For your perusal, the Co-chairs of the AAAI-97 Mobile Robot Competition are providing *Draft* versions of several events under consideration for the upcoming conference. They are:
1. The contemporary, Find life on Mars event
2. The equally important, Find the remote control event
3. Home vacuum (topic of a previous AAAI symposium).
Here is also a fourth event that will be held at the reception and judged by the attendees:
4. Hors d'oeuvres anyone? (thanks to Dave Miller)
Sketchy descriptions of each follow. Do not get hung up on the rules now, these will be formulated in detail later within rules committees. It is likely that only two of the top three will be held, so we'd like your feedback as soon as possible. We also intend to have separate rules committees for each of these events (if we get enough volunteers).
What we'd like from you at this point is the following:
A. A brief *one sentence* description of what you think of each event. We do not want extended reviews.
B. Whether or not you think you would be willing to compete in each event.
C. Whether or not you would like to serve on the rules committee of an event in which you do not plan on competing.
That's it for now.
Reply to Ronald Arkin.
This is a DRAFT. The actual event will look similar to this, but may have some differences. If you have any comments on this please contact us. We are very open to suggestions on how to improve the event or the scoring and how to accommodate the greatest number of robots.
Event 1: Find life on Mars
This mission 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. There has also been recent emphasis by the U.S. Administration on robotic missions to Mars, so why not start at AAAI?
The robot will be placed in a large physically bounded area. In the area with the robot will be a variety of objects: unmodeled rock-like obstacles (both large and small), unusual small objects (unusual by virtue of color or shape) and moving martians (squiggle balls). A significant number of the rocks will be small and movable, thus a blind sweeping of everything in the area would gather significantly more garbage than actual life-forms, so a random strategy of picking up everything will not work.
The robot will start at a given location within the area near the center where the lander is located. The lander itself will be a pen capable of containing the retrieved martian samples. As power is at a premium, and time is of the essence (who knows what those Martians are up to), the robot's goal is to explore the unmapped area surrounding the lander in the most efficient manner possible, retrieving as many of the martian life forms to the lander as possible in the time allotted. The items retrieved will also need to be sorted into 3 possible classes: moving, stationary-1, and stationary-2.
It may be that some life-forms are located underneath rock-like objects. There will be clues to their presence, such as obvious trails or deposits ("martian droppings") which can be used to determine which small rocks are worth knocking over (a simple but firm bump would be adequate to expose them).
There will be a maximum limit to the physical size of the robot or robots used based upon the launch requirements. Multiagent entries are acceptable but the total volume of robotic hardware on Mars cannot exceed * cubic feet.
TBD
There will be two classes of winners: Those robots that retrieve the most objects, and those that most accurately map where the objects are located (not the whole world, just the objects of interest). The map will be of use for future missions, or high-powered orbiting telescopes to focus upon (it is expensive to return objects from Mars after all). An entry can compete in one or both categories if desired.
Details TBD
Penalties will be assessed for misclassifying objects (as this would gum up the processing machinery), or dropping a life form.
Returning non-life form material to the lander also results in a penalty.
Questions or comments to: See "What we'd like to hear . . ."
NOTE: Squiggle balls can be purchased from The Scientific Revolution at 415-322-1876 or at your local scientific or toy stores.
This event is inspired by the need for robot assistants to perform 'fetch-it' tasks in partially known environments. Imagine a robot assistant helping a handicapped person around the home. The person might ask the robot to fetch an orange, the TV remote, a cup of coffee, and so on. While the robot may not know where all of these items are initially, over time it will learn roughly where they are kept.
The event will take place in an arena that contains tables, chairs, and shelves at varying heights. Scattered throughout the area, on the floor, the shelves, and the tables, will be 12 different objects. The robot will start the event near a human sitting in a chair (ie. judge) who will ask the robot to fetch three items. Once these items have been returned, the human will ask for three more items. The winner will be the robot that can find and return the most items in the allotted time.
Questions or comments to: See "What we'd like to hear . . ."
This is a DRAFT. The actual event will look similar to this, but may have some differences. If you have any comments on this please contact us. We are very open to suggestions on how to improve the event or the scoring and how to accommodate the greatest number of robots.
Event 3: Home Vacuum (inspired by an earlier AAAI Symposium and Pete Bonasso's paper "What Good is your Vacuuming Robot's Intelligence?")
This task involves the creation of a robot (or robots) that are capable of effectively cleaning a one-bedroom (or studio) apartment - complete with natural furniture. The robotic system is assumed to start within a closet in the bedroom. "Dirt" confetti will be uniformly scattered throughout the two rooms. There will be some regions of high concentration of dirt as well. The robot's task is to come out during the day, while the owner is at work, and clean-up the apartment. This should involve vacuuming under furniture (it may be moved as long as it's replaced) and in corners. Additional points will be provided for vacuuming the sofa. A map will be available of the apartment, including the layout of the furniture.
The robot must return back to its home closet upon completion and discharge its dust into a suitable receptacle (competitor defined).
TBD
Judging will be based on time to complete the task and the overall cleanliness of the room upon completion.
Questions or comments to: See "What we'd like to hear . . ."
This is a DRAFT. The actual event will look similar to this, but may have some differences. If you have any comments on this please contact us. We are very open to suggestions on how to improve the event or the scoring and how to accommodate the greatest number of robots.
Event 4: Reception hors d'oeuvres server (concept thanks to Dave Miller)
This event will occur at the AAAI main reception where there will be heavy interaction with the attendees. Judging will be conducted by the attendees. The goal is to provide solid refreshments to the attendees in close quarters. Safety and self-protection are paramount. A human escort (only one allowed per team within the area) will always be nearby for safety and control of the robot (i.e., if it moves out of the designated area), but is limited in their interaction with the attendees (just how is yet to be determined). The robots must be fully autonomous. The escort will also replenish the hors d'oeuvres on an as needed basis.
Preliminaries will be conducted prior to the reception to ensure that the robots are safe: both from harming the attendees as well as for their own self-protection.
At the reception, a large area will be available to which the robots are confined (the size of the area will be available ahead of time). Attendees will be milling about taking hors d'oeuvres from off the robotic servers. All robots must be capable of carrying a standard tray. Human interaction is the key to success. The robots must move about autonomously within the reception area and can interact by speech, vision, tactile, infrared, or whatever with potential servees. Personality counts here. If needed the number of attendees in the area will be regulated to prevent overcrowding.
Additionally, there may also be a more formal judging by official judges who review the robots at their task in a more rigorous setting (not popularity). Safety, human interaction, and efficiency count here.
Attendees entering the area will receive one token that they can drop in a box corresponding to their favorite server at the exit of the reception. This is analogous to tipping (little batteries are a possibility). The winners will be selected by the largest number of tips.
Rules for other performance judging will be developed later.
Questions or comments to: See "What we'd like to hear . . ."