Marcello Frixione

A cognitive architecture for artificial vision

Abstract A new cognitive architecture for artificial vision is proposed. The architecture, aimed at an autonomous intelligent system, is cognitive in the sense that several cognitive hypotheses have been postulated as guidelines for its design. The first one is the existence of a conceptual representation level between the subsymbolic level, that processes sensory data, and the linguistic level, that describes scenes by means of a high level language. The conceptual level plays the role of the interpretation domain for the symbols at the linguistic levels. A second cognitive hypothesis concerns the active role of a focus of attention mechanism in the link between the conceptual and the linguistic level: the exploration process of the perceived scene is driven by linguistic and associative expectations. This link is modeled as a time delay attractor neural network. Results are reported obtained by an experimental implementation of the architecture.

Understanding dynamic scenes

We propose a framework for the representation of visual knowledge in a robotic agent, with special attention to the understanding of dynamic scenes. According to our approach, understanding involves the generation of a high level, declarative description of the perceived world. Developing such a description requires both bottom-up, data driven processes that associate symbolic knowledge representation structures with the data coming out of a vision system, and top-down processes in which high level, symbolic information is in its turn employed to drive and further refine the interpretation of a scene. On the one hand, the computer vision community approached this problem in terms of 2D/3D shape reconstruction and of estimation of motion parameters. On the other, the AI community developed rich and expressive systems for the description of processes, events, actions and, in general, of dynamic situations. Nevertheless, these two approaches evolved separately and concentrated on different kinds of problems. We propose an architecture that integrates these two traditions in a principled way. Our assumption is that a link is missing between the two classes of representations mentioned above. In order to fill this gap, we adopt the notion of conceptual space (CS—Gardenfors (2000)), a representation where information is characterized in terms of a metric space. A CS acts as an intermediate representation between subconceptual (i.e., not yet conceptually categorized) information, and symbolically organized knowledge. The concepts of process and action have immediate characterizations in terms of structures in the conceptual space. The architecture is illustrated with reference to an experimental setup based on a vision system operating in a scenario with moving and interacting people.

Anchoring symbols to conceptual spaces: the case of dynamic scenarios

Abstract This paper deals with the anchoring of one of the most influential symbolic formalisms used in cognitive robotics, namely the situation calculus , to a conceptual representation of dynamic scenarios. Our proposal is developed with reference to a cognitive architecture for robot vision. An experimental setup is presented, aimed at obtaining intelligent monitoring operations of a robotic finger starting from visual data.

Tractable Competence

In the study of cognitive processes, limitations on computational resources (computing time and memory space) are usually considered to be beyond the scope of a theory of competence, and to be exclusively relevant to the study of performance. Starting from considerations derived from the theory of computational complexity, in this paper I argue that there are good reasons for claiming that some aspects of resource limitations pertain to the domain of a theory of competence.

An architecture for autonomous agents exploiting conceptual representations

An architecture for autonomous agents is proposed that integrates the functional and the behavioral approaches to robotics. The integration is based on the introduction of a conceptual level, linking together a subconceptual, behavioral, level, and a linguistic level, encompassing symbolic representation and data processing. The proposed architecture is described with reference to an experimental setup, in which the robot task is that of building a significant description of its working environment.

A cognitive architecture for robot self-consciousness

OBJECTIVE One of the major topics towards robot consciousness is to give a robot the capabilities of self-consciousness. We propose that robot self-consciousness is based on higher order perception of the robot, in the sense that first-order robot perception is the immediate perception of the outer world, while higher order perception is the perception of the inner world of the robot. METHODS AND MATERIAL We refer to a robot cognitive architecture that has been developed during almost 10 years at the RoboticsLab of the University of Palermo. The architecture is organized in three computational areas. The subconceptual area is concerned with the low level processing of perceptual data coming from the sensors. In the linguistic area, representation and processing are based on a logic formalism. In the conceptual area, the data coming from the subconceptual area are organized in conceptual categories. RESULTS To model higher order perceptions in self-reflective agents, we introduce the notion of second-order points in conceptual space. Each point in this space corresponds to a self-reflective agent, i.e., the robot itself, persons, and other robots with introspective capabilities. CONCLUSIONS The described model of robot self-consciousness, although effective, highlights open problems from the point of view of the computational requirements of the current state-of-art computer systems. Some future works that lets the robot to summarize its own past experiences should be investigated.

