[Theory] REMINDER: 10/19 TTIC Colloquium: Anca Dragan, UC Berkeley

[Mary Marre]

*When:*      Monday, October 19th at 11:10 am



*Where:*     Zoom Virtual Talk (*register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_mhE2QB-YTCe9aaoc2OFDQA>*)



*Who: *       Anca Dragan, UC Berkeley



*Title:*        Getting Human-Robot Interaction Strategies to Emerge from
First Principles


*Abstract:* One of the most exciting things for me in robotics is when
robots find interesting strategies for how to interact with the world, like
navigating closer to a wall to help localization, as solutions to the
sequential decision-making problems they are faced with. I want robots to
be able to do the same when interacting with people, and much of my work to
date has been about formulating HRI problems and modeling/learning enough
about people for that to happen. I'd like to use this talk as an
opportunity to reflect on some of the things we've been able to accomplish
so far -- cars figure out how to negotiate intersections and merges, robots
figure out how to use their physical actions to probe for information, and
they automatically become more conservative when they are wrong as a
consequence of having the right uncertainty -- and on the road ahead.



*Host:* Matthew Walter <mwalter at ttic.edu>

For more information on the *colloquium* series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Sun, Oct 18, 2020 at 3:13 PM Mary Marre <mmarre at ttic.edu> wrote:

>
> *When:*      Monday, October 19th at 11:10 am
>
>
>
> *Where:*     Zoom Virtual Talk (*register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_mhE2QB-YTCe9aaoc2OFDQA>*
> )
>
>
>
> *Who: *       Anca Dragan, UC Berkeley
>
>
>
> *Title:*        Getting Human-Robot Interaction Strategies to Emerge from
> First Principles
>
>
> *Abstract:* One of the most exciting things for me in robotics is when
> robots find interesting strategies for how to interact with the world, like
> navigating closer to a wall to help localization, as solutions to the
> sequential decision-making problems they are faced with. I want robots to
> be able to do the same when interacting with people, and much of my work to
> date has been about formulating HRI problems and modeling/learning enough
> about people for that to happen. I'd like to use this talk as an
> opportunity to reflect on some of the things we've been able to accomplish
> so far -- cars figure out how to negotiate intersections and merges, robots
> figure out how to use their physical actions to probe for information, and
> they automatically become more conservative when they are wrong as a
> consequence of having the right uncertainty -- and on the road ahead.
>
>
>
> *Host:* Matthew Walter <mwalter at ttic.edu>
>
> For more information on the *colloquium* series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Mon, Oct 12, 2020 at 5:54 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:*      Monday, October 19th at 11:10 am
>>
>>
>>
>> *Where:*     Zoom Virtual Talk (*register in advance here
>> <https://uchicagogroup.zoom.us/webinar/register/WN_mhE2QB-YTCe9aaoc2OFDQA>*
>> )
>>
>>
>>
>> *Who: *       Anca Dragan, UC Berkeley
>>
>>
>>
>> *Title:*        Getting Human-Robot Interaction Strategies to Emerge
>> from First Principles
>>
>>
>> *Abstract:* One of the most exciting things for me in robotics is when
>> robots find interesting strategies for how to interact with the world, like
>> navigating closer to a wall to help localization, as solutions to the
>> sequential decision-making problems they are faced with. I want robots to
>> be able to do the same when interacting with people, and much of my work to
>> date has been about formulating HRI problems and modeling/learning enough
>> about people for that to happen. I'd like to use this talk as an
>> opportunity to reflect on some of the things we've been able to accomplish
>> so far -- cars figure out how to negotiate intersections and merges, robots
>> figure out how to use their physical actions to probe for information, and
>> they automatically become more conservative when they are wrong as a
>> consequence of having the right uncertainty -- and on the road ahead.
>>
>>
>>
>> *Host:* Matthew Walter <mwalter at ttic.edu>
>>
>> For more information on the colloquium series or to subscribe to the
>> mailing list, please see http://www.ttic.edu/colloquium.php
>>
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 517*
>> *Chicago, IL  60637*
>> *p:(773) 834-1757*
>> *f: (773) 357-6970*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20201019/63bb3856/attachment-0001.html>