Camera control for learning nonlinear target dynamics via Bayesian nonparametric Dirichlet-process Gaussian-process (DP-GP) models

• Published in: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 95 - 102
• Main Authors: Hongchuan Wei, Wenjie Lu, Pingping Zhu, Ferrari, Silvia, Klein, Robert H., Omidshafiei, Shayegan, How, Jonathan P.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2014
• Subjects: Atmospheric measurements; Cameras; Particle measurements; Position measurement; Time measurement; Vectors; Velocity measurement
• ISSN: 2153-0858; 2153-0866
• DOI: 10.1109/IROS.2014.6942546

This paper presents a camera control approach for learning unknown nonlinear target dynamics by approximating information value functions using particles that represent targets' position distributions. The target dynamics are described by a non-parametric mixture model that can learn a potentially infinite number of motion patterns. Assuming that each motion pattern can be represented as a velocity field, the target behaviors can be described by a non-parametric Dirichlet process-Gaussian process (DP-GP) mixture model. The DP-GP model has been successfully applied for clustering time-invariant spatial phenomena due to its flexibility to adapt to data complexity without overfitting. A new DP-GP information value function is presented that can be used by the sensor to explore and improve the DP-GP mixture model. The optimal camera control is computed to maximize this information value function online via a computationally efficient particle-based search method. The proposed approach is demonstrated through numerical simulations and hardware experiments in the RAVEN testbed at MIT.