A Linear Approach towards Modeling Human Behavior

Antunes, Rui; Coito, Fernando; Duarte-Ramos, H.

doi:10.1007/978-3-642-19170-1_33

Cited by 4 publications

(3 citation statements)

References 11 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The delay in reaction time is a significant human factor that impacts the performance of operators [20]. To account for the characteristics of human central nervous latencies, neuromuscular system, and other human and environmental factors, a transfer function with time delay has been formulated in [21] to model the human response as…”

Section: Preliminaries a First-principles Model Of Human-driven Vehiclesmentioning

confidence: 99%

Longitudinal motion control for vehicle platooning in mixed traffic based on virtual mass-spring-damper theory

Jiang

Ren

et al. 2020

IJVD

View full text Add to dashboard Cite

As autonomous vehicles (AVs) become more prevalent on public roads, they will inevitably interact with humandriven vehicles (HVs) in mixed traffic scenarios. To ensure safe interactions between AVs and HVs, it is crucial to account for the uncertain behaviors of HVs when developing control strategies for AVs. In this paper, we propose an efficient learning-based modeling approach for HVs that combines a first-principles model with a Gaussian process (GP) learning-based component. The GP model corrects the velocity prediction of the firstprinciples model and estimates its uncertainty. Utilizing this model, a model predictive control (MPC) strategy, referred to as GP-MPC, was designed to enhance the safe control of a mixed vehicle platoon by integrating the uncertainty assessment into the distance constraint. We compare our GP-MPC strategy with a baseline MPC that uses only the first-principles model in simulation studies. We show that our GP-MPC strategy provides more robust safe distance guarantees and enables more efficient travel behaviors (higher travel speeds) for all vehicles in the mixed platoon. Moreover, by incorporating a sparse GP technique in HV modeling and a dynamic GP prediction in MPC, we achieve an average computation time for GP-MPC at each time step that is only 5% longer than the baseline MPC, which is approximately 100 times faster than our previous work that did not use these approximations. This work demonstrates how learning-based modeling of HVs can enhance safety and efficiency in mixed traffic involving AV-HV interaction.

show abstract

Section: Preliminaries a First-principles Model Of Human-driven Vehiclesmentioning

confidence: 99%

Longitudinal motion control for vehicle platooning in mixed traffic based on virtual mass-spring-damper theory

Jiang

Ren

et al. 2020

IJVD

View full text Add to dashboard Cite

show abstract

“…In addition, it is considered in [76] that the cerebellum has the function of the Simith Predictor which compensates the delay in the closed loop. Although the nonlinear methods typically improve the prediction performance to some extent, it is still very appealing to use linear/hybrid models due to their convenience for analysis and design [84,88,89]. A new hybrid fuzzy-ARX modeling method has been developed for predicting the human operator control actions in [85].…”

Section: Human Response Modelingmentioning

confidence: 99%

A tutorial on learning human welder's behavior: Sensing, modeling, and control

Liu

Zhang

2014

Journal of Manufacturing Processes

View full text Add to dashboard Cite

Human welder's experiences and skills are critical for producing quality welds in manual GTAW process. Learning human welder's behavior can help develop next generation intelligent welding machines and train welders faster. In this tutorial paper, various aspects of mechanizing the welder's intelligence are surveyed, including sensing of the weld pool, modeling of the welder's adjustments and this model-based control approach. Specifically, different sensing methods of the weld pool are reviewed and a novel 3D vision-based sensing system developed at University of Kentucky is introduced. Characterization of the weld pool is performed and human intelligent model is constructed, including an extensive survey on modeling human dynamics and neuro-fuzzy techniques. Closed-loop control experiment results are presented to illustrate the robustness of the model-based intelligent controller despite welding speed disturbance. A foundation is thus established to explore the mechanism and transformation of human welder's intelligence into robotic welding system. Finally future research directions in this field are presented.

show abstract

“…By adopting this approach, the human-machine MIMO system may be modeled from two independent linear transfer functions, leading to a diagonal state-space dynamic matrix pattern. Each axis input-output transfer function can then be experimentally obtained from several pursuit manual tracking experiments, using the frequency analysis methods already developed in previous work [13] , [14], [15].…”

Section: The Human-machine Modeling Strategymentioning

confidence: 99%

Improving Operator Performance through the Use of a Multivariable Human-Machine Control Strategy

Antunes

Coito

Duarte-Ramos

2012

Technological Innovation for Value Creation

Self Cite

View full text Add to dashboard Cite

Most of the mechatronics equipments and gadgets that we all nowadays rely on incorporate some kind of multidimensional human-machine systems. There is an increasing concern for improving the usability, performance, ergonomics and safety of such devices, and ultimately this will lead to the mass-production of next-generation intelligent machines, which will be capable to assist the human operator and to reduce the global effort by estimating and measuring its skills. This ongoing work introduces a novel human-machine multi-dynamic modeling methodology which can be applied on the development of these Human Adaptive Mechatronic (HAM) machines, able to adapt to the skill/dexterity levels of its users, and to enhance Human's proficiency. As a new strategy for model development, a number of twodimensional independent pursuit manual tracking experiments are evaluated. A human-machine state-space linear model is obtained and successfully applied to design an improved closed-loop multivariable control structure.

show abstract

A Linear Approach towards Modeling Human Behavior

Cited by 4 publications

References 11 publications

Longitudinal motion control for vehicle platooning in mixed traffic based on virtual mass-spring-damper theory

Longitudinal motion control for vehicle platooning in mixed traffic based on virtual mass-spring-damper theory

A tutorial on learning human welder's behavior: Sensing, modeling, and control

Improving Operator Performance through the Use of a Multivariable Human-Machine Control Strategy

Contact Info

Product

Resources

About