Mangal Kothari

Papers

Total Citations

H-Index

About

Mangal Kothari is a robotics researcher whose work bridges deep learning and legged locomotion, with a focus on enabling autonomous systems to perceive and navigate their environments. His key research areas include mobile robot relocalization using convolutional neural networks (CNNs) and hierarchical control strategies for quadruped robots. Kothari’s most cited work, “Convolutional Neural Network Based Sensors for Mobile Robot Relocalization” (2018, 13 citations), addresses a critical challenge in robotics: achieving accurate camera pose prediction without relying on computationally heavy deep architectures. By proposing a lightweight CNN-based sensor, he made relocalization more feasible for resource-constrained mobile robots, advancing practical deployment in real-world settings. In his more recent work, “Path Tracking Strategy for Quadruped Robots Using a Hierarchical Framework” (2022, 2 citations), Kothari introduces a novel approach to continuous gait control, decomposing complex locomotion into discrete motion templates—such as translation and turning—using a Linear Inverted Pendulum Model (LIPM). This hierarchical framework simplifies path tracking on flat, rigid terrain, offering a scalable solution for quadruped navigation. Though early in his career, Kothari’s contributions demonstrate a clear trajectory toward making autonomous robots more efficient, adaptable, and computationally accessible.