BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240314T172651Z UID:922AA752-A5C0-44A1-94B1-71AD9C244D89 DTSTART;TZID=America/Los_Angeles:20240313T183000 DTEND;TZID=America/Los_Angeles:20240313T200000 DESCRIPTION:Balancing performance and safety are crucial to deploying auton omous vehicles in multi-agent environments. In particular\, autonomous rac ing is a domain that penalizes safe but conservative policies\, highlighti ng the need for robust\, adaptive strategies. Current approaches either ma ke simplifying assumptions about other agents or lack robust mechanisms fo r online adaptation. In this talk we will explore research themes on perce ption\, planning and control at the limits of performance. We explore:\n\n (1) How to generate the most competitive agents who dynamically balance sa fety and assertiveness by using distributionally robust online adaptation and Game-theoretic planning\n(2) How to be better-than-the-best using imit ation learning with multiple imperfect experts\n(3) Using invertible neura l networks to solve inverse problems in localization and SLAM\n(4) How to build the most efficient autonomous racecar with Multi-domain optimization across vehicle design\, planning and control\;\n\nWe realize all our rese arch in the [https://f1tenth.org](https://f1tenth.org/) autonomous racecar platform that is 10th the size\, but 10x the fun! The main takeaway from this talk is how you can get involved in very exciting research on safe au tonomous systems. I will also present projects on AV Gokart that we are do ing in the Autoware Center of Excellence for Autonomous Driving.\n\nSpeake r(s): Rahul Mangharam\, \n\nVirtual: https://events.vtools.ieee.org/m/3998 72 LOCATION:Virtual: https://events.vtools.ieee.org/m/399872 ORGANIZER:dt@ieee.org SEQUENCE:27 SUMMARY:MAD Games - Multi-Agent Dynamic Games: What can you learn from Auto nomous Racing? URL;VALUE=URI:https://events.vtools.ieee.org/m/399872 X-ALT-DESC:Description: <br /><p>Balancing performance and safety are cruci al to deploying autonomous vehicles in multi-agent environments. In partic ular\, autonomous racing is a domain that penalizes safe but conservative policies\, highlighting the need for robust\, adaptive strategies. Current approaches either make simplifying assumptions about other agents or lack robust mechanisms for online adaptation. In this talk we will explore res earch themes on perception\, planning and control at the limits of perform ance. We explore:&nbsp\;</p>\n<p>(1) How to generate the most competitive agents who dynamically balance safety and assertiveness by using distribut ionally robust online adaptation and Game-theoretic planning&nbsp\;<br>(2) How to be better-than-the-best using imitation learning with multiple imp erfect experts<br>(3) Using invertible neural networks to solve inverse pr oblems in localization and SLAM&nbsp\;<br>(4) How to build the most effici ent autonomous racecar with Multi-domain optimization across vehicle desig n\, planning and control\;&nbsp\;</p>\n<p>We realize all our research in t he <a href="https://f1tenth.org/">https://f1tenth.org</a> autonomous racec ar platform that is 10th the size\, but 10x the fun! The main takeaway fro m this talk is how you can get involved in very exciting research on safe autonomous systems. &nbsp\;I will also present projects on AV Gokart that we are doing in the Autoware Center of Excellence for Autonomous Driving.< /p> END:VEVENT END:VCALENDAR