Friday, August 17, 2018

2018-08-17: New ATTRACTOR Project Continues NASA Tradition of Latin Mottos

Introducing: the new and exciting ATTRACTOR project, brought to you by the Autonomy Incubator's very own Social Media Intern, Payton Heyman, and linguistics expert, Erica Meszaros!

The ATTRACTOR (Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability) project's mission is to work toward both human trust in autonomous systems and creating autonomous systems worthy of trust through explainable AI (XAI).  The motto chosen to represent this mission is docendo discimus, a Latin aphorism, which translates to "by teaching, we learn."  This proverb is often attributed to Seneca's seventh letter to Lucilius; however, throughout time it has been a frequently used motto for institutions around the world, gracing the logos of Central Washington University, the University of Chichester in England, Novosibirsk State Technical University in Russia, and more!  So how did it end up a part of the logo for the ATTRACTOR project?

Dr. Natalia Alexandrov, a mathematician in the Aeronautics Systems Analysis Branch at NASA Langley and Co-Principal Investigator for ATTRACTOR, was the person who chose it.  "It's a perfect fit for the machine learning component of ATTRACTOR," she said.  "As we 'teach' the machine, via, say, active learning methods, we 'learn' about the gaps in problem formulation, the models, and algorithms.  Conversely, the machine 'learns' from data and 'teaches' us what it needs to be a better predictor."

Between our curiosity around the Latin motto, both Erica and I found ourselves diving deep into the depths of a NASA tradition and discovered a long and intricate history of using them.  The badge for the fated Apollo 13 mission bears the word ex luna, scientia, explaining the scientific goal of gaining knowledge from the moon.  To honor Apollo 1 astronauts, there is a plaque at the site where they perished with the Latin phrase ad astra per aspera, which translates to "a rough road leads to the stars" or "to the stars through difficulty."  This was also the name of the 50th anniversary tribute exhibit for the launch at the Kennedy Space Center Visitor Complex in 2017.

Arrogans avis cauda gravis, which translates to "the proud bird with the heavy tail," was the motto of the 2TV-1 altitude test of the Apollo Command Module (CM) and Lunar Module (LM) in the 1960s.  A current example includes mission operations at NASA's Armstrong Center, which claims the motto of ex binarii, cognition, evoking Apollo 13’s motto for its own goal of gaining understanding from binary.

Seneca, the previously mentioned Roman philosopher who is credited with the motto of "by teaching, we learn," exhorts us to turn to those who would seek to make us better and then, in return, accept those whom we could make better.  While Seneca was talking about humans in his letter, there’s no reason that his sentiment should not hold true for relationships between humans and autonomous systems.  We provide what information we can and listen to and interpret the information provided from our autonomous teammates.  But more than speaking to the action of teaming, Seneca’s quote-turned-aphorism can provide guidance for a style of research that is at the heart of the Autonomy Incubator.

In a lab researching autonomous systems, perhaps the first question is who is teaching and who is learning? We, as researchers, are often tasked with teaching other humans, a process highlighted by the incredible number of interns that are welcomed into the Ai. In teaching and collaborating with interns we may uncover surprising aspects of our own research and open ourselves up to new opportunities.

This humans-teaching-humans process is, perhaps, the most Senecan of the lot, but it’s worth considering where machines fit in. As we teach algorithms and models to understand, replicate, and even learn, we in turn gain additional knowledge. In gathering descriptive training data for a GAN designed to produce images for a search and rescue mission, the HINGE team has gained insight into how human language changes when elicited in different situations and provide through different modalities. (Read here to learn more about HINGE!)

Here, we see humans teaching machines while learning from them, but what if the tables were turned? What if autonomous systems were teaching us? Perhaps the sci-fi vision of machine-tutors is a dream of the future, but it’s not hard to imagine a system that gains information from the field and provides that information to a human operator, who in turn updates an aspect of the machine’s system only to start the process all over.

The truth behind docendo discimus is that it locks us – delightfully! – into a cyclical system, trading off teaching and learning roles with our other teammates, be they human or machine.  Yes, the aphorism itself has a history of its own, and NASA has an increasingly long list of Latin phrases to follow behind it, but it's not always about the weight of connotation.  Natalia, when discussing why she decided to make the phrase ours, explained how she also simply "likes the way [it] sounds.  There is something nice about alliteration."



  1. Such a great blog. Got many useful inforamations about this thechnology.
    Very useful for the freshers. Good keep it up.
    machine learning course
    machine learning certification
    machine learning training
    machine learning training course


  2. Thanks for sharing this valuable information and we collected some information from this blog.
    Machine Learning Training Course in Noida

  3. This concept is a good way to enhance the knowledge.thanks for sharing. please keep it up machine learning online course

  4. Nice and good article. It is very useful for me to learn and understand easily.
    Machine Learning Training in Delhi
    Machine Learning Course in Delhi