Enhancing Human-Machine System Performance by Introducing Artificial Cognition in Vehicle Guidance Work Systems

This paper advocates the introduction of so-called cognitive and cooperative automation into vehicle guidance work systems. The work system of UAV guidance will be taken as an example. This idea radically breaks with the traditional approach of supervisory control. According to our approach the human will no longer be the only instance in the work process being responsible for the pursuit of the given work objective. We call this novel mode of human-automation interaction cooperative control. Suchlike automation will take over a more active part and develop its own initiative to achieve the aim of work and thereby enhance the human-machine system’s performance. This paper provides a comprehensive description of the top-level work system design incorporating cognitive automation, a brief outline on the realisation of artificial cognition and the description of an application example taken from the multi-UAV guidance and mission management domain. The experiments show that cognitive cooperation provides a high potential for human performance enhancement on the level of cognitive work. 1.0 INTRODUCTION Vehicle guidance of any kind has always been a very demanding task for human operators. Driving a car and navigating in dense traffic is probably the most complex sensori-motor and cognitive task an average person is ever exposed to in daily life. In fact, a whole set of psycho-physiological limitations confine human performance, e.g. associated with visual perception or reaction time. Fatigue might as well be a major issue. Obviously operating a military aircraft requires much more specialised human capabilities and poses extremely high demands on pilots. In addition to the aforementioned problems physiological human performance limitations in connection with e.g. acceleration tolerance, hypoxia or motion sickness arise. With the advent of more and more automation in the work environment the nature of work has been changed considerably. Many of the purely manual control tasks vanished, while supervisory control [1] became the predominant mode of human-machine interaction in vehicle guidance. This led to a great relief from demanding high-bandwidth tasks and the size of operating crews could be considerably scaled down, e.g. the flight deck crew of civil airliners from four or even five persons in the earlier years to two pilots as usual today. Accompanied with that, however, work environments became much more complex, requiring increasing skills and knowledge on behalf of the human operators in order to still cope with the complexity. In fact, human cognitive performance limits became the predominant restriction. Unless high efforts invested in the optimisation of human-machine systems typical reactive designs could not really succeed in counteracting suchlike problems. Cognitive and cooperative automation represent novel approaches to this problem, radically breaking with the tradition of supervisory controlled automation. The Institute of Flight Systems (and it’s predecessor organisations) at the Universität der Bundeswehr München (Munich University of the German Armed Forces) has been working on experimental prototypes since more than two decades now. Many experimental works proving the concepts have been performed enhancing human-system performance in particular in aerial applications. Report Documentation Page Form Approved OMB No. 0704-0188 Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. 1. REPORT DATE OCT 2009 2. REPORT TYPE N/A 3. DATES COVERED 4. TITLE AND SUBTITLE Enhancing Human-Machine System Performance by Introducing Artificial Cognition in Vehicle Guidance Work Systems 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e. TASK NUMBER 5f. WORK UNIT NUMBER 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) Universität der Bundeswehr München Institute of Flight Systems (LRT-13) 85577 Neubiberg, GERMANY 8. PERFORMING ORGANIZATION REPORT NUMBER 9. SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS(ES) 10. SPONSOR/MONITOR’S ACRONYM(S) 11. SPONSOR/MONITOR’S REPORT NUMBER(S) 12. DISTRIBUTION/AVAILABILITY STATEMENT Approved for public release, distribution unlimited 13. SUPPLEMENTARY NOTES See also ADA562561. RTO-MP-HFM-181 Human Performance Enhancement for NATO Military Operations (Science, Technology and Ethics) (Amelioration des performances humaines dans les operations militaires de l’OTAN (Science, Technologie et Ethique)). RTO Human Factors and Medicine Panel (HFM) Symposium held in Sofia, Bulgaria, on 5-7 October 2009., The original document contains color images. 14. ABSTRACT This paper advocates the introduction of so-called cognitive and cooperative automation into vehicle guidance work systems. The work system of UAV guidance will be taken as an example. This idea radically breaks with the traditional approach of supervisory control. According to our approach the human will no longer be the only instance in the work process being responsible for the pursuit of the given work objective. We call this novel mode of human-automation interaction cooperative control. Suchlike automation will take over a more active part and develop its own initiative to achieve the aim of work and thereby enhance the human-machine systems performance. This paper provides a comprehensive description of the top-level work system design incorporating cognitive automation, a brief outline on the realisation of artificial cognition and the description of an application example taken from the multi-UAV guidance and mission management domain. The experiments show that cognitive cooperation provides a high potential for human performance enhancement on the level of cognitive work. 15. SUBJECT TERMS 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT SAR 18. NUMBER OF PAGES 22 19a. NAME OF RESPONSIBLE PERSON a. REPORT unclassified b. ABSTRACT unclassified c. THIS PAGE unclassified Standard Form 298 (Rev. 8-98) Prescribed by ANSI Std Z39-18 Enhancing Human-Machine System Performance by Introducing Artificial Cognition in Vehicle Guidance Work Systems 18 2 RTO-MP-HFM-181 In order to provide a closer insight into the approach of cognitive and cooperative automation in the following chapters the work system will be introduced as human factors engineering theory and applied to the field of multi-UAV guidance. The work system allows a systematic systems engineering approach of deriving requirements for so-called Artificial Cognitive Units (ACUs). In the next chapter a brief description will be given, how an ACU shall be built, in order to be enabled to yield knowledge-based behaviour. Finally, in the following chapter an example application of multi-UAV guidance and mission management will be described and respective experimental results will be given. 2.0 WORK PROCESS ANALYSIS OF HUMAN-MACHINE SYSTEMS 2.1 Work Process and Work System To figure out a solution to the challenges of future vehicle guidance systems, the first step shall be the characterisation of today available conventional automation in the work process as opposed to the introduction of cognitive automation. Therefore, the consideration of the work system as top-level human factors engineering framework shall be used. The work system (see Figure 1) as a general ergonomics concept has been utilised in a modified definition, adapted to the application domain of human-machine cooperation in flight guidance by [2] and to machine-machine cooperation by [3].