Transformer-Guided Deep Reinforcement Learning for Trajectory Design
Location
Havener Center, Miner Lounge / Wiese Atrium, 1:30pm-3:30pm
Start Date
4-2-2026 1:30 PM
End Date
4-2-2026 3:30 PM
Presentation Date
April 2, 2026; 1:30pm-3:30pm
Description
Electric vertical takeoff and landing (eVTOL) aircraft are limited in range by battery capacity, making energy-efficient takeoff trajectory design critical for practical operation. While deep reinforcement learning (DRL) enables adaptive control, it often struggles to discover feasible solutions due to highly nonlinear dynamics, strict constraints, and high sample complexity. This work introduces a transformer-guided deep reinforcement learning (TDRL) framework for eVTOL takeoff trajectory design. A transformer trained on optimal control trajectories learns temporal relationships in control sequences and guides policy exploration by restricting actions to feasible, energy-conscious regions. The approach is evaluated across a design space varying aircraft parameters, namely efficiency and wing planform scale. Transformer-guided agents achieved feasible trajectories at all evaluated design points, maintaining energy consumption within 5% of optimal solutions, whereas vanilla DRL failed in most cases. Results demonstrate that transformer guidance improves training reliability and performance across vehicle configurations.
Biography
Nathan Roberts II is a doctoral student in the Mechanical and Aerospace Engineering Department, and a Kummer Innovation and Entrepreneurship (I&E) Doctoral Fellow. He earned his bachelor’s degree in aerospace engineering from Missouri University of Science and Technology in 2024. He is studying in the Physical Artificial Intelligence (PHLAI) Lab under the supervision of his advisor, Dr. Xiaosong Du. Nathan’s research interests include deep reinforcement learning, transformer architectures for sequence modeling, and physics-informed machine learning.
Meeting Name
2026 - Miners Solving for Tomorrow Research Conference
Department(s)
Mechanical and Aerospace Engineering
Document Type
Poster
Document Version
Final Version
File Type
event
Language(s)
English
Rights
© 2026 The Authors, All rights reserved
Transformer-Guided Deep Reinforcement Learning for Trajectory Design
Havener Center, Miner Lounge / Wiese Atrium, 1:30pm-3:30pm
Electric vertical takeoff and landing (eVTOL) aircraft are limited in range by battery capacity, making energy-efficient takeoff trajectory design critical for practical operation. While deep reinforcement learning (DRL) enables adaptive control, it often struggles to discover feasible solutions due to highly nonlinear dynamics, strict constraints, and high sample complexity. This work introduces a transformer-guided deep reinforcement learning (TDRL) framework for eVTOL takeoff trajectory design. A transformer trained on optimal control trajectories learns temporal relationships in control sequences and guides policy exploration by restricting actions to feasible, energy-conscious regions. The approach is evaluated across a design space varying aircraft parameters, namely efficiency and wing planform scale. Transformer-guided agents achieved feasible trajectories at all evaluated design points, maintaining energy consumption within 5% of optimal solutions, whereas vanilla DRL failed in most cases. Results demonstrate that transformer guidance improves training reliability and performance across vehicle configurations.
Comments
Advisor: Xiaosong Du, xiaosongdu@mst.edu