Monday, August 31, 2015

2015-08-31: Autonomy Incubator Student Exit Presentation - Michael Esswein

On July 30th, the Autonomy Incubator Summer 2015 Aero Scholars delivered their exit presentations documenting and demoing their research results. Michael Esswein, an undergraduate at The University of Buffalo, reported on his work in modeling and simulation.

Michael Esswein presents on his multifaceted summer project

Friday, August 28, 2015

2015-08-28: Autonomy Incubator Hosts Student Artists

A group of young students, winners of the annual NASA LaRC Art Contest, and their families stopped by the Autonomy Incubator today for a tour. Following a Dances with Drones demo (#DancesWithDrones) starring Dr. Loc Tran, in which he demonstrated a UAV navigating around obstacles, the kids lined up for a chance to fly a UAV using Meghan Chandarana's gesture recognition program.

A young girl successfully navigates her UAV through an obstacle course. 
Meghan taught the students how to perform a series of simple hand gestures over a sensor in order to navigate the UAV through an obstacle course of trees. Many of the children, such as the young girl above, excelled at the task and were able to successfully fly the UAV through a path and around the obstacles.

Meghan assists a couple of students in navigating the UAV.
Future AI engineers!
Although not all of our UAV pilots picked up the skill with the same dexterity, everyone was excited to learn about AI and to steer the UAVs through the tree maze. Along with other organizations at NASA Langley, the Autonomy Incubator team is proud to support STEM and to spur careers in science and engineering!

A pilot and his co-pilot.

Thursday, August 27, 2015

2015-08-27: Autonomy Incubator Hosts Two NASA Center Directors, Dr. David Bowles and Christopher Scolese

Yesterday, Langley Autonomy Incubator hosted Congressional Staffers as well as GSFC Director Christopher Scolese who was accompanied by LaRC Center Director Dr. David Bowles.

 Goddard Center Director Christopher Scolese (left) and Langley Center Director Dr. David Bowles (right)
discuss the advancements that the Autonomy Incubator has made on the Mars Flyer while Danette Allen listens in.

Following demonstrations in which our team showed obstacle avoidance and trajectory planning through gesture-based controls, Loc Tran and Jim Neilan presented the AI's applied research in visual odometry integrated onto the Mars Flyer prototype vehicle. As with our other ongoing autonomy-related efforts, the goal with the Mars Flyer is for it to take off, navigate, achieve its mission, and land autonomously...all without external data such as GPS.

During the demonstration, Loc Tran moves the Mars Flyer over an image of the surface of Mars as Jim Neilan explains how data-deprived localization is achieved. The AI team plans to integrate this same on-board hardware and autonomy algorithms on other vehicles such as quadrotors, robots, and maybe even underwater vehicles. During their visit, Center Directors Christopher Scolese and Dr. David Bowles discussed possible applications for this technology across other areas of science, space, and aeronautics.

Wednesday, August 26, 2015

2015-08-26: Autonomy Incubator Student Exit Presentation - Abbey Hartley

On July 6th, the Autonomy Incubator Summer 2015 Student Interns delivered their exit presentations documenting and demoing their research results. Abbey Hartley, a rising senior at Dartmouth University, reported on her experience and products as the social media intern for #LaRCAi.

Abbey Hartley presents "Social Media - Selling America On #Autonomy"

Tuesday, August 25, 2015

2015-08-25: Autonomy Incubator Hosts Steve Jurczyk, AA for NASA STMD

Steve Jurczyk, the Associate Administrator (AA) for NASA Space Technology Mission Directorate (STMD), stopped by Building 1222 for a tour of the Autonomy Incubator (AI).

Meghan enthralls Steve Jurczyk with her presentation on gesture recognition.
After Danette (head of the AI) and Steve explored the potential application of AI technologies in space and aero with center director, Dave Bowles, and other senior leaders at LaRC, our team demonstrated trajectory planning through gesture-based controls, visual odometry and obstacle avoidance.

