Author: Department of Aeronautics and Astronautics<\/p>\n
Artificial intelligence has rapidly transformed software engineering. Generative AI and large language models (LLMs) can create huge volumes of code and documentation; machine-learning algorithms can monitor performance and detect security vulnerabilities. But when the task is to conceive, design, and make a complex physical system such as a jet engine, are those AI tools equally transformative?<\/p>\n
This past semester, the JARVIS Challenge (Jet-engine AI Research and Validation Intensive Sprint) set out to explore whether AI can compress the design-build-test cycle, asking MIT undergraduates to discover whether AI can help them to build faster and better.\u00a0<\/p>\n
\u201cThe JARVIS challenge showed that AI can substantially accelerate safety-critical hardware engineering, but engineering judgment remains the decisive differentiator. An AI-native engineer is not defined by using AI, but by leading it \u2014 knowing when to trust it, when to challenge it, and how to translate AI outputs into working hardware. Manufacturing \u2014 not engineering design or analysis \u2014 remained the fundamental rate-limiting step,\u201d says Professor Zolti Spakovszky, director of the MIT Gas Turbine Laboratory<\/a>.<\/p>\n The teams, the tools, the task<\/strong><\/p>\n The challenge gave undergraduates four weeks to design, fabricate, assemble, and test a small gas turbine aero engine, using AI as their primary engineering partner. The objective: build a \u201cJARVIS-class\u201d single-spool jet engine producing 50\u2013100 pounds of thrust, running on Jet-A, and completing five 60-second runs. Teams had total freedom over design, materials, and fabrication.\u00a0<\/p>\n Representing nearly every department in the School of Engineering, 31 students organized into seven teams, ranging from all first-years to senior-heavy groups. Many of the competitors initially had little experience in turbomachinery, compressible flows, or, in the case of the younger students, even thermodynamics. Many had never seen the inside of a gas turbine before signing up to build one.\u00a0\u00a0<\/p>\n At their disposal: MIT\u2019s machine shops and manufacturing vendors; commercial software including Concepts NREC, SolidWorks, and ABAQUS; and various test rigs for characterizing and assembling individual components.<\/p>\n The teams also had access to MIT Parley<\/a>, a newly launched platform that aggregates frontier large language models through a single interface. Through Parley, JARVIS leads could see directly how the students were using the AI tools, including their prompts, the cost per prompt, the specific LLMs being used, and other critical information. The JARVIS leads secured early access to Parley for all participants, and with financial support from MIT Lincoln Laboratory, the Department of Mechanical Engineering, and corporate sponsors Safran, Voyager Technologies, and Beehive Industries, students had access to essentially unlimited use of AI.<\/p>\n The sponsors were drawn by recruiting interest and genuine curiosity about how AI might reshape engineering workflows.\u00a0<\/p>\n \u201cWe see this as the future of engineering,\u201d Ryan (Hal) Hefron of Voyager Technologies told the students. \u201cYou\u2019re honing skills that are not just nice to have \u2014 they\u2019re going to be the future baseline in the engineering workforce.\u201d<\/p>\n Vincent Garnier, managing director of Safran Tech, watched the competition unfold with excitement.\u00a0\u201cJARVIS was a genuine experiment, a learning endeavor. We frankly didn\u2019t know what to expect, from the students or from the AI models. What struck me coming from the students was: first, the enthusiasm to explore; then, as the project developed, they all came to the cool-headed realization of what AI could or could not help them with, and then almost instantly adapted for that,\u201d he says. \u201cIt makes me confident that this generation of leading engineers will probably not fall prey to easy and shortsighted use of AI, and will do so by keeping ever more in contact with experiments \u2014 physical or thought experiments.\u201d<\/p>\n The faculty leadership \u2014 professors Zachary Cordero, Zolti Spakovszky, Masha Folk, and Andreea Bobu of the Department of Aeronautics and Astronautics, along with Lincoln Laboratory engineers and a team of teaching assistants \u2014 were there to ensure safety. In weekly progress reviews, they would critically evaluate the student progress and assess how the students were using AI.<\/p>\n Spakovszky developed a careful technique for guiding teams in the right direction without giving away answers or providing help. After a team\u2019s presentation, he might ask: \u201cDo you know what a rabbet fit is? Take in the comment.\u201d<\/p>\n Where AI helps and hurts<\/strong><\/p>\n By the end of week 1, one team withdrew from the competition; the others had, with varying degrees of success, developed an initial design for their gas turbines. Different teams used AI to summarize textbooks, teach them to use design software, source vendors, create Excel sheets, answer specific questions, find references, and create comparative analysis between design decisions. One team created an agent in Parley and tasked it with serving as their project manager.\u00a0<\/p>\n By week 2, teams had to start working on detailed CAD designs, ordering parts, and prototyping their combustors. This is where the teams started to hit limitations in their use of AI. While Claude and ChatGPT were good at offering design alternatives and filling knowledge gaps, teams found that the hallucinations, sycophancy, and lack of physical understanding that have become notorious features of generative AI were undermining their confidence and slowing them down.\u00a0<\/p>\n \u201cAI is a helpful tool, great at finding information, helping organize things, and can write well, but it can\u2019t do design,\u201d says Elizabeth Tupaj, a member of team 811 Crew. \u201cThe moment the engineer doesn\u2019t know what is going on and the AI is in charge is the moment the design becomes unreliable, at least with AI at its present capabilities.\u201d<\/p>\n Teaching assistant John Zhang notes, \u201cseeing this firsthand with the students reminded me how much first impressions matter. If the students couldn\u2019t get answers from the AI early on, they quickly grew frustrated and formed a lasting opinion that precluded them from using it later.