Results for “Unmanned Aerial” — Page 48

NASA NTRSDate not supplied

What Went Wrong: A Survey of Wildfire UAS Mishaps through Named Entity Recognition

Increasingly, unmanned aircraft systems (UAS) are being applied to wildfire incidents for tasks such as mapping, aerial ignition, and delivery. As a result, aviation incident reporting systems for wildfires are beginning to accumulate data related to UAS mishaps in wildfire response. In this research, we apply state-of-the-art natural language processing (NLP) techniques to develop a custom Named Entity Recognition (NER) model which extracts entities relevant to safety analysts. The custom NER model is built by fine-tuning an existing Bidirectional Encoder Representations from Transformers (BERT) model, resulting in a generalizable NER model that can extract engineering relevant entities including failure modes, causes, effects, control processes, and recommendations from failure-relevant text. This model performs passably, with a weighted average f1 score of 0.33 across entity types, indicating more labeled training data is needed. Extracted entities are used to form a Failure Modes and Effects Analysis (FMEA)-style survey of wildfire UAS mishaps reported using the SAFECOM system. Similar mishaps are manually clustered and reported as single rows within an FMEA. Foreach cluster, we compute frequency, severity, and overall riskin accordance with FAA standards. This methodology can beapplied as part of a broader safety management system totrack trends in mishaps (e.g., likelihood, severity) and discoverknowledge (e.g., causes, effects) that can be utilized to improvesafety outcomes and system performance.

Machine Learning↗

NASA NTRSDate not supplied

What Went Wrong: A Survey of Wildfire UAS Mishaps through Named Entity Recognition

Increasingly, unmanned aircraft systems (UAS) are being applied to wildfire incidents for tasks such as mapping, aerial ignition, and delivery. As a result, incident reporting systems for wildfires are beginning to accumulate data related to UAS mishaps in wildfire response. In this research, we apply state-of-the-art natural language processing (NLP) techniques to develop a custom Named Entity Recognition (NER) model which extracts a Failure Modes and Effects Analysis (FMEA)-style survey of wildfire UAS mishaps reported in SAFECOM. The custom NER model is built by fine-tuning an existing (BERT) model, resulting in a generalizable NER model that can extract engineering relevant entities including failure modes, causes, effects, control processes, and recommendations from any failure-relevant text. Similar mishaps are clustered and reported as single rows within the FMEA. For each cluster, frequency, severity, and overall risk are computed. The methodology can be applied as part of a broader safety management system to track trends in mishaps and discover knowledge that can be utilized to improve safety outcomes and system performance.

Machine Learning↗

NASA NTRSDate not supplied

Immutable Secure Data Exchange and Storage for Urban Air Mobility Environments

The Urban Air Mobility (UAM) environment is derived from the Unmanned Traffic Management (UTM) concept of operations. Within the environment, UAM operators work independently to manage aerial vehicles in the urban environment. Providers of Services (PSU), UAM operators, and Supplemental Data Service Providers provide services to support flight operations within the UAM environment. The intent of this work is to leverage a permissioned blockchain approach, to, simulate secure data exchange and storage for UAM environments. Blockchain technologies can be used for identity management of vehicles, people, and systems.

Blockchain↗

NASA NTRSDate not supplied

Evolving Role of Aircraft and Airspace Operations for Aerial Fire Mitigation

Various sizes and types of aircraft are envisioned to play a critical role in fighting fires. Multiple aircraft, including drones, operating simultaneously to fight fires requires coordination to maintain effectiveness as well as safety. Presently, firefighting is limited to day time, high visibility, and low wind conditions. It is also impacted if unmanned aircraft system operates in the area or nearby. NASA is exploring opportunities where a variety of aircraft and their coordinated airspace management would improve the effectiveness of aerial firefighting. Dr. Kopardekar will discuss future aircraft requirements, approach for coordinated firefighting as well as a path towards improving effectiveness.

