Abhishek Agarwal

National Institute of Technology Durgapur

Papers

Total Citations

H-Index

About

Abhishek Agarwal’s research lies at the intersection of robotics, control theory, and machine learning, with a focus on enabling more adaptive and intelligent robot locomotion and manipulation. His early work on quadrupedal robots, particularly the 2010 paper "Dynamic Modeling and Optimal Foot Force Distribution of Quadruped Walking Robot" (5 citations), established foundational methods for balancing stability and efficiency in legged locomotion through dynamic modeling and force optimization. More recently, Agarwal has advanced the use of generative models for robot control, as demonstrated in his 2020 paper "Learning a generative model for robot control using visual feedback" (2 citations). This work introduces a novel framework that learns a probabilistic mapping from robot actions to visual observations of end-effector features, enabling robots to infer their own state and precisely reach target positions using only camera feedback. By integrating visual perception directly into the control loop, Agarwal’s approach reduces reliance on expensive sensors and opens new possibilities for robots operating in unstructured environments. His contributions bridge classical dynamics with modern learning-based methods, offering practical pathways toward more autonomous and visually guided robotic systems.