Derek Boase
Papers
2
Total Citations
21
H-Index
2
About
Derek Boase is a researcher advancing the frontiers of intelligent control systems, with a primary focus on reinforcement learning (RL) for complex, uncertain, and underactuated nonlinear systems. His work bridges the gap between theoretical optimal control and real-world application, particularly in aerospace robotics. Boase’s most impactful contribution, “Real-time measurement-driven reinforcement learning control approach for uncertain nonlinear systems” (2023, 19 citations), pioneers a data-driven framework that enables controllers to adapt in real-time without requiring an explicit system model—a critical advantage for dynamic environments. In a notable companion study on underactuated MIMO airship control (2023, 2 citations), he developed a novel online model-free controller for a dirigible, integrating RL and optimal control theory. This work overcomes the traditional dependence on future value functions by employing a neural network, allowing the controller to learn and stabilize the airship’s complex, underactuated dynamics in real time. Boase’s research is distinguished by its practical, measurement-driven approach, offering scalable solutions for autonomous vehicles and robotics. His contributions are paving the way for more resilient, adaptive control systems in uncertain operational conditions.
Research Focus
Key Achievements
Top Papers
- 1
- 2