Loc Tran demonstrates visual odometry. 
"Remember - only YOU can prevent forest fires." - Kyle, obstacle avoidance guru.

Monday, August 24, 2015

2015-08-24: Autonomy Incubator Hosts White House Visitors

Today, the Autonomy Incubator team hosted several White House visitors, Dr. Chris Fall from Office of Science & Technology Policy (OSTP) and Erik Brine from  Office of Management and Budget (OMB). In twenty minutes, we demonstrated natural interaction for trajectory planning through gesture recognition, coordinated trajectories, obstacle avoidance, and visual odometry for data-deprived environments.

Kyle readies himself for the "catwalk" and obstacle avoidance

Meghan demonstrates gesture recognition

Jim explains visual odometry

Loc explains single board computers and global shutter cameras as used on the Mars Flyer

Sunday, August 23, 2015

2015-08-21: Autonomy Incubator Hosts Visitors from NSWCCD Little Creek

Danette Allen, head of the AI, invited colleagues from Naval Surface Warfare Center Carderok Division (NSWCCD) to spend the morning at NASA LaRC to tour facilities and explore potential R&D areas for collaboration. 

The NSWCCD group learns about the LaRC SR-22 UAS Surrogate

Frank Jones points out the potential of our newest flight asset

Trying their hand as pilots in the Cockpit Motion Facility

Scott Belbin talks about Asteroid Rendezvous and Retrieval

Loc Tran speaks about Visual Odometry

2015-08-20: Autonomy Incubator Student Exit Presentation - Alex Hagiopol

On August 6th, the Autonomy Incubator Summer 2015 Student Interns delivered their exit presentations documenting and demoing their research results. Alex Hagiopol, a second year Master's student at Georgia Tech, reported on the application of semi-direct visual odometry (SVO) for navigation in data-deprived environments.

Alex Hagiopol presents "Visual Odometry On The Surface Of Mars"

2015-08-19: Autonomy Incubator Student Exit Presentation - Bilal Mehdi and Javier Puig-Navarro

On August 6th, the Autonomy Incubator Summer 2015 Student Interns delivered their exit presentations documenting and demoing their research results. Bilal Mehdi and Javier Puig-Navarro, PhD candidates at The University of Illinois Urbana-Champaign (UIUC), reported on the progress they've made this summer towards provably correct coordinated trajectories for small and micro UAS.

Javier and Bilal present "Coordinated Trajectories"

2015-08-18: Autonomy Incubator Hosts Aviation Week

Graham Warwick, the Technology Managing Editor for Aviation Week, toured NASA LaRC today and was treated to presentations by Danette Allen, Jim Neilan, Loc Tran, Meghan Chandrana, Anna Trujillo, Ben Kelley, and Kyle McQuarry. As a team, the Autonomy Incubator covered the R&D waterfront for autonomy with demos around object detection and avoidance, coordinated trajectories for heterogeneous UAVs, natural interaction for multi-agent teaming, and visual odometry.

Loc Tran speaks about Machine Learning for Obstacle Avoidance

Jim Neilan explains Visual Odometry

2015-08-17: Autonomy Incubator Student Exit Presentation - Gil Montague

On August 6th, the Autonomy Incubator Summer 2015 Student Interns delivered their exit presentations documenting and demoing their research results. Gil Montague, a rising senior at Baldwin Wallace University, reported on the the AI's motion planning testbed, obstacle detection and avoidance, and a data-centric approach to networked communication via DDS.

Gil Montague presents "Distributed Control of Small UAVs"

2015-08-14: Autonomy Incubator Student Exit Presentation - Nick Woodward

On August 6th, the Autonomy Incubator Summer 2015 Student Interns delivered their exit presentations documenting and demoing their research results. Nick Woodward, a rising senior at Worcester Polytechnic Institute, reported on the application of machine learning to Geo-containment for sUAS.

