TY - JOUR
T1 - Local-HDP
T2 - Interactive open-ended 3D object category recognition in real-time robotic scenarios
AU - Ayoobi, Hamed
AU - Mohades Kasaei, Hamidreza
AU - Cao, Ming
AU - Verbrugge, Rineke
AU - Verheij, Bart
N1 - Funding Information:
Ming Cao is a professor of networks and robotics with the Engineering and Technology Institute at the University of Groningen, the Netherlands. He received the Bachelor degree in 1999 and the Master degree in 2002 from Tsinghua University, China, and the Ph.D. degree in 2007 from Yale University, USA, all in Electrical Engineering. He was a research associate in 2008 at Princeton University, USA and a research intern in 2006 at the IBM T. J. Watson Research Center, USA. He is the 2017 recipient of the Manfred Thoma medal from the International Federation of Automatic Control (IFAC) and the 2016 recipient of the European Control Award sponsored by the European Control Association (EUCA). He is a Senior Editor for Systems and Control Letters, and an Associate Editor for IEEE Transactions on Automatic Control. His research interests include autonomous agents and multi-agent systems, complex networks and decision-making processes.
Funding Information:
This work is conducted at the center of Data Science and Systems Complexity (DSSC) and sponsored with a Marie Skłodowska-Curie COFUND grant, agreement no. 754315 .
Publisher Copyright:
© 2021 The Author(s)
PY - 2022/1
Y1 - 2022/1
N2 - We introduce a non-parametric hierarchical Bayesian approach for open-ended 3D object categorization, named the Local Hierarchical Dirichlet Process (Local-HDP). This method allows an agent to learn independent topics for each category incrementally and to adapt to the environment in time. Each topic is a distribution of the visual words over a predefined dictionary. Using an inference algorithm, these latent variables are inferred from the dataset. Subsequently, the category of an object is determined based on the likelihood of generating a 3D object from the model. Hierarchical Bayesian approaches like Latent Dirichlet Allocation (LDA) can transform low-level features to high-level conceptual topics for 3D object categorization. However, the efficiency and accuracy of LDA-based approaches depend on the number of topics that is chosen manually. Moreover, fixing the number of topics for all categories can lead to overfitting or underfitting of the model. In contrast, the proposed Local-HDP can autonomously determine the number of topics for each category. Furthermore, the online variational inference method has been adapted for fast posterior approximation in the Local-HDP model. Experiments show that the proposed Local-HDP method outperforms other state-of-the-art approaches in terms of accuracy, scalability, and memory efficiency by a large margin. Moreover, two robotic experiments have been conducted to show the applicability of the proposed approach in real-time applications.
AB - We introduce a non-parametric hierarchical Bayesian approach for open-ended 3D object categorization, named the Local Hierarchical Dirichlet Process (Local-HDP). This method allows an agent to learn independent topics for each category incrementally and to adapt to the environment in time. Each topic is a distribution of the visual words over a predefined dictionary. Using an inference algorithm, these latent variables are inferred from the dataset. Subsequently, the category of an object is determined based on the likelihood of generating a 3D object from the model. Hierarchical Bayesian approaches like Latent Dirichlet Allocation (LDA) can transform low-level features to high-level conceptual topics for 3D object categorization. However, the efficiency and accuracy of LDA-based approaches depend on the number of topics that is chosen manually. Moreover, fixing the number of topics for all categories can lead to overfitting or underfitting of the model. In contrast, the proposed Local-HDP can autonomously determine the number of topics for each category. Furthermore, the online variational inference method has been adapted for fast posterior approximation in the Local-HDP model. Experiments show that the proposed Local-HDP method outperforms other state-of-the-art approaches in terms of accuracy, scalability, and memory efficiency by a large margin. Moreover, two robotic experiments have been conducted to show the applicability of the proposed approach in real-time applications.
KW - Open-Ended Learning
KW - Lifelong learning
KW - Class-Incremental Learning
KW - 3D Object Category Recognition
KW - Local Hierarchical Dirichlet Process
KW - Human-Robot Interaction
U2 - 10.1016/j.robot.2021.103911
DO - 10.1016/j.robot.2021.103911
M3 - Article
VL - 147
JO - Robotics and Autonomous Systems
JF - Robotics and Autonomous Systems
SN - 0921-8890
M1 - 103911
ER -