M. A. Johnson

About

Dr. M. A. Johnson is a pioneering figure in the field of intelligent robotic control, whose work has fundamentally advanced the high-speed precision of robotic manipulators. His research centers on the intersection of adaptive control theory and artificial neural networks, specifically developing model-based architectures that enable robots to compensate for complex, dynamic disturbances. Johnson’s seminal 1991 paper, "Neural network payload estimation for adaptive robot control," introduced a groundbreaking concept for using neural networks to enhance tracking accuracy by adapting to payload variations, earning 46 citations and establishing a foundational approach in the field. He later extended this work with two key contributions in 2002: the robust model-based neural-network controller (RMBNNC) and the adaptive model-based neural-network controller (AMBNNC). These controllers synergize feedforward neural network adaptation with robust feedback mechanisms, validated through rigorous experimental evaluation. While his later papers have accrued fewer citations, their methodological rigor and clear validation protocols provide a crucial blueprint for researchers seeking to bridge theoretical neural network control with practical robotic applications. Johnson’s legacy lies in his systematic, model-based integration of learning and control, making him an essential reference for anyone working on adaptive and intelligent robotic systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Neural network payload estimation for adaptive robot control

   46 citations · 1991
2. 2
   Robust model-based neural network control

   6 citations · 2002
3. 3
   Adaptive model-based neural network control: validation and analysis

   4 citations · 2002

Key Collaborators

Contact & Links