BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250811T180130Z UID:83B19D32-E6B4-425B-B524-6F92968B8CE6 DTSTART;TZID=America/New_York:20250811T130000 DTEND;TZID=America/New_York:20250811T140000 DESCRIPTION:[]\n\nJoin the IEEE Toronto Instrumentation & Measurement – R obotics & Automation Joint Chapter for a technical talk presented by Dr. R oya Fallah Firoozi from University of Waterloo.\n\nMonday\, August 11\, 20 25 @ 1:00 – 2:00 PM (EST)\n\nAbstract: As a robot manipulates 3D objects and navigates within 3D scenes\, it requires spatial reasoning to ensure safe planning. Recent advances in 3D scene representation\, such as Neural Radiance Fields (NeRFs) and Gaussian Splatting\, provide high-fidelity di gital twins of arbitrary real-world environments from multi-view images. I n the first part of the talk\, Dr. Firoozi will discuss employing these 3D visual fields augmented to 3D vision-language fields using internet-scale semantic representations from Vision-Language Models (VLMs) for open-voca bulary robot planning.\n\nAs the robot interacts with other dynamic agents in the scene (multi-agent settings)\, it also requires temporal reasoning to ensure safe interactive planning. In the second part of the talk\, Dr. Firoozi will discuss safe and fault-resilient planning techniques across two categories of interactive planning: (i) Model Predictive Control (MPC) \, where the prediction and planning steps are decoupled\, and (ii) more a bstract approaches such as game-theoretic planning\, where these steps are tightly coupled. While MPC offers computational efficiency\, game-theoret ic planning enables more complex modeling of agents' preferences and their mutual influences.\n\nSpeaker(s): Roya Fallah Firoozi\, Ph.D.\, \n\nVirtu al: https://events.vtools.ieee.org/m/487494 LOCATION:Virtual: https://events.vtools.ieee.org/m/487494 ORGANIZER:s.sedghizadeh.ca@ieee.org SEQUENCE:24 SUMMARY:Safe Robot Autonomy in Interactive Open-World Environments URL;VALUE=URI:https://events.vtools.ieee.org/m/487494 X-ALT-DESC:Description: <br /><p>&nbsp\;</p>\n<p><img style="display: block \; margin-left: auto\; margin-right: auto\;" src="https://events.vtools.ie ee.org/vtools_ui/media/display/548bbef0-5f37-466d-b145-6a943276d975" alt=" " width="770" height="433"></p>\n<p><span style="font-size: 14pt\;">Join t he&nbsp\;<strong>IEEE Toronto Instrumentation &amp\; Measurement &ndash\; Robotics &amp\; Automation Joint Chapter</strong>&nbsp\;for a technical ta lk presented by&nbsp\;<strong>Dr. Roya Fallah Firoozi </strong>from<strong > University of Waterloo.</strong></span></p>\n<p><span style="color: rgb( 186\, 55\, 42)\; font-size: 14pt\;"><strong>Monday\, August 11\, 2025 @ 1: 00 &ndash\; 2:00 PM (EST)</strong></span></p>\n<p class="MsoNormal" style= "background: white\;"><strong><span style="font-size: 12.0pt\; mso-ascii-f ont-family: Aptos\; mso-fareast-font-family: 'Times New Roman'\; mso-hansi -font-family: Aptos\; mso-bidi-font-family: 'Times New Roman'\; color: bla ck\; mso-font-kerning: 0pt\; mso-ligatures: none\;">Abstract:</span></stro ng><span style="font-size: 12.0pt\; mso-ascii-font-family: Aptos\; mso-far east-font-family: 'Times New Roman'\; mso-hansi-font-family: Aptos\; mso-b idi-font-family: 'Times New Roman'\; color: black\; mso-font-kerning: 0pt\ ; mso-ligatures: none\;">&nbsp\;As a robot manipulates 3D objects and navi gates within 3D scenes\, it requires spatial reasoning to ensure safe plan ning. Recent advances in 3D scene representation\, such as Neural Radiance Fields (NeRFs) and Gaussian Splatting\, provide high-fidelity digital twi ns of arbitrary real-world environments from multi-view images. In the fir st part of the talk\, <strong>Dr. Firoozi</strong> will discuss employing these 3D visual fields augmented to 3D vision-language fields using intern et-scale semantic representations from Vision-Language Models (VLMs) for o pen-vocabulary robot planning.</span></p>\n<p class="MsoNormal" style="bac kground: white\;"><span style="font-size: 12.0pt\; mso-ascii-font-family: Aptos\; mso-fareast-font-family: 'Times New Roman'\; mso-hansi-font-family : Aptos\; mso-bidi-font-family: 'Times New Roman'\; color: black\; mso-fon t-kerning: 0pt\; mso-ligatures: none\;">&nbsp\;</span><span style="font-si ze: 12.0pt\; mso-ascii-font-family: Aptos\; mso-fareast-font-family: 'Time s New Roman'\; mso-hansi-font-family: Aptos\; mso-bidi-font-family: 'Times New Roman'\; color: black\; mso-font-kerning: 0pt\; mso-ligatures: none\; ">As the robot interacts with other dynamic agents in the scene (multi-age nt settings)\, it also requires temporal reasoning to ensure safe interact ive planning. In the second part of the talk\, <strong>Dr. Firoozi</strong > will discuss safe and fault-resilient planning techniques across two cat egories of interactive planning: (i) Model Predictive Control (MPC)\, wher e the prediction and planning steps are decoupled\, and (ii) more abstract approaches such as game-theoretic planning\, where these steps are tightl y coupled. While MPC offers computational efficiency\, game-theoretic plan ning enables more complex modeling of agents' preferences and their mutual influences.</span></p> END:VEVENT END:VCALENDAR