CHENNAI: Researchers of IIT-Madras and Harvard University jointly developed a novel Machine Learning algorithm named ‘CombSGPO’ (Combined Security Game Policy Optimization) to help control wildlife poaching. An IIT statement said, the research team developed the algorithm to optimise use of forest rangers and drones to develop strategies to protect wildlife.
It uses animal population data in the area and strategises patrolling. Balaraman Ravindran, professor, department of computer science and engineering, IIT-Madras, collaborated with Milind Tambe’s Research Group at Harvard University in the US to carry out the study.
Ravindran said the algorithm uses a Game Theorybased model created by the researchers. (Game theory is a theoretical framework for conceiving social situations among competing players.) In the context of wildlife protection, the theory predicts areas where poaching may occur.
“The resources considered are human patrollers, and surveillance drones that have object detectors mounted on them, perform strategic signalling, and communicate among themselves and human patrollers,” said Ravindran. The work was peer-reviewed and well-received at the 20th International Conference on Autonomous Agents and Multi-Agent Systems, the statement said.