8 papers
Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models
Alex E. Ballentine, Nachiket U. Bapat, Raghvendra V. Cowlagi
The deployment of reinforcement learning (RL)-based controllers on physical systems is often limited by poor generalization to real-world scenarios, known as the simulation-to-real…
Trajectory Optimization for Minimum Threat Exposure using Physics-Informed Neural Networks
Alexandra E. Ballentine, Raghvendra V. Cowlagi
We apply a physics-informed neural network (PINN) to solve the two-point boundary value problem (BVP) arising from the necessary conditions postulated by Pontryagin's Minimum Princ…
Optimal Coupled Sensor Placement and Path-Planning in Unknown Time-Varying Environments
Prakash Poudel, Raghvendra V. Cowlagi
We address path-planning for a mobile agent to navigate in an unknown environment with minimum exposure to a spatially and temporally varying threat field. The threat field is esti…
Case Studies of Generative Machine Learning Models for Dynamical Systems
Nachiket U. Bapat, Randy C. Paffenroth, Raghvendra V. Cowlagi
Systems like aircraft and spacecraft are expensive to operate in the real world. The design, validation, and testing for such systems therefore relies on a combination of mathemati…
Synthetic Data Generation for Minimum-Exposure Navigation in a Time-Varying Environment using Generative AI Models
Nachiket U. Bapat, Randy C. Paffenroth, Raghvendra V. Cowlagi
We study the problem of synthetic generation of samples of environmental features for autonomous vehicle navigation. These features are described by a spatiotemporally varying scal…
Inverse Reinforcement Learning for Minimum-Exposure Paths in Spatiotemporally Varying Scalar Fields
Alexandra E. Ballentine, Raghvendra V. Cowlagi
Performance and reliability analyses of autonomous vehicles (AVs) can benefit from tools that ``amplify'' small datasets to synthesize larger volumes of plausible samples of the AV…