Hybrid control framework of uavs under varying wind and payload conditions

A Coursey, A Zhang… - 2024 American …, 2024 - ieeexplore.ieee.org
Reinforcement learning (RL) algorithms are increasingly applied to engineering control
applications. They offer a promising alternative to traditional control methods, which often …

Probabilistic Evaluation for Flight Mission Feasibility of a Small Octocopter in the Presence of Wind

A Taye, EL Thompson, P Wei, T Bonin… - AIAA AVIATION 2023 …, 2023 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-3964. vid The Advanced Air
Mobility (AAM) concept envisions small unmanned aerial systems (UASs) and some larger …

Adaptive Learning of Design Strategies over Non-Hierarchical Multi-Fidelity Models via Policy Alignment

A Agrawal, C McComb - arxiv preprint arxiv:2411.10841, 2024 - arxiv.org
Multi-fidelity Reinforcement Learning (RL) frameworks significantly enhance the efficiency of
engineering design by leveraging analysis models with varying levels of accuracy and …

Quantifying the Sim-To-Real Gap in UAV Disturbance Rejection

A Coursey, M Quinones-Grueiro… - … on Principles of …, 2024 - drops.dagstuhl.de
Due to the safety risks and training sample inefficiency, it is often preferred to develop
controllers in simulation. However, minor differences between the simulation and the real …

A Reinforcement Learning Approach for Robust Supervisory Control of UAVs Under Disturbances

I Ahmed, M Quinones-Grueiro, G Biswas - arxiv preprint arxiv:2305.12543, 2023 - arxiv.org
In this work, we present an approach to supervisory reinforcement learning control for
unmanned aerial vehicles (UAVs). UAVs are dynamic systems where control decisions in …

Flight Mission Feasibility Assessment of Urban Air Mobility Operations under Battery Energy Constraint

AG Taye, P Wei - AIAA SCITECH 2024 Forum, 2024 - arc.aiaa.org
This paper introduces a decision-making framework for Urban Air Mobility (UAM) and
Unmanned Aerial Systems (UAS) operations that addresses the dual challenges of collision …

High-Fidelity Simulation of a Cartpole for Sim-to-Real Deep Reinforcement Learning

L Bantel, P Domanski, D Pflüger - 2024 4th Interdisciplinary …, 2024 - ieeexplore.ieee.org
This work proposes a novel physics-based Cartpole simulation environment as a new
benchmark to address the sim-to-real transfer. Our simulation environment extends the …

Robust trajectory planning for multi-rotor aerial vehicles subject to saturation faults and wind disturbances

M Quinones-Grueiro, I Ahmed, G Biswas - AIAA AVIATION 2023 Forum, 2023 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-4041. vid In this paper, we propose
a trajectory planning approach to accommodate saturation faults associated with the …

Adaptive Fault-tolerant Control Using Reinforcement Learning

I Ahmed - 2023 - search.proquest.com
Cyber-physical systems are ubiquitous in the modern world. They can be intricate and
diverse as they are prevalent. Such systems may operate with tight time-constants in the …

Combining Reinforcement Learning and Cascade Pid Control for Uav Disturbance Rejection

A Coursey, M Quinones-Grueiro, L Alvarez… - Available at SSRN … - papers.ssrn.com
Ensuring the safety of unmanned aerial vehicles (UAVs) under unknown disturbances, like
wind, is crucial due to their lightweight design. Traditional control-based approaches often …