Active vision systems have the capability of continuously interacting with the environment. The rapidly changing environment of such systems means that it is attractive to replace static representations with visual routines that compute information on demand. Such routines place a premium on image data structures that are easily computed and used. The purpose of this paper is to propose a general active vision architecture based on efficiently computable iconic representations. This architecture employs two primary visual routines, one for identifying the visual image near the fovea (object identification), and another for locating a stored prototype on the retina (object location). This design allows complex visual behaviors to be obtained by composing these two routines with different parameters. The iconic representations are comprised of high-dimensional feature vectors obtained from the responses of an ensemble of Gaussian derivative spatial filters at a number of orientations and...

this paper, we describe a hierarchical network model of visual recognition that explains these experimental observations by using a form of the extended Kalman filter as given by the Minimum Description Length (MDL) principle. The model dynamically combines input-driven bottom-up signals with expectation-driven top-down signals to predict current recognition state. Synaptic weights in the model are adapted in a Hebbian manner according to a learning rule also derived from the MDL principle. The resulting prediction/learning scheme can be viewed as implementing a form of the Expectation-Maximization (EM) algorithm. The architecture of the model posits an active computational role for the reciprocal connections between adjoining visual cortical areas in determining neural response properties. In particular, the model demonstrates the possible role of feedback from higher cortical areas in mediating neurophysiological effects due to stimuli from beyond the classical receptive field. Si

This paper presents U-Tree, a reinforcement learning algorithm that uses selective attention and shortterm memory to simultaneously address the intertwined problems of large perceptual state spaces and hidden state. By combining the advantages of work in instance-based (or "memory-based") learning and work with robust statistical tests for separating noise from task structure, the method learns quickly, creates only task-relevant state distinctions, and handles noise well. U-Tree uses a tree-structured representation, and is related to work on Prediction Suffix Trees [Ron et al., 1994] , Parti-game [Moore, 1993] , G-algorithm [Chapman and Kaelbling, 1991] , and Variable Resolution Dynamic Programming [Moore, 1991] . It builds on Utile Suffix Memory [McCallum, 1995c] , which only used short-term memory, not selective perception. The algorithm is demonstrated solving a highway driving task in which the agent weaves around slower and faster traffic. The agent uses active perception with ...

All intelligence relies on search --- for example, the search for an intelligent agent's next action. Search is only likely to succeed in resource-bounded agents if they have already been biased towards finding the right answer. In artificial agents, the primary source of bias is engineering. This dissertation

The emerging viewpoint of embodied cognition holds that cognitive processes are deeply rooted in the body’s interactions with the world. This position actually houses a number of distinct claims, some of which are more controversial than others. This paper distinguishes and evaluates the following six claims: 1) cognition is situated; 2) cognition is time-pressured; 3) we off-load cognitive work onto the environment; 4) the environment is part of the cognitive system; 5) cognition is for action; 6) off-line cognition is body-based. Of these, the first three and the fifth appear to be at least partially true, and their usefulness is best evaluated in terms of the range of their applicability. The fourth claim, I argue, is deeply problematic. The sixth claim has received the least attention in the literature on embodied cognition, but it may in fact be the best documented and most powerful of the six claims.

Children learn a variety of verbs for hand actions starting in their second year of life. The semantic distinctions can be subtle, and they vary across languages, yet they are learned quickly. Howis this possible? This dissertation explores the hypothesis that to explain the acquisition and use of action verbs, motor control must be taken into account. It presents a model of embodied semantics|based on the principles of neural computation in general and on the human motor system in particular|which takes a set of labelled actions and learns both to label novel actions and to obey verbal commands. Akey feature of the model is the executing schema, anactivecontroller mechanism which, by actually driving behavior, allows the model to carry out verbal commands. A hard-wired mechanism links the activity of executing schemas to a set of linguistically important features including hand posture, joint motions, force, aspect and goals. The feature set is relatively small and is xed, helping to make learning tractable. Moreover, the use of traditional feature structures facilitates the use of model merging, a Bayesian probabilistic learning algorithm which rapidly learns plausible word meanings, automatically determines an appropriate number of senses for each verb, and can plausibly be mapped to a connectionist recruitment

www.elsevier.com/locate/cognit This paper argues that a theory of situated vision, suited for the dual purposes of object recognition and the control of action, will have to provide something more than a system that constructs a conceptual representation from visual stimuli: it will also need to provide a special kind of direct (preconceptual, unmediated) connection between elements of a visual representation and certain elements in the world. Like natural language demonstratives (such as `this ' or `that') this direct connection allows entities to be referred to without being categorized or conceptualized. Several reasons are given for why we need such a preconceptual mechanism which individuates and keeps track of several individual objects in the world. One is that early vision must pick out and compute the relation among several individual objects while ignoring their properties. Another is that incrementally computing and updating representations of a dynamic scene requires keeping track of token individuals despite changes in their properties or locations. It is then noted that a mechanism meeting these requirements has already been proposed in order to account for a number of disparate empirical phenomena, including subitizing, search-subset selection and multiple object tracking

The agent-based approach emphasizes the importance of learning through organism-environment interaction. This approach is part of a recent trend in computational models of learning and development toward studying autonomous organisms that are embedded in virtual or real environments. In this paper we introduce the concepts of online and offline sampling and highlight the role of online sampling in agent-based models. After comparing the strengths of each approach for modeling particular developmental phenomena and research questions, we describe a recent agent-based model of infant causal perception. We conclude by discussing some of the present limitations of agent-based models and suggesting how these challenges may be addressed. © 2001 Academic Press Computational models of learning and development are playing an increasingly critical role in child development research (Cassidy, 1990;

In everyday tasks, selecting actions in the proper sequence requires a continuously updated representation of temporal context. Many existing models address this problem by positing a hierarchy of processing units, mirroring the roughly hierarchical structure of naturalistic tasks themselves. Such an approach has led to a number of difficulties, including a reliance on overly rigid sequencing mechanisms, an inability to account for context sensitivity in behavior, and a failure to address learning. We consider here an alternative framework, according to which the representation of temporal context is facilitated by recurrent connections within a network mapping from environmental inputs to actions. Applying this approach to a specific, and in many ways prototypical, everyday task (coffee-making), we examine its ability to account for several central characteristics of normal and impaired human performance. The model we consider learns to deal flexibly with a complex set of sequencing constraints, encoding contextual information at multiple time-scales within a single, distributed internal representation. Mildly degrading this context representation leads

We argue that the analysis of agent#environmentinteractions should be extended to include the conventions and invariants maintained by agents throughout their activity. We refer to this thicker notion of environmentasalifeworld and present a partial set of formal tools for describing structures of lifeworlds and the ways in which they computationally simplify activity. As one speci#c example, we apply the tools to the analysis of the Toast system and showhowversions of the system with very di#erent control structures in fact implement a common control structure together with di#erent conventions for encoding task state in the positions or states of objects in the environment.