For the past seven years collegiate teams, with the backing of industry and government have fielded autonomous flying robots in an attempt to perform missions that required robotic behaviors never before exhibited in a flying machine. In 1990, the term "Aerial Robotics" was coined by competition creator Robert Michelson to describe a new class of small highly intelligent flying machines. The successive years of competition saw these aerial robots grow in their capabilities from vehicles that could at first barely maintain themselves in the air, to the most recent automatons which are self-stable, self-navigating, and able to interact with their environment-- especially, objects on the ground.

The primary goal of the competition has been to provide a reason for the state-of-the art in aerial robotics to move forward. Challenges set before the international collegiate community have been geared to produce advances in the state-of-the-art at an evermore aggressive pace. The initial mission to move a metallic disc from one side of an arena to another with a completely autonomous flying robot was seen by many as almost impossible. Those lacking vision labeled the competition as a "crash and burn" event or a source of demoralization for the students, while pundits in the media predicted that it would be the year AD 2000 before that mission was achievable.

Just as an infant stumbles in its attempts to learn to walk, the college teams continued to improve their entries over the next two years when the competition saw its first autonomous takeoff, flight, and landing by a team from the Georgia Institute of Technology. Three years later in 1995 a team from Stanford University was able to acquire a single disk and move it from one side of the arena to the other in a fully autonomous flight-- half a decade earlier than some media predictions.

The competition mission was then toughened and made a bit less abstract by requiring teams to search for a toxic waste dump, map the location of partially-buried randomly-oriented toxic waste drums, identify the contents of each drum from the hazard labels found somewhere on the outside of each drum, and bring a sample back from one of the drums. Again the pundits threw up their hands and said that this was nearly impossible for a fully autonomous flying machine, particularly one made by university students.

That year, a team from the Massachusetts Institute of Technology and Boston University, with backing from Draper Labs, created a small fully autonomous flying robot that repeatedly and correctly mapped the location of all five of the toxic waste drums while correctly identifying the contents of two from the air, thereby completing approximately seventy five percent of the mission. In 1997 the mission was left the same, but some of the structure was removed to make it more realistic. The number of drums became an unknown a priori. In addition to radioactive and biohazardous toxic waste, a third category of explosive material was included and the retrieval of the sample became mandatory.

In a triumph of technology, a team from Carnegie Mellon University attacked the mission with a large helicopter-based robot and was able to identify the location of all drums as well as read the labels on each correctly. Their aerial robot came within centimeters of acquiring the sample on several runs. All of this was achieved from a fully-autonomous aerial robot that stayed aloft for more than twenty minutes per run and modified its actions in real-time based on what it learned about its environment.

As realistic as the mission of 1997 was, it was still highly structured. The arena was limited in extent, the number of target drum types was only three, the exact number of drums (though unknown) was guaranteed to be less than eleven. Still, the primary goal of the competition has been served in that the state-of-the-art has advanced by providing a reason and benchmarks to entice its move forward.

The International Aerial Robotics Competition has grown in stature over the past seven years to the point that corporations now seek teams to sponsor, major governmental agencies such as the U.S. Department of Energy and the U.S. Department of Defence support the event with personnel, judges, and funding for logistics. Top venues such as Walt Disney World seek to have the event hosted at their locations. The students who participate and develop entries that perform well are likewise recognized by industry and government observers as the best of the next generation of young engineering and computer scientists to hire.

Since the level of technical performance demonstrated to date has increased exponentially, the time has come to move the International Aerial Robotics Competition mission to a higher level of realism and attendant difficulty. The following paragraphs define the mission in general terms to allow potential entrants to plan and begin development.

The Earth is a violent planet regularly wreaking havoc upon mankind in the form of natural disasters. The nature of some groups of individuals is similarly violent and often mimics the mass destruction occasioned by natural forces. Between what befalls mankind apart from his control, and that which befalls him by his own hand, there is a seeming endless parade of disasters from which mankind must extricate itself. Those seeking prophecy in ancient literature have often interpreted the utterances of Nostradamus as portending catastrophe with the coming of the new millennium. In the wake of such upheavals, mankind would require massive assistance in dealing with multiple emergencies. Unmanned Systems exist to remove mankind from dull, dirty, and dangerous tasks or to allow the conduct of missions with duration beyond a life span.

The International Aerial Robotics Competition will celebrate its tenth anniversary at the dawning of the new millennium. Accordingly, the mission definition will involve the use of autonomous robots in a human search-and-rescue role during and immediately after a catastrophe of major proportions in which an urban area has been decimated by earthquake, tsunami, and wind. The ultimate cause could be volcanism, the impact of an erratic near-Earth orbiting asteroid, or multiple nuclear explosions triggered by terrorists in an underground storage bunker. Information is unavailable-- all you and your design team know is that your research facility has somehow survived the night along with its complement of autonomous robots. Ensuing chemical fires rage amid the wreckage of buildings. Toxic clouds of smoke choke the skies and obscure the view. Your sensors indicate that low level radiation is present.

There are other survivors out there who are injured and must be found before they die. Fire fighters in hazmat suits and respirators are attempting to find survivors and extract them to a safer location. Your autonomous robots have to be reprogrammed to search for living humans on the ground and either find and report their location to the human rescue team who will attempt to save them, or if possible your robots may attempt to extricate the survivors.

The Arena: A disaster scene will be replicated with highly unstructured and unpredictable events. Your autonomous robot(s) will have to be robust enough to operate in a realistic environment that contains wreckage, fire, smoke and aerosols, acoustic shock waves, motion on the ground and in the air, as well as unbriefed obstacles.

Your targets are injured humans on the ground that are simulated by animatronic synthetics capable of limited limb motion and sound. All survivors will be incapacitated and unable to move to safety under their own power. These synthetics will be programmed to expire at predetermined intervals unknown to the team. The number of injured humans and their location relative to the disaster scene is unknown.

Alternate targets of interest will represent potential hazards to rescue teams entering the area. These lower priority targets will include items such as drums of hazardous material, some potentially explosive, amid others which are inert.

Scoring: An actual human search-and-rescue team will be given one chance to enter the area to rescue as many injured people as possible. Their time in the area will be limited due to the simulated radiation hazard. They will be encumbered with hazmat suits and respirators and will have to deal with fire threats and smoke obscuration. The human search-and-rescue team will set the baseline performance comparison to which the autonomous robots will be judged.

Teams will be able to field one or more fully autonomous robots which may work simultaneously and synergistically to identify and map targets of interest. Ground robots may be deployed from the aerial robots, or may be launched from the starting point to work in concert with the aerial robots.

Points will be accrued for successfully performing tasks that would normally have to be done by human search-and-rescue teams or fire fighters. These will include, but are not at this time limited to: identifying the location of survivors, identifying the location of dead bodies, identifying hazards to be avoided, and identifying potential hazards. Given enough time (less than one hour), all survivors will become dead bodies. More points will be allotted for identifying the living. In addition, actions taken by the autonomous robots to improve the situation will accrue points. This will include, but not at this time be limited to: extinguishing fires, extracting survivors, providing life-support equipment to survivors, laying down paths/markers/lines through wreckage to survivors or to other locations requiring the attention of emergency personnel.

Administration: Multiple robots may be entered from a given University, but there will only be one official team from each school.

Each entry must involve at least one autonomous aerial robot, however autonomous ground robots are also allowed. If multiple autonomous robots are offered as part of a single entry, they must communicate with one another as a distributed sensor and intelligence rather than independent entities.

There will be an entry fee that is partially refundable upon successfully meeting certain mission criteria.

Various "qualifiers" must be passed in order to become a finalist in the Millennial event. These qualifiers will occur in 1998 and 1999. The qualifiers will allow entries to demonstrate behaviors necessary to successfully compete in the Millennial event. Therefore this will be a three year effort and some participants may not be able to see event to completion. For this reason, the student eligibility requirements allow certified team graduates to remain involved with a team.

As in 1998, the location for the 1999 and 2000 qualifiers, and the competition in AD 2000 will be the U.S. Department of Energy's Hazardous Material Management and Emergency Response (HAMMER) facility near the Hanford nuclear plant in Washington State.

Thirty thousand dollars (or more) will be awarded to the winner(s) of the competition (this amount will grow as additional benefactors join AUVSI in sponsoring the Millennial Event). Small monetary awards for successfully passing the annual qualifying tests leading to eligibility in the Millennial event may also be awarded.

How to Get Started: The first qualifier in 1998 involved demonstration of autonomous flight over a large area (five acres or more) containing briefed obstacles.

In 1999, aerial robots should be able to locate at least one of several items that will be encountered in the Millennial event. This will range from partially-buried, randomly-oriented drums of potentially explosive materials (amid debris and drums of inert materials), the location of fire sources, simulated dead bodies, or a simulated injured survivor on the ground that is signalling for help with a "waving arm motion". The more items correctly identified, the higher the qualifying score. The 1999 qualifier will require interaction with the target items, but still in a semi-structured environment. The inclusion and demonstration of autonomous ground robots will be possible in 1999.

During the various qualifiers, all entries must amass at least 2000 points in order to progress toward finalist status and admission into the Millennial event in AD 2000. At the organizer's discretion, a qualifier may also be held immediately prior to the Millennial Event in AD 2000 for those teams having earned the majority of their 2000 points in either the 1998 or 1999 qualifiers, but which can credibly be expected to meet the requirement given one more chance (this could also provide relief for documented hardship cases).

Go on to the 1998 Millennial Event Qualifier Rules.

or take me back to the International Aerial Robotics Competition home page.