Aerial Fire Mitigation↗

NASA NTRSDate not supplied

Digital Flight: Enabling the Era of Scalable Mobility in the National Airspace System

In the 21st Century, new aviation markets, vehicle types, and technologies are fast emerging, inspiring new operational concepts for the National Airspace System such as Unmanned Aircraft Systems Traffic Management and Urban Air Mobility. These novel operations envision a dramatic increase in aerial mobility, or the ability to navigate freely through the airspace with unprecedented access and operational flexibility. Implementing these concepts presents a major challenge to the existing operational modes of Visual Flight Rules (VFR) and Instrument Flight Rules (IFR), developed under the limitations of early 20th Century technology and procedures to ensure safe navigation and separation from traffic. To meet this challenge and to support the needs of operators in the 21st Century and beyond, this paper proposes that VFR and IFR be augmented by new flight rules – Digital Flight Rules (DFR) – that leverage modern and emerging technologies and are not bound by restrictions borne of the state of technology 75-100 years ago. The objective of DFR is to provide safe and unfettered access to the airspace to all participating vehicle operators under all visibility conditions without incurring the limitations in operational flexibility inherent to IFR and even VFR. Advancements in communications, navigation, surveillance, aircraft connectivity, information access, automation technology, and supporting ground infrastructure provide the opportunity for the vehicle operator to engage at an unprecedented level in managing their flights regardless of flight visibility. Under DFR, these advancements enable the vehicle operator to assume full responsibility for traffic separation and therefore full trajectory management authority in all visibility conditions and airspace regions. The changes in roles and responsibilities are expected to enable greater airspace access and operational flexibility than afforded by IFR and VFR, thus enabling the emergence of new operations and a new era of advanced aerial mobility.

Mobility↗

NASA NTRSDate not supplied

NASA’s Secured Airspace for Urban Air Mobility (UAM)

The Urban Air Mobility (UAM) architecture is leveraged from the Unmanned Traffic Management (UTM) concept of operations. Within the UAM environment, UAM operators work collaboratively to manage aerial vehicles in the urban environment. Providers of Services for UAM (PSU), UAM operators, and Supplemental Data Service Providers (SDSP) provide services to support flight operations within that environment. As a recognized need, various views of UAM flight information are provided to the public and public safety entities. To accomplish this, among other goals, the Federal Aviation Administration (FAA) can coordinate flight information between the FAA controlled National Airspace System (NAS) and the UAM environments through the FAA-Industry Data Exchange Protocol (FIDXP). This concept of UAM proposes to develop short-range, point-to-point transportation systems in metropolitan areas using vertical take-off and landing (VTOL) or short take-off and landing (STOL) aircraft to overcome increasing surface congestion. To garner the support of UAM and to realize its potential, an assurance of cybersecurity is critical for public acceptance. Understanding the various components communicating with one-another cybersecurity, like in other industries, has come to the forefront highlighting the need to protect these networks and systems from cyberattacks. With the planned growth and reach of UAM systems, it’s clear that the associated data exchange and service interactions will be at risk due to numerous types of cybersecurity attacks. Consequently, as these threats evolve, the UAM cybersecurity capabilities must adapt to these changes as well. While learning is always the goal, the overall intent of this workshop is to make recommendations on the following: (1) how future UAM environments can be protected against cyber-attacks, and (2) what mechanisms should be put in place to detect attacks against UAM environments.

UAM↗

NASA NTRSDate not supplied

Urban Air Mobility Community Noise Test Planning

The term “Advanced Air Mobility” has been adopted by NASA to describe safe, sustainable, affordable, and accessible aviation for transformational local and intraregional missions. By this definition, Advanced Air Mobility includes both “rural” and “urban” applications including cargo and passenger transport missions, and other aerial missions (e.g., infrastructure inspection). There will be a range of aircraft types performing such missions, including small and medium Unmanned Aircraft Systems (UAS), electric Conventional Takeoff and Landing (eCTOL) aircraft, and electric Vertical Takeoff and Landing (eVTOL) aircraft. Urban Air Mobility (UAM) is a challenging use case for transporting cargo and passengers in an urban environment and is a new opportunity for aviation that could revolutionize the transportation system. The National Aeronautics and Space Administration and the Noise Division of the Federal Aviation Administration Office of Environment and Energy have initiated discussions for planning UAM community noise test(s) at the end of this decade. This presentation discusses the test goals, candidate test objectives, and some of activities needed in preparation for the test(s). It also draws distinctions between the type of study envisioned (observational vs. staged), and between it and recent and planned studies on large fixed-wing transports and commercial supersonic transports.

