Akhil Nagariya

Indian Institute of Technology Hyderabad, Texas A&M University

Papers

Total Citations

H-Index

About

Akhil Nagariya’s research bridges the critical gap between perception and control in autonomous systems, with a focus on robust navigation and dynamic modeling. His early work tackled fundamental sensor limitations, developing methods to remove rolling shutter and motion blur distortions from depth cameras like the Microsoft Kinect—a contribution that improved the reliability of structured light sensors for mobile robotics. This paper has garnered 10 citations, reflecting its value in addressing a practical challenge often overlooked in the literature. Nagariya’s expertise extends to motion planning and control in complex environments. He proposed a novel time-scaled collision cone approach for navigating non-holonomic robots amidst humans, explicitly modeling human intent and uncertainty to enable safer, more predictable interactions. This work, cited 3 times, offers a framework for human-centered autonomy. More recently, he evaluated Iterative Linear Quadratic Regulator (ILQR) controllers for trajectory tracking on diverse platforms, from off-road skid-steer robots to on-road vehicles, using neural network dynamics models. This 2020 study (6 citations) demonstrates his commitment to bridging model-based control with data-driven learning for real-world deployment. Across his career, Nagariya has consistently tackled the messy realities of field robotics—from sensor noise to human unpredictability—making his work essential for researchers building autonomous systems that must operate reliably outside the lab.