Kush Aggarwal
Papers
2
Total Citations
49
H-Index
2
About
Kush Aggarwal is a researcher specializing in robotics, automation, and intelligent computational methods, with a particular focus on industrial manipulator systems and kinematic analysis. His work bridges classical robotics theory with modern machine learning techniques, exploring innovative approaches to longstanding engineering challenges in robotic control and workspace optimization. Aggarwal's most significant contribution is his 2014 investigation into applying artificial neural networks — specifically feed-forward multi-layer perceptron networks with backpropagation — to solve the notoriously complex inverse kinematics problem. Using the widely studied PUMA 560 robot as a testbed, this work demonstrated a non-conventional yet effective computational pathway for kinematic solutions while also enabling the visual identification of singularity zones, a critical safety and performance concern in robotic systems. This paper has garnered 46 citations, reflecting its meaningful influence within the robotics and automation research community. Complementing this, Aggarwal also contributed a reconfigurable algorithmic framework for evaluating the functional workspace of industrial manipulators, addressing reachability and dexterity — essential parameters for deploying robotic arms in real-world manufacturing and logistics environments. Together, his publications position him as a thoughtful contributor to the intersection of computational intelligence and practical robotics engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2