urban air mobility↗

NASA NTRS2022

Applicability of Digital Flight to the Operations of Self-Piloted Unmanned Aircraft Systems in the National Airspace System

Unmanned Aircraft Systems (UAS) hold great promise for a new era of specialized missions, including personal air transportation, cargo flight operations, aerial surveys, inspections, firefighting and more. The anticipated market growth is significant. To unlock its scalability and incumbent benefits requires a human to oversee multiple flights simultaneously, focusing on multi-vehicle mission management and relinquishing to autonomous systems their active role in controlling the aircrafts’ flight paths. Key to the realization of these scalability benefits is minimally-encumbered access to the National Airspace System (NAS), which poses some unique challenges for self-piloted UAS aircraft operations. These include the requirement for compatibility with existing airspace structures and operations including Visual Flight Rules (VFR) and Instrument Flight Rules (IFR), neither of which were developed to accommodate the unique needs and capabilities of UAS. This paper explores the applicability of Digital Flight to the operations of self-piloted UAS. As proposed by NASA, Digital Flight is a flight operations capability, enabled by a set of cooperative procedures and digital technologies, in which flight operators ensure flight-path safety through automated separation and flight path management in lieu of visual procedures and Air Traffic Control separation services. Flights operating under potentially-forthcoming rules of Digital Flight employ advanced automation technologies, information sharing, connectivity to operational data, and cooperative behaviors through distributed decision-making to maintain safety and achieve mission objectives. Designed for integration with VFR and IFR operations in shared NAS airspace, potentially as a third set of flight rules, Digital Flight may provide the mechanism for UAS operators – and all aircraft operators – to scale and diversify their operations beyond what is achievable under current regulations.

DFR↗

NASA NTRSDate not supplied

Drone Applications for Wildfires and Other Emergency Situations

Potential Solutions to Wildfires This project is looking at multiple aspects of the use of UAV’s during wildfire season. This project identifies multiple solutions to communication problems, early action response, and innovative tactics to fight wildfires during the dark hours of the second shift. This project will identify the features and innovations needed to create a second shift that can more effectively fight wildland fires at night. In addition, this project will look to find which satellite systems work best for detection of wildfires, with a special focus on remote locations with more rural communities. There will also be a focus on ways to improve current UAVs and sensors for aerial fire surveillance as well as the understanding on how to establish a safe airspace for these UAVs during wildfires. More specifically, unmanned ariel vehicles (UAV) or drones can be used during natural disasters and other situations to help first responders be a more efficient team, ultimately saving hundreds of more lives. Depending on the situation, drones can be equipped with many different accessories, each with their own advantages. When it comes to operating a drone, communication between the first responder, dispatcher, and the person flying the drone is very important when exchanging useful information. A focus on existing systems, and what changes could be made to create more novel systems will also be shown. Moreover, wildfires not only pose a hazard to human safety and a dent on communication methods, but it also has detrimental effects on the environment. Specifically, the use of common fire retardants have dangerous health effects on human health and the environment as a whole. Therefore, this project will also explore the use of alternative eco-friendly fire retardants and recent innovations to the use of sustainable retardants.

Drones↗

NASA NTRS2014

Intelligent UAS Sense-and-Avoid Utilizing Global Constraints

Sense-and-avoid (SAA) is a critical research topic for enabling the operation of Unmanned Aircraft Systems (UAS) in civilian airspace. SAA involves two planning related problems: 1) plan-recognition to predict the future trajectory of nearby aircraft, and 2) path planning to avoid conflicts with nearby aircraft that pose a threat. We have designed and built components of a novel intelligent sense-and-avoid (iSAA) reasoning framework that takes into account information about aircraft type, transponder code, communications, local routes, airports, airspace, terrain, and weather to more accurately predict near- and medium-term trajectories of nearby aircraft. By using this additional information both the on-board control software and the ground-based UAS operator can make more informed, intelligent decisions to effectively predict and avoid conflicts and maintain separation. While this capability benefits all categories of UASs operating under both Instrument Flight Rules (IFR) and Visual Flight Rules (VFR), it is absolutely essential for allowing smaller UASs to operate VFR at low altitude in uncontrolled airspace for operations such as survey work, wildlife tracking, aerial photography, utilities inspection, crop dusting, and package delivery.

