Indian Institute technology Researchers from (IIT) Madras and Harvard University have developed a novel machine learning algorithm called ‘CombSGPO’ (Combined Security Game Policy Optimization) that can help protect wildlife from poaching.
The algorithm works by handling resource allocation and creating a patrolling strategy after identifying the extent of the available resources. For this task, it uses data on animal populations in the protected area and assumes that poachers are aware of patrols being carried out at various sites.
This developed algorithm uses a game theory-based model created by the researchers. Game theory is a theoretical framework for visualizing social situations among competitive players. In the context of wildlife conservation, game theory is concerned with predicting areas where poaching may occur. These predictions are based on earlier poaching incidents and the interactions between hunters and defenders.
Read | Youth want to become entrepreneur in India, to fly abroad Jobs Near: IIT Madras Director
The institutions claim that this new algorithm provides highly efficient strategies that are more scalable than those previously created for the same purpose.
Professor Balaraman Ravindran, Mindtree Faculty Fellow and Professor, Department of Computer Science and Engineering, IIT Madras, and Head of the Robert Bosch Center for Data Science and Artificial Intelligence (RBCDSAI), IIT Madras collaborated with Prof. Milind Tambe’s Research Group – Teamcore . – To do this study at Harvard University in the US.
The work has been peer-reviewed and was well received at the 20th International Conference on Autonomous Agents and Multi-Agent Systems.
Highlighting the need for such research, Professor Balaraman Raveendran, Head, Robert Bosch Center for Data Science and Artificial Intelligence (RBCDSAI), IIT Madras said, “This work is based on strategic resource allocation and the need for patrolling in green security. was inspired. Domain to prevent illegal activities such as wildlife poaching, illegal logging and illegal fishing. The resources we consider are human patrols (forest rangers) and surveillance drones, which have object detectors for animals and predators and can perform strategic signals and interact with each other as well as with human patrols. can communicate.
Elaborating on the project, study’s first author Arvind Venugopal and Post-Baccalaureate Fellow, RBCDSAI, IIT Madras, said, “The game model and the kind of resources we use for such ‘illegal play’ between defenders.” (Forest Rangers and Drones) and attackers (hunters) are based on the widely studied ‘Stackelberg Security Game Model’ and are linked to drones already deployed by Air Shepherd (A foundation that deploys drones to stop elephant and rhino poaching. Africa).
According to World According to the Wide Fund for Nature (WWF), the wildlife trade poses the second biggest direct threat to the survival of the species after habitat destruction. While many organizations and regulatory authorities are trying to curb incidents of poaching, it seems that poachers always have to be one step ahead of patrollers. This collaborative research work of two reputed universities will help in curbing incidents of poaching.
To expand this research for application in areas such as aerial mapping for security, search and rescue and agriculture, the team is looking to learn sample-efficient multi-agent reinforcement learning with as little data as the data. Collecting is expensive in a real world scenario.
read all breaking news , today’s fresh news And IPL 2022 Live Updates Here.