Adaptive Automation Research Articles

Risk Awareness and Decision Making in Shipping

Risk is a multidimensional notion in any industrial sector and society depends on the actors involved, social-economical factors, complexity and nature of the technology and the safety culture of the environment in which its operates. Risk, as an aspect in decison making in operator tasks, is also multidimensional. Accident analysis in various fleet segments in the maritime industry demonstrate that a specific approach to risk decision making is required to fully understand the nature of the decisions and risk perception of the operators. In additon to the traditional frequentistic approach, die use of a scenario approach could improve the identification of typical events, taking into the culture and context in which they occur. Such an approach could lay the basis for adaptive automation and knowledge based training of operators to improve their problem solving capacity and to enhance their risk decision making processes.

The performance and workload effects of task re-location during automation

We report an experiment which investigated the performance and workload effects associated with the functional grouping of automated displays in a multi-task flight simulation. Eleven rated pilots performed tracking, systems monitoring, and target acquisition sub-tasks in manual conditions and when the targeting task was automated. In the latter condition, the target acquisition display was relocated either proximally, distally, or neutrally with respect to the functionally similar, systems monitoring display. It was hypothesized that an automated task display relocated near its functional equivalent (the proximal condition) would result in increased performance efficiency and lower perceived workload compared to the other relocation positions. An advantage for adaptive automation was confirmed with pilots exhibiting less tracking error, lower monitoring response times, lower target response times, and increased percentage of target responses during automated compared with manual conditions. Results did not confirm the hypothesized benefits for display location. However, when interpreted within the Proximity Compatibility Principle framework where both perceptual and processing proximity are recognized, results confirmed an advantage for the functional grouping layout of the display. Specifically, the proximal grouping condition was the only condition that resulted in both performance and workload benefits. Some observations on the implications for display design in systems using automation are provided.

Psychophysiology and adaptive automation

Adaptive automation is an approach to automation design where tasks are dynamically allocated between the human operator and computer systems. Psychophysiology has two complementary roles in research on adaptive automation: first, to provide information about the effects of different forms of automation thus promoting the development of effective adaptive logic; and second, psychophysiology may yield information about the operator that can be integrated with performance measurement and operator modelling to aid in the regulation of automation. This review discusses the basic tenets of adaptive automation and the role of psychophysiological measures in the study of adaptive automation. Empirical results from studies of flight simulation are presented. Psychophysiological measures may prove especially useful in the prevention of performance deterioration in underload conditions that may accompany automation. Individual differences and the potential for learned responses require research to understand their influence on adaptive algorithms. Adaptive automation represents a unique domain for the application of psychophysiology in the work environment.

A Bio-Cybernetic System for Adaptive Automation

A bio-cybernetic, closed-loop system was validated for use in an adaptive automation environment. Subjects were asked to perform either a single task or multiple tasks from the Multi-Attribute Task Battery. EEG was continuously sampled while they performed the task(s) and an EEG index was derived (20 Beta/Alpha + Theta). The system switched between manual and automatic modes according to the level of operator engagement based upon the EEG index. The NASA-TLX was administered after each trial. The results of the study demonstrated that it was possible to moderate an operator's level of engagement through a closed-loop system driven by the operator's EEG. In addition, the system was sensitive to increases in task load. These findings show promise for designing adaptive automation technology around psychophysiological input.

Complex Task Performance as a Basis for Developing Cognitive Engineering Guidelines in Adaptive Automation

This paper describes the first of a series of Cockpit Automation Studies (CAS-1). The study examines performance on two tasks performed separately and in combination. The tasks were selected to represent tasks found in a tactical aircraft cockpit and were derived from standard laboratory tasks. The results of the study have implications for the utility of resource theory in understanding and predicting complex task performance, and for the use of adaptive automation systems. On-going and planned research is also discussed.

Conditions of Effectiveness of Adaptive Automation

Production automation occupies a leading place among the directions of STP [scientific-technical progress]. The effectiveness of the costly means of adaptive automation, particularly robotics, must be assured not by special methods of calculating the effect but by a complex of organizational and economic measures relating to the development, production, and utilization of this technology.

The Application of Microcomputers in Automated Arc Welding Systems

An overview is presented of the functions, capabilities, and operation of the microcomputer as it relates to automated arc welding. This is followed by examples of the use of the microcomputer ranging from automatic joint tracking to complete weld system programming and data logging. A discussion of future applications of the microcomputer in the role of full, adaptive weld automation is given.

An adaptive automaton controller for discrete-time markov processes

The computation of an optimal feedback controller characteristic for a non-linear stochastic system may be facilitated by the use of a stochastic automaton as a system model. A problem of particular interest is that of a long duration stationary Markov process in which the state is observable but the process dynamics and disturbance characteristics are initially unknown. The determination of a suitable control algorithm, in the form of an adaptive automation in the feedback loop, is considered in this paper for such a process. Since the algorithm is to be used on-line to perform simultaneously the functions of estimation and control, it must constitute an efficient convergent multi-stage dual control strategy. It is shown that an existing method for dual control of a repetitive single-stage stochastic process may be extended to apply to the present case. A method is introduced of calculating successive policy estimates recursively, so that the task of updating the estimated optimal feedback policy at each stage of the process is rendered feasible. The application of the automaton controller is illustrated by the simulated adaptive control of a non-linear conditionally stable heat treatment process disturbed by multiplicative noise.

An Adaptive Automaton for Teaching Small Groups

Abstract : It was first argued that the automated teaching of small groups requires, for most skills, a rather special kind of adaptive automation which can organise the group members by manipulating their channels of communication. An example of such an automaton was then described and its potentialities pointed out. (Author)

Strategy of Data Selection for Adaptive Automation

The problems of selection of logged process variables by a control computer with limited memory for continuous on-line process automation in the presence of erroneous, erratic and irrelevant data sources are considered from a strategic viewpoint. Markov and simple learning strategies are presented that allow a computer to learn about the current behavior of a process with respect to variable relevancy, resulting in a considerable increase in data selection efficiency over a random selection strategy. The case of single variable selection using a Markov strategy is solved analytically and computer simulation is used to estimate the performance of a simple learning strategy.