How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations

by   Franck Djeumou, et al.

We present a framework and algorithms to learn controlled dynamics models using neural stochastic differential equations (SDEs) – SDEs whose drift and diffusion terms are both parametrized by neural networks. We construct the drift term to leverage a priori physics knowledge as inductive bias, and we design the diffusion term to represent a distance-aware estimate of the uncertainty in the learned model's predictions – it matches the system's underlying stochasticity when evaluated on states near those from the training dataset, and it predicts highly stochastic dynamics when evaluated on states beyond the training regime. The proposed neural SDEs can be evaluated quickly enough for use in model predictive control algorithms, or they can be used as simulators for model-based reinforcement learning. Furthermore, they make accurate predictions over long time horizons, even when trained on small datasets that cover limited regions of the state space. We demonstrate these capabilities through experiments on simulated robotic systems, as well as by using them to model and control a hexacopter's flight dynamics: A neural SDE trained using only three minutes of manually collected flight data results in a model-based control policy that accurately tracks aggressive trajectories that push the hexacopter's velocity and Euler angles to nearly double the maximum values observed in the training dataset.


Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equations

Neural Stochastic Differential Equations (NSDE) have been trained as bot...

Differentiable Physics-based Greenhouse Simulation

We present a differentiable greenhouse simulation model based on physica...

Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control

Model-based reinforcement learning (MBRL) is believed to have much highe...

Physics-constrained neural differential equations for learning multi-ionic transport

Continuum models for ion transport through polyamide nanopores require s...

Deterministic Inference of Neural Stochastic Differential Equations

Model noise is known to have detrimental effects on neural networks, suc...

Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Nonholonomic control is a candidate to control nonlinear systems with pa...

Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models

Differential equations in general and neural ODEs in particular are an e...

Please sign up or login with your details

Forgot password? Click here to reset