Engineering topics

Janakiraman, Vijay

Publications and source records attributed to Janakiraman, Vijay.

3 records

NASA NTRS2018

Variables Influencing RNAV STAR Adherence

In this study we investigated how variables in the aviation domain impact adherence levels of aircraft flying area navigation arrivals with optimized profile descents (RNAV OPDs) (RNAV STARs: aRea NAVigation Standard Terminal Arrival Routes). Variable categories were: weather, aircraft, procedure, and traffic. Non-adherence events analyzed were: miss above, miss below, skip before merge, and skip after merge. Miss below and miss above describe when a flight does not comply vertically with a procedure. Skips refer to a flight leaving a procedure, then returning. Findings of this work reveal that vertical events are most impacted by altitude restriction size, steepness of flight paths, and merging routes. Lateral events were impacted by merging flight conflicts, number of speed restrictions, and the flow rate of the arrival traffic. This study helps increase understanding of how the system is functioning and identifies where procedures are not flexible enough to handle the variability in normal operations.major airports, procedure design, and recommendations for future work.

RNAV OPD↗

NASA NTRS2018

Toward Justifiable Trust in Autonomous Systems Incorporating Human Knowledge in Autonomous Systems through Machine Learning

Trust in Autonomous Systems is largely about humans trusting the decisions made by autonomous systems. This trust can be increased through learning from domain experts. In particular, autonomous systems can learn offline from past mission operations before conducting any operations of its own. Additionally, autonomous systems can learn online by obtaining human feedback during operations. We will discuss several classes of machine learning methods and our application of them to autonomous systems. The first class of methods is anomaly detection, which uses operations data to identify examples of anomalous operations. The second class of methods is inverse reinforcement learning, also known as apprenticeship learning, that takes past operations data as input and yields a controller that is able to duplicate the operations described by the data. The third class is active learning, which identifies examples on which the model is most uncertain and requests domain expert feedback.

Oza, Nikunj C.↗

NASA NTRS2018

Using ADOPT Algorithm and Operational Data to Discover Precursors to Aviation Adverse Events

The US National Airspace System (NAS) is making its transition to the NextGen system and assuring safety is one of the top priorities in NextGen. At present, safety is managed reactively (correct after occurrence of an unsafe event). While this strategy works for current operations, it may soon become ineffective for future airspace designs and high density operations. There is a need for proactive management of safety risks by identifying hidden and "unknown" risks and evaluating the impacts on future operations. To this end, NASA Ames has developed data mining algorithms that finds anomalies and precursors (high-risk states) to safety issues in the NAS. In this paper, we describe a recently developed algorithm called ADOPT that analyzes large volumes of data and automatically identifies precursors from real world data. Precursors help in detecting safety risks early so that the operator can mitigate the risk in time. In addition, precursors also help identify causal factors and help predict the safety incident. The ADOPT algorithm scales well to large data sets and to multidimensional time series, reduce analyst time significantly, quantify multiple safety risks giving a holistic view of safety among other benefits. This paper details the algorithm and includes several case studies to demonstrate its application to discover the "known" and "unknown" safety precursors in aviation operation.

aviation safet↗