Nonparametric Bayesian Models to Represent Knowledge Uncertainty for Decentralized Planning

Project Description:

This research enables radically new capabilities to deploy intelligent decentralized knowledge learning and planning algorithms for teams of heterogeneous autonomous static and mobile agents. The research plan is based on the key insight that Bayesian nonparametric models (BNPM) provide a powerful framework for reasoning about objects and relations in settings in which these objects and relations are not predefined. This feature is particularly attractive for missions such as long term persistent surveillance for which it is virtually impossible to specify the size of the model and the number of variables a priori.

Peer-Reviewed Publications:

  • Hongchuan Wei, Pingping Zhu, Miao Liu, Jonathan P. How, and Silvia Ferrari, “Automatic Pan-tilt Camera Control for Learning Dirichlet Process Gaussian Process (DPGP) Mixture Models of Multiple Moving Targets,” IEEE Transactions on Automatic Control, 2018 [Link].
  • Hongchuan Wei, Wenjie Lu, Pingping Zhu, Silvia Ferrari, Miao Liu, Robert H. Klein, Shayegan Omiddshafiei, Jonathan P. How, “Information value in nonparametric Dirichlet-process Gaussian-process (DPGP) mixture models,” Automatica, 74, 360-368, 2016. [Link][PDF]
  • Hongchuan Wei, Wenjie Lu, Pingping Zhu, Silvia Ferrari, Robert Klein, Shayegan Omidshaei, Patrick How, "Camera Control for Learning Nonlinear Target Dynamics Via Bayesian Nonparametric Dirichlet Process Gaussain Process (DP-GP) Models," Intelligent Robots and Systems (IROS) IEEE/RSJ International Conference on, 2014. [Link]
  • Hongchuan Wei, Wenjie Lu, Pingping Zhu, Guoquan Huang, John Leonard, Silvia Ferrari, "Optimized Visibility Motion Planning for Target Tracking and Localization," Intelligent Robots and Systems (IROS) IEEE/RSJ International Conference on, 2014. [Link]