Kush Grover

Papers

Total Citations

H-Index

About

Kush Grover is a robotics researcher whose work lies at the intersection of formal methods, motion planning, and decision-making under uncertainty. His key contributions focus on enabling autonomous robots to execute complex, temporally specified missions—such as those described by syntactically co-safe Linear Temporal Logic (scLTL)—in initially unknown environments. In his most cited work, "Semantic Abstraction-Guided Motion Planning for scLTL Missions in Unknown Environments" (2021, 7 citations), Grover pioneered a method that leverages semantic abstractions to efficiently guide a robot's exploration and trajectory generation, ensuring mission satisfaction even without prior environmental knowledge. This approach addresses a critical challenge in robotics: bridging high-level task specifications with low-level control in dynamic settings. His follow-up work, "Planning via model checking with decision-tree controllers" (2022, 4 citations), introduces a novel perspective by using model checking to synthesize universal, decision-tree-based controllers that provide robust, fault-tolerant plans—eliminating the need for constant replanning. This work highlights his ability to merge theoretical rigor with practical robustness. With a growing citation footprint, Grover is establishing himself as a rising voice in formal synthesis for autonomous systems, offering elegant solutions to the problem of verifiable, adaptive robot behavior in the real world.