Sumanth Dathathri

Papers

Total Citations

H-Index

About

Sumanth Dathathri is a researcher specializing in formal methods, control theory, and autonomous systems, with a focus on ensuring safety and performance in complex, uncertain environments. His work bridges the gap between data-driven techniques and formal verification, addressing critical challenges in the design of reliable autonomous systems. In his 2020 paper, "Counter-example Guided Learning of Bounds on Environment Behavior," Dathathri introduced a novel data-driven framework that uses counterexamples to iteratively refine bounds on environment dynamics, enabling robust system guarantees despite incomplete models. This work, which has garnered 4 citations, is foundational for safety-critical applications like robotics and cyber-physical systems. Earlier, in his 2017 paper "Enhancing tolerance to unexpected jumps in GR(1) games," he tackled the problem of model uncertainty in linear-time temporal logic (LTL) synthesis, proposing strategies to maintain correctness even when dynamics deviate unexpectedly. With 2 citations, this contribution highlights his ability to address practical vulnerabilities in hybrid controllers. Dathathri’s research is notable for its interdisciplinary approach, combining theoretical rigor with practical data-driven solutions, making him a rising voice in the quest for trustworthy autonomous systems.