news

Clarifications1-09

2009-10-07T02:47:38Z

Hi all,

I've had some questions about assignments 2 and 3, and I thought I'd post the answers here for everyone.

In assignment 2, Q 2.1 I ask you to describe the state space you'd use. Perhaps the easiest way to clarify this question is to answer it for the RoboCup AIBOs. For the Baysian filter in that system the state space consists of 16 dimensions: X, Y and Theta for each robot, as well as the 2D position and velocity of the ball.

In assignment three I was asked to clarify what I meant by 'pause' when the robot thinks it is over a marked point. I would prefer if the robot didn't move its head about. I'll need to mark the position under the robots shoulders, and that is easier if the head isn't moving.

Will

Welcome 2009

2009-07-15T04:05:45Z

Welcome to Semester 2 2009.

Classes start next Tuesday (21st July) at 11am in Quadrangle 1046 (K-E15-1046).

Feedback please

2008-10-19T23:35:50Z

Hi all,

The University is running its CATEI evaluations again. This is another opportunity for you to give feedback on my course. (Feedback is welcome outside of CATEI too.)

I really appreciate all feedback. Positive feedback helps me convince NICTA to keep running the course. Constructive negative feedback lets me know how to improve the course for future years. Even if you loved the course, please let me know of any suggestions for improvement in the comments section.

Be well,

Will

Here is a, slightly edited, excerpt from the announcement mail I received (and everyone enrolled in the course should have received a similar one):

Students can access evaluation form(s) by login into myUNSW, click the CATEI icon in the left menu bar on my survey area.

Only those students who have yet to finish all forms will be sent reminders in the UNSW email account.

If you require any further information, please contact your school CATEI coordinator:

John Shepherd - School of Computer Science

Bill Wilson - School of Computer Science

Colin Taylor - School of Computer Science

Exam Time & Place

2008-10-14T23:32:11Z

The exam will be 3 hours.

It will be held on the morning of Monday 3rd November in room ASB 220.

You should be there by 8:45am, and it should end around noon.

The exam is open book. A calculator is allowed and may be useful for some questions. You are not allowed to use any communications device to communicate with another human during the exam.

Relevant talk...

2008-09-09T02:39:42Z

The seminar-ai@cse mailing list announces talks that people in this class might find interesting. For example, here is an announcement for Thursday:

Dear All,

Announcing a New AI Seminar. The details are:

Title: Model-based Programming of Robust Agile Systems

Presenter: Brian C. Williams

Presenter URL: http://people.csail.mit.edu/williams/Web%20site/williams.shtml

Affiliation: Model-based Embedded and Robotic Systems, Massachusetts Institute of Technology

Affiliation URL: http://groups.csail.mit.edu/mers/mers.htm

Date: Thursday 11th September 2008

Time: 12:00:00

Location: CSE Seminar Room, Level 1, K17

Abstract: Autonomous, self-repairing explorers, such as deep space probes, have successfully performed complex missions by employing model-based executives that continuously monitor mission goals, diagnose failures and plan repairs. These executives employ models encoded as probabilistic constraint automata, in order to observe and control the hidden states of the system. These executives have also been incorporated within model-based programming languages that facilitate the creation of a wide range of fault adaptive systems, including automobiles and naval ships.

Future explorers, such as autonomous air vehicles and walking robots, will require far greater agility, in order to robustly achieve their missions. For example, to avoid falling, a walking robot must quickly detect a loss of balance, and replan its control trajectory appropriately. This talk presents recent advances in model-based programming and execution for agile systems. First, to reason about a system~Rs dynamics, these executives employ probabilistic constraint automata that are extended to hybrid discrete/continuous constraints. Second, to robustly achieve missions, these executives employ planning methods that reason about continuous, as well as discrete, state changes, and employ compilation and model-predictive control methods in order to adapt on the fly. Finally, these executives employ estimation methods for hybrid PHA that detect subtle failures through active control. Model-based execution is demonstrated both on a team of cooperative air vehicles and a biped walking machine.

Biography of Speaker: Professor Williams leads the Model-based Embedded and Robotic Systems http://mers.csail.mit.edu/mers.htm group, within the Computer Science and Artificial Intelligence Laboratory http://www.csail.mit.edu/index.php(CSAIL) at the Massachusetts Institute of Technology http://web.mit.edu/. His research concentrates on model-based autonomy http://ic-www.arc.nasa.gov/ic/project/mba/index.html -- the creation of long-lived systems that explore autonomously, while commanding, diagnosing and repairing themselves using fast, commonsense reasoning. Current research focuses on model-based programming and cooperative robotics: Model-based programming supports goal-directed programming of robust explorers and everyday devices, by incorporating model-based deductive capabilities within traditional embedded programming languages. Cooperative robotics extends model-based autonomy to robotic networks of cooperating space, air, land and undersea vehicles, on Earth and on other planets.

Professor Williams received his S.B., S.M and Ph.D. in Computer Science and Electrical Engineering at MIT, and worked at the Xerox Palo Alto Research Center and NASA Ames Research Center, prior to joining the faculty at MIT. He is a pioneer in the fields of qualitative reasoning, model-based diagnosis and autonomous systems. He received a NASA Space Act Award for Remote Agent, the first fully autonomous, self-repairing space explorer, demonstrated onboard the NASA Deep Space One probe in May, 1999. He was a member of the Tom Young Blue Ribbon Team in 2000, assessing future Mars missions in light of the Mars Climate Orbiter and Polar Lander incidents, and is currently a member of the Advisory Council of the NASA Jet Propulsion Laboratory at Caltech. He has won four best paper prizes for his research in diagnosis, qualitative algebras, propositional inference and soft constraints. He is a fellow of AAAI, has served as guest editor of the Artificial Intelligence Journal http://www.elsevier.nlinca/publications/store/5/0/5/6/0/1/ and has been on the editorial boards of the Journal of Artificial Intelligence Research http://www.jair.org/, and MIT Press.

Host: Toby Walsh

Seminar Convenor: Van Hai Ho

Thankyou

Assignment 2

2008-09-03T03:53:04Z

Assignment 2 has been released. Not all the work in that assignment has been covered yet, but will be at least a week before the assignment is due.

Assignment 1

2008-08-19T10:17:39Z

Hi all, A few notes on Assignment 1. All of this has been mentioned in class - I'm just documenting it here.

The assignment is the same as last year, so you can use last year's assignment sheet: assign1-2007.pdf
The due date on the assignment sheet from last year is wrong (that's last year's due date). Use the one on the lecture plan instead.
The due date of the assignment has changed. You have an extra week now. It is now due at the start of the week 6 lab (and will be marked in that lab).

If anyone does not have a group for the first assignment they should see me ASAP!

Be well,

Will :-}

Timetable Changes

2008-07-27T23:51:33Z

Hi all,

Just a quick note about what happened at the timetabling meeting last Thursday.

There were no clash-free times to move the Thursday class to. (Monday afternoon was best, but wasn't any better than the current time, and I'd prefer to leave things as they are if possible.)
I found out that one of the other classes that was clashing is planning to move, and it appears it is easier for them to move than for us.
I am trying to expand the size of the 11am lab on Tuesday and cancel the noon lab. Noone at the meeting had a problem with this and it will make things run more smoothly.

Overview: No changes in lecture times. I'm looking to cancel the noon lab and just run the 11am lab.

See you all tomorrow,

Will

Pages from old wiki

2008-07-23T01:41:24Z

I've moved web pages across from the old rUNSWift and COMP3431 wikis. Currently all the ported pages are linked from the AIBO page. You'll also find them in the Site Map link.

These pages are all in the wrong wiki format for this wiki. This wiki uses Markdown as its format. The previous wiki used the Trac wiki format. At the moment you'll just see the raw Trac wikitext, but it is still very readable. Feel free to convert what you want.

Week 0 location

2008-07-23T01:22:47Z

Just a quick note to confirm the location for tomorrow's timetabling meeting: ASB 219 (ASB == Australian School of Business). This is the currently timetabled location for the Thursday class for the rest of semester.

Be well,

Will