Max Robotics — Global Service Robot Directory + US Certification

About

Dustin Nottage is a researcher at the forefront of intelligent control systems, specializing in reinforcement learning, adaptive filtering, and fuzzy inference systems for autonomous robotics and localization. His most impactful work, "Deep Reinforcement Learning for Autonomous Dynamic Skid Steer Vehicle Trajectory Tracking" (13 citations), addresses the complex nonlinear dynamics of skid-steered robots by designing controllers that learn robust behaviors directly from interaction, overcoming challenges like wheel slip and tire-ground interaction. Nottage further advances state estimation with his "Robust Error State Sage-Husa Adaptive Kalman Filter for UWB Localization" (7 citations), improving ultra-wideband positioning accuracy through a refined adaptive filter that handles sensor noise and interference. He also contributes to interpretable AI with his hierarchical rule-base reduction approach for ANFIS, optimized online via Deep Deterministic Policy Gradient (DDPG), achieving efficient, symmetric fuzzy inference systems. With a growing citation record and a focus on bridging learning-based control with practical robotic and localization challenges, Nottage’s work is shaping the next generation of adaptive, autonomous systems.