Friday, October 30, 2015

2015-10-30: Autonomy Incubator Celebrates Halloween & Welcomes Bubbles

As the Autonomy Incubator celebrates Halloween, we welcome our new Ai mascot and resident trick-or-treat enthusiast. Meet Bubbles, the spider. #MeetOurTeam

video


While Bubbles spends most of her day hanging out in her web inspiring our team's research in autonomy and robotics, in her off hours she indulges in errant Crazyflies.

Introducing Bubbles, our Autonomy Incubator mascot.

On Tuesday, the Autonomy Incubator team will be entering the Langley Chili Cook-off, where Bubbles and her family will be making their NASA debut. Stay tuned with us on social media for more on this exciting partnership.


Twitter: @AutonomyIncub8r
Instagram: @AutonomyIncubator

Wednesday, October 28, 2015

2015-10-28: Autonomy Incubator Demonstrates Package Delivery

Here at the Autonomy Incubator, we're researching ways to safely deliver packages using small unmanned aerial vehicles (UAVs). Our designs include vehicle components to carefully deliver a package, using computer vision to detect and classify objects, obstacle avoidance, and programs such as our "Follow Me" behavior

The commercial applications for this technology are vast, and provide potential solutions to missions dangerous for humans, such as delivering humanitarian aid or fighting forest fires. However, most widely known is the potential this technology holds for future commercial package delivery by companies. In fact, Flirtey, an Australian commercial delivery service that uses UAVs, stopped by the Autonomy Incubator on Monday to learn more about the work our team is currently doing.


As companies, and NASA, look towards the future of package delivery, safety is a prime concern. Here at the Autonomy Incubator, we're solving these concerns by developing programs for obstacle avoidance and navigation in data-deprived environments. Although known paths and locations will likely be present in a majority of the areas that we would be delivering to on Earth, we will require the capacity to navigate without GPS as a back-up if the signal is lost, as well as for exploratory missions in space and on planets where GPS is not available

A mechanical engineer at the Autonomy Incubator, Joe Lemanski, recently designed a mechanism we have used to carry and release a package from a UAV. As said by Dr. Loc Tran, with this mechanism, "we fully employ the use of gravity"; in other words, we're safely dropping off the package on a designated landing spot.

Danette looks on as visitors hold and discuss the drop mechanism developed by Joe Lemanski.

Meanwhile, Dr. Loc Tran and our fall intern Deegan Atha have been working on projects within the realm of computer vision. At present, we are leveraging computer vision as a means to detect obstacles and to classify objects, such as a destination point for a package delivery.


Representatives from Flirtey watch as Ben Kelley demonstrates safe obstacle avoidance with UAVs.

The "Follow Me" behavior, created by our software architect Ben Kelley, is still relatively new. As we move past these early stages of development, we'll be looking into the possibility of using this behavior with a fleet of vehicles. In a manner similar to a paperboy and the basket on his bike that he reaches into for a paper, the small UAVs could go to and from a moving rover to pick up packages and deliver them to their destinations. As the rover moves, the UAV will employ the "Follow Me" behavior to catch up with the rover, pick up another package, deliver the package, and then employ the "Follow Me" behavior again to repeat the cycle. 


Jim Neilan tests the UAV package delivery mechanism with Herbie, our rover.

Tuesday, October 27, 2015

2015-10-27: Autonomy Incubator begins celebration of NASA Langley Centennial

On October 27th, the Autonomy Incubator team gathered with about 1,000 employees, retirees and family members for an aerial photo outside the hangar at NASA Langley Research Center. This centennial photo marks the beginning of our celebrations commemorating 100 years of research at NASA Langley. 


Credits: NASA/Sandie Gibbs

In 1917, the U.S. government established Langley Research Center, marking it as the oldest of NASA's field centers. Just fourteen years after the success of the Wright Flyer, Langley focused on furthering research in aeronautics and scientific discovery.  As the center continues with centennial festivities, culminating in events on July 17, 2017, we reflect on our center history and look towards another 100 years of cutting edge developments. 


This quote from Neil Armstrong lies outside the front entrance to the Autonomy Incubator. 

Here at the Autonomy Incubator, we're doing the same. Next week marks one year that we've been in our building, the old Reid Center, and over the course of the upcoming year we will be transition in name to the Langley Autonomy and Robotics Center (AR) as NASA extends the scope and duration of our research. As autonomy becomes increasingly vital to the success of science, space and aeronautics missions, Langley is integrating our work with a variety of projects. NASA Langley recently announced that our Autonomy Incubator team will be working on developing "a flying armada of 100 unmanned aerial vehicles", to be exhibited at the centennial event on July 17, 2017.

To stay updated on our progress with the flying armada, and our continuing work in package delivery, computer vision, obstacle avoidance, and localization, follow us on social media.
Twitter: @AutonomyIncub8r
Instagram: @AutonomyIncubator

The Autonomy Incubator team at the centennial photo.

Monday, October 26, 2015

2015-10-26: Autonomy Incubator Demonstrates "Follow Me" Behavior

Recently, the Autonomy Incubator has been demonstrating the "Follow Me" behavior designed by our software architect Ben Kelley. 



The behavior begins with our motion capture system's xyz position data. The interface then converts this data into our room coordinates, and these are in turn converted to relative latitude and longitude (World Coordinates). "Follow Me" is the behavior itself, which occurs when the UAV receives message of the rover's position and alters its current waypoint (destination) to reflect the location one meter above the rover.

Jim Neilan and James Rosenthal set up our rover and "Green Machine" UAV.

The Follow Me behavior runs at 1 Hz, which means that the UAV updates it's waypoint to reflect the current location of the rover every second. In the video below, we see our "Green Machine" UAV following the rover in real time.



2015-10-20: Autonomy Incubator Celebrates Anna Trujillo's 25 Years of Service

For 25 years, Anna Trujillo has been an integral part of the NASA Langley Research Center. As our resident human factors specialist at the Autonomy Incubator, Anna develops operator interfaces and leads our research on the interaction between machine and human.


For 25 years, Anna Trujillo has been an integral part of the NASA Langley Research Center.

Anna began her engineering career as an undergraduate at MIT, where her love of science led her to major in aerospace engineering. The Three Mile Island accident in 1979 inspired Anna to pursue a career to improve the interaction and efficiency between humans and technology, and so after she completed her undergraduate degree, Anna studied human factors at the University of Michigan. Human factors was a relatively new field, and it was initially classified under industrial engineering. Anna also took classes in psychology, and focused on aeronautics with a subspecialty in controls.

Directly out of college, Anna accepted a job offer from NASA Langley Research Center as a human factors engineer. Her first project was a high speed civil transport, the HSCT. A commercial version of supersonic transport (SST), the HSCT was NASA's vision of a supersonic passenger jet that would be able to travel distances in less than half the time of a modern subsonic airplane. 


For about 10 years, Anna worked with Aviation Safety, and completed important research for cockpit safety regarding warning systems and information displays. "I always liked airplanes and the piloting side of what they were doing", she says; "what are they doing, and can what they're doing be improved?" One of Anna's many research papers focuses on her work with displays and alerting systems. What information does the pilot really need? She looked into new ways of showing information, so that someone could quickly understand the issue that was being indicated by the display. The idea, she says, is to give the pilot more time in the event of failure. 

While working on Aviation Safety, Anna also helped with The Unmanned Aircraft Systems Integration in the National Airspace System project, which is based out of the NASA Armstrong Flight Research Center. The project focuses on improving unmanned aircraft systems to safety integrate them into daily life, and during this time Anna became interested in the application of small UAVs as they "change the way you look at piloting a vehicle".

This led Anna to the Autonomy Incubator, where she currently lends her expertise in human factors, controls, and developing effective pilot and operator interfaces. Our team celebrates Anna's impressive 25 years of work, and her ongoing commitment to NASA and the American public.

You can check out Anna's research papers below.
     -A Centralized Display for Mission Monitoring
     -Experience and Grouping Effects when handling Non-Normal Situations
     -Predicting Information: Status or Alert Information? 
     -Using Simulation Speeds to Differentiate Controller Interface Concepts

Wednesday, October 21, 2015

2015-10-21: Autonomy Incubator Hosts Booth at the Hampton Roads Transportation Expo

Carol Castle and Rebecca Goodpasture represented NASA LaRC Autonomy at the Hampton Roads Transportation Expo. Groups across the transportation, infrastructure and construction industries hosted booths and spoke with educators and high school students about career opportunities.

Carol Castle and Rebecca Goodpasture at the NASA LaRC Autonomy Incubator booth.

Along with our representatives from the Autonomy Incubator team, Mike Logan of the Small Unmanned Aerial Vehicle (SUAVE) Lab fielded questions pertaining to mechanical engineering and UAV projects. Mike brought two UAVs that were designed at NASA Langley, as well as a virtual reality headset to demonstrate the "first person" flying experience of UAVs with attached cameras. Most of the kids in attendance expressed an interest in learning to design and develop similar vehicles.

Many students that we talked to were surprised at the wide array of research that is currently underway at NASA Langley, and we touched upon current projects involving air quality and climate change, the development of Lunar Habitatsthe work our team and the SUAVE Lab are doing with autonomy and UAVs, and so on. Correspondingly, there is a range of educational backgrounds and skills that are needed for the overall success of the center as well as on each project. We talked to students interested in chemistry, medicine, engineering, computer vision, psychology, social media, business, atmospheric science, and more.

