Papers
45
Total Citations
1,162
H-Index
15
About
S. Jagannathan is a prolific researcher whose work sits at the intersection of neural networks, reinforcement learning, and advanced control systems, with particular expertise in robotics and nonlinear dynamical systems. Over more than two decades, he has made foundational contributions to intelligent control theory, pioneering methods that harness neural networks and adaptive critics to govern complex, uncertain systems. His 1997 monograph on neural network control of robot arms established early frameworks that continue to influence the field, while his 2011 paper on reinforcement learning-based adaptive critic controllers for nonlinear discrete-time systems—garnering 188 citations—demonstrated how online approximators could effectively manage multi-input, multi-output systems under real-world disturbances. Jagannathan has been especially impactful in multi-robot formation control, developing backstepping and RISE feedback strategies for leader-follower configurations that achieve rigorous asymptotic stability guarantees. His later work explores event-triggered control, reduced-communication architectures, and dual-loop optimal planning, culminating in practical warehouse automation applications. With cumulative citations spanning hundreds of publications and contributions ranging from cerebellar model controllers to dynamic table tennis trajectory generation, Jagannathan's research portfolio represents a sustained and wide-ranging effort to make intelligent autonomous systems both theoretically rigorous and practically deployable.
Research Focus
Key Achievements
Top Papers
- 1
- 2Neural Network Control of Robot Arms and Nonlinear Systems171 citations · 1997
- 3Neural Network Control of Mobile Robot Formations Using RISE Feedback125 citations · 2008
- 4
- 5
- 6
- 7
- 8CMAC neural network control of robot manipulators45 citations · 1997
- 9
- 10