Papers
6
Total Citations
1,876
H-Index
3
About
Suresh Jagannathan is a prominent researcher whose work spans neural network-based control systems, safe robot navigation, and the integration of large language models into robotic task planning. His most celebrated contribution, "Neural Network Control of Robot Manipulators and Non-Linear Systems," has amassed an remarkable 1,851 citations, establishing him as a foundational voice in the development of universal controllers that replicate human learning processes to adaptively improve robotic performance in real time. This landmark work laid critical groundwork for intelligent, self-improving robotic systems across a wide range of applications. Jagannathan's subsequent research has consistently pushed toward safer and more reliable autonomous systems. His work on model-free Neural Lyapunov Control addresses safety assurance in deep reinforcement learning, while his recent contributions on LLM-driven task planning tackle the challenge of constraint adherence in complex, long-horizon robotic missions. Earlier investigations into adaptive critic neural networks for three-finger grippers demonstrated his enduring interest in practical manipulation challenges, including agricultural robotics contexts. More recently, his examination of adversarial robustness in learning-enabled controllers reflects a growing commitment to securing cyber-physical systems against real-world threats. Across decades of research, Jagannathan has made lasting contributions to intelligent, safe, and adaptive robotics.
Research Focus
Key Achievements
Top Papers
- 1Neural Network Control Of Robot Manipulators And Non-Linear Systems1,851 citations · 2020
- 2Model-free Neural Lyapunov Control for Safe Robot Navigation10 citations · 2022
- 3
- 4
- 5
- 6Robustness to Adversarial Attacks in Learning-Enabled Controllers3 citations · 2020