Sensor Fusion
Many imperfect signals in. One governed pose out.
AI can write software, draft contracts and beat grandmasters, but ask it where the forklift is and it has no idea. A site has plenty of positioning data. What it lacks is one answer.
Sensor Fusion gives Physical AI that answer: a single live position for every person, vehicle, robot and asset on site, with the uncertainty stated.
Swipe the diagram, or pick a stage
1Senseat the edge
Every positioning source on site reports to a Mapped gateway: UWB, Bluetooth, Wi-Fi, cameras, GNSS, robot odometry, and door and gate events. The gateway puts them on one clock and stamps where each measurement came from.
2Fusein the Mapped cloud
Measurements are converted to common units, carried into a shared coordinate frame and aligned in time. One solve then produces a pose for each subject. Identical inputs give identical answers, and a conflict between sources is reported rather than averaged away.
3Actwherever the work is
The pose stream feeds dashboards, fleet software and AI agents. Every consumer gets the same answer, in the coordinate frame it asks for.
A position you can check
A dot on a map is easy to draw and hard to trust. Every pose from Sensor Fusion carries the four things a system needs before it acts on one.
- Frame
- A named coordinate frame from a governed hierarchy, so the same pose reads correctly in site, building, floor or global coordinates.
- Time
- The instant the pose describes, which is not the instant it arrived.
- Uncertainty
- A stated error, in meters, that widens when a sensor drops out and tightens when it returns.
- Provenance
- The sensors that contributed, so a consumer can decide how much weight to give it.
In the same model as everything else
Poses land in the knowledge graph Mapped already keeps for a site. A forklift’s position sits beside the rack it is approaching, the door it will pass and the air handler overhead, and one query reaches all of it.
That is what lets an AI agent go from a question to a working application in hours. It asks for things by type, follows relationships that are already there, and now knows where everything is.
Warehouses
Forklifts, tuggers, autonomous robots, drones and people, tracked together across the floor and the yard.
Datacenters
A rack inlet temperature and the technician walking toward it, in one model at the same instant.
Airports
Gates, jet bridges, baggage and the crews working them, across every level of a terminal.
Why it matters: Read the Physical AI manifesto
["<script nonce=\"b3diaTZnbXkzOG0=\" src=\"https://js.hsforms.net/forms/embed/v2.js\"></script>","<script nonce=\"b3diaTZnbXkzOG0=\" src=\"https://static.claydar.com/init.v1.js?id=cByptbsZbj\"></script>","<script nonce=\"b3diaTZnbXkzOG0=\">(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':\nnew Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],\nj=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src=\n'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);\n})(window,document,'script','dataLayer','GTM-N2BZQZZG');</script>","<script nonce=\"b3diaTZnbXkzOG0=\" id=\"hs-script-loader\" async defer src=\"https://js-na2.hs-scripts.com/22297332.js\"></script>","<script nonce=\"b3diaTZnbXkzOG0=\">(function(l) { if (!l){window.lintrk = function(a,b){window.lintrk.q.push([a,b])}; \nwindow.lintrk.q=[]} var s = document.getElementsByTagName(\"script\")[0]; \nvar b = document.createElement(\"script\"); b.type = \"text/javascript\";b.async = true; \nb.src = \"https://snap.licdn.com/li.lms-analytics/insight.min.js\"; s.parentNode.insertBefore(b, s);})(window.lintrk);</script>","<script nonce=\"b3diaTZnbXkzOG0=\">!function(f,b,e,v,n,t,s) {if(f.fbq)return;n=f.fbq=function(){n.callMethod? n.callMethod.apply(n,arguments):n.queue.push(arguments)}; if(!f._fbq)f._fbq=n;n.push=n;n.loaded=!0;n.version='2.0'; n.queue=[];t=b.createElement(e);t.async=!0; t.src=v;s=b.getElementsByTagName(e)[0]; s.parentNode.insertBefore(t,s)}(window, document,'script', 'https://connect.facebook.net/en_US/fbevents.js'); fbq('init', '1280785792734144'); fbq('track', 'PageView');</script>","<script nonce=\"b3diaTZnbXkzOG0=\">_linkedin_partner_id = \"3501468\"; window._linkedin_data_partner_ids = window._linkedin_data_partner_ids || []; window._linkedin_data_partner_ids.push(_linkedin_partner_id);</script>","<script nonce=\"b3diaTZnbXkzOG0=\">(function(l) { if (!l){window.lintrk = function(a,b){window.lintrk.q.push([a,b])}; window.lintrk.q=[]} var s = document.getElementsByTagName(\"script\")[0]; var b = document.createElement(\"script\"); b.type = \"text/javascript\";b.async = true; b.src = \"https://snap.licdn.com/li.lms-analytics/insight.min.js\"; s.parentNode.insertBefore(b, s);})(window.lintrk);</script>","<script nonce=\"b3diaTZnbXkzOG0=\">function initApollo(){var n=Math.random().toString(36).substring(7),o=document.createElement(\"script\"); o.src=\"https://assets.apollo.io/micro/website-tracker/tracker.iife.js?nocache=\"+n,o.async=!0,o.defer=!0, o.onload=function(){window.trackingFunctions.onLoad({appId:\"66185ade46511d01c73477f0\"})}, document.head.appendChild(o)}initApollo();</script>","<script nonce=\"b3diaTZnbXkzOG0=\">!function(e,r){try{if(e.vector)return void console.log(\"Vector snippet included more than once.\");var t={};t.q=t.q||[];for(var o=[\"load\",\"identify\",\"on\"],n=function(e){return function(){var r=Array.prototype.slice.call(arguments);t.q.push([e,r])}},c=0;c<o.length;c++){var a=o[c];t[a]=n(a)}if(e.vector=t,!t.loaded){var i=r.createElement(\"script\");i.type=\"text/javascript\",i.async=!0,i.src=\"https://cdn.vector.co/pixel.js\";var l=r.getElementsByTagName(\"script\")[0];l.parentNode.insertBefore(i,l),t.loaded=!0}}catch(e){console.error(\"Error loading Vector:\",e)}}(window,document); vector.load(\"6ab6ecb3-724c-49c1-ba70-ddc6c268e21a\");</script>"]