\u201d\u00a0<\/p>\n In the final weeks, the finalists hit another obstacle no AI could solve: working with vendors. \u201cAI searches found vendors we had no rapport with, who had no interest in our tight timeline,\u201d students reported. \u201cThe vendors who came through were the ones our team had personal relationships with.\u201d<\/p>\n Of the three finalists, only Fast and Fractured achieved first-attempt ignition of their mini-combustor. The team had used AI heavily for trade studies and architecture comparisons, arriving at a viable design despite none of them having prior gas turbine experience.<\/p>\n \u201cThe JARVIS Challenge showed what\u2019s possible when you combine AI-enabled design with motivated students and a culture of rapid experimentation,\u201d says Masha Folk, the Charles Stark Draper Career Development Professor of Aeronautics and Astronautics. \u201cThe moment that stood out most was when the first student-designed combustor was installed on the test stand. It ignited flawlessly, ramped to full power, transitioned to dual-fuel operation, and then sustained stable combustion on 100 percent Jet-A fuel. This was proof that we can dramatically accelerate the cycle of design, build, and test while giving students hands-on experience with a real engineering challenge.\u201d<\/p>\n At the vanguard of AI-native engineering<\/strong><\/p>\n By the end of May, the two more senior teams \u2013 Fast and Fractured and 811 Crew \u2013 had completed full engine tests. Fast and Fractured, with their AI-assisted design, were delayed by vendor headaches week after week, but finally made it to test. Unfortunately, their hot fire was cut short when the rotor rubbed and seized against the stationary housing. Team 811 Crew, however, who had more exposure to turbomachinery and propulsion concepts going into the competition, emerged victorious. Their engine started, successfully transitioned to Jet-A, and generated net thrust.\u00a0<\/p>\n \u201cAs we stood there with the air-starter, hearing their engines spool up and watching them spit fire, it felt like my heart was racing out of my chest. There were so many ways it could go wrong! What these students accomplished in such a short time span is nothing short of amazing,\u201d says PhD student Joe Chiapperi.\u00a0<\/p>\n The 811 team had been resistant to using AI throughout the competition, trusting instead to their fundamentals and teamwork. \u201cWe had people who were at least somewhat familiar with the design software, mechanical engineers who knew how to build anything, and aerospace engineers who had taken classes on the design of gas turbine engines specifically,\u201d says Tupaj.\u00a0<\/p>\n From the start of the JARVIS Challenge, younger students used Parley more frequently and cleverly, while the juniors and seniors leveraged deeper experience.\u00a0<\/p>\n \u201cJARVIS taught me that getting value from AI takes two things: enough expertise to judge what it tells you and catch it when it\u2019s wrong, and enough curiosity to actually lean on it where it could help,\u201d says Professor Andreea Bobu. \u201cThe team that moved fastest in the sprint was experienced and leaned heavily on AI to get there. The team that eventually won was more resistant to AI; they had the expertise, but that skepticism made them slower. The sweet spot seems to be knowing enough to stay in charge of the tool, and being eager enough to pick it up in the first place. To me, that\u2019s the real opportunity ahead: training the next generation of engineers who have the judgment to direct these AI tools and the instinct to reach for them.\u201d<\/p>\n The competition\u2019s clearest finding: engineering experience is a multiplier, and the human factor remains a vital element. Mastering the first principles and fundamental concepts breeds good engineering judgment and the ability to navigate strings of tough decisions in the face of incomplete information. And when it comes to building safety-critical physical systems, nothing can replace human hands and human accountability.\u00a0<\/p>\n \u201cJARVIS has shown that AI copilots can have a multiplicative effect on engineering productivity, with judgment and first-principles thinking serving as the key differentiators among teams,\u201d adds teaching assistant Kyle Woody.\u00a0<\/p>\n But the implications of AI in aerospace are significant. If small teams using well-managed AI copilots can compress design-build-test cycles from years to weeks, the consequences for workforce structure, R&D timelines, and competitive dynamics could be substantial. The students who tackled the JARVIS Challenge are among the first engineers to grapple with those stakes not as a thought experiment, but in a machine shop, with a jet engine on the test stand.<\/p>\n \u201cJARVIS highlighted the power of AI in the design of physical systems,\u201d says Cordero, associate director of the MIT Gas Turbine Laboratory. \u201cBut it also showed that the key to unlocking that power is education, through coursework, internships, and hands-on extracurriculars like MIT Motorsports and Rocket Team. Performance in JARVIS correlated strongly with year in school. My main takeaway is that in the AI era, education is more valuable than ever.\u201d<\/p>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Author: Department of Aeronautics and Astronautics Artificial intelligence has rapidly transformed software engineering. Generative AI and large language models (LLMs) can create huge volumes of […] Read More<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":457,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"footnotes":""},"categories":[24],"tags":[],"_links":{"self":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/9194"}],"collection":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/comments?post=9194"}],"version-history":[{"count":0,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/9194\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media\/459"}],"wp:attachment":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media?parent=9194"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/categories?post=9194"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/tags?post=9194"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}