Design and Testing of an Approach to Automated In-Flight Safety Risk Management for sUAS Operations

Ancel, Ersin; Young, Steven D.; Quach, Cuong C.; Haq, Rafia F.; Darafsheh, Kaveh; Smalling, Kyle M.; Vazquez, Sixto L.; Dill, Evan T.; Condotta, Ryan C.; Ethridge, Bailey E.; Teska, Logan R.; Johnson, Thomas A.

doi:10.2514/6.2022-3459

Cited by 9 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Airplanes are one of the modes of air transportation needed to accelerate long-distance transportation (Kiracı & Bakır, 2019;Zhang & Graham, 2020). In the world of aviation whose development is relatively very rapid, there is still a need to evaluate and improve aspects of safety and security in aviation (Ancel et al, 2022;Kakaletsis et al, 2021;Lager & Melin, 2021;Majid et al, 2022;Peysakhovich et al, 2018). Overall aviation always pays attention to flight safety, flight discipline, flight efficiency and comfort (Chen & Zhang, 2022;Patel & D'cruz, 2017;Priyambodo & Nugraha, 2019).…”

Section: Introductionmentioning

confidence: 99%

Design Pitot Tube Cover with Artificial Intelligence (Arduino) Based Warning System on Piper Seneca V Aircraft

Putra,

Wibowo,

Kuncoro

et al. 2023

jppipa, pendidikan ipa, fisika, biologi, kimia

View full text Add to dashboard Cite

The pitot tube is a component in the fuselage to measure the pressure generated by air movement or wind, while the placement of the pitot tube is usually on the wing. A trivial thing that can be fatal is that before flying, sometimes the pilot/flight instructor neglects to remove the pitot tank cover. This negligence resulted in the malfunctioning of the Air Speed Indicator (ASI), Vertical Speed Indicator and Altimeter. Appropriate technology in the form of a pitot tube cover with a warning using an ultrasonic sensor with the support of artificial intelligence technology using Arduino has been applied to the Piper Seneca V aircraft to prevent negligence in removing the pitot tube cover before flying. The Piper Seneca V has been chosen as the object of the application of technology because the Piper Seneca V type aircraft is of the low wing type so that the pitot tubes are not visible when not inspecting the underside of the aircraft's wings. During 30 days of testing with 12 hours of testing time each day and exposure to different temperatures and humidity each day, both battery life and component resistance can be ensured that they are still in optimal conditions. During testing in the simulation room, the tool worked well with a 1 meter object detection configuration. Using a 3.7 volt battery with a storage capacity of 1600 mAh can make the device last for 4 days with 2 hours of recharging time.

show abstract

Section: Introductionmentioning

confidence: 99%

Design Pitot Tube Cover with Artificial Intelligence (Arduino) Based Warning System on Piper Seneca V Aircraft

Putra,

Wibowo,

Kuncoro

et al. 2023

jppipa, pendidikan ipa, fisika, biologi, kimia

View full text Add to dashboard Cite

show abstract

A Systematic Review of Enhancing Aerospace Safety with Augmented Reality

Wu,

Moore,

Duffy

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Towards a Standardized Reinforcement Learning Framework for AAM Contingency Management

Alvarez,

Brittain,

Breeden

2023

2023 IEEE/AIAA 42nd Digital Avionics Systems Conference (DASC)

View full text Add to dashboard Cite

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process. I. IntroductionT he air transportation system is currently undergoing a rapid evolution with the introduction of novel concepts and the demand for an increase in operational efficiency. One of those novel concepts is Advanced Air Mobility (AAM), which foresees the transport of cargo and passengers across cities, as well as communities currently under-served by aviation. These AAM operations may include electric vertical take-off and landing (eVTOL) aircraft, high-density operations, and a combination of piloted (i.e., remote or on-board) and autonomous flights. Across the world, organizations such as the FAA, NASA, and EASA expect these operations to increase in density from a single operation per hour to over 100 simultaneous operations per hour over a local region [1][2][3][4]. The FAA and NASA refer to the increasing phases of complexity for AAM operations as Urban Air Mobility (UAM) Maturity Levels (UML). Low-density human piloted airspace operations are classified as UML 1, while highly autonomous and dense operations are described as UML 4 and beyond. Evident in NASA's and the FAA's concepts of operations, is an expectation that some types of operations will transition from human piloted to fully autonomous operations. Artificial Intelligence (AI) techniques are viewed as one way to enable higher levels of autonomy because the operations will need to make safety critical DISTRIBUTION STATEMENT A. Approved for public release. Distribution is unlimited.

show abstract

Design and Testing of an Approach to Automated In-Flight Safety Risk Management for sUAS Operations

Cited by 9 publications

References 19 publications

Design Pitot Tube Cover with Artificial Intelligence (Arduino) Based Warning System on Piper Seneca V Aircraft

Design Pitot Tube Cover with Artificial Intelligence (Arduino) Based Warning System on Piper Seneca V Aircraft

A Systematic Review of Enhancing Aerospace Safety with Augmented Reality

Towards a Standardized Reinforcement Learning Framework for AAM Contingency Management

Contact Info

Product

Resources

About