Search Results for author: David Millard

Found 6 papers, 3 papers with code

Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation

no code implementations18 Sep 2021 Eric Heiden, Christopher E. Denniston, David Millard, Fabio Ramos, Gaurav S. Sukhatme

We address the latter problem of estimating parameters through a Bayesian inference approach that approximates a posterior distribution over simulation parameters given real sensor measurements.

Bayesian Inference Code Generation

NeuralSim: Augmenting Differentiable Simulators with Neural Networks

2 code implementations9 Nov 2020 Eric Heiden, David Millard, Erwin Coumans, Yizhou Sheng, Gaurav S. Sukhatme

Differentiable simulators provide an avenue for closing the sim-to-real gap by enabling the use of efficient, gradient-based optimization algorithms to find the simulation parameters that best fit the observed sensor readings.


Domain Adversarial Neural Networks for Dysarthric Speech Recognition

no code implementations7 Oct 2020 Dominika Woszczyk, Stavros Petridis, David Millard

The results are compared to a speaker-adaptive (SA) model as well as speaker-dependent (SD) and multi-task learning models (MTL).

Multi-Task Learning Speech Recognition

Augmenting Differentiable Simulators with Neural Networks to Close the Sim2Real Gap

1 code implementation12 Jul 2020 Eric Heiden, David Millard, Erwin Coumans, Gaurav S. Sukhatme

We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical models with neural networks at any point of the computation.

Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamics

no code implementations22 Jan 2020 David Millard, Eric Heiden, Shubham Agrawal, Gaurav S. Sukhatme

A key ingredient to achieving intelligent behavior is physical understanding that equips robots with the ability to reason about the effects of their actions in a dynamic environment.

Interactive Differentiable Simulation

2 code implementations26 May 2019 Eric Heiden, David Millard, Hejia Zhang, Gaurav S. Sukhatme

While learning-based models of the environment dynamics have contributed to significant improvements in sample efficiency compared to model-free reinforcement learning algorithms, they typically fail to generalize to system states beyond the training data, while often grounding their predictions on non-interpretable latent variables.


Cannot find the paper you are looking for? You can Submit a new open access paper.