Timezone: »

 
Poster
Learning Physics Constrained Dynamics Using Autoencoders
Tsung-Yen Yang · Justinian Rosca · Karthik Narasimhan · Peter J. Ramadge

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #526
in Poster Session 3 »

We consider the problem of estimating states (e.g., position and velocity) and physical parameters (e.g., friction, elasticity) from a sequence of observations when provided a dynamic equation that describes the behavior of the system. The dynamic equation can arise from first principles (e.g., Newton’s laws) and provide useful cues for learning, but its physical parameters are unknown. To address this problem, we propose a model that estimates states and physical parameters of the system using two main components. First, an autoencoder compresses a sequence of observations (e.g., sensor measurements, pixel images) into a sequence for the state representation that is consistent with physics by including a simulation of the dynamic equation. Second, an estimator is coupled with the autoencoder to predict the values of the physical parameters. We also theoretically and empirically show that using Fourier feature mappings improves generalization of the estimator in predicting physical parameters compared to raw state sequences. In our experiments on three visual and one sensor measurement tasks, our model imposes interpretability on latent states and achieves improved generalization performance for long-term prediction of system dynamics over state-of-the-art baselines.

Keywords: Autoencoder with Latent Physics · Deep Learning and its Application

Author Information

Tsung-Yen Yang (Princeton University / Meta AI)

I am a graduate student in the Department of Electrical Engineering at Princeton University, working with Prof. Peter Ramadge and Prof. Karthik Narasimhan since September 2017. My research interests lie at the intersection of machine learning, reinforcement learning, and natural language processing. Specifically, I work on safe reinforcement learning, focusing on building autonomous systems that acquire knowledge by interacting with the world, and providing provable safety guarantees during training and deployment.

Justinian Rosca (Siemens Corporation, Technology)
Karthik Narasimhan (Princeton University)
Peter J. Ramadge (Princeton)

More from the Same Authors