|
Volume 01 |
Issue 24 |
November 16, 2020
|
SpaceX ISS, AI Safety Critical, White box for AI
Welcome back to the Future of Aerospace, where each week we dive into a few of the trends rapidly defining the next generation of aircraft and aerial markets.
On Sunday Nov. 15 at 7:27 p.m. EST, SpaceX’s Crew Dragon spacecraft became the first FAA-licensed human crewed commercial spaceflight, starting a new era for the commercial space industry. More on that below.
THIS WEEK: SpaceX's successful launch of its Crew Dragon spacecraft on a mission to the International Space Station on Sunday, Nov. 15 was a significant milestone for the company, but only the beginning of a six-month process where key technology and physiological aspects of future commercial human space travel will be evaluated. (Longshots)
Technologies like artificial intelligence (AI) and machine learning (ML) continue to be a black box for many in the aviation industry, Luuk van Dijk, founder and CEO of Daedalean– a Zürich, Switzerland-based startup–said during a Nov. 10 virtual Revolution.Aero town hall. (Autonomy & AI)
While artificial intelligence/machine learning (AI/ML) is a priority for technologists seeking to advance military, civil and commercial aerospace, machines will not likely be running the air and space domains any time soon. (Autonomy & AI)
Thanks for reading.
—The Future of Aerospace Team
|
|
| SpaceX Crew-1 Launch Starts New Era in Commercial Human Space Travel |
|
Image: SpaceX
SpaceX's successful launch of its Crew Dragon spacecraft on a mission to the International Space Station on Sunday, Nov. 15 was a significant milestone for the company, but only the beginning of a six-month process where key technology and physiological aspects of future commercial human space travel will be evaluated.
The historic launch occurred at 7:27 p.m. EST from Launch Complex 39A at the Kennedy Space Center featuring NASA astronauts Mike Hopkins, Victor Glover, Shannon Walker, and Japan Aerospace Exploration Agency (JAXA) astronaut Soichi Noguchi onboard.
Among the historic firsts achieved by SpaceX on the flight include the first NASA-certified commercial system designed for crew transportation, officially moving Dragon from development to regular commercial human-carrying spaceflights. Additionally, it was the first FAA-licensed human orbital spaceflight launch.
What’s next for SpaceX and Crew Dragon?
|
- During a press conference following the launch, SpaceX President and COO Gwynne Shotwell said the company plans to perform seven launches over the next 15 months.
- SpaceX plans on performing their Crew-2 mission within four to five months, with Crew-3 to follow six months later, according to Shotwell.
- The company also has plans to perform a commercial mission to the ISS with Axiom Space, a Houston-based aerospace manufacturer and provider of orbital spaceflight services.
- Shotwell: "Falcon 9 looked beautiful, I don't have any specifics on any anomalies that we had which is great, we'll get more data as we go. Dragon was dropped off roughly 12 minutes into the mission into a beautiful orbit, the machine is operating just fine, all systems nominal."
- During their stay on the orbiting laboratory, Crew-1’s astronauts expect to see a range of uncrewed spacecraft flights to the ISS including SpaceX’s next-generation cargo Dragon spacecraft, Northrop Grumman’s Cygnus, Boeing’s CST-100 Starliner making an uncrewed flight test to the station.
- They also will conduct a variety of spacewalks and welcome crews of the Russian Soyuz vehicle and the next SpaceX Crew Dragon in 2021, according to NASA.
- NASA Administrator Jim Bridenstine said that Sunday's SpaceX flight was also historic because it helps transition NASA into a customer of space travel on U.S.-made spacecraft after spending the last decade reliant on Russia's Soyuz for trips back and forth to the ISS.
|
Bridenstine: "Our goal has been and will be to be one customer of many customers in a very robust commercial marketplace in low earth orbit. But we also want to have numerous providers that are competing on cost and innovation and safety, we've seen amazing work from SpaceX already there's more coming from Boeing. I think this ecosystem, this very virtuous cycle of continuous development is going to pay benefits to the American taxpayer and space exploration."
