BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240528T123240
DTSTART;TZID=America/Detroit:20240603T103000
DTEND;TZID=America/Detroit:20240603T123000
SUMMARY:Presentation:Learning and Inference for Adaptable Manipulation Planning
DESCRIPTION:Committee Chair: Dmitry Berenson\n\nAbstract:\nA central challenge for developing general-purpose robot assistants is the development of algorithms for robot manipulation that can perform a wide range of tasks across a diverse set of environments. This thesis develops planning and trajectory optimization methods that can adapt to new and unforeseen systems. The key to these methods is the ability of robots to learn from experience and reason about related uncertainty. Using modern machine learning and approximate probabilistic inference techniques\, the work in this thesis improves the ability of planning methods to do so. \n\nProbabilistic inference is useful in two ways. First\, by using a probabilistic framing\, probabilities can be used as a way of expressing confidence in our current models. I develop a method that learns to predict the uncertainty of a given dynamics model with a small amount of data collected online and avoids areas where the model is uncertain. I also propose an approach that learns a generative model of control sequences to complete a given task. I demonstrate that we can detect and adapt this generative model to situations where the environment differs from the training environments. \n\nSecond\, I incorporate probabilistic inference into the proposed methods by viewing planning itself as an inference problem. By framing planning as inference\, we construct probability distributions over trajectories. This framework allows me to develop a method that views constrained trajectory optimization as inference\, generating diverse sets of constraint-satisfying trajectories for completing manipulation tasks. This allows improved adaptation to online disturbances\, since at any given time\, there is a set of trajectories to select from. I demonstrate the effectiveness of this method on several different tasks\, including a 7DoF manipulator turning a wrench and a 16DoF multi-fingered hand turning a precision screwdriver.
UID:122330-21848612@events.umich.edu
URL:https://events.umich.edu/event/122330
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Engineering,Michigan Robotics,Robotics
LOCATION:Ford Robotics Building - 2300
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20240618T123126
DTSTART;TZID=America/Detroit:20240603T130000
DTEND;TZID=America/Detroit:20240603T140000
SUMMARY:Careers / Jobs:Coffee Chats for Grad Students: Creating a Compelling Resume
DESCRIPTION:We are offering a number of virtual coffee chats for the graduate student community this summer\, hosted by Rackham’s embedded University Career Center career counselors. The topic for this session is resumes. Are you interested in articulating your academic experiences to applyfor opportunities beyond the professoriate? Whether you are looking to improve your current resume or build one from scratch\, this session will provide you with strategies to help you craft a compelling resume that showcases your experiences\, talents\, and skills. Register here: https://sessions.studentlife.umich.edu/track/event/session/79128
UID:122355-21848650@events.umich.edu
URL:https://events.umich.edu/event/122355
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:
LOCATION:
CONTACT:
END:VEVENT
END:VCALENDAR