Nick Woodward presents "Geo-Safety Net for Vehicle Dynamic Control"

2015-08-13: Autonomy Incubator Student Exit Presentation - Josh Eddy

On August 6th, the Autonomy Incubator Summer 2015 Student Interns delivered their exit presentations documenting and demoing their research results. Josh Eddy, a recent graduate of Virginia Tech, reported on the application of Kalman Filtering for Sensor Fusion in the AI's AEON architecture.

Josh Eddy presents on "Sensor Fusion and Position Estimation for Small UAS"

2015-08-12: Autonomy Incubator Student Exit Presentation - Jeremy Lim

On August 6th, the Autonomy Incubator Summer 2015 Student Interns delivered their exit presentations documenting and demoing their research results. Jeremy Lim, a rising junior at Penn State, reported on MICEHAB - Multigenerational Independent Colony for Extra Terrestrial Habitation, Autonomy, and Behavioral Health.

Jeremy Lim presents "MICEHAB"

Sunday, August 16, 2015

2015-08-11: Autonomy Incubator Seminar Series, Adele Luta

Adele Luda presented to the center, toured TES, and walked though the Hangar.
Adele Luta, a research affiliate at MIT's Brain and Cognitive Science Department
was the August speaker in our Monthly AI Seminar Series on autonomy. Her talk, entitled "Selecting and Training the Future Operator" focused around three questions: 

  1. Do we really understand how technology is changing the skills/traits/needs of the future operator/pilot/controller? 
  2. With the myriad of computer and pen-and-paper based measures, why does there still seem to be a gap in advanced cognitive assessment tools related to cognitive readiness?   
  3. How can mobile technology enable instructors to enhance their evaluation skills without cognitively overloading the instructor? 
Audience participation was encouraged lots of lively discussion was peppered throughout Adele's presentation.

Adele Luta supports the defense sector as a cognitive neuroscientist. Previously, she was an astronaut instructor and flight controller at NASA-Johnson Space Flight Center after which she transitioned to cognitive neuroscience after observing operators work in time dependent, highly technical, life critical situations. Adele spent several years as a full time researcher at MIT's Brain and Cognitive Science Department where she currently holds a research affiliate position. Her research interests include strategic cognitive skills and advanced theory of mind.

Monday, August 10, 2015

2015-08-10: All's Quiet on the Autonomy Incubator Front

The Autonomy Incubator Summer 2015 NIFS Interns
(Abbey, Nick, Meghan, Bilal, Alex, Jeremy, Josh, Gil, Javier)

We are down from thirteen to three student interns today so things are much quieter here in the AI this week than last. And, sadly, the AI blog has been left in the hands of its head who will do her best to keep up with the precedent set by our Summer 2015 Social Media Intern, Abbey.

On Friday, we had a going away luncheon (thanks to Carol for the amazing taco bar!) and distributed Autonomy Incubator shirts (check them out in the top pic) for everyone to take back to their universities and wear proudly. Everyone loved the banana on the sleeve!

The team enjoying their going-away luncheon

It's been a great summer and, thankfully, we have another week with Nick and Alex who are busy wrapping up their tasks, cleaning up their code, and documenting their work. Meghan will be with us for three more weeks and will overlap with the Fall 2015 students. Gotta love the continuity!

Friday, August 7, 2015

2015-08-07: Autonomy Incubator Masterpiece Theater Presents: A Farewell To Blogs

Me, at work.

Today, to my complete shock, is my last day as the Autonomy Incubator social media intern. After this, the blog will be in the capable hands of AI head Dr. Danette Allen until the end of August, when I'm happy to announce a new social media intern will take my place for the fall and continue providing the American public with accessible, interesting articles about NASA LaRC's autonomy research. As of this afternoon, I'll be just a regular gal on the street with an above-average knowledge of small UAVs. So, with my last few hours of complete and unchecked power over this small slice of the internet, I'm going to do what I do best: talk about myself.

I'm Abbey Hartley, in case my worst fears are true and no one actually checks the author credits on the blogs I write.  I'm a rising senior at Dartmouth College in New Hampshire, and I'm an English major with a concentration in Creative Writing. My hometown is Lake Wylie, South Carolina, where I live with my family and two very charismatic dogs.  My pizza order is mushroom and jalapeño on thin crust.

When Danette took the massive leap of faith she did to hire me on as a social media intern--a newly invented position this summer--I was intimidated by how unfamiliar the world of the Autonomy Incubator would be for me. So determined was I to make sure that I didn't embarrass myself in front of the engineers, that I did the unthinkable for a humanities major and took Intro to Computer Science for one of my classes during spring term. It was my first time making below a 30 on a final exam. This did not help my nerves.

If I could have known how welcoming everyone in the AI would be, from the PIs to the interns, then I wouldn't have spent a second worrying about being the lone non-STEM person in a robotics lab (and I definitely wouldn't have put my GPA through so much trauma). Every single one of my questions met with a patiently explained answer, no matter how basic, and I am so, so happy to have been a part of this community of brilliant, funny people for ten weeks. Really, I don't know how people work in labs that aren't the AI. We have so much fun here, and we still crank out some of the most kick-ass autonomy research in the field.

The newly-kindled camaraderie between my writing and the tech world is far from over, however. I have loved my job here so much that I've decided to apply for similar positions as I start my career search this year. In even more surprising news, I've discovered that my experience at the AI could bolster my lifelong dream of being an English professor--some English PhD programs would let me do a thesis in "Tech Studies," which would basically entail researching the intersection of technology and literature. How amazing is that? I could teach at a university and be Dr. Hartley, PhD someday, all based on the things I learned about myself and robots this summer.

Thank you for reading my work this summer. To the fall intern taking over soon: you have so many delights ahead of you. And keep my desk warm for me--I'm coming back as soon as I can.

Thursday, August 6, 2015

2015-08-06: Autonomy Incubator Summer Interns Complete Their Summer Missions

Stop all the clocks, cut off the telephone, prevent the dog from barking with a juicy bone—the Autonomy Incubator (AI) interns are done. Tomorrow brings the NASA Internships Fellowships and Scholarships (NIFS) closing ceremony and the promise of a taco bar catered by AI administrative assistant Carol Castle, and after that, they will all go trickling back into the great expanse of America, from Illinois to Pennsylvania to rural New Hampshire, separated by time and space yet connected forever by the invisible threads of collective memory.

Except for Meghan and Nick. They have a while before their ten weeks are up. They're still required to be sad, though.

As we reminisce on the events of the past two months—the things we learned and the things we flew—AI social media intern Abbey Hartley has put together a time-lapse video of the entire summer to help us remember.  She used eight GoPro cameras stationed around Building 1222 to take pictures at thirty-second intervals all day, every day, then manually sifted through over 100 gigabytes of photos to create a highlight reel of our demos and daily routines.  Enjoy it below.

What do you think? Did you see your favorite Autonomy Incubator vehicle/demo/intern in the video? Was there something else we should have included? Leave a comment for us!

Wednesday, August 5, 2015

2105-08-05: Autonomy Incubator Interns Prepare For Exit Presentations

Alex Hagiopol explains why it would be foolish to question SVO's superiority over GPS positioning.

This is usually the time of day when the Autonomy Incubator (AI) social media intern would seat herself before her government-issued blogging laptop and crank out yet another witty, engaging, and informative post about the goings-on here at the AI. Indeed, when you clicked on this article, you were probably expecting to see journalistic lede in this very spot, with a topic sentence and some relevant details about an event or a person of interest. "What happened today, O intern?" you're probably wondering at this very moment. "What delicious blend of lovable hijinks and high-tech wizardry have the folks at the lab served up for us this time?"

Well, dear readers, we have good news, and we have bad news. The bad news is, today did not hold much excitement vis á vis expanding the frontiers of science because over half of the lab was busy readying their exit presentations for Thursday.  The good news is, the exit presentations are going to be incredible.

