Pranav Kamojjhala

Papers

Total Citations

H-Index

About

Pranav Kamojjhala is a roboticist whose work lies at the intersection of task planning, motion planning, and decision-making under uncertainty. His research focuses on developing algorithms that enable robots to reason abstractly while remaining grounded in the physical constraints of motion—a critical challenge for long-horizon, complex tasks. Kamojjhala’s most cited paper, “Anytime Integrated Task and Motion Policies for Stochastic Environments” (2020, 3 citations), introduces a framework that seamlessly combines high-level symbolic planning with low-level motion control, even in unpredictable settings. This work addresses the fundamental tension between the lossiness of abstract models and the need for executable robot policies, offering an anytime approach that improves solution quality over time. By tackling the integration of task and motion planning in stochastic environments, Kamojjhala contributes to making robots more autonomous and reliable in real-world applications. His research is particularly relevant for domains like service robotics, manufacturing, and autonomous navigation, where robots must adapt to changing conditions while executing complex sequences of actions.