105 citations · 256 across the 14 of their papers we have counts for
14 papers
Modeling Large-Scale Adversarial Swarm Engagements using Optimal Control
Claire Walton, Isaac Kaminer, Qi Gong +2
We study optimal control of large-scale autonomous systems under adversarial conditions in which agents may be probabilistically destroyed during an engagement. Because attrition c…
An Actor Critic Method for Free Terminal Time Optimal Control
Evan Burton, Tenavi Nakamura-Zimmerer, Qi Gong +1
Optimal control problems with free terminal time present many challenges including nonsmooth and discontinuous control laws, irregular value functions, many local optima, and the c…
Neural Network Optimal Feedback Control with Guaranteed Local Stability
Tenavi Nakamura-Zimmerer, Qi Gong, Wei Kang
Recent research shows that supervised learning can be an effective tool for designing near-optimal feedback controllers for high-dimensional nonlinear dynamic systems. But the beha…
Neural network optimal feedback control with enhanced closed loop stability
Tenavi Nakamura-Zimmerer, Qi Gong, Wei Kang
Recent research has shown that supervised learning can be an effective tool for designing optimal feedback controllers for high-dimensional nonlinear dynamic systems. But the behav…
Defense Against Adversarial Swarms with Parameter Uncertainty
Claire Walton, Isaac Kaminer, Qi Gong +2
This paper addresses the problem of optimal defense of a High Value Unit against a large-scale swarm attack. We show that the problem can be cast in the framework of uncertain para…
Modeling and Control of Large-Scale Adversarial Swarm Engagements
Theodoros Tsatsanifos, Abram H. Clark, Claire Walton +2
We theoretically and numerically study the problem of optimal control of large-scale autonomous systems under explicitly adversarial conditions, including probabilistic destruction…
Neural Network Approximations of Compositional Functions With Applications to Dynamical Systems
Wei Kang, Qi Gong
As demonstrated in many areas of real-life applications, neural networks have the capability of dealing with high dimensional data. In the fields of optimal control and dynamical s…
QRnet: optimal regulator design with LQR-augmented neural networks
Tenavi Nakamura-Zimmerer, Qi Gong, Wei Kang
In this paper we propose a new computational method for designing optimal regulators for high-dimensional nonlinear systems. The proposed approach leverages physics-informed machin…
Algorithms of Data Development For Deep Learning and Feedback Design
Wei Kang, Qi Gong, Tenavi Nakamura-Zimmerer
Recent research reveals that deep learning is an effective way of solving high dimensional Hamilton-Jacobi-Bellman equations. The resulting feedback control law in the form of a ne…
Density Propagation with Characteristics-based Deep Learning
Tenavi Nakamura-Zimmerer, Daniele Venturi, Qi Gong +1
Uncertainty propagation in nonlinear dynamic systems remains an outstanding problem in scientific computing and control. Numerous approaches have been developed, but are limited in…
A new scalable algorithm for computational optimal control under uncertainty
Panos Lambrianides, Qi Gong, Daniele Venturi
We address the design and synthesis of optimal control strategies for high-dimensional stochastic dynamical systems. Such systems may be deterministic nonlinear systems evolving fr…
Adaptive Deep Learning for High-Dimensional Hamilton-Jacobi-Bellman Equations
Tenavi Nakamura-Zimmerer, Qi Gong, Wei Kang
Computing optimal feedback controls for nonlinear systems generally requires solving Hamilton-Jacobi-Bellman (HJB) equations, which are notoriously difficult when the state dimensi…
A Pseudospectral Approach to High Index DAE Optimal Control Problems
Harleigh C. Marsh, Mark Karpenko, Qi Gong
Historically, solving optimal control problems with high index differential algebraic equations (DAEs) has been considered extremely hard. Computational experience with Runge-Kutta…
Scaling and Balancing for High-Performance Computation of Optimal Controls
I. M. Ross, Q. Gong, M. Karpenko +1
It is well-known that proper scaling can increase the efficiency of computational problems. In this paper we define and show that a balancing technique can substantially improve th…