Engineering topics

Trujillo, Anna

Publications and source records attributed to Trujillo, Anna.

12 records

NASA NTRS2017

Natural Language Based Multimodal Interface for UAV Mission Planning

As the number of viable applications for unmanned aerial vehicle (UAV) systems increases at an exponential rate, interfaces that reduce the reliance on highly skilled engineers and pilots must be developed. Recent work aims to make use of common human communication modalities such as speech and gesture. This paper explores a multimodal natural language interface that uses a combination of speech and gesture input modalities to build complex UAV flight paths by defining trajectory segment primitives. Gesture inputs are used to define the general shape of a segment while speech inputs provide additional geometric information needed to fully characterize a trajectory segment. A user study is conducted in order to evaluate the efficacy of the multimodal interface.

Chandarana, Meghan↗

NASA NTRS2017

'Fly Like This': Natural Language Interface for UAV Mission Planning

With the increasing presence of unmanned aerial vehicles (UAVs) in everyday environments, the user base of these powerful and potentially intelligent machines is expanding beyond exclusively highly trained vehicle operators to include non-expert system users. Scientists seeking to augment costly and often inflexible methods of data collection historically used are turning towards lower cost and reconfigurable UAVs. These new users require more intuitive and natural methods for UAV mission planning. This paper explores two natural language interfaces - gesture and speech - for UAV flight path generation through individual user studies. Subjects who participated in the user studies also used a mouse-based interface for a baseline comparison. Each interface allowed the user to build flight paths from a library of twelve individual trajectory segments. Individual user studies evaluated performance, efficacy, and ease-of-use of each interface using background surveys, subjective questionnaires, and observations on time and correctness. Analysis indicates that natural language interfaces are promising alternatives to traditional interfaces. The user study data collected on the efficacy and potential of each interface will be used to inform future intuitive UAV interface design for non-expert users.

Chandarana, Meghan↗

NASA NTRS2016

Using Multimodal Input for Autonomous Decision Making for Unmanned Systems

Autonomous decision making in the presence of uncertainly is a deeply studied problem space particularly in the area of autonomous systems operations for land, air, sea, and space vehicles. Various techniques ranging from single algorithm solutions to complex ensemble classifier systems have been utilized in a research context in solving mission critical flight decisions. Realized systems on actual autonomous hardware, however, is a difficult systems integration problem, constituting a majority of applied robotics development timelines. The ability to reliably and repeatedly classify objects during a vehicles mission execution is vital for the vehicle to mitigate both static and dynamic environmental concerns such that the mission may be completed successfully and have the vehicle operate and return safely. In this paper, the Autonomy Incubator proposes and discusses an ensemble learning and recognition system planned for our autonomous framework, AEON, in selected domains, which fuse decision criteria, using prior experience on both the individual classifier layer and the ensemble layer to mitigate environmental uncertainty during operation.

Neilan, James H.↗

NASA NTRS2016

A Safe Cooperative Framework for Atmospheric Science Missions with Multiple Heterogeneous UAS using Piecewise Bezier Curves

Autonomous operation of UAS holds promise for greater productivity of atmospheric science missions. However, several challenges need to be overcome before such missions can be made autonomous. This paper presents a framework for safe autonomous operations of multiple vehicles, particularly suited for atmospheric science missions. The framework revolves around the use of piecewise Bezier curves for trajectory representation, which in conjunction with path-following and time-coordination algorithms, allows for safe coordinated operations of multiple vehicles.

Mehdi, S. Bilal↗

NASA NTRS2016

A Natural Interaction Interface for UAVs Using Intuitive Gesture Recognition

The popularity of unmanned aerial vehicles (UAVs) is increasing as technological advancements boost their favorability for a broad range of applications. One application is science data collection. In fields like Earth and atmospheric science, researchers are seeking to use UAVs to augment their current portfolio of platforms and increase their accessibility to geographic areas of interest. By increasing the number of data collection platforms UAVs will significantly improve system robustness and allow for more sophisticated studies. Scientists would like be able to deploy an available fleet of UAVs to fly a desired flight path and collect sensor data without needing to understand the complex low-level controls required to describe and coordinate such a mission. A natural interaction interface for a Ground Control System (GCS) using gesture recognition is developed to allow non-expert users (e.g., scientists) to define a complex flight path for a UAV using intuitive hand gesture inputs from the constructed gesture library. The GCS calculates the combined trajectory on-line, verifies the trajectory with the user, and sends it to the UAV controller to be flown.

Chandarana, Meghan↗

NASA NTRS2015

Operating in "Strange New Worlds" and Measuring Success - Test and Evaluation in Complex Environments

Software tools are being developed by the Autonomy Incubator at NASA's Langley Research Center that will provide an integrated and scalable capability to support research and non-research flight operations across several flight domains, including urban and mixed indoor-outdoor operations. These tools incorporate a full range of data products to support mission planning, approval, flight operations, and post-flight review. The system can support a number of different operational scenarios that can incorporate live and archived data streams for UAS operators, airspace regulators, and other important stakeholders. Example use cases are described that illustrate how the tools will benefit a variety of users in nominal and off-nominal operational scenarios. An overview is presented for the current state of the toolset, including a summary of current demonstrations that have been completed. Details of the final, fully operational capability are also presented, including the interfaces that will be supported to ensure compliance with existing and future airspace operations environments.

