IIT-M, Harvard researchers develop algorithm to combat wildlife poaching

Researchers from the prestigious Indian Institute of Technology-Madras (IIT-M) and Harvard University have come together to develop a novel machine-learning algorithm named ‘CombSGPO’ aimed at saving wildlife from poaching by using data on animal populations in conserved areas.

The researchers say the algorithm, Combined Security Game Policy Optimization, provides “highly efficient strategies” that are more scalable than the earlier ones created for the same purpose. During the course of the study, they found that combined and coordinated use of Forest Rangers and drones was a good way to protect wildlife from poaching.

As the resources (rangers and drones) are limited, the researchers developed this algorithm which provides a good strategy to protect wildlife with the resources available, the researchers felt. The algorithm works by handling resource allocation and strategizing patrolling after the extent of resources available had been identified.

For this task, it utilises data on the animal population in the conserved area and assumes that poachers are aware of the patrolling being done at various sites, the researchers said.

Prof. Balaraman Ravindran, Mindtree Faculty Fellow and Professor, Department of Computer Science and Engineering, IIT-M, collaborated with Prof. Milind Tambe’s Research Group – Team core - at Harvard University, U.S., to carry out this study.

The work has been peer-reviewed and was well received at the 20th International Conference on Autonomous Agents and Multi-Agent Systems.

Prof. Ravindran said the work was motivated by the need to perform strategic resource allocation and patrolling in green security domains to prevent illegal activities such as wildlife poaching, illegal logging, and illegal fishing. “The resources we consider are human patrollers (forest rangers) and surveillance drones, which have object detectors mounted on them for animals and poachers and can perform strategic signalling and communicate with each other as well as the human patrollers,” he said.

The algorithm utilizes a Game Theory-based model created by the researchers. Aravind Venugopal, the first author of the study, said the game model and the kind of resources used to simulate such a ‘poaching game’ between the defender (Forest Rangers and drones) and attackers (poachers) are based on the widely studied ‘Stackelberg Security Game Model’ and are linked to drones that have already been deployed by Air Shepherd (a foundation that deploys drones to stop elephant and Rhino poaching in Africa).

While several organizations and regulatory authorities are trying to curb the incidences of poaching, the poachers seem to have always remained one step ahead of the patrollers. This collaborative research work by two esteemed universities will help in keeping poaching incidents in check, the IIT-M said.

To extend this research for application in domains such as security, search and rescue and aerial mapping for agriculture among others, the team is trying to perform sample-efficient multi-agent reinforcement learning to learn with the least amount of data since data collection is costly in a real-world scenario.