Unmanned Aerial Systems Health Monitoring Architecture

Dunham, Joel; Johnson, Eric N.

doi:10.1109/aero.2019.8741584

Cited by 4 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research in real-time health assessment of UAS [68] developed a system that provides good, warning, and failure indications of various UAS subsystems, which results in a comprehensive health diagnostic for the UAS. Three known limitations of this system are as follows:…”

Section: Scenario and Test Setupmentioning

confidence: 99%

“…These parameters were chosen to provide a similar balance between each of the first three metrics before comparisons were made between the systems. The final metric is a requirement for running on small UAS, which is previously demonstrated on the baseline system [68] and must be evaluated on the test system. Since the baseline system did not include the concept of safe zones and multiple hypotheses, Table 2 The numerical decision criteria for the UAS Dempster-Shafer network.…”

Section: B Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

Application of Dempster–Shafer Networks to a Real-Time Unmanned Systems Risk Analysis Framework

Dunham

Johnson

Féron

et al. 2021

Journal of Aerospace Information Systems

Self Cite

View full text Add to dashboard Cite

Unmanned Aerial Systems (UASs) are continuing to proliferate rapidly [1]. Quantitative risk assessment for UAS operations, both a-priori and during the operation, are necessary for governing authorities and insurance companies to understand the risks and properly approve operations and assign insurance premiums, respectively. This paper reports the results of the 2018 UAS Safety Symposium held at the Georgia Institute of Technology, which was conducted as part of this research. This symposium was comprised of experts in UAS law, insurance, regulations, operations, and research discussing the direction of the UAS industry and the necessary steps to move the industry forward. Those results motivate the remainder of this research including the novel application of Dempster-Shafer networks using auto-updating transition matrices to the problem of UAS risk analysis and decision-making. This research trains a DS network based on simulated operation data, tests the capabilities of the trained network to make real-time decisions on a small UAS against a baseline system in a representative mission, and explores how this system would extend to the full UAS ecosystem as discussed in the 2018 UAS safety symposium. Conclusions are drawn with respect to the research performed, and additional research tangents are proposed.

show abstract

Section: Scenario and Test Setupmentioning

confidence: 99%

Section: B Evaluation Metricsmentioning

confidence: 99%

Application of Dempster–Shafer Networks to a Real-Time Unmanned Systems Risk Analysis Framework

Dunham

Johnson

Féron

et al. 2021

Journal of Aerospace Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Typically all UAS currently include some form of health monitoring, with the minimum being a battery voltage monitor. Various health monitoring architectures have been tested [56,57], with some of the principle decisions being whether the health monitoring subsystem runs on a companion computer or internally on the autopilot hardware, and the implications thereof. While the companion computer enables the health monitoring code to not impact the flight critical (guidance, control, navigation, path planning, etc.)…”

Section: Health Monitoringmentioning

confidence: 99%

“…The left display, which is part of the Mission Planner [52] display, includes a heads down display that is pilot-centric. In comparison, the right display, which is part of the GUST [39] display, is operator-centric, only alerting the operator to the status of the vehicle while not providing sufficient information for operator-based flight control level of independence from the primary flight hardware, implementing the health monitoring routines on the primary flight computer gives direct access into all the autopilot data, thereby enabling much more detailed monitoring without bandwidth limitations between the primary flight computer and a companion computer [57].…”

Section: Health Monitoringmentioning

confidence: 99%

“…Regardless of the hardware architecture, advances have been made from independently monitoring various indicators (e.g., battery voltage level and GPS position dilution of precision (PDOP)) to cohesive health monitoring systems that combine indicators from multiple subsystems to provide overall decision analysis [56,57]. Furthermore, research has been performed in decision analysis applied to real-time UAS decision-making for applying risk analysis principles to in-flight choices, shifting decisions from what is happening to what will likely happen [58,59].…”

Section: Health Monitoringmentioning

confidence: 99%

See 1 more Smart Citation

Avionics of Aerial Robots

et al. 2021

Self Cite

View full text Add to dashboard Cite

Purpose of Review This work provides an overview of avionic systems, which can be used as an entry point to learn about their architecture and components, and as a guide for studying the recent development of unmanned aerial systems avionics. Recent FindingsThe development trend of avionics for unmanned aerial systems tends toward the one used for a large aircraft both in the structure of the architecture and in design and implementation processes. However, due to the differences in the operational environment, challenges remain in specifying the proper requirements, and proving their safety and security. SummaryThe paper reviews the functionalities and importance of avionic systems, especially in unmanned aerial systems. It also provides the historical background and the future trend of system development in terms of safety, security, and certification for the purpose of integrating these unmanned aerial systems into an urban airspace.

show abstract

Automated mission planning for aerial large‐scale power plant thermal inspection

Romanov,

Gyrichidi,

Volkova

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

Close‐range aerial inspection of large‐scale industrial facilities such as power plants is complex. It is characterized by a few areas suitable for safe landing, many obstacles, complicated radio communication, and so forth. The paper presented a new offline approach for automated mission planning in such conditions. It is based on novel concepts of ‐shaped flight profile and safe altitude map. These concepts reduce the mission planning task to a multiple traveling salesmen problem on a two‐dimensional map, which is solved using rapidly exploring random tree and genetic algorithms. A computational fluid dynamics‐based local turbulence map concept was proposed to avoid turbulence zones during inspection flights. As an advantage, this map can be generated at least 6.8× faster than the known approaches. Our new multicopter flight time prediction model provides an error of less than 10% in most cases and significantly outperforms those implemented in commercial mission planning software. All the proposed solutions were verified during a 2400‐MW power plant inspection. Our algorithms managed to plan to visit all the inspection points in six routes, approximately 15 min long each. This mission set has a comparable overall duration but better safety and even battery usage compared with the routes planned by a qualified operator. Moreover, the designed aerial inspection system provides higher quality images than manually from the ground using a thermal camera with two times higher sensitivity and equipped with more advanced optics. To our knowledge, this research is the first to report the successful implementation of autonomous unmanned aerial vehicle‐based power equipment diagnostics on a large‐scale thermal power plant.

show abstract

Unmanned Aerial Systems Health Monitoring Architecture

Cited by 4 publications

References 5 publications

Application of Dempster–Shafer Networks to a Real-Time Unmanned Systems Risk Analysis Framework

Application of Dempster–Shafer Networks to a Real-Time Unmanned Systems Risk Analysis Framework

Avionics of Aerial Robots

Automated mission planning for aerial large‐scale power plant thermal inspection

Contact Info

Product

Resources

About