Qualls, Garry↗

NASA NTRS2015

Reinforcement Learning with Autonomous Small Unmanned Aerial Vehicles in Cluttered Environments

We present ongoing work in the Autonomy Incubator at NASA Langley Research Center (LaRC) exploring the efficacy of a data set aggregation approach to reinforcement learning for small unmanned aerial vehicle (sUAV) flight in dense and cluttered environments with reactive obstacle avoidance. The goal is to learn an autonomous flight model using training experiences from a human piloting a sUAV around static obstacles. The training approach uses video data from a forward-facing camera that records the human pilot's flight. Various computer vision based features are extracted from the video relating to edge and gradient information. The recorded human-controlled inputs are used to train an autonomous control model that correlates the extracted feature vector to a yaw command. As part of the reinforcement learning approach, the autonomous control model is iteratively updated with feedback from a human agent who corrects undesired model output. This data driven approach to autonomous obstacle avoidance is explored for simulated forest environments furthering autonomous flight under the tree canopy research. This enables flight in previously inaccessible environments which are of interest to NASA researchers in Earth and Atmospheric sciences.

Tran, Loc↗

NASA NTRS2013

Adaptive Controller Adaptation Time and Available Control Authority Effects on Piloting

Adaptive control is considered for highly uncertain, and potentially unpredictable, flight dynamics characteristic of adverse conditions. This experiment looked at how adaptive controller adaptation time to recover nominal aircraft dynamics affects pilots and how pilots want information about available control authority transmitted. Results indicate that an adaptive controller that takes three seconds to adapt helped pilots when looking at lateral and longitudinal errors. The controllability ratings improved with the adaptive controller, again the most for the three seconds adaptation time while workload decreased with the adaptive controller. The effects of the displays showing the percentage amount of available safe flight envelope used in the maneuver were dominated by the adaptation time. With the displays, the altitude error increased, controllability slightly decreased, and mental demand increased. Therefore, the displays did require some of the subjects resources but these negatives may be outweighed by pilots having more situation awareness of their aircraft.

Trujillo, Anna↗

NASA NTRS2008

Using Simulation Speeds to Differentiate Controller Interface Concepts

This study investigated two concepts: (1) whether speeding a human-in-the-loop simulation (or the subject's "world") scales time stress in such a way as to cause primary task performance to reveal workload differences between experimental conditions and (2) whether using natural hand motions to control the attitude of an aircraft makes controlling the aircraft easier and more intuitive. This was accomplished by having pilots and non-pilots make altitude and heading changes using three different control inceptors at three simulation speeds. Results indicate that simulation speed does affect workload and controllability. The bank and pitch angle error was affected by simulation speed but not by a simulation speed by controller type interaction; this may have been due to the relatively easy flying task. Results also indicate that pilots could control the bank and pitch angle of an aircraft about equally as well with the glove as with the sidestick. Non-pilots approached the pilots ability to control the bank and pitch angle of an aircraft using the positional glove - where the hand angle is directly proportional to the commanded aircraft angle. Therefore, (1) changing the simulation speed lends itself to objectively indexing a subject s workload and may also aid in differentiating among interface concepts based upon performance if the task being studied is sufficiently challenging and (2) using natural body movements to mimic the movement of an airplane for attitude control is feasible.

Trujillo, Anna↗

NASA NTRS2002

Glass-Cockpit Pilot Subjective Ratings of Predictive Information, Collocation, and Mission Status Graphics: An Analysis and Summary of the Future Focus of Flight Deck Research Survey

NASA Langley Research Center has been researching ways to improve flight crew decision aiding for systems management. Our current investigation is how to display a wide variety of aircraft parameters in ways that will improve the flight crew's situation awareness. To accomplish this, new means are being explored that will monitor the overall health of a flight and report the current status of the aircraft and forecast impending problems to the pilots. The initial step in this research was to conduct a survey addressing how current glass-cockpit commercial pilots would value a prediction of the status of critical aircraft systems. We also addressed how this new type of data ought to be conveyed and utilized. Therefore, two other items associated with predictive information were also included in the survey. The first addressed the need for system status, alerts and procedures, and system controls to be more logically grouped together, or collocated, on the flight deck. The second idea called for the survey respondents opinions on the functionality of mission status graphics; a display methodology that groups a variety of parameters onto a single display that can instantaneously convey a complete overview of both an aircraft's system and mission health.

Bartolone, Anthony↗

NASA NTRS2002

Vertex Movement for Mission Status Graphics: A Polar-Star Display

Humans are traditionally bad monitors, especially over long periods of time on reliable systems, and they are being called upon to do this more and more as systems become further automated. Because of this, there is a need to find a way to display the monitoring information to the human operator in such a way that he can notice pertinent deviations in a timely manner. One possible solution is to use polar-star displays that will show deviations from normal in a more salient manner. A polar-star display uses a polygon's vertices to report values. An important question arises, though, of how the vertices should move. This experiment investigated two particular issues of how the vertices should move: (1) whether the movement of the vertices should be continuous or discrete and (2) whether the parameters that made up each vertex should always move in one direction regardless of parameter sign or move in both directions indicating parameter sign. The results indicate that relative movement direction is best. Subjects performed better with this movement type and they subjectively preferred it to the absolute movement direction. As for movement type, no strong preferences were shown.

Trujillo, Anna↗

NASA NTRS2000

Rapidly Re-Configurable Flight Simulator Tools for Crew Vehicle Integration Research and Design

While simulation is a valuable research and design tool, the time and difficulty required to create new simulations (or re-use existing simulations) often limits their application. This report describes the design of the software architecture for the Reconfigurable Flight Simulator (RFS), which provides a robust simulation framework that allows the simulator to fulfill multiple research and development goals. The core of the architecture provides the interface standards for simulation components, registers and initializes components, and handles the communication between simulation components. The simulation components are each a pre-compiled library 'plug-in' module. This modularity allows independent development and sharing of individual simulation components. Additional interfaces can be provided through the use of Object Data/Method Extensions (OD/ME). RFS provides a programmable run-time environment for real-time access and manipulation, and has networking capabilities using the High Level Architecture (HLA).

Schutte, Paul C.↗