Data-Driven Human Modeling: Quantifying Personal Tendency Toward Laziness

• Published in: IEEE control systems letters Vol. 5; no. 4; pp. 1219 - 1224
• Main Authors: Hara, Keita, Inoue, Masaki, Maestre, Jose Maria
• Format: Journal Article
• Language: English
• Published: IEEE 01.10.2021
• Subjects: <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L ₂/<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L ₁ optimal control; Cost function; Estimation; Human tendency modeling; Mathematical model; model predictive control; Optimal control; Predictive models
• ISSN: 2475-1456; 2475-1456
• DOI: 10.1109/LCSYS.2020.3023337

This letter addresses the modeling of a personal tendency by utilizing the data collected from a manned control system. In the control system, it is assumed that a control operator, namely a human controller, determines the control actions based on his/her tendency toward laziness. The tendency is described by a cost function that includes the <inline-formula> <tex-math notation="LaTeX">L_{2} </tex-math></inline-formula> norm of the state and the <inline-formula> <tex-math notation="LaTeX">L_{1} </tex-math></inline-formula> norm of the control action. Then, the operator behavior is modeled by the solution to the optimization problem formulated with the <inline-formula> <tex-math notation="LaTeX">L_{2} </tex-math></inline-formula>-state/<inline-formula> <tex-math notation="LaTeX">L_{1} </tex-math></inline-formula>-action cost function and the plant model. The tendency modeling is reduced to the problem of estimating the cost function. The estimation problem is further extended by taking into account the operator dynamics caused by the recognition and motion to derive an MPC-based formulation. Finally, the estimation method is demonstrated via an actual manned control experiment with a toy game.