie

Abstract

The purpose of this paper is to present a novel curved Gaussian Mixture Model (CGMM) and to study the application of it in motion skill encoding. Primarily, Gaussian mixture model (GMM) has been widely applied on many occasions when a probability density function is needed to approximate a complex probability distribution. However, GMM cannot efficiently approach highly non-linear distributions. Thus, the proposed novel CGMM, as a weighted mixture of curved Gaussian models (CGM), is structured with non-linear transfers, which reshapes the flat GMM into a geo-metrically curved one. As a consequence, CGMM has more freedoms and flexibilities than the flat GMM so a CGMM requires fewer number of components in fitting highly non-linear motion trajectories. Moreover, we derive a dedicated iterative parameter estimation algorithm for the CGMM based on maximum likelihood estimation (MLE) theory. To evaluate the performance of the CGMM and its parameter estimation algorithm, a series of quantitative experiments are carried out. We first test the model performance in the data fitting task with the generated synthetic data. Then a motion skill encoding test is carried out on a human motion trajectory dataset built by a Virtual Reality (VR) based motion tracking system. The empirical results support that CGMM outperforms state-of-the-arts in the model performance test. Meanwhile, CGMM has a significant improvement in encoding high dimensional non-linear trajectory data compared to the GMM in motion skill encoding test with its dedicated parameter estimation algorithm.

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• Start Date: Sep 27, 2021
• End Date: Oct 1, 2021
• Acceptance Date: Jun 30, 2021
• Publication Date: Dec 16, 2021
• Deposit Date: Nov 4, 2022
• Publicly Available Date: Dec 17, 2023
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Pages: 7813-7818
• Series Title: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• Series ISSN: 2153-0866
• Book Title: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• ISBN: 9781665417143
• DOI: https://doi.org/10.1109/IROS51168.2021.9636121
• Keywords: Non-linear Transfer, Curved Gaussian Mix-ture Model, Expectation-Maximization Algorithm, Motion Skill Encoding, Solid modeling, Maximum likelihood estimation, Parameter estimation, Tracking, Fitting, Virtual reality, Encoding
• Public URL: https://uwe-repository.worktribe.com/output/10117763
• Publisher URL: https://ieeexplore.ieee.org/document/9636121
• Related Public URLs: https://ieeexplore.ieee.org/xpl/conhome/9635848/proceeding