You like jokes? Josh Eddy has jokes. He just makes them up on the spot like a comedy genius, because he wants to keep you entertained while he teaches you about Kalman filters.

The phrase "down-home country-style homemade GPUs" makes an appearance.
Gil Montague has a fancy PowerPoint with a myriad of illustrations and a ton of interesting knowledge. He's already done a branch presentation for the Flight Systems Safety Branch this week, so he's been prepared to knock this one out of the park since Monday afternoon.

The knowing smirk of a champion.

Jeremy Lim doesn't have his MICEHAB model in place yet, but once hardware moves it over here, he's going to shock and awe everyone with how skilled his robot arm will be at taking care of mice in space.

Jeremy walks the audience through our "Agile" approach before launching into MICEHAB.
And then there's Javier Puig Navarro and Bilal Mehdi: just when you thought their coordinated flight demos could not get any more compelling, they're capping off their summer in the AI by flying a heterogenous fleet of two quadrotors and two micro-UAVs in coordination. We saw a sneak peek of the routine today, and be assured, it's even cooler than it sounds.

Look at them go!

The team might be a little zealous about this demo.

Speaking of flying trajectories, Nick Woodward will present on his geo-containment systems research that we just talked about.  He has a plethora of drawings and flow charts to explain his software much better than we could, and he also has a fresh batch of AI keychains in the printer that he's been passing out to the team. Thanks, Nick!

Nick using some of the aforementioned drawings to illustrate geo-containment.

Of the interns, only Meghan Chandarana will not present tomorrow, because her tenure at the AI ends three weeks from now. Even though she has no obligation to participate, she has been extremely involved in coaching the others on presentation style and good PowerPoint form. We all very much appreciate the time and effort she's invested in the work of others, especially when she has such exciting work to be doing on her own project.

Tuesday, August 4, 2015

2015-08-04: Autonomy Incubator Intern Nick Woodward Designs UAV Geo-Containment Software, Plastic Bananas

Nick, surrounded by recent projects, edits a design for the 3D printer.

The most noticeable thing about Nick Woodward's workspace is not the complex code covering his two desktop screens, nor is it the vivid illustrations adorning his PowerPoint slides as he prepares for his exit presentation on Thursday. It's the bananas. When he's not elbow-deep in unmanned flight safety research (which is most of the time), Nick relaxes by designing and 3D printing tiny plastic props for the Autonomy Incubator's demonstrations. Once they're implemented, the intention is to offer them as souvenirs to high-profile visitors as well. Some offices give out pens with their logo on them; we send people home with bananas and Pac-Man figurines.

NASA's tiniest airplane, banana for scale.

Blinky, with "AUTONOMY INCUBATOR" printed on his head.

Pac-Man, also representing the AI in his own way.

We bet you're REALLY wondering what we're doing with a plastic human heart.

"I sort of inserted myself as the CAD guy," he said, citing a long history of 3D printing experience. "It's a lot of fun."

His adventures in 3D printing are only a casual hobby during his breaks from his real project, however-- his area of research this summer has been autonomous flight safety, and his end result is a piece of software that sets and enforces geographic boundaries for autonomous UAVs during outdoor flight. Think of it like an invisible fence for your dog.

"We have the actual safety net up in the flight area to protect the humans," Nick said. "This project is aimed toward maintaining not only [outdoor] vehicle safety, but the safety of those around the vehicle."

Nick's program divides the geo-containment area into a flight zone, where the UAV is approved to fly, a "soft border" zone, and a "hard border" boundary. If a vehicle strays across the soft border, "The software basically tells the vehicle, 'Hey, you're close to leaving the flight zone, but as long as you don't make a dash for the hard border, we're good,'" Nick explained.  The program also steps in and the UAV's flight trajectory to predict if it's preparing to leave the geo-containment area while it's in the soft border zone.

On the off chance that a vehicle crosses the hard border, two things can happen: The first thing the software will do is command the vehicle to land immediately, since that's one possible safe maneuver. If the land command doesn't work for some reason, then the program can shut off the motors.

