DATA-DRIVEN DECISION MAKING AND CONTROL OF RATIONAL AGENTS
Abstract
This dissertation studies the problem of data-driven optimal decision making. The 4main contributions of this work are listed here. First, we develop a model-based and data-driven techniques for learning the cost of an Ex-pert agent. This ties fields of Inverse Optimal Control and Inverse Reinforcement Learning and represents a first data-driven algorithm of this kind in the control community. Next, we have developed optimally adaptive dynamic control allocation mechanism that optimally re-configures redundant actuators in a model-free fashion, that is, based on collected data. This work pushed the multiple frontiers of control allocation research, since state-of-the-art control allocation was Next, we have introduced an uncertainty aware trajectory optimization technique that uses the information about the model uncertainty to inform the generation of local feedback policy which makes the open loop solution more reliable and robust. Finally, a cooperative protocol for distributed formation control has been developed and tested on the real system in the lab. This was among the first real world examples of multi-agent distributed formation control.
Related items
Showing items related by title, author, creator and subject.
-
Impact of Stability and Control on Vehicle Geometry and Performance: A Design Study on Traditional Hypersonic Vehicles VS Controlled Configured Hypersonic Vehicles
Buritica Yate, Juan Camilo; 0000-0003-2326-0190Hypersonic vehicles have been in development for over 60 years, yet a control-configure-vehicle has yet to be designed to understand the possible improvements over statically stable configurations. ... -
A ROBUST CONTROLLER DESIGN FOR A TAILLESS UAV WITH EFFECTIVE CONTROL ALLOCATION
Orhan, Ethem Hakan; 0000-0002-5767-0529 (2019-12-06)Attempts to completely remove the tails from aircraft can be dated back to the early days of modern aviation. A number of stability and control problems arising from the unique characteristics of the configuration resulted ... -
An Integration Of A Modern Flight Control System Design Technique Into A Conceptual Design Stability And Controls Tool, AeroMech
Omoragbon, Amen (Aerospace Engineering, 2010-11-01)The aircraft conceptual design (CD) phase is the most abstract, thus challenging phase of the entire aircraft design process. It is the responsibility of the CD engineer to identify and then to explore various aircraft ...