{"id":15706,"date":"2022-01-20T08:58:24","date_gmt":"2022-01-20T13:58:24","guid":{"rendered":"https:\/\/engineering.jhu.edu\/magazine-archive\/?p=15706"},"modified":"2022-01-20T08:58:24","modified_gmt":"2022-01-20T13:58:24","slug":"ensuring-the-safety-of-ai-based-systems","status":"publish","type":"post","link":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/","title":{"rendered":"Ensuring the Safety of AI-Based Systems"},"content":{"rendered":"\"A\n

Using a $7.5 million, five-year grant from the U.S. Department of Defense, a multi-university team that includes Johns Hopkins engineers is tackling one of today’s most complex and important technological challenges: how to ensure the safety of autonomous systems, from self-driving cars and aerial delivery drones to robotic surgical assistants.<\/p>\n

\u201cThe potential practical ramifications of this project are broad and boil down to making sure that artificial intelligence-based systems are safe,\u201d says Ren\u00e9 Vidal<\/a>, the Herschel L. Seder Professor of Biomedical Engineering<\/a> and the inaugural director of the\u00a0Mathematical Institute for Data Science<\/a>. He is working with Noah Cowan<\/a>, professor of mechanical engineering<\/a> and director of the\u00a0Locomotion in Mechanical and Biological Systems laboratory<\/a>, and collaborators at Northeastern University, the University of Michigan, and the University of California, Berkeley on the Multidisciplinary University Research Initiative, or MURI project, called Control and Learning Enabled Verifiable Robust AI, or CLEVR-AI.<\/p>\n

\u201cUsing this grant,\u201d says Vidal, \u201cwe are developing theoretical and algorithmic foundations to support a new class of verifiable, safe, AI-enabled dynamical systems that, like living systems, will adapt to novel scenarios, where data are generated \u2014 and decisions are made \u2014 in real time.\u201d<\/p>\n

Despite recent advances in artificial intelligence and machine learning, the goal of designing control systems capable of fully using AI\/machine learning methods to learn from and interact with the environment the way humans and animals do remains elusive, the researchers say.<\/p>\n

\u201cAnimals, including humans, move with such grace and agility, and are able to adjust and change their movements and behavior according to what is happening around them,\u201d says Cowan. \u201cAs engineers, we seek to learn from them while creating robust control systems that are safe and reliable. Our goal here is to bridge the gap between biological sensing and control systems, and safe and reliable autonomous systems.\u201d<\/p>\n

The field of artificial intelligence has tried to address this gap by building computational systems that attempt to mimic or approximate aspects of the brain. Unfortunately, that approach and the resulting designs do not reliably create safe systems. The team\u2019s project seeks to overcome this by combining machine learning, dynamical systems theory, and formal verification methods, leveraging each team member\u2019s strengths. For instance, Vidal is an expert in machine learning, computer vision, and biomedical data science, and Cowan’s expertise is in understanding sensing, computation, and control in animals. Both are leading authorities in the field of robotics and control theory.<\/p>\n

\u201cOur approach,\u201d says Cowan, \u201cwill integrate traditional mathematical control theory with new and emerging AI to make systems verifiable, robust, safe, and correct.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

Johns Hopkins engineers are tackling one of today’s most complex and important technological challenges: how to ensure the safety of autonomous systems, from self-driving cars and aerial delivery drones to robotic surgical assistants.<\/p>\n","protected":false},"author":4,"featured_media":15708,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[24],"tags":[],"class_list":["post-15706","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-impact","issue-winter-2022"],"acf":[],"yoast_head":"\nEnsuring the Safety of AI-Based Systems - JHU Engineering Magazine<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Ensuring the Safety of AI-Based Systems - JHU Engineering Magazine\" \/>\n<meta property=\"og:description\" content=\"Johns Hopkins engineers are tackling one of today's most complex and important technological challenges: how to ensure the safety of autonomous systems, from self-driving cars and aerial delivery drones to robotic surgical assistants.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/\" \/>\n<meta property=\"og:site_name\" content=\"JHU Engineering Magazine\" \/>\n<meta property=\"article:published_time\" content=\"2022-01-20T13:58:24+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2022\/01\/shutterstock_1035067897.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"900\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Abby Lattes\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Abby Lattes\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/\"},\"author\":{\"name\":\"Abby Lattes\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\"},\"headline\":\"Ensuring the Safety of AI-Based Systems\",\"datePublished\":\"2022-01-20T13:58:24+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/\"},\"wordCount\":433,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2022\\\/01\\\/shutterstock_1035067897.jpg\",\"articleSection\":[\"Impact\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/\",\"name\":\"Ensuring the Safety of AI-Based Systems - JHU Engineering Magazine\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2022\\\/01\\\/shutterstock_1035067897.jpg\",\"datePublished\":\"2022-01-20T13:58:24+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#primaryimage\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2022\\\/01\\\/shutterstock_1035067897.jpg\",\"contentUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2022\\\/01\\\/shutterstock_1035067897.jpg\",\"width\":1200,\"height\":900,\"caption\":\"A blue butterfly lands on the outstretched finger of a robotic hand\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2022\\\/01\\\/ensuring-the-safety-of-ai-based-systems\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Ensuring the Safety of AI-Based Systems\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#website\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/\",\"name\":\"JHU Engineering Magazine\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\",\"name\":\"Abby Lattes\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"caption\":\"Abby Lattes\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Ensuring the Safety of AI-Based Systems - JHU Engineering Magazine","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/","og_locale":"en_US","og_type":"article","og_title":"Ensuring the Safety of AI-Based Systems - JHU Engineering Magazine","og_description":"Johns Hopkins engineers are tackling one of today's most complex and important technological challenges: how to ensure the safety of autonomous systems, from self-driving cars and aerial delivery drones to robotic surgical assistants.","og_url":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/","og_site_name":"JHU Engineering Magazine","article_published_time":"2022-01-20T13:58:24+00:00","og_image":[{"width":1200,"height":900,"url":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2022\/01\/shutterstock_1035067897.jpg","type":"image\/jpeg"}],"author":"Abby Lattes","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Abby Lattes","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#article","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/"},"author":{"name":"Abby Lattes","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742"},"headline":"Ensuring the Safety of AI-Based Systems","datePublished":"2022-01-20T13:58:24+00:00","mainEntityOfPage":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/"},"wordCount":433,"commentCount":0,"image":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#primaryimage"},"thumbnailUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2022\/01\/shutterstock_1035067897.jpg","articleSection":["Impact"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/","name":"Ensuring the Safety of AI-Based Systems - JHU Engineering Magazine","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#website"},"primaryImageOfPage":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#primaryimage"},"image":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#primaryimage"},"thumbnailUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2022\/01\/shutterstock_1035067897.jpg","datePublished":"2022-01-20T13:58:24+00:00","author":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742"},"breadcrumb":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#primaryimage","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2022\/01\/shutterstock_1035067897.jpg","contentUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2022\/01\/shutterstock_1035067897.jpg","width":1200,"height":900,"caption":"A blue butterfly lands on the outstretched finger of a robotic hand"},{"@type":"BreadcrumbList","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2022\/01\/ensuring-the-safety-of-ai-based-systems\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/engineering.jhu.edu\/magazine-archive\/"},{"@type":"ListItem","position":2,"name":"Ensuring the Safety of AI-Based Systems"}]},{"@type":"WebSite","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#website","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/","name":"JHU Engineering Magazine","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/engineering.jhu.edu\/magazine-archive\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742","name":"Abby Lattes","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","caption":"Abby Lattes"}}]}},"_links":{"self":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/15706","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/comments?post=15706"}],"version-history":[{"count":2,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/15706\/revisions"}],"predecessor-version":[{"id":15718,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/15706\/revisions\/15718"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/media\/15708"}],"wp:attachment":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/media?parent=15706"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/categories?post=15706"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/tags?post=15706"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}