unmanned aircraft systems↗

NASA NTRS2022

Using Trajectory Smoothness Metrics to Identify Drones in Radar Track Data

The identification of unmanned aircraft systems (UAS) using trajectory data is considered. Specifically, a number of smoothness metrics are proposed, which can be used to distinguish UAS from other aerial objects even when they are engaged in accelerative maneuvers (non-constant-velocity flight). The metrics are evaluated on a data set from a UAS sense-and-avoid field test, which contains track data of aerial objects recorded by a vehicle-board radar system during a flight test. The metrics are found to effectively differentiate UAS from other objects such as birds for this data set. In addition, an initial statistical performance analysis of one of the smoothness metrics is undertaken, using 15 data sets deriving from multiple flight tests. The smoothness metric is shown to identify the target UAS with 95% accuracy (95% true positive rate), while achieving a false positive rate of less than 9%.

Sandip Roy↗

NASA NTRSDate not supplied

Developing an Unmanned Aircraft System Pilot (UASP-kit) for Wildland Fire UAS Operators

The use of unmanned aircraft systems (UAS) to support disaster management is becoming more widespread. Uninhibited by many of the operational constraints imposed on crewed aircraft, UAS have the potential to augment the aerial response in a number of ways, including supporting situation awareness, thereby accelerating disaster management efforts. The intent of the Scalable Traffic management for Emergency Response Operations (STEReO) activity is to build an ecosystem that will allow small UAS (sUAS) operations to fly safely in the airspace during disaster management events. The first step toward this goal is to develop a small, single-user tool (the UASP-kit) that will enhance an sUAS pilot’s situation awareness of the airspace. User needs for the functions and features of this tool were collected during a walkthrough over multiple days with subject matter experts from the US Forest Service. A prototype of the UASP-kit was then taken on an extended demonstration to multiple users, who were able to interact with it. User feedback was largely positive and users discussed the information they needed to support situation awareness in context. The demonstration also highlighted features that were unintuitive to use, and functions that need to be modified to make the kit more user-friendly and robust.

STEReO↗

NASA NTRSDate not supplied

Developing an Unmanned Aircraft System Pilot Kit (UASP-kit) for Wildland Fire UAS Operators

The use of unmanned aircraft systems (UAS) to support disaster management is becoming more widespread. Uninhibited by many of the operational constraints imposed on crewed aircraft, UAS have the potential to augment the aerial response in a number of ways, including supporting situation awareness, thereby accelerating disaster management efforts. The intent of the Scalable Traffic management for Emergency Response Operations (STEReO) activity is to build an ecosystem that will allow small UAS (sUAS) operations to fly safely in the airspace during disaster management events. The first step toward this goal is to develop a small, single-user tool (the UASP-kit) that will enhance an sUAS pilot’s situation awareness of the airspace. User needs for the functions and features of this tool were collected during a walkthrough over multiple days with subject matter experts from the US Forest Service. A prototype of the UASP-kit was then taken on an extended demonstration to multiple users, who were able to interact with it. User feedback was largely positive and users discussed the information they needed to support situation awareness in context. The demonstration also highlighted features that were unintuitive to use, and functions that need to be modified to make the kit more user-friendly and robust.

STEReO↗

NASA NTRSDate not supplied

Advanced Capabilities for Emergency Response Operations (ACERO)

The use of unmanned aircraft systems (UAS) to support disaster management is becoming more widespread. Uninhibited by many of the operational constraints imposed on crewed aircraft, UAS have the potential to augment the aerial response in a number of ways, including supporting situation awareness, thereby accelerating disaster management efforts. The intent of the Scalable Traffic management for Emergency Response Operations (STEReO) activity is to build an ecosystem that will allow small UAS (sUAS) operations to fly safely in the airspace during disaster management events. The first step toward this goal was to develop a small, single-user tool (the UASP-kit) that will enhance an sUAS pilot’s situation awareness of the airspace. In a subsequent project (Advanced Capabilities for Emergency Response Operations (ACERO)) the UASP-kit will be expanded and built upon to develop and airspace management tool.