Conceptual Spaces for Computer Vision Representations

A framework for high-level representations in computer vision architectures is described. The framework is based on the notion of conceptual space. This approach allows us to define a conceptual semantics for the symbolic representations of the vision system. In this way, the semantics of the symbols can be grounded to the data coming from the sensors. In addition, the proposed approach generalizes the most popular frameworks adopted in computer vision.

Representing concepts in formal ontologies. Compositionality vs. typicality effects

The problem of concept representation is relevant for many subfields of cognitive research, including psychology and philosophy, as well as artificial intelligence. In particular, in recent years it has received a great deal of attention within the field of knowledge representation, due to its relevance for both knowledge engineering as well as ontology-based technologies. However, the notion of a concept itself turns out to be highly disputed and problematic. In our opinion, one of the causes of this state of affairs is that the notion of a concept is, to some extent, heterogeneous, and encompasses different cognitive phenomena. This results in a strain between conflicting requirements, such as compositionality, on the one hand and the need to represent prototypical information on the other. In some ways artificial intelligence research shows traces of this situation. In this paper, we propose an analysis of this current state of affairs. Since it is our opinion that a mature methodology with which to approach knowledge representation and knowledge engineering should also take advantage of the empirical results of cognitive psychology concerning human abilities, we outline some proposals for concept representation in formal ontologies, which take into account suggestions from psychological research. Our basic assumption is that knowledge representation systems whose design takes into account evidence from experimental psychology (and which, therefore, are more similar to the human way of organizing and processing information) may therefore give better results in many applications (e.g. in the fields of information retrieval and semantic web).

A Cognitive Hybrid Model for Autonomous Navigation

Action representation and planning is one among the most important research fields in which it has been experienced the failure of single paradigms in isolation to solve real, complex problems. The goal of this paper is to present a system for action representation and reasoning in complex, real-world, and real time scenarios, characterised by the integration of different representation paradigms: symbolic, diagrammatic, and procedural. In this sense the system is called “hybrid”. The paper focuses on the cognitive model and on the representation and reasoning system. A realistic navigation system for the guidance and control of autonomous mobile robots is used as an example to describe the potentiality of the system in solving real complex problems and it is currently being tested in an indoor environment.

Conceptual Spaces for Cognitive Architectures: A lingua franca for different levels of representation

During the last decades, many Cognitive Architectures (CAs) have been realized adopting different assumptions about the organization and the representation of their knowledge level. Some of them (e.g. SOAR (Laird, 2012)) adopt a classical symbolic approach, some (e.g. LEABRA O’Reilly and Munakata (2000)) are based on a purely connectionist model, while others (e.g. CLARION (Sun, 2006)) adopt a hybrid approach combining connectionist and symbolic representational levels. Additionally, some attempts (e.g. biSOAR) trying to extend the representational capacities of CAs by integrating diagrammatical representations and reasoning are also available (Kurup & Chandrasekaran, 2007). In this paper we propose a reflection on the role that Conceptual Spaces, a framework developed by Gardenfors (2000) more than fifteen years ago, can play in the current development of the Knowledge Level in Cognitive Systems and Architectures. In particular, we claim that Conceptual Spaces offer a lingua franca that allows to unify and generalize many aspects of the symbolic, sub-symbolic and diagrammatic approaches (by overcoming some of their typical problems) and to integrate them on a common ground. In doing so we extend and detail some of the arguments explored by Gardenfors (1997) for defending the need of a conceptual, intermediate, representation level between the symbolic and the sub-symbolic one. In particular we focus on the advantages offered by Conceptual Spaces (with respect to symbolic and sub-symbolic approaches) in dealing with the problem of compositionality of representations based on typicality traits. Additionally, we argue that Conceptual Spaces could offer a unifying framework for interpreting many kinds of diagrammatic and analogical representations. As a consequence, their adoption could also favor the integration of diagrammatical representation and reasoning in CAs.