Heteroscedastic Uncertainty for Robust Generative Latent Dynamics
Authors:
- Oliver LimoyoOLOliver Limoyo
- Bryan ChanBCBryan Chan
- Filip MarićFMFilip Marić
- Brandon WagstaffBWBrandon Wagstaff
- Rupam MahmoodRMRupam Mahmood
- Jonathan KellyJKJonathan Kelly
Preprint
Abstract
Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The problem has recently been studied from a generative perspective through latent dynamics: high-dimensional observations are embedded into a lower-dimensional space in which the dynamics can be learned. Despite some successes, latent dynamics models have not yet been applied to real-world robotic systems where learned representations must be robust to a variety of perceptual confounds and noise sources not seen during training. In this paper, we present a method to jointly learn a latent state representation and the associated dynamics that is amenable for long-term planning and closed-loop control under perceptually difficult conditions. As our main contribution, we describe how our representation is able to capture a notion of heteroscedastic or input-specific uncertainty at test time by detecting novel or out-of-distribution (OOD) inputs. We present results from prediction and control experiments on two image-based tasks: a simulated pendulum balancing task and a real-world robotic manipulator reaching task. We demonstrate that our model produces significantly more accurate predictions and exhibits improved control performance, compared to a model that assumes homoscedastic uncertainty only, in the presence of varying degrees of input degradation.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Unsupervised separation of dynamics from pixelsMETRON, 2019
- Kalman Filtering With Intermittent ObservationsIEEE Transactions on Automatic Control, 2004
- Variational Learning for Switching State-Space ModelsNeural Computation, 2000
- An Introduction to Variational Methods for Graphical ModelsMachine Learning, 1999
- Maximum likelihood estimates of linear dynamic systemsAIAA Journal, 1965
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960