activity
20152021
most citedModel Predictive Path Integral Control using Covariance Variable Importance Sampling

68 citations · 199 across the 10 of their papers we have counts for

collaborators

10 papers

eess.SY2021★ 62 cited

Robust Model Predictive Path Integral Control: Analysis and Performance Guarantees

Manan Gandhi, Bogdan Vlahov, Jason Gibson +2

In this paper we propose a novel decision making architecture for Robust Model Predictive Path Integral control (RMPPI) and investigate its performance guarantees and applicability…

cs.RO2019★ 9 cited

Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamics

Grady Williams, Brian Goldfain, James M. Rehg +1

We consider the problem of online adaptation of a neural network designed to represent vehicle dynamics. The neural network model is intended to be used by an MPC control law to au…

cs.RO2018

Vision-Based High Speed Driving with a Deep Dynamic Observer

Paul Drews, Grady Williams, Brian Goldfain +2

In this paper we present a framework for combining deep learning-based road detection, particle filters, and Model Predictive Control (MPC) to drive aggressively using only a monoc…

math.OC2018★ 1 cited

Information Theoretic Model Predictive Control on Jump Diffusion Processes

Ziyi Wang, Grady Williams, Evangelos A. Theodorou

In this paper we present an information theoretic approach to stochastic optimal control problems for systems with compound Poisson noise. We generalize previous work on informatio…

cs.RO2017★ 31 cited

Aggressive Deep Driving: Model Predictive Control with a CNN Cost Model

Paul Drews, Grady Williams, Brian Goldfain +2

We present a framework for vision-based model predictive control (MPC) for the task of aggressive, high-speed autonomous driving. Our approach uses deep convolutional neural networ…

cs.RO2017★ 9 cited

Autonomous Racing with AutoRally Vehicles and Differential Games

Grady Williams, Brian Goldfain, Paul Drews +2

Safe autonomous vehicles must be able to predict and react to the drivers around them. Previous control methods rely heavily on pre-computation and are unable to react to dynamic e…