STEReO↗

NASA NTRS2015

Enabling UAS Research at the NASA EAV Laboratory

The Exploration Aerial Vehicles (EAV) Laboratory at NASA Ames Research Center leads research into intelligent autonomy and advanced control systems, bridging the gap between simulation and full-scale technology through flight test experimentation on unmanned sub-scale test vehicles.

UTM↗

NASA NTRS2021

Aerial Data Acquisition Platform for Firefront Monitoring

Over the past century, wildfires have grown in their destructive tendencies, and have become a threat to civilian lives, infrastructure, and emergency officials. The 2021 NASA Academy at Langley Research Center was tasked with utilizing NASA technology to increase situational awareness and communication amongst both incident officials and the public. With this mission in mind, the Data Acquisition sub-team chose to develop an outline for a small unmanned aircraft system (UAS) package including required specifications, a payload layout, and mission planning. The proposed system would be capable of mapping firelines at a speed of about 9.8 m/s for periods of up to 3.6 hours. The system would also be able to gather near real time data at a lower cost than currently utilized systems.

Firefront monitoring↗

NASA NTRSDate not supplied

Aerial Vehicle Routing and Scheduling for UAS Traffic Management: A Hybrid Monte Carlo Tree Search Approach

We present the Multi-Route Weighted Package Delivery Problem (MRWPDP) and a scalable solution methodology as a major step towards enabling an airspace deconfliction service for drone delivery operations. The problem is motivated by Strategic deconfliction under the FAA’s “Unmanned Aircraft Systems Traffic Management” Concept of Operations. MRWPDP falls under a class of vehicle routing and scheduling problems, and as such is NP-Hard. In MRWPDP, a graph network is given which consists of depots, drop-off sites, and multiple routes connecting the two. In addition, routes are weighted by the associated ground risk and total travel distance for package delivery. The goal is to optimally schedule the departure time and assign routes to a known set of vehicles at the depot. We propose a heuristic solution to the problem by borrowing techniques from Mixed Integer Linear Programming (MILP), Constraint Programming, and Monte Carlo Tree Search (MCTS). The resulting hybrid framework is MCTS with Bound-and-Prune (BP) and rapid simulated updates (U), or MCTS-BP-U. This approach is able to quickly provide a feasible solution for MRWPDP, even for large problem instances up to 1000 vehicles. We provide a MILP formulation of MRWPDP and compare its performance against MCTS-BP-U in terms of solution quality. An agent-based model simulation is conducted as a final step to validate the efficacy of our approach.

air traffic scheduling↗

NASA NTRSDate not supplied

Aerial Vehicle Routing and Scheduling for UAS Traffic Management: A Hybrid Monte Carlo Tree Search Approach

We present the Multi-Route Weighted Package Delivery Problem (MRWPDP) and a scalable solution methodology as a major step towards enabling an airspace deconfliction service for drone delivery operations. The problem is motivated by Strategic deconfliction under the FAA’s “Unmanned Aircraft Systems Traffic Management” Concept of Operations. MRWPDP falls under a class of vehicle routing and scheduling problems, and as such is NP-Hard. In MRWPDP, a graph network is given which consists of depots, drop-off sites, and multiple routes connecting the two. In addition, routes are weighted by the associated ground risk and total travel distance for package delivery. The goal is to optimally schedule the departure time and assign routes to a known set of vehicles at the depot. We propose a heuristic solution to the problem by borrowing techniques from Mixed Integer Linear Programming (MILP), Constraint Programming, and Monte Carlo Tree Search (MCTS). The resulting hybrid framework is MCTS with Bound-and-Prune (BP) and rapid simulated updates (U), or MCTS-BP-U. This approach is able to quickly provide a feasible solution for MRWPDP, even for large problem instances up to 1000 vehicles. We provide a MILP formulation of MRWPDP and compare its performance against MCTS-BP-U in terms of solution quality. An agent-based model simulation is conducted as a final step to validate the efficacy of our approach.

air traffic scheduling↗