Abstract not found

This thesis presents a study of the provision of emotions for artificial agents with the ultimate aim of enhancing their autonomy, i.e. making them more flexible, robust and self-sufficient. 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 insocial interaction and therefore much of the emotions research done in artificial 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 artificial 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 artificial neural network where emotions influence the perception

A routine is a habitually repeated performance of some actions. Agents use routines to guide their everyday activities and to enrich their abstract concepts about acts. This dissertation addresses the question of how an agent who is engaged in ordinary, routine activities changes its behavior over time, how the agent's internal representations about the world is affected by its interactions, and what is a good agent architecture for learning routine interactions with the world. In it, I develop a theory that proposes several key processes: (1) automaticity, (2) habituation and skill refinement, (3) abstraction-bychunking, and (4) discovery of new knowledge chunks. The process of automaticity caches the agent's knowledge about actions into a flat stimulus-response data structure that eliminates knowledge of action consequences. The stimulus-response data structure produces a response to environmental stimuli in constant time. The process of habituation and skill refinement uses environm...

If behavior networks, which use spreading activation to select actions, are analogous to connectionist methods of pattern recognition, then recurrent behavior networks, which use energy minimization, are analogous to Hopfield networks. Hopfield networks memorize patterns by making them attractors. Similarly, each behavior of a recurrent behavior network should be an attractor of the network, to inhibit fruitless, repeated switching between different behaviors in response to small changes in the environment and in motivations. I overcome two major objections to this view, and demonstrate that the performance in a test domain of the Do the Right Thing recurrent behavior network is improved by redesigning it to create desirable attractors and basins of attraction. I further show that this performance increase is correlated with an increase in persistence and a decrease in undesirable behavior-switching. On a more general level, this work encourages the study of action selection as a dynam...

In contrast to "conscious", reasoned behaviors, we consider behaviors that are automatic and unreasoned to be "unconscious". The latter are commonly

We present a computational model of color categorization using a normalized Gaussian function of perceptual color space coordinates as the basic category model, and an application based on the model that can name, point out, and select colors in images, and provide a confidence or (fuzzy) membership value for each categorial judgement. We quantify the performance of our model relative to existing data about human color naming behavior, and relative to the use of different color spaces, including a novel one derived from neurophysiological measurements. The application we present is to some extent able to deal with the color constancy problem in real images made in an unmodified office environment with low-grade uncalibrated equipment. We present some empirical results with an example of this kind of image. The novelty of the approach lies in the fact that it models graded or fuzzy color categories as found in anthropological, psychological and psychophysical color perception work, and...

Routines are patterns of interaction between an agent and its world. Getting in or out of a car, changing lane, and flipping pages of a book can be routines for an agent if the agent consistently engages in these activities in a similar way. I.e., a task for an agent is a routine if the agent that has choices about how to accomplish that task, nevertheless does it in the same way. Consistently putting on the left leg of pants before putting on the right leg would be a routine for an agent. A routine is either imposed upon the agent (a plan at the conscious level to be followed), in which case it need not be discovered, or performed by the agent automatically, i.e., unconsciously. The latter may or may not ever be discovered, i.e., noticed and made conscious. However, the existence of such a routine may guide the agents actions. If it remains unconscious, it aids in choosing among competing actions unconsciously as an unexplained tendency or a preference. If it is noticed and made consc...

GLAIR (Grounded Layered Architecture with Integrated Reasoning) is a multi-layered cognitive architecture for embodied agents operating in real, virtual, or simulated environments containing other agents. The highest layer of the GLAIR Architecture, the Knowledge Layer (KL), contains the beliefs of the agent, and is the layer in which conscious reasoning, planning, and act selection is performed. The lowest layer of the GLAIR Architecture, the Sensori-Actuator Layer (SAL), contains the controllers of the sensors and effectors of the hardware or software robot. Between the KL and the SAL is the Perceptuo-Motor Layer (PML), which grounds the KL symbols in perceptual structures and subconscious actions, contains various registers for providing the agent’s sense of situatedness in the environment, and handles translation and communication between the KL and the SAL. The motivation for the development of GLAIR has been “Computational Philosophy”, the computational understanding and implementation of human-level intelligent behavior without necessarily being bound by the actual implementation of the human mind. Nevertheless, the approach has been inspired by human psychology and biology.

A mobile robot operating in a real world environment requires the ability to cope with uncertain, incomplete, and approximate information in real time. In this paper, a new architecture for controlling a mobile robot which takes abstracts goals into consideration is described. Schema theory is used to specify the primitive behaviours of the robot and these behaviours are combined by a fuzzy-logic controller . Simulation results are presented which demonstrate the feasibility of the approach. 1 Introduction There are many approaches to the control of mobile robots which interact with a dynamic, uncertain environment. Brooks [4] discusses the problems of applying traditional AI techniques to mobile robot control and instead proposes a physically-grounded, reactive subsumption architecture for the intelligent control of mobile robots. This view is challenged in [5], where the authors state that although a Brooksian behaviour generation approach can go a long way towards modelling intel...

I address the issue of cognitive control of a robot by implementing the GLAIR architecture in a.NET environment. Firstly, I control the basic functions of a robot and give it primitive behaviors. Secondly, I approach the issue of cognitive control by examining what it means to be cognitive for a robot and what would be necessary to implement such a system. Finally, I develop an application implemented as a finite state machine to realize some of these requirements and