Read more on SpaceX's mission to the International Space Station.
|
| Daedalean Explains Path to Safety-Critical Certification for Artificial Intelligence in Avionics |
Technologies like artificial intelligence (AI) and machine learning (ML) continue to be a black box for many in the aviation industry, Luuk van Dijk, founder and CEO of Daedalean– a Zürich, Switzerland-based startup–said during a Nov. 10 virtual Revolution.Aero town hall. However, van Dijk sees AI/ML as a way to simplify aviation operations and improve on current human piloting capabilities all while being safety-critical certified.
Van Dijk saw a gap in the developing electric vertical take-off and landing (eVTOL) industry four years ago and decided to tackle it, he said during the webinar. While others in the industry were building new energy storage and propulsion systems, he would tackle AI, which he believed others lacked the skill set and risk appetite for.
How will he do it?
|
- Van Dijk: “You take well-defined subtasks of the art of flying and then you can build a system that meets the VFR [visual flight rules] requirements of seeing other aircraft on visual, even the ones that don't show up on a radar, or ones that can recognize the runway on visual and make the call to abort or not because there's the burning wreck of the previous guy to try to land there. There are clearly there's no equivalent system today and you have to solve these problems.”
- While certification of AI will not be trivial or easy, van Dijk said, it is not impossible. He compares the path for AI certification to how avionics software is certified by the FAA, DO-178B.
What obstacles still exist?
- Before AI is ready to pilot an aircraft, there has to be a reconning of the mystery behind how it works. Van Dijk said he prefers to talk about machine learning systems to get rid of the idea that AI is a “magic black box.”
- AI will have to prove it is safer than human piloting, van Dijk said. These systems will have to deal with uncertainty in real-world environments.
|
Van Dijk: "The paradox is, and this is actually kind of surprising that by going for this harder class of systems, we can actually get to a higher level of safety, provided we do it right.”
|
| 'White Box' Likely a Key in Future AI Aviation Use |
While artificial intelligence/machine learning (AI/ML) is a priority for technologists seeking to advance military, civil and commercial aerospace, machines will not likely be running the air and space domains any time soon.
AI/ML algorithms so far lack the cognitive abilities required to make trusted, safety-critical decisions. In terms of "general artificial intelligence," aviation authorities and aerospace firms are "decades away from something like that," Alex Georgiades, the United Kingdom Civil Aviation Authority's (CAA) innovation services principal for autonomous systems, said during a Nov. 10 webinar hosted by the Royal Aeronautical Society (RAeS).
What is preventing a full-on embrace of AI in aircraft systems?
|
- Civil aviation authorities, including the U.K. CAA and the Federal Aviation Administration (FAA), have been bounding AI/ML systems under constraints so that a chain reaction will not lead to a catastrophic failure.
- Wes Ryan, the FAA's unmanned and pilotless aircraft technology lead: “The place that we're just beginning to delve into is systems like the recently certified Garmin Autoland system that in the event of an emergency can look for and identify the best landing site to put the aircraft back on the ground with a single button push.”
- The next step is likely to be increased scrutiny of how AI/ML functions under such bounded conditions on an aircraft.
- An understanding of the functioning of AI/ML in whatever limited role it performs on an aircraft could yield significant safety benefits.
How could a ‘white box’ for AI help?
- Monty Christy, the founder of London-based Christy Aerospace and Technology: "The problem is the black box where we don't fully understand what's going on, but something has happened–we may like the result; we may not like the result.”
- A "white box" would allow personnel to identify and correct systems' inadvertent automation biases in data sets and existing programming languages.
- The hope is that programmers will be able to write a new, AI/ML language that lacks such biases.
- Developing AI/ML systems that lack automation biases and that can reliably analyze and correlate data to aid pilot decision making will be a challenge, as will not granting AI/ML systems too much autonomy.
|
Christy: "We're not talking about taking an off-the-shelf program and modifying it for our own purposes in the aviation/aerospace industry. We may be talking about a new language that's built from scratch to provide that traceability and the identification and removal of bias on Day One when a code is put together to support a system."
Read more about considerations for a white box for AI in aircraft.
|
|