Students interested in internship opportunities at Langley should check out the NASA student portal (https://intern.nasa.gov), which offers opportunities for current students in high school, college, as well as recent college graduates. Educators that would like to schedule a visit to their class from a NASA Langley representative can do so through our Langley Research Center Speakers Bureau (https://www.nasa.gov/centers/langley/news/speakers.html).

Monday, October 19, 2015

2015-10-08: Autonomy Incubator Team Observes ONR Flight Test

The Autonomy Incubator team traveled to Flying Circus Airfield in Bealeton, VA to observe a day of flight testing for Autonomous Aerial Cargo/Utility System (AACUS).


AACUS is an Innovative Naval Prototype (INP) program sponsored by the Office of Naval Research (ONR) that explores advanced autonomous capabilities for reliable resupply/retrograde and, in the long term, casualty evacuation by an unmanned air vehicle under adverse conditions. AACUS consists of software and sensors that can be applied to a variety of rotary wing aircraft, and will provide the U.S. Marine Corps with the ability to rapidly support forces on the front lines, as an alternative to convoys, manned aircraft or air drops in all weather and possibly hostile conditions, with minimal training required by the requestor.

Wednesday, October 14, 2015

2015-10-06: Autonomy Incubator Welcomes Small Businesses

On October 6th, the Autonomy Incubator welcomed a group of small businesses from southern Virginia. The tour was hosted by the Office of Small Business Programs, which provides small businesses an opportunity to participate in NASA contracts in space exploration, scientific discovery, and aeronautics research.

Representatives from small businesses arrives at the Autonomy Incubator.

The Autonomy Incubator team presented the usual demonstrations, as we highlighted the various applications of autonomous technology. After Ben Kelley showcased our work with UAV obstacle avoidance, which is integral to unmanned package delivery, Jim Neilan discussed his research on data-deprived localization, and the importance it holds to safe navigation on Earth and planetary exploration on Mars. These demonstrations were particularly applicable to the representatives from businesses that are (like us!) involved with autonomy and robotics.

Ben Kelley demonstrates autonomous UAV obstacle avoidance. In the above image,
he mimics a pedestrian on a cell phone. Without any action on his part, the UAV
detects him as an obstacle and maintains a safe distance.

Jim Neilan describes the application of autonomous
capabilities to aircraft headed for Mars. 

It was a pleasure to provide a tour for these local small businesses, and we look forward to future interaction. Thank you for visiting the Autonomy Incubator!


Shielded by a protective barrier, Kyle McQuarry sets up the program that launches the UAVs in flight.

Thursday, October 1, 2015

2015-09-28: Autonomy Incubator Seminar Series, Simon Haykin

Once a month, the Autonomy Incubator invites a speaker from the field of autonomy to share their expertise. Last week, the distinguished guest of our seminar was Dr. Simon Haykin of McMaster University. 


Dr. Simon Haykin
Titled “Risk Control in the Cognitive Dynamic System”, Dr. Haykin’s presentation touched on his efforts to link engineering with cognitive science for the benefit of autonomously intelligent machines. He began by discussing the communication problems in linking the two disciplines, an issue our AI human factors engineer, Anna Trujillo, often touches on. 

The lecture then focused primarily on the concept of controlling risk and mimicking a human's cognitive processing. How do we strengthen and improve an autonomous system? Dr. Haykin proposes the following: supply the system with cognition, bring in control and decision, and ultimately the machine can manage both uncertainty and risk.

Evaluating and overcoming risk is the most difficult cognitive function for a machine to mimic. It requires a similar structure to the feedback channels in humans, as the internal network must process how to act based on observation and evaluation of the environment. The ability of a machine to observe and evaluate thus become integral, to which Dr. Haykin suggests a machine's working memory. Split into two libraries of potential action, one library holds actions that have been taught, while the other holds past experiences. In the face of uncertainty, the latter of the two libraries is more reliable and closer to the world, as the machine can pull on it's experiences in a situation rather than a learned action for the given circumstance.

At the Autonomy Incubator, we design autonomous systems that have the self-contained ability to execute a mission without direct human involvement, and so much of our work falls in accordance with this concept. Similar to Dr. Haykin's ideal system in which the machine recognizes the correct cognitive action to be performed within the environment, our computer vision engineer Dr. Loc Tran is researching machine learning to provide path training and autonomous obstacle avoidance (tree-dodging). 

Thanks again to Dr. Haykin for coming to NASA LaRC!


The Autonomy Incubator team with Dr. Simon Haykin.