Conference Papers

Authors: Ellis L. Thompson, Abenezer G. Taye, Wei Guo, Peng Wei,Marcos Quinones, Ibrahim Ahmed, Gautam Biswas, Jesse Quattrociocchi, Steven Carr, Ufuk Topcu, James C. Jones and Marc W. Brittain


Conference: AIAA AVIATION 2023

Abstract: In this research, we have identified and surveyed three categories of hazards for advancedair mobility (AAM): (i) adverse weather with a special focus on winds, (ii) eVTOL vehicleand component level faults/degradation, and (iii) AAM corridor incursion by non-cooperativeaircraft. While these categories of hazards may be independent of one another as first ordereffects, their collective impact on safety is also an important factor. This paper is the firstpublication from the NASA funded project named ‚ÄúDemonstration of the In-Time Learning-Based Safety Management for Scalable Heterogeneous AAM Operations‚ÄĚ. Our research teamproposes the design, development and demonstration of an in-time learning-based aviationsafety management system (ILASMS) for scalable heterogeneous AAM operations. We proposethree core functions (F1-mission level, F2-vehicle level, and F3-airspace level) in the ILASMS,to address these hazards. This survey paper will identify possible hazards that will define thefunction groups design requirements and specifications. We will perform system validation andscenario demonstrations with use case simulations and sub-scale flight tests.

Bibtex Citation:

@inbook{doi:10.2514/6.2022-3539, author = {Ellis L. Thompson and Abenezer G. Taye and Wei Guo and Peng Wei and Marcos Quinones and Ibrahim Ahmed and Gautam Biswas and Jesse Quattrociocchi and Steven Carr and Ufuk Topcu and James C. Jones and Marc W. Brittain}, title = {A Survey of eVTOL Aircraft and AAM Operation Hazards}, booktitle = {AIAA AVIATION 2022 Forum}, chapter = {}, pages = {}, doi = {10.2514/6.2022-3539}, URL = {}, eprint = {}, }


Authors: Ellis L. Thompson, Yan Xu and Peng Wei


Abstract: Strategic pre-flight systems focus on the planning and deconfliction of routes for aircraft systems. The urban air mobility concept calls for higher levels of autonomy with both onboard and en route systems but also strategic and other pre-flight systems. Existing endeavors into strategic pre-flight systems focus on improving the route generation and strategic deconfliction of these routes. Introduced with the urban air mobility concept is the premise of operational volumes, 4D regions of airspace, including time, a single aircraft is expected to operate within, forming a contract of finite operational volumes over the duration of a route. It is no longer enough to only deconflict routes within the airspace, but to now consider these 4D operational volumes. To provide an effective all-in-one approach, we propose a novel framework for generating routes and accompanying contracts of operational volumes, along with deconfliction focused around 4D operational volumes. Experimental results show efficiency of operational volume generation utilising reachability analysis and demonstrate sufficient success in deconfliction of operational volumes.

Bibtex Citation:

@misc{, doi = {10.48550/ARXIV.2301.12961}, url = {}, author = {Thompson, Ellis Lee and Xu, Yan and Wei, Peng}, keywords = {Other Computer Science (cs.OH), Systems and Control (eess.SY), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering}, title = {A Framework for Operational Volume Generation for UAM Strategic Deconfliction}, publisher = {arXiv}, year = {2023}, copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International} }

Authors: Pouria Razzaghi, Amin Tabrizian, Wei Guo, Shulu Chen, Abenezer Taye, Ellis L. Thompson, Alexis Bregeon, Ali Baheri and Peng Wei


Abstract: Compared with model-based control and optimization methods, reinforcement learning (RL) provides a data-driven, learning-based framework to formulate and solve sequential decision-making problems. The RL framework has become promising due to largely improved data availability and computing power in the aviation industry. Many aviation-based applications can be formulated or treated as sequential decision-making problems. Some of them are offline planning problems, while others need to be solved online and are safety-critical. In this survey paper, we first describe standard RL formulations and solutions. Then we survey the landscape of existing RL-based applications in aviation. Finally, we summarize the paper, identify the technical gaps, and suggest future directions of RL research in aviation.

Bibtex Citation:

@misc{10.48550 doi = {10.48550/ARXIV.2211.02147}, url = {}, author = {Razzaghi, Pouria and Tabrizian, Amin and Guo, Wei and Chen, Shulu and Taye, Abenezer and Thompson, Ellis and Bregeon, Alexis and Baheri, Ali and Wei, Peng}, title = {A Survey on Reinforcement Learning in Aviation Applications}, publisher = {arXiv}, year = {2022}, copyright = { perpetual, non-exclusive license} }

In Progress

Authors: Abenezer Taye, Ellis L. Thompson, Peng Wei, Timothy Bonin, James Jones, Marcos Quinones-Grueiro and Guatam Biswas

Link: TBA

Abstract: N/A

Bibtex Citation:

@misc{Thompson2022, author = {Abenezer G. Taye and Ellis L. Thompson and Peng Wei and Timothy Bonin and James Jones and Marcos Quinones-Grueiro and Guatam Biswas}, title = {Probabilistic Evaluation for Flight Mission Feasibility of A Small Octocopter in the Presence of Wind}, year = {2022} }