Nick is proud of his finished product, but says that working on emergency safety protocols has been an unusual experience for him.

"The weird thing about this project is, this is a piece of software I hope never gets used," he said.

This summer has been Nick's second in the AI; he first joined the team in 2014 when he came on board to help build a "dual hardware-in-the-loop simulator." Since the AI didn't have an in-house flight range last year, building sophisticated simulators was the only way for the team to run tests.

"We would strap the [UAV] components onto a table, feed it false information, and pipe its output back," he said.

Of the incredibly diverse roles he's played in the Incubator, he merely shrugs the challenge off as part of the job.

"I'm a robotics engineer, so I'm supposed to be able to tackle things as they pop up," he said. "Being able to evolve and adapt to the problem at hand is an important part of being an engineer."

Nick and high school intern Nick in one of their friendly debates.

Soon, Nick will depart the AI for Worcester Polytechnic Institute, which is apparently pronounced "WOO-ster," not "Wor-kes-ter." We're just as baffled as you are.

Monday, August 3, 2015

2015-08-03: Autonomy Incubator Tests Project Tango-Equipped UAV

The quadrotor takes the Tango for its first spin around the flight range. 

Corin Sandford, an intern with Autonomy Incubator (AI) member Gary Qualls, who joined us in Building 1222 for the later half of his internship, test flew a custom-built quadrotor carrying Google's Project Tango tablet in our GPS-emulation area today. The Tango tablet, currently only available as a developers kit, is a tablet that uses a combination of IMU (Inertial Measurement Unit), RGB camera, infrared camera, and infrared projector point cloud data to map and navigate through its surroundings. Corin's work explores the potential for using the tablet as a mapping and navigation system for autonomous unmanned vehicles, a problem many of the AI's engineers are also working to to solve—think of PI Loc Tran's work with MSCKF navigation, Alex's SVO research, and the Kalman filter research Josh and Mike have done for Loc and PI Jim Neilan's investigations into sensor fusion.

The tablet clips into a case on the bottom of the UAV.

Corin's project for the summer seems straightforward at first: find out if and how the Tango tablet could be useful to NASA's research into autonomous, GPS-deprived navigation. However, the Tango presents some interesting possibilities and challenges, especially because of the unique way it localizes itself. Instead of finding features in real time and localizing itself as it goes along, for example, the Tango has a 'learning mode" that requires the user to carry or fly it around the environment beforehand, so that it can make a map of the surroundings. Once it's created the map, the tablet uses it as a ground truth for navigation during the mission.

"It localizes against the map you created in learning mode," Corin explained. "It's trying to match the visual odometry to the map... if you find a point where you know where you are, you can stop averaging [sensor data] and start over." Essentially, while it's in learning mode, it records its position in "poses" with x,y, and z coordinates and a rotation quaternion per frame of video, and whenever a pose from its memory matches a pose in real time, it re-localizes itself and starts the algorithm over. By constantly updating the program's point of reference, this method cuts down on drift and allows for more precise positioning.

Corin "flies" the UAV around by hand before the flight test.

Corin finds that while the tablet's methods give it an excellent idea of where it is in space, those same methods create challenges for using it aboard an autonomous vehicle in unknown surroundings. Its dependence on comparisons between its internal map and the real-time environment mean that it cannot detect and avoid moving obstacles; in addition, its infrared projector does not function in daylight, limiting its use in outdoor missions like search-and-rescue.

While he emphasized that the Tango was not built to have some functionalities, like obstacle avoidance—"Just because it sees a wall, it doesn't know not to run into it"—he remained enthusiastic about what the tablet can do.

"Here in the Autonomy Incubator, it could be used for path projection," he said.

Although his project ends this week, Corin has an exciting new life waiting for him outside NASA Langley's gates: he'll be attending CU Boulder to begin a Computer Science PhD in the fall, which will also allow him to work in the university's Autonomous Robotics and Perceptions Group (ARPG) lab.