As a new type of marine unmanned intelligent equipment, autonomous underwater vehicle (AUV) has been widely used in the field of ocean observation, maritime rescue, mine countermeasures, intelligence reconnaissance, etc. Especially in the underwater search mission, the technical advantages of AUV are particularly obvious. However, limited operational capability and sophisticated mission environments are also difficulties faced by AUV. To make better use of AUV in the search mission, we establish the DMACSS (distributed multi-AUVs collaborative search system) and propose the ACSLA (autonomous collaborative search learning algorithm) integrated into the DMACSS. Compared with the previous system, DMACSS adopts a distributed control structure to improve the system robustness and combines an information fusion mechanism and a time stamp mechanism, making each AUV in the system able to exchange and fuse information during the mission. ACSLA is an adaptive learning algorithm trained by the RL (Reinforcement learning) method with a tailored design of state information, reward function, and training framework, which can give the system optimal search path in real-time according to the environment. We test DMACSS and ACSLA in the simulation test. The test results demonstrate that the DMACSS runs stably, the search accuracy and efficiency of ACSLA outperform other search methods, thus better realizing the cooperation between AUVs, making the DMACSS find the target more accurately and faster.

Autonomous Underwater Vehicles: Current Activities and Research Opportunities

Multi-AUVs Cooperative Target Search Based on Autonomous Cooperative Search Learning Algorithm

Preface This is a thesis for the degree of Licenciat (a Swedish degree between M.Sc. and Ph.D.) The thesis consists of four parts, where the first part is a comprehensive introduction to the general topic under study. The first part can be considered as the main work whereas the other parts are smaller in-depth studies of particular topics. Part I is essentially a survey paper and is only published in this thesis. It is an effort to pull together different lines of argumentation within cognitive science, philosophy , and artificial intelligence in order to establish a solid foundation for further research. Some of the material in this part originates from: Acknowledgements First of all, I would like to thank my advisor Dr. Eric Astor for his invaluable help and encouragement during the work described in this thesis, Bertil Ekdahl and Robert Pallbo (who together with Eric and I constitute the AI-group) for their willingness to ii discuss and criticize my work from different perspectives, and everyone else at the Department of Computer Science for providing a pleasant research environment. I also want to thank everybody at the Department of Cognitive Science, led by Prof. Peter G ¨ ardenfors, for always providing inspiring discussions on a seemingly unlimited range of topics, and especially Christian Balkenius for reviewing an earlier draft of this thesis. Furthermore, I would like to thank Olof Tilly at the Department of Philosophy for his detailed comments on content and style of the last draft of this thesis, Prof. Lars Löfgren at the Department of Systems Theory for stimulating discussions in the beginning of my graduate studies, and Prof. of Karlskrona/Ronneby for showing interest in my graduate work. Finally, I want to thank Tanja for love and patience, and my parents for their continuous support.

Concepts and Autonomous Agents

This thesis presents a study of the provision of emotions for arti cial agents with the ultimate aim of enhancing their autonomy, i.e. making them more exible, robust and self-su cient. In recent years, the importance of emotions and their assistance to cognition has been increasingly acknowledged. Emotions are no longer considered undesirable or simply useless. Their role in various aspects of human and animal cognition like perception, attention, memory, decision-making and social interaction has been recognised as essential. The importance of emotions is much more evident in social interaction and therefore much of the emotions research done in arti cial systems focuses on the expression and recognition of emotions. However, recent neurophysiological research suggests that emotions also play a crucial part in cognition itself. This thesis investigates ways in which arti cial emotions can improve autonomous behaviour in the domain of a simple, but complete, solitary learning agent. For this purpose, a non-symbolic emotion model was designed and implemented. It takes the form of a recurrent arti cial neural network where emotions in uence the perception of the state of the world, on which they ultimately depend. This is done through a hormone system that acts as a persistence mechanism. This model is somewhat more sophisticated than those usually found in equivalent non-symbolic systems, yet the emotions themselves were restricted to a few simpli ed emotions that do not try to mimic the complexity of the human counterparts, but are a orded by the agent's interaction with the environment. Several hypotheses were investigated of how the emotion model above could be integrated in a reinforcement learning framework which, by itself, provides the base for the adaptiveness necessary for autonomy. Experiments were carried out in a realistic robot simulator that compared the performance of emotional with non-emotional agents in a survival task that consists of maintaining adequate energy levels in an environment with obstacles and energy sources. One of the most common roles attributed to emotions is as source of reinforcement and was therefore examined rst. In experiments with a controller that selects between primitive actions, the reinforcement provided by emotions was found inappropriate because of the time scale discrepancies introduced by the emotion model. The reinforcement provided by emotions proved to be much more successful when used by a controller that selects between behaviours rather than actions, achieving equivalent performance to that of a standard reinforcement function. One of the crucial issues for e cient and productive learning, highlighted by the latter experiments, is to determine exactly when the controller should re-evaluate its decision concerning which behaviour to activate. The emotions proved to be particularly helpful in this role, enabling better performance with substantially less computational e ort than the best suited interruption mechanism using regular time intervals. The modulation of learning parameters such as learning rate and the exploration vs. exploitation ratio was also explored. Experiments suggested that emotions might also be useful for this purpose. This research led to the conclusion that arti cial emotions are a useful construct to have in the domain of behaviour-based autonomous agents, because they provide a unifying way to tackle di erent issues of control, analogous to natural systems' emotions.

Autonomous Underwater Vehicles: Current Activities and Research Opportunities

Citations

Multi-AUVs Cooperative Target Search Based on Autonomous Cooperative Search Learning Algorithm

Concepts and Autonomous Agents

Reinforcement Learning in Autonomous Robots: An Empirical Investigation of the Role of Emotions

Related Papers (5)

Development of Autonomous Underwater Vehicles

Review of Autonomous Underwater Vehicles

Think on the development in autonomous underwater vehicles

Autonomous Underwater Vehicles - achievements and current trends

An Overview of Autonomous Underwater Vehicle Systems and Sensors at Georgia Tech