|
|
CS294A
STAIR: STanford AI Robot project
Winter 2009
|
- The first class met on Wednesday January 7th.
If you were unable to attend this but would like to
take CS294A, please email us at
cs294a-qa@cs.stanford.edu
to let us know, so that we can help you find a project for the class.
|
STAIR Project Description
|
Many of us already have robots in our homes today. They're called the
dishwasher, the washing machine, and the dryer. We believe that a
revolution in robotics will come when, instead of building such
special-purpose robots, we can instead build a single robot
that can carry out a wide range of tasks. In the STAIR (STanford Artificial
Intelligence Robot) project, we seek to build such a robot, and
spark off this revolution in robotics.
Concretely, within a decade we hope to develop the technology that'll make
it useful to put a general-purpose robot into every home. We envision
a single robot that can carry out tasks such as:
- Fetch a book or a person from an office, in response to a verbal request.
- Tidy up a living-room after a party, including picking up and throwing away
trash, and loading the dishwasher.
- Using multiple tools (screwdriver, hammer, pliers, etc.) as
needed, assemble a bookshelf.
- Prepare simple meals using a normal household kitchen.
A robot capable of these tasks will revolutionize home and office automation, and have important applications ranging from machine shop assistants to elderly care.
However, building such a robot will require significant advances in AI.
Since its birth in 1956, the AI dream has been to build systems that
exhibit broad-spectrum competence and intelligence.
However, AI has since splintered into many different subfields, such as
machine learning, vision, navigation, manipulation, planning,
reasoning, and speech/natural language processing.
To realize the vision of a useful home and office assistant
robot, we will take and attempt to unify methods drawn from all
of these AI subfields. This is in distinct contrast to
the 30 year old trend of working on fragmented AI sub-fields,
and so we hope STAIR will also be a unique vehicle for driving
forward research towards true, integrated AI.
As a student in CS294A, you will help spearhead these advances in AI.
Course Instructor:
Andrew Ng.
(ang@cs.stanford.edu)
Class meetings:
This is a project course. There will be no homeworks and no weekly lectures, and we
will instead spend the quarter working in teams on different STAIR-related
research projects (such as computer vision, robot manipulation,
spoken dialog/NLP, planning, learning, etc.).
The whole class will meet on 7th January (4.15pm-5.30pm, Gates 120) and
11th Feb (4.15-5.30pm). Final project presentations will
be on 19th March (4.15-5.30pm). The instructor and TAs will also have smaller
weekly meetings with each project team.
If you were unable to attend the first meeting but would like
to take CS294A, please email
cs294a-qa@cs.stanford.edu
to let us know.
More information: