From aaai97-owner@cc.gatech.edu Fri Feb 14 06:38:18 1997
Date: Fri, 14 Feb 1997 06:13:22 -0500 (EST)
From: arkin@cc.gatech.edu (Ronald Arkin)
Message-Id: <199702141113.GAA08565@arkin.cc.gatech.edu>
To: aaai97@cc.gatech.edu
Subject: Complete Rules for Find Life on Mars Event
Cc: arkin@cc.gatech.edu
Sender: owner-aaai97@cc.gatech.edu
Precedence: bulk
Status: RO
Attached below are the complete rules for the find-life-on-mars event.
Anyone who is interested in competing in this event and has questions
regarding the rules should contact Reid Simmons (reids+@cs.cmu.edu)
for clarification.
N.B. These are not the absolute final rules. Competitors will have one
month to bring up issues with the rule committee prior to their
solidification.
Good luck!
- Ron
================================================================
AAAI-97 Mobile Robot Competition Event 1
Draft of February 13, 1997
Comments to reids@cs.cmu.edu
Event 1: Find life on Mars
Mission Objectives
==================
This task is inspired by the upcoming Pathfinder Mission to Mars, as well as
the tantalizing (albeit limited) possibility of life on Mars as depicted by
the recent meteorite analysis. Your mission, should you decide to accept it,
is to explore a large area of Mars, looking for signs of past and current
life, and return the life-forms, and only those life-forms, to the lander for
further analysis. From satellite imagery, we have some clues as to where life
may exist, but it is up to you to make a thorough exploration before your
batteries run dead.
Event Specifics
===============
The robot will be placed in a large physically bounded area. The arena will
be several hundred square feet (approximately 30x40'), with lexan walls
delimiting the boundaries (the robot landed in a crater). In about the center
of the arena will be a small enclosed pen with two openings (the "lander").
The floor of the arena will be littered with a variety of small objects: both
small and large (> 20cm in height) rock-like objects (distinguished by their
shape and color), different colored and shaped immobile objects ("past
life-forms") and a few squiggle balls ("present life-forms"). The openings of
the pen will have small lips (size TBD) to prevent the squiggle balls from
escaping. Currently, we anticipate two types of immobile objects (spheres and
cubes), with five different colors for each shape.
The robot will start adjacent to the pen. The objective is for it to collect
as many of the colored objects and squiggle balls in the given time (5-10
minutes), and deposit them in the pen, sorted by mobility (that is, one door
of the pen is for squiggle balls, the other is for all the different colored
objects). Penalties are given for mixing mobile and non-mobile objects in the
pen, and for putting the rock-like objects in the pen. Penalties are also
given for colliding with any of the large rock-like objects (the Mars rover is
fragile!)
Teams of multiple robots may enter the contest, but the overall score will be
divided by the total number of the robots used in the contest. This
normalization will hopefully prevent teams from doing well simply by having
swarms of robots. The idea is to have teams demonstrate that multiple robots
actually have a super-linear scaling effect on task performance.
Before the contest begins, maps will be provided showing where certain colored
objects and large rock-like objects *may* be located. These maps, which are
not guaranteed to be totally accurate, may be used by the robots to help them
decide where to explore. The intention is to structure the event so that it
would be difficult for an entry to explore the whole arena in the time
allotted (for example, each trial may decrease the length of the event).
In addition, certain areas of the arena will be "danger zones", where travel
within the zone will add penalty points. The danger zones will be marked by
laying colored paper on the floor (exact color TBD, depending on the natural
color of the exhibition hall floor), and also by marking the location within
the map.
Scoring
=======
General
=======
Each trial will run for a predetermined length (5-10 minutes). Points and
penalties will be given as described below. Team score will be divided by
the number of robots in the team.
There will be separate categories for robots with and without manipulators,
each with separate awards. Robots without manipulators will have to either
touch, or get within a predetermined distance (say, 6 inches) of an object,
and announce that they have spotted that type of object. In the
non-manipulator category, robots do not actually have to return the objects to
the lander. Let us know whether you feel that the robots should actually have
to touch the objects.
In all trials, points will be awarded for the *first* object of a given
shape/color, and then a different (typically smaller, but it may be the same)
number of points will be awarded for each subsequent object of that particular
shape/color. This is to encourage robots to find a diversity of "life-forms".
No modifications to the "Martian" environment will be allowed (rock-like
objects, "life-forms", danger zones, surrounding walls), although
modifications to the "lander" itself will be allowed for penalty points.
Several trials will be held, of increasing difficulty. The task itself will
not change between trials, only the complexity of the environment (and one
aspect of scoring). The parameters of the environment that can change are:
number of different colored objects (some trials may have fewer different
colors); density of rocks; density of "life-forms"; accuracy of the a priori
map; placement of objects (e.g., certain objects may be surrounded on three
sides by rocks and/or danger zones to make it harder to get at them). Another
parameter that may be altered is the ratio between the number of points
awarded for the first object of a given type, and the subsequent ones.
Probably, the points will be equal for the first trial, but for other trials
the first object will be worth significantly more points.
Note that we will not alter all the above parameters, and certainly not all at
once. We will decide which parameters to alter based on the feedback we get,
if any, over the months leading up to the competition and how well teams are
doing during the competition itself.
Teams will start out with 500 points. For each point/penalty category list
below, the number in [brackets] is a first guess at the point value, but this
will be undoubtedly refined over the coming months (and may, in fact, change
from trial to trial). We encourage feedback on whether the scoring is deemed
"fair".
Points
======
TBD number of points [20] for picking up the first of a given type of colored
object ("past life-form")
TBD number of points [10] for picking up subsequent objects a given type.
TBD number of points [50] for picking up the first squiggle ball ("present
life-form")
TBD number of points [40] for picking up subsequent squiggle balls a given type
TBD number of points [50] for placing the first of a given type of colored
object in the pen ("lander")
TBD number of points [25] for placing subsequent objects in the pen
TBD number of points [100] for placing the first squiggle ball in the pen
TBD number of points [80] for placing subsequent squiggle balls in the pen
Penalties
=========
TBD penalty points [20] for placing an object in the wrong door of the pen
TBD penalty points [40] for placing a rock-like object in the pen
TBD penalty points [5] for colliding with a large rock-like object
TBD penalty points [20] for traveling within a danger zone
TBD penalty points [100] for passively marking the pen and/or the openings of
the pen
TBD penalty points [200] for actively marking the pen and/or the openings of
the pen with beacons
TBD penalty points [50] for supplying your own doors to the pen
TBD penalty points [50] for breaking a squiggle ball (remember the Prime
Directive!)
NOTE: Squiggle balls can be purchased from The Scientific Revolution
at 415-322-1876 or at your local scientific or toy stores.