Learning Deep Dynamical Models From Image Pixels
2015 (English)In: Proceedings of the 17th IFAC Symposium on System Identification, 2015Conference paper (Refereed)
Modeling dynamical systems is important in many disciplines, such as control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional observations. In these cases, system identification, i.e., finding the measurement mapping and the transition mapping (system dynamics) in latent space can be challenging. For linear system dynamics and measurement mappings efficient solutions for system identification are available. However, in practical applications, the linearity assumptions does not hold, requiring nonlinear system identification techniques. If additionally the observations are high-dimensional (e.g., images), nonlinear system identification is inherently hard. To address the problem of nonlinear system identification from high-dimensional observations, we combine recent advances in deep learning and system identification. In particular, we jointly learn a low-dimensional embedding of the observation by means of deep auto-encoders and a predictive transition model in this low-dimensional space. We demonstrate that our model enables learning good predictive models of dynamical systems from pixel information only.
Place, publisher, year, edition, pages
Deep neural networks, system identification, nonlinear systems, low-dimensional embedding, auto-encoder
IdentifiersURN: urn:nbn:se:liu:diva-122393OAI: oai:DiVA.org:liu-122393DiVA: diva2:866118
17th IFAC Symposium on System Identification (SYSID), October 19-21, Beijing, China
FunderSwedish Foundation for Strategic Research , COOPLOCSwedish Research Council, 621-2013-5524