Heteroscedastic Uncertainty for Robust Generative Latent Dynamics
- 11 August 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (4) , 6654-6661
Abstract
Learning dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including robot motion planning 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
Funding Information
- Canada CIFAR AI Chairs Program
- Canada Research Chairs
This publication has 14 references indexed in Scilit:
- Safe Visual Navigation via Deep Learning and Novelty Detection2017
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- Kalman Filtering With Intermittent ObservationsIEEE Transactions on Automatic Control, 2004
- Variational Learning for Switching State-Space ModelsNeural Computation, 2000
- System Identification1998
- Probable networks and plausible predictions — a review of practical Bayesian methods for supervised neural networksNetwork: Computation in Neural Systems, 1995
- Novelty detection and neural network validationIEE Proceedings - Vision, Image, and Signal Processing, 1994
- Input Reconstruction Reliability Estimation1993
- Maximum likelihood estimates of linear dynamic systemsAIAA Journal, 1965
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960