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.

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. © 1998 Elsevier Science B.V. All rights reserved.

Was King Arthur a King by Definition?

Current research in knowledge representation distinguishes between descriptional and assertional interpretations of semantic nets. This paper explores theoretical and applicative problems, which arise from that distinction in a historic domain. A prolog implementation of KL-ONE is used as a vehicle to compare the various alternatives available to represent knowledge related to single elements of the domain insertion or not of this knowledge in semantic nets in their descriptional sense. The final section of the paper discusses the problem in relation to the theories concerning the functioning of proper names from a logical and philosophical point of view.

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 s…

<title>HAP: a hybrid system for reasoning about actions and plans in robotics</title>

The paper describes the main ideas and principles of HAP (Hybrid representation of Actions and Plans), a system for hybrid representation and reasoning in advanced robotics. In this context, hybrid representation refers to the integration of both symbolic and analogic knowledge representation paradigms. In particular, the logic/symbolic component is based on a KL-ONE-like representation language. The system embeds "analogic experts", that are concurrent procedures operating in a direct and fast way on the world representation. These "experts" help the system in planning a correct temporal sequence of actions. As a reference scenario, assembly (and disassembly) problems are considered. The a…

Towards a conceptual representation of actions

An autonomous robot involved in missions should be able to generate, update and process its own actions. It is not plausible that the meaning of the actionsus ed by the robot isgiv en form the outside of the system itself. Rather, this meaning should be anchored to the world through the perceptual abilitiesof the robot. We present an approach to conceptual action representation based on a "conceptual" level that actsasan intermediate level between symbolsand data coming form sensors. Symbolic representations are interpreted by mapping them on the conceptual level through a mapping mechanism based on artificial neural networks.

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 comi…

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 and Chandrasekaran (2007)]. In this p…

Planning by imagination in Cicerobot, a robot for museum tours

An associative link from geometric to symbolic representations in artificial vision

Recent approaches to modelling the reference of internal symbolic representations of intelligent systems suggest to consider a computational level of a subsymbolic kind. In this paper the integration between symbolic and subsymbolic processing is approached in the framework of the research work currently carried on by the authors in the field of artificial vision. An associative mapping mechanism is defined in order to relate the constructs of the symbolic representation to a geometric model of the observed scene.

A Hybrid Neural Network Architecture for Dynamic Scene Understanding

A hyprdid (neural and symbolic) architecture allowing for a deep understanding of moving scenes is described. The architecture is based on a working and effective integration among three levels of representation of data coming out from external sensors.

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 ling…

Anchoring symbols to conceptual spaces: the case of dynamic scenarios.

In recent years, there have been several proposals for the realization of models inspired to biological solutions for pattern recognition. In this work we propose a new approach, based on a hierarchical modular structure, to realize a system capable to learn by examples and recognize objects in digital images. The adopted techniques are based on multiresolution image analysis and neural networks. Performance on two different data sets and experimental timings on a single instruction multiple data (SIMD) machine are also reported.

Symbolic and conceptual representation of dynamic scenes: Interpreting situation calculus on conceptual spaces

In (Chella et al. [1,2]) we proposed a framework for the representation of visual knowledge, with particular attention to the analysis and the representation of scenes with moving objects and people. One of our aims is a principled integration of the models developed within the artificial vision community with the propositional knowledge representation systems developed within symbolic AI. In the present note we show how the approach we adopted fits well with the representational choices underlying one of the most popular symbolic formalisms used in cognitive robotics, namely the situation calculus.

Knowledge representation for robotic vision based on conceptual spaces and attentive mechanisms

A new cognitive architecture for artificial vision is proposed. The architecture is aimed for an autonomous intelligent system, as several cognitive hypotheses have been postulated as guidelines for its design. The design is based on a conceptual representation level between the subsymbolic level processing the sensory data, and the linguistic level describing scenes by means of a high-level language. The architecture is also based on the active role of a focus of attention mechanism in the link between the conceptual and the linguistic level. The link between the conceptual level and the linguistic level is modelled as a time-delay attractor neural network.

A hybrid scheme for action representation

Strong deficiencies are present in symbolic models for action representation and planning, regarding mainly the difficulty of coping with real, complex environments. These deficiencies can be attributed to several problems, such as the inadequacy in coping with incompletely structured situations, the difficulty of interacting with visual and motorial aspects, the difficulty in representing low-level knowledge, the need to specify the problem at a high level of detail, and so on. Besides the purely symbolic approaches, several nonsymbolic models have been developed, such as the recent class of subsym-bolic techniques. A promising paradigm for the modeling of reasoning, which combines feature…

Perceptual Anchoring via Conceptual Spaces

Perceptual anchoring is the problem of creating and maintaining in time the connection between symbols and sensor data that refer to the same physical objects. This is one of the facets of the general problem of integrating symbolic and non-symbolic processes in an intelligent system. Gärdenfors’ conceptual spaces provide a geometric treatment of knowledge which bridges the gap between the symbolic and subsymbolic approaches. As such, they can be used for the study of the anchoring problem. In this paper, we propose a computational framework for anchoring based on conceptual spaces. Our framework exploits the geometric structure