Sandhya Saisubramanian

Papers

Total Citations

H-Index

About

Sandhya Saisubramanian is a leading researcher in artificial intelligence and robotics, specializing in planning under uncertainty for autonomous systems. Her work addresses fundamental challenges in stochastic environments, where robots must make robust decisions despite incomplete or changing information. A key contribution is her development of adaptive outcome selection using reduced models, which allows autonomous robots to efficiently plan in complex, stochastic settings by selectively improving model fidelity—a technique that balances computational tractability with solution quality. Her 2019 paper on this topic, with 5 citations, introduces the innovative 0/1 reduced model framework. Saisubramanian also pioneered the Goal Uncertain Stochastic Shortest Path (GUSSP) problem, a general framework for path planning and decision-making when goals are dynamic or unknown, extending classical stochastic shortest path models to real-world scenarios where goal uncertainty is inevitable. This work, cited 4 times, has significant implications for search-and-rescue, autonomous navigation, and human-robot interaction. Her research is widely recognized for bridging theoretical planning algorithms with practical deployment challenges, making her a rising authority in safe and adaptive autonomous decision-making.