{"id":11,"date":"2025-11-25T02:19:08","date_gmt":"2025-11-25T02:19:08","guid":{"rendered":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/?page_id=11"},"modified":"2026-02-20T23:32:14","modified_gmt":"2026-02-21T04:32:14","slug":"design-documentation","status":"publish","type":"page","link":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/design-documentation\/","title":{"rendered":"System Design"},"content":{"rendered":"\n<p><strong>Project: Humanoid Navigation &amp; Loco-Manipulation in Multi-Story<br>Human Spaces<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>We aim to develop an autonomous integrated stack for <em><strong>multi-story indoor navigation<\/strong><\/em> and <em><strong>loco-manipulation<\/strong><\/em>. Given natural language prompt from human, the humanoid robot shoule be able to understand command and scene, navigate to the goal room in a multi-floor building either via stair or elevator, and open doors encountered along the way.<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"661\" height=\"201\" src=\"http:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/blackbox.png\" alt=\"\" class=\"wp-image-44\" srcset=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/blackbox.png 661w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/blackbox-300x91.png 300w\" sizes=\"auto, (max-width: 661px) 100vw, 661px\" \/><\/figure>\n\n\n\n<pre class=\"wp-block-preformatted\"><strong>Fig 0 : System Paradigm. <\/strong>The system paradigm abstracts the whole system design with high-level input &amp; output of each sub-system.<\/pre>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1357\" height=\"748\" src=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/usecase.png\" alt=\"\" class=\"wp-image-70\" srcset=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/usecase.png 1357w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/usecase-300x165.png 300w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/usecase-768x423.png 768w\" sizes=\"auto, (max-width: 1357px) 100vw, 1357px\" \/><\/figure>\n\n\n\n<p><strong>Fig 1 : Use case of the system. <\/strong>The robot traverse rooms, doors and elevators to find and reach the destination with simple prompt.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<!--more Functional Architecture-->\n\n\n\n<pre class=\"wp-block-preformatted\"><strong>System Design &amp; Architecture:<\/strong><\/pre>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>System Requirements:<\/strong><\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1576\" height=\"1492\" src=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/successrate.png\" alt=\"\" class=\"wp-image-73\" srcset=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/successrate.png 1576w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/successrate-300x284.png 300w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/successrate-768x727.png 768w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2026\/02\/successrate-1536x1454.png 1536w\" sizes=\"auto, (max-width: 1576px) 100vw, 1576px\" \/><\/figure>\n\n\n\n<p><strong>Fig 2 : System Performance Requirements<\/strong>. The system requirements are majorly based on success rate.<\/p>\n\n\n\n<div class=\"wp-block-group is-layout-constrained wp-block-group-is-layout-constrained\">\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-28f84493 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:100%\"><\/div>\n<\/div>\n<\/div>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Functional Architecture:<\/strong><\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"806\" height=\"391\" src=\"http:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/functional.png\" alt=\"\" class=\"wp-image-43\" srcset=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/functional.png 806w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/functional-300x146.png 300w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/functional-768x373.png 768w\" sizes=\"auto, (max-width: 806px) 100vw, 806px\" \/><\/figure>\n\n\n\n<p><strong>Fig 3 : Functional Architecture. <\/strong>The functional architecture demonstrates the logic of all functions of the system. The functions are structured with sensor data flow and information flow.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Cyber-physical Architecture:<\/strong><\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1159\" height=\"481\" src=\"http:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/cyberphysical.png\" alt=\"\" class=\"wp-image-42\" srcset=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/cyberphysical.png 1159w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/cyberphysical-300x125.png 300w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/cyberphysical-768x319.png 768w\" sizes=\"auto, (max-width: 1159px) 100vw, 1159px\" \/><\/figure>\n\n\n\n<p><strong>Fig 4 : Cyber-physical Architecture. <\/strong>Our cyberphysical architecture encapsulates all the deployment logic and structure. Our system is divided into to parts: Neural serve as the backbone of the system with integrated reasoning. Whenever needed, the neural calls functions represented as the Symbolic. Symbolic serve as low-level skill modules in charge of separate specific tasks, such as navigate, open a door or take elevator.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Objectives:<\/strong><\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full is-style-default\"><img loading=\"lazy\" decoding=\"async\" width=\"1001\" height=\"551\" src=\"http:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreeshort.png\" alt=\"\" class=\"wp-image-46\" srcset=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreeshort.png 1001w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreeshort-300x165.png 300w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreeshort-768x423.png 768w\" sizes=\"auto, (max-width: 1001px) 100vw, 1001px\" \/><\/figure>\n\n\n\n<p><strong>Fig 5 : General Objective Tree. <\/strong>The overall division of all objectives of our project. Gree nodes represents threshold objectives, while red node are target objectives.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1001\" height=\"651\" src=\"http:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreelong.png\" alt=\"\" class=\"wp-image-45\" srcset=\"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreelong.png 1001w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreelong-300x195.png 300w, https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-content\/uploads\/sites\/92\/2025\/11\/objectivestreelong-768x499.png 768w\" sizes=\"auto, (max-width: 1001px) 100vw, 1001px\" \/><\/figure>\n\n\n\n<p><strong>Fig 6 : Detailed Objective Tree.<\/strong> The detailed version objective tree   with definition and explanation of each objective.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Project: Humanoid Navigation &amp; Loco-Manipulation in Multi-StoryHuman Spaces Fig 0 : System Paradigm. The system paradigm abstracts the whole system design with high-level input &amp; output of each sub-system. Fig 1 : Use case of the system. The robot traverse rooms, doors and elevators to find and reach the destination with simple prompt.<\/p>\n","protected":false},"author":432,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-11","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/pages\/11","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/users\/432"}],"replies":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/comments?post=11"}],"version-history":[{"count":12,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/pages\/11\/revisions"}],"predecessor-version":[{"id":126,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/pages\/11\/revisions\/126"}],"wp:attachment":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2026teama\/wp-json\/wp\/v2\/media?parent=11"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}