|
|
CS294B/CS294W
STAIR: STanford AI Robot project
Winter 2005
|
|
Announcements
|
(Last updated 12/21/05)
|
|
STAIR Project Description
|
Since its birth in 1956, the AI dream has been to build systems that exhibit broad-spectrum competence
and intelligence. In the STAIR (STanford AI Robot) project, we will build a robot that can navigate
home and office environments, that can pick up and interact with objects and tools, and that can
intelligently converse with and help people in these environments. Our single robot platform will
integrate methods drawn from all areas of AI, including machine learning, vision, navigation,
manipulation, planning, reasoning, and speech/natural language processing. This is in distinct
contrast to the 30 year old trend of working on fragmented AI sub-fields, and will be a unique vehicle
for driving forward research towards true, integrated AI.
Over the long term, we envision a single robot that can perform tasks such as:
- Fetching a book or a person from an office, in response to a verbal request.
- Tidying up a living-room after a party,
including picking up and throwing away trash, and placing dirty plates and
placing dirty plates and glasses in the dishwasher.
- Using multiple tools (screwdriver, hammer, pliers, etc.) as necessary to assemble a bookshelf.
- Showing guests around an active research lab (in which things change daily), answering questions and
keeping track of the entire group.
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, carrying out
such tasks will require significant advances in integrated learning, manipulation, perception,
spoken dialog, and reasoning.
In CS294B, we will work on these problems, and develop the first STAIR.
STAIR represents a collaboration among ten different research groups
in the Stanford AI Lab. You can also read more about STAIR in the following article.
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 on different STAIR-related AI research
projects (such as computer vision, robot manipulation, spoken dialog/NLP, learning, etc.).
The class' first meeting was on Wednesday 11th January morning. If had missed that
meeting but would like to take CS294B, please
email cs294b-qa@cs.stanford.edu
to let us know.
More information: