On-line instrumental variable-based feedforward tuning for non-resetting motion tasks

Data-driven feedforward control for tracking of varying and non-resetting point-to-point references requires continuous updating of feedforward parameters instead of task-by-task updating. The aim of this paper is to develop an adaptive feedforward controller for non-resetting point-to-point motion tasks by a data-driven feedforward...

Validating the win-rate of heroes in Dota 2 using instrumental variable estimation

This research provides additional insights in to when instrumental variable estimation is a proper method to use when investigating or removing causal effects in randomized experiments. this is done by using instrumental variables on the game Dota 2, in which win-rates of a couple heroes are validated and reviewed to test the effectiveness and...

Endogeneity in water use behaviour across case studies of household water treatment adoption in developing countries

Endogeneity or reverse causality in regression analysis results in biased estimation of the effects of independent variables on the dependent variable and leads to inaccurate interpretations. However, the biased estimation of the effects of psychological factors on water–related behaviours are rarely discussed. This study investigated the...

Neural Network Training Using Closed-Loop Data: Hazards and an Instrumental Variable (IVNN) Solution

An increasing trend in the use of neural networks in control systems is being observed. The aim of this paper is to reveal that the straightforward application of learning neural network feedforward controllers with closed-loop data may introduce parameter inconsistency that degrades control performance, and to provide a solution. The...

Investigating the effects of sleepiness in truck drivers on their headway: An instrumental variable model with grouped random parameters and heterogeneity in their means

Sleepiness is a common human factor among truck drivers resulting from sleep loss or time of day and causing impairment in vigilance, attention, and driving performance. While driver sleepiness may be associated with increased risk on the road, sleepy drivers may drive more cautiously as a result of risk-compensating behaviour. This endogeneity...

Eligibility traces and forgetting factor in recursive least-squares-based temporal difference

We propose a new reinforcement learning method in the framework of Recursive Least Squares-Temporal Difference (RLS-TD). Instead of using the standard mechanism of eligibility traces (resulting in RLS-TD((Formula presented.))), we propose to use the forgetting factor commonly used in gradient-based or least-square estimation, and we show that...

Stiffness and Pliability: Developing an Algorithm to Identify Intrinsic and Reflexive Stiffness during Voluntary Movement and a Shared Mental Model Making Cross-Disciplinary Collaboration Dynamics Meaningful to Engineers

System identification techniques to analyse movement disorders are in development, but concrete clinical evidence to receive broad support from the clinical world is lacking. This master thesis proposes two ways to accelerate their development as part of the master’s programmes in Mechanical Engineering and Science Communication. The Mechanical...

Underground Reservoir Identification Using Generalized Wellbore Data

We present a novel method for estimating physical properties of an underground hydrocarbon reservoir, on the basis of generally measured wellbore ow rate and pressure signals at the bottom of a producing well. The method uses instrumental variable-based system identification techniques to solve for a closed-loop errors-in-variables problem....