Dual Process Control Models in the Brain and Machines with Application to Autonomous Vehicle Control

The field of autonomous vehicle control (AVC) is a rapidly growing one which promises improved performance, fuel economy, emission levels, comfort and safety.Application of conventional control methods can generate adequate results under restricted circumstances,but have high design and computational costs and are fragile under real environmental changes (winds, proximity of other vehicles etc).There is therefore a pressing need for alternative approaches to AVC.One particularly promising alternative is to break the task into a set of sub-tasks,each valid over a restricted range of conditions, and to switch between them when required.Dr Hussain's group in Stirling has been developing a novel framework for such'modular learning controllers'over the last few years.The problem of selecting from amongst a set of actions or behaviours is also a central problem for animals.There is growing evidence that a set of central brain nuclei -the basal ganglia- are used by all vertebrates to help solve this problem.Research in Prof Gurney's lab has,over the last decade,been developing computational models of how the basal ganglia support behavioural selection.Thus,we believe that the basal ganglia act as a central 'selector' or 'switch' in all vertebrate brains,in that they examine requests for behaviour and allow the most urgent or salient requests to be selected for behavioural expression Given the similarity between the two problems' domains of AVC and action selection in animals, this project aims to leverage new results from psychology and neurobiology (discovered in Prof Gurney's lab) and apply them to the AVC controllers under development in Dr Hussain's group.One aspect of action selection which appears particularly promising in this respect has to do with there being two general modes of behavioural selection.To see this,consider the following scenarios.First,imagine making tea soon after getting out of bed in the morning in your own kitchen.You probably know exactly what to do without having to consciously be aware of it--the location of the tea,milk,sugar,kettle and water-tap are all well learned, as is the motor actions required to interact with the objects in these locations.Introspection after the event leads us to use terms such as;`I did it in my sleep' or `I was on auto-pilot'.Now consider doing the same task if you are staying at a friend's house for the first time.A completely different strategy appears to be used.Thus,we have to be alert, explore, and use high level cognitive knowledge that we hope generalises well (for example,we hope the tea will be in a cupboard near the sink, not in the living room)These two modes of control are well recognised in the psychological literature as automatic and controlled or executive processing respectively.There is also growing neurobiological evidence for the existence of different control regimes, supported by different brain systems.In addition, the new AVC systems developed at Stirling have two major components:a high level 'supervisory' controller and a set of basic (but adaptable) controllers that direct the actual vehicle behaviour.We believe the similarities with the biological notions of executive and automatic control are highly indicative of a mutually fruitful interaction between neuroscientific and control theoretic domains in this regard.Thus, while our general aim is to exploit a range of similarities between systems in control engineering and the animal brain, we will focus specifically on the concepts of automatised and controlled (or executive) processing and how they might map onto modular AVC solutions of the kind described above.The outcome should be a new generation real-time AVC controller, more directly inspired by the biological ideas. We will work with our industrial partners (Industrial Systems Control and SciSys) to evaluate the benefits of these novel controllers within the context of regular road driving and planetary rover vehicles.

The novel and more directly biologically inspired technologies that will emerge from the proposed interdisciplinary research will have a direct and potentially ground breaking impact on the technological base underpinning much of the UK's autonomous systems control industry. The envisaged technologies will embed integrated cognitive features (like learning, event-driven adaptation, decision making, action selection) that will enhance the system autonomy, reliability and performance. From an economic view point, the next generation of complex industrial processes and systems making use of cognitive control would be able to maintain operation for longer periods before it is necessary to shut down for maintenance. One particular class of complex systems that will be addressed in the project is that of autonomous vehicle control (AVC). In this arena, whilst computers are increasingly assuming driving-related tasks in some commercial vehicles, it is well recognised that, at present, conventional computer generated control algorithms for autonomous driving cannot match the performance of human drivers. This project is ideally placed to contribute to the development of the next generation of in-vehicle computing systems that will integrate essential aspects of cognitive intelligence and behaviours to allow future autonomous vehicles to manage driving actuators in a way similar to humans. Preliminary results (using realistic validated complex vehicle models) have demonstrated the ability of the current modular controllers to both simultaneously track desired longitudinal and lateral displacements, and vehicle speed changes, and to achieve the desired speed of response, whilst penalising excessive control actions - with significant potential implications for both fuel and emission economy. The proposed industrial collaboration with SciSys will also impact the development of next generation low-cost autonomous rover vehicle control systems for challenging planetary missions. Interplanetary exploration is increasingly likely to be conducted by robotic missions as they represent a considerable saving in mission cost compared to their human counterparts. The industrial support of SciSys Ltd. will significantly enhance the commercialization potential of project outcomes in this arena. Working with our other industrial partner, Industrial Systems & Control (ISC) Ltd., will also help maximise project impact. Their advice on simulation test-bed design and access to their benchmark AVC case study will ensure project work is kept relevant for commercialisation. ISC will also help assess the commercialisation potential of any outcomes with a view to negotiating a license agreement with one of their major (partner) companies. The project will also have an impact in the scientific domains of neuroscience and theoretical psychology. While there is no immediate economic impact for the work in these areas, insights into the fundamental computations performed by the brain during executive and automatic processing will certainly underpin future research into neural developmental disorders believed to involve deficits in one of these processing styles. These include (for example) attention deficit hyperactivity disorder (ADHD), dyslexia and dyspraxia. More generally, the project will impact all areas where cognitive decision making is a current focus of (inter-disciplinary) research including: robotics, experimental neuroscience, and computational neuroscience of frontal and prefrontal cortices. Finally, the project will also have a direct impact on the future collaborative research productivity potential of the investigators themselves as well on the interdisciplinary research and career development prospects of the post-doctoral researcher appointed on this challenging project.