Poaching has long been a problem all throughout Africa. Tigers, elephants, rhinoceros, and other different species of animals have been brought to the brink of extinction due to illegal poaching. With most parks being understaffed and underfunded, ranger patrols have become poorly planned, reactive rather than pro-active, and habitual. To help these rangers out a research team out of USC in collaboration with the National Science Foundation and the Army Research Office, has developed a new Artificial Intelligence (AI)-based application employing game theory to efficiently map out patrol routes and areas.
The team is being led by Milind Tambe, professor of computer science and industrial and systems engineering at USC and their research builds on what they call “green security games.” Or simply the application of game theory to wildlife protection. The software Tambe’s team created,”Protection Assistant for Wildlife Security” or PAWS, uses game theory models to effectively analyze data from previous patrols and evidence of poaching to predict where poachers might strike next. The more data fed to the application, the more it can “learn” the topography, terrain, natural paths, foot traffic and animal traffic of the protective area. As a result a poaching “street map” can be developed, providing rangers with the most effective patrol routes. The application also randomizes the patrol routes, making it difficult for poachers to predict any types of discernible patterns. The researchers first created PAWS in 2013 and tested the application in Uganda and Malaysia in 2014. Already, the system has led to more observations of poacher activities per kilometer and the research won the Innovative Applications of Artificial Intelligence award for deployed application, as one of the best AI applications with measurable benefits.
It is amazing seeing how using concepts we are learning such as game theory to come up with what is the most rational decision for these poachers are be combined with cutting edge machine learning techniques to help under-resourced park rangers keep up with poachers. The combination of game theory and artificial intelligence has the potential to radically change the way we are able to predict and react to all kinds of illegal activity. The ability to discern where a crime might occur next or come up with the best patrol route has applications not just for poaching, but potentially be useful in all cities across the world.
The team have also gone on to apply the same game theory model and principles for fisheries, The Coast Guard, and Transportation Security Administration to protect airports and waterways. A paper containing their research can be found here.