{"id":5103,"date":"2026-05-13T15:08:54","date_gmt":"2026-05-13T19:08:54","guid":{"rendered":"https:\/\/oge.mit.edu\/msrp\/?post_type=profiles&#038;p=5103"},"modified":"2026-08-10T12:10:44","modified_gmt":"2026-08-10T16:10:44","slug":"joshua-harris","status":"publish","type":"profiles","link":"https:\/\/oge.mit.edu\/msrp\/profiles\/joshua-harris\/","title":{"rendered":"Joshua Harris"},"content":{"rendered":"<div class=\"wp-block-image\">\n<figure class=\"alignleft size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"400\" height=\"599\" src=\"https:\/\/oge.mit.edu\/msrp\/wp-content\/uploads\/sites\/2\/2026\/05\/Harris-Joshua.jpg\" alt=\"by Corban Swain\" class=\"wp-image-5600\" style=\"aspect-ratio:1;object-fit:cover;width:200px;height:auto\" srcset=\"https:\/\/oge.mit.edu\/msrp\/wp-content\/uploads\/sites\/2\/2026\/05\/Harris-Joshua.jpg 400w, https:\/\/oge.mit.edu\/msrp\/wp-content\/uploads\/sites\/2\/2026\/05\/Harris-Joshua-200x300.jpg 200w\" sizes=\"auto, (max-width: 400px) 100vw, 400px\" \/><\/figure>\n<\/div>\n\n\n<div class=\"wp-block-group\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\">\n<p class=\"wp-block-paragraph\"><strong>University of Maryland, Baltimore County<\/strong><br>Faculty Advisor: Prof. Danielle Wood<br>Research Supervisors: Scott Dorrington, Alissa Chavalithumrong<br>Department: Electrical Engineering and Computer Science<\/p>\n<\/div><\/div>\n\n\n\n<div style=\"height:0px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Biography<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">Joshua Harris is a rising sophomore and Meyerhoff Scholar at the University of Maryland,<br>Baltimore County (UMBC), studying Computer Science with minors in Mathematics and<br>Entrepreneurship. Growing up in Prince George\u2019s County, Maryland, he developed a passion for<br>computer science that pushed him to explore how artificial intelligence and machine learning can<br>be used to build secure software and innovative systems that benefit society at the intersection of<br>health, education, security, and integration. At MIT\u2019s Space Enabled Group, Josh is building and<br>training a multimodal large language model to help NASA\u2019s robots on the International Space<br>Station operate more efficiently. At UMBC, he is committed to service and building community on<br>campus, volunteering for UMBC\u2019s Choice Program, as well as serving as the Parliamentarian for<br>UMBC\u2019s NSBE chapter, and the Ambassador for UMBC\u2019s Campus Connect platform. His passion,<br>combined with his experience, enables other students around him to excel.<\/p>\n\n\n\n<p class=\"has-text-align-center wp-block-paragraph\"><br><strong>Augmenting the Astrobee: Deploying Multimodal Models in Microgravity-Based<br>Human-Robot Interactions<\/strong><br>Joshua Harris1, Alissa Chavalithumrong2,3, Scott Dorrington2, and Danielle Wood2,3<br>1Department of Computer Science and Electrical Engineering, University of Maryland &#8211;<br>Baltimore County<br>2Program in Media Arts and Sciences, Massachusetts Institute of Technology<br>3Department of Aeronautics and Astronautics, Massachusetts Institute of Technology<\/p>\n\n\n\n<p class=\"has-text-align-center wp-block-paragraph\"><br>As missions to the International Space Station (ISS) progress, astronaut time remains tightly<br>constrained. Free-flying robots, such as NASA\u2019s Astrobee, help optimize astronaut time by<br>performing routine tasks on the ISS. Current robot systems, however, lack the necessary<br>context-aware interactions to communicate with astronauts efficiently. Recent studies show<br>that multimodal models (MMMs), which process several types of data at a time, offer a path<br>toward more flexible interaction in microgravity. However, not enough current research<br>confirms or validates the feasibility of deploying a MMM on Astrobee and other free-flying<br>robots on the ISS. This study aims to determine the feasibility of how a MMM can be<br>integrated into Astrobee to optimize microgravity-based human-robot interactions on the ISS.<br>To conduct this study, a formal system architecture was designed to showcase the process of a<br>MMM being integrated into Astrobee\u2019s internal software, using NASA JPL\u2019s ROSA agent and<br>a Large-Language Model to build the model. A prototype model is still in the process of being<br>developed, and it will be tested in simulation using a Linux environment and RViz software. If<br>successful, this research provides the first concrete assessment of applying a multimodal model<br>to increase overall efficiency in microgravity-based human-robot interactions.<\/p>\n","protected":false},"featured_media":5455,"template":"","profile_category":[25],"class_list":["post-5103","profiles","type-profiles","status-publish","has-post-thumbnail","hentry","profile_category-2026-interns"],"acf":[],"_links":{"self":[{"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/profiles\/5103","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/profiles"}],"about":[{"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/types\/profiles"}],"version-history":[{"count":3,"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/profiles\/5103\/revisions"}],"predecessor-version":[{"id":5707,"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/profiles\/5103\/revisions\/5707"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/media\/5455"}],"wp:attachment":[{"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/media?parent=5103"}],"wp:term":[{"taxonomy":"profile_category","embeddable":true,"href":"https:\/\/oge.mit.edu\/msrp\/wp-json\/wp\/v2\/profile_category?post=5103"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}