2026 ASEE Annual Conference & Exposition

A Risk-Free Approach to Validate Drone Flight Paths Using Computer Simulation and Reinforcement Learning

Presented at Manufacturing Division (MFG) Technical Session 4: Curriculum Development in Manufacturing Education II

Validating autonomous drone flight paths in physical environments poses safety risks and limits hands-on experimentation in engineering education. To address this challenge, this study presents a simulation-based learning platform that integrates computer modeling and reinforcement learning (RL) to support experiential learning in drone navigation and control. A 3D grid-based drone workspace was developed in FlexSim and connected to the Stable Baselines3 Proximal Policy Optimization (PPO) algorithm through a custom Gym-compatible Python interface. Within this virtual environment, students can observe and experiment with an RL-controlled drone learning to reach target locations while avoiding obstacles and boundary collisions. The effectiveness of the learned policies is evaluated using quantitative metrics such as collision rate, path length efficiency, and task success rate, enabling both performance assessment and instructional discussion. The platform has been introduced as a laboratory-style learning module, allowing students to visualize policy learning, trial-and-error decision-making, and fail-safe behavior in a classroom or laboratory setting. The framework demonstrates how simulation-driven RL environments can enhance teaching and learning in robotics, controls, and artificial intelligence courses.

Authors

Dr. Md Fashiar Rahman http://orcid.org/0000-0002-0437-2587 The University of Texas at El Paso [biography]

Dr. Md Fashiar Rahman is an Assistant Professor of the Industrial, Manufacturing and Systems Engineering (IMSE) Department at The University of Texas at El Paso. He holds a Ph.D. degree in Computational Science Program. He has years of research experience across projects in image data mining, machine learning, deep learning, and computer simulation for industrial and healthcare applications. In addition, Dr. Rahman has taught various engineering courses in industrial and manufacturing engineering. His research area covers advanced quality technology, AI applications in smart manufacturing, health care applications, computational intelligence/data analytics, and decision support systems.
Selim Molla http://orcid.org/0009-0007-2969-2791 University of Texas at El Paso [biography]

Selim Molla is a PhD student in the Computational Science Program at the University of Texas at El Paso (UTEP), USA. He received his M.Sc. in Computational Science from UTEP and his B.Sc. in Industrial and Production Engineering from Khulna University of Engineering and Technology (KUET), Bangladesh. His research focuses on computational modeling, simulation, and optimization of complex systems, with applications in manufacturing, industrial, and healthcare domains. He also works on integrating machine learning and deep learning with simulation to support data-driven decision-making and intelligent system design.
Prof. Tzu-liang Bill Tseng http://orcid.org/0000-0002-3903-529X University of Texas at El Paso [biography]

Dr. Bill Tseng is a Professor and Chair of Department of Industrial, Manufacturing and Systems Engineering at the UTEP. He is also a Director of Research Institute for Manufacturing & Engineering Systems, the host institute of Texas Manufacturing Assistan
Dr. Richard Y Chiou Drexel University [biography]

Dr. Richard Y. Chiou is a Professor within the Department of Engineering, Leadership, and Society at Drexel University, Philadelphia, USA. His educational background is in manufacturing with an emphasis on mechatronics. In addition to his years of industrial experience, he has taught many different engineering and technology courses at undergraduate and graduate levels. His tremendous research experience in manufacturing includes intelligent manufacturing, eco-manufacturing, Internet based robotics, and clean energy and energy efficiency. He has conducted many experimental studies on virtual reality robotics, ultrasonic robotic welding, Internet-of-Things (IoT) in intelligent manufacturing. He has also developed augmented reality/virtual reality (AR/VR) robotics and clean energy and energy efficiency laboratory recently. He has secured many research and education grants from the National Science Foundation, the US Department of Education, the Society of Manufacturing Engineers Education Foundation, and industries. Techniques developed from his research projects have been extended to the educational activities involving intelligent manufacturing with clean energy and energy efficiency.
Dr. Md Abdul Quddus North Carolina State University at Raleigh [biography]

Dr. Md Abdul Quddus, PhD is an Assistant Professor in the Department of Textile Engineering, Chemistry and Science at NC State University and Associate Faculty in the Operations Research Graduate Program. His research focuses on supply chain and logistics, big data analytics, stochastic programming, geospatial analytics for optimization, and simulation. Furthermore, his specialties also include on the application of AI, deep learning, cloud computing, and operations research techniques to solve large scale supply chain network and risk management problems. Dr. Quddus has over five years of industry experience as a Senior Operations Research Advisor at FedEx Express. His research has been published in journals such as Expert Systems with Applications, Transportation Research Part E, International Journal of Production Economics, and Applied Energy.

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026

« View session