BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Denver
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:MDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:MST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241127T005341Z
UID:E0C20499-EC15-483C-B55A-C1F1227A2CEE
DTSTART;TZID=America/Denver:20241114T160000
DTEND;TZID=America/Denver:20241114T180000
DESCRIPTION:November 14\, 2024\, 4:00 PM – 6:00 PM (MDT)\n\nAI\, Robotics
 \, and Computation Presentations:\n\nMulti-modal communication in Multi-ta
 sk context\n\nGlobal Point Cloud Registration in Structured Scenes\n\nNavi
 gating the Energy Frontier: Efficient Motion Planning for Mobile Robots\n\
 nSpeaker(s): Yifei (Rena) Zhu\, Abolfazl Babanazari\, Tanmay Desai\n\nAg
 enda: \nNovember 14\, 2024\, 4:00 PM – 6:00 PM (MDT)\n\nYifei (Rena) Zhu
 \n\nColorado School of Mines\n\nPhD Student in Robotics\n\nRena is a third
 -year PhD student in Robotics in the Mines Interactive Robotics Research L
 ab at the Colorado School of Mines. Rena is interested in exploring human-
 centered design paradigms within Mixed/Augmented Reality and Human-robot i
 nteraction (HRI)\, and understanding what role MR/AR technology can\, and 
 should\, play in HRI through an interdisciplinary lens. Moreover\, Rena is
  interested in technology ethics\, AI ethics\, and technology policy\, and
  wants to explore how research efforts may impact society at large.\n\nPre
 sentation: Understanding Multi-modal communication in Multi-task context\n
 \nAbstract: Multiple Resource Theory suggests that the mind has largely di
 stinct types of cognitive resources associated with different sensory moda
 lities\, with subdivisions along a number of other dimensions. In this wor
 k we explore how the modality of communication used by task guidance syste
 ms meant to assist in multi-task contexts interacts with the modality of u
 nderlying tasks to determine overall cognitive load and task performance. 
 Our results suggest that users can strategically avoid overload by selecti
 vely attending to dimensions of multi-modal communication.\n\nAbolfazl Bab
 anazari\n\nColorado School of Mines\n\nPhD in Computer Science\n\nAbolfazl
  is a graduate student currently pursuing a PhD in Computer Science at the
  Colorado School of Mines under supervision of Kaveh Fathian. Abolfazl has
  prior experience working in the medical field on stereo systems and devel
 oping AR systems for surgical navigation. Abolfazl&#39;s research interests in
 clude Linear Algebra\, Graph Theory\, and Optimization\, particularly in t
 heir applications to Robotics and Autonomy\, such as Simultaneous Localiza
 tion and Mapping (SLAM) and perception. Abolfazl is currently focusing on 
 robust data association techniques from both a theoretical and practical a
 spect.\n\nPresentation: Global Point Cloud Registration in Structured Scen
 es\n\nAbstract: Point cloud registration\, especially without an initial t
 ransformation\, is crucial for many tasks in robotics and computer vision.
  When the corresponding parts of two point clouds are unknown\, the soluti
 on search space grows exponentially with the size of the point clouds. A w
 idely used approach to address this issue involves leveraging local surfac
 e properties around given points and matching these to corresponding point
 s across point clouds. While effective\, this technique struggles in envir
 onments with repetitive patterns\, such as man-made structures\, urban are
 as\, or indoor settings\, where point-based matching methods can generate 
 associations with an extremely high outlier ratio. In this presentation\, 
 we explore the potential of using primitive mathematical shapes and the po
 ssibility of integrating them into existing Global Point-Based Registratio
 n (GPBR) algorithms. By reducing the number of associations and outlier ra
 tio\, this technique can significantly improve the accuracy and robustness
  of point cloud registration.\n\nTanmay Desai\n\nColorado School of Mines\
 n\nPhD student in Robotics\n\nTanmay is a second-year PhD student in Robot
 ics advised by Dr. Iris Bahar at the Colorado School of Mines. Tanmay is i
 nterested in exploring better motion planning algorithms and how can we ut
 ilize hardware accelerators specifically Field Programmable Gate Arrays (F
 PGAs) to get power efficient and faster convergence to controls in stochas
 tic environments.\n\nPresentation: Navigating the Energy Frontier: Efficie
 nt Motion Planning for Mobile Robots\n\nAbstract: Mobile robots often stru
 ggle with the computational demands of sampling-based motion planning algo
 rithms. This research explores the potential of FPGAs as a more energy-eff
 icient alternative to GPUs. By leveraging their parallel architecture and 
 hardware-specific optimizations\, FPGAs could significantly improve the pe
 rformance-per-watt ratio of motion planning systems.\n\nRoom: 222\, Bldg: 
 Marquez Hall\, 1600 Arapahoe St\, Golden\, Colorado\, United States\, 8040
 1
LOCATION:Room: 222\, Bldg: Marquez Hall\, 1600 Arapahoe St\, Golden\, Color
 ado\, United States\, 80401
ORGANIZER:gowansj@ieee.org
SEQUENCE:2
SUMMARY:CIR\, CIS\, &amp; Mines: Triple AI\, Robotics and Computation Event
URL;VALUE=URI:https://events.vtools.ieee.org/m/445313
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;November 14\, 20
 24\, 4:00 PM &amp;ndash\; 6:00 PM (MDT)&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nb
 sp\;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;AI\, Robotics\, and Computation Pre
 sentations:&amp;nbsp\;&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;&amp;nbsp\;&amp;nbsp
 \; Multi-modal communication in Multi-task context&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=
 &quot;MsoNormal&quot;&gt;&lt;strong&gt;&amp;nbsp\;&amp;nbsp\; Global Point Cloud Registration in Stru
 ctured Scenes&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;&amp;nbsp\;&amp;nbsp\; Na
 vigating the Energy Frontier: Efficient Motion Planning for Mobile Robots&lt;
 /strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p
  class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;November 14\, 2024\, 4:00 PM &amp;ndash\; 6:00 PM (
 MDT)&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;
 &amp;nbsp\;&lt;strong&gt;Yifei (Rena) Zhu&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;
 &amp;nbsp\;&amp;nbsp\; &lt;em&gt;Colorado School of Mines&lt;/em&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;
 &gt;&lt;em&gt;&amp;nbsp\;&amp;nbsp\;&amp;nbsp\; PhD Student in Robotics&lt;/em&gt;&lt;/p&gt;\n&lt;p class=&quot;Mso
 Normal&quot;&gt;&amp;nbsp\;Rena is a third-year PhD student in Robotics in the Mines I
 nteractive Robotics Research Lab at the Colorado School of Mines. Rena is 
 interested in exploring human-centered design paradigms within Mixed/Augme
 nted Reality and Human-robot&amp;nbsp\;interaction (HRI)\, and understanding w
 hat role MR/AR technology can\, and should\, play in HRI through an interd
 isciplinary lens. Moreover\, Rena is interested in technology ethics\, AI 
 ethics\, and technology policy\, and wants&amp;nbsp\;to explore how research e
 fforts may impact society at large.&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&lt;stro
 ng&gt;Presentation: Understanding Multi-modal communication in Multi-task con
 text&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&lt;strong&gt;Abstract: &lt;/strong&gt;
 Multiple Resource Theory suggests that the mind has largely distinct types
  of cognitive resources associated with different sensory modalities\, wit
 h subdivisions along a number of other dimensions. In this work we explore
  how the modality of communication used by task guidance systems meant to 
 assist in multi-task contexts interacts with the modality of underlying ta
 sks to determine overall cognitive load and task performance. Our results 
 suggest that users can strategically avoid overload by selectively attendi
 ng to dimensions of multi-modal communication.&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;
 nbsp\;&amp;nbsp\;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Abolfazl&amp;nbsp\;Babanazari&lt;
 /strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&amp;nbsp\;&amp;nbsp\; &lt;em&gt;Colorado&amp;nbsp
 \;School of Mines&lt;/em&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;em&gt;&amp;nbsp\;&amp;nbsp\;&amp;nbsp\;
  PhD in Computer Science&lt;/em&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;Abolfazl is
  a graduate student currently pursuing a PhD in Computer Science at the Co
 lorado School of Mines under supervision of Kaveh Fathian. Abolfazl has pr
 ior experience working in the medical field on stereo systems and developi
 ng AR systems for surgical navigation. Abolfazl&#39;s research interests inclu
 de Linear Algebra\, Graph Theory\, and Optimization\, particularly in thei
 r applications to Robotics and Autonomy\, such as Simultaneous Localizatio
 n and Mapping (SLAM) and perception. Abolfazl is currently focusing on rob
 ust data association techniques from both a theoretical and practical aspe
 ct.&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&lt;strong&gt;Presentation: Global Point&amp;nb
 sp\;Cloud Registration in Structured Scenes&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNor
 mal&quot;&gt;&amp;nbsp\;&lt;strong&gt;Abstract:&lt;/strong&gt;&amp;nbsp\;Point cloud registration\, es
 pecially without an initial transformation\, is crucial for many tasks in 
 robotics and computer vision. When the corresponding parts of two point cl
 ouds are unknown\, the solution search space grows exponentially with the 
 size of the point clouds. A widely used approach to address this issue inv
 olves leveraging local surface properties around given points and matching
  these to corresponding points across point clouds. While effective\, this
  technique struggles in environments with repetitive patterns\, such as ma
 n-made structures\, urban areas\, or indoor settings\, where point-based m
 atching methods can generate associations with an extremely high outlier r
 atio. In this presentation\, we explore the potential of using primitive m
 athematical shapes and the possibility of integrating them into existing G
 lobal Point-Based Registration (GPBR) algorithms. By reducing the number o
 f associations and outlier ratio\, this technique can significantly improv
 e the accuracy and robustness of point cloud registration.&lt;/p&gt;\n&lt;p class=&quot;
 MsoNormal&quot;&gt;&amp;nbsp\;&amp;nbsp\;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Tanmay&amp;nbsp\;D
 esai&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;&amp;nbsp\;&amp;nbsp\; &lt;em&gt;Colorado
  School&amp;nbsp\;of Mines&lt;/em&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;em&gt;&amp;nbsp\;&amp;nbsp\;&amp;n
 bsp\; PhD student in Robotics&lt;/em&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&amp;nbsp\;Tanmay
  is a second-year PhD student in Robotics advised by Dr. Iris Bahar at the
  Colorado School of Mines. Tanmay is interested in exploring better motion
  planning algorithms and how can we utilize hardware accelerators specific
 ally Field Programmable Gate Arrays (FPGAs) to get power efficient and fas
 ter convergence to controls in stochastic environments.&lt;/p&gt;\n&lt;p class=&quot;Mso
 Normal&quot;&gt;&amp;nbsp\;&lt;strong&gt;Presentation: Navigating the Energy Frontier: Effic
 ient Motion Planning for Mobile Robots&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;
 &amp;nbsp\;&lt;strong&gt;Abstract:&lt;/strong&gt; Mobile robots often struggle with the co
 mputational demands of sampling-based motion planning algorithms. This res
 earch explores the potential of FPGAs as a more energy-efficient alternati
 ve to GPUs. By leveraging their parallel architecture and hardware-specifi
 c optimizations\, FPGAs could significantly improve the performance-per-wa
 tt ratio of motion planning systems.&lt;/p&gt;
END:VEVENT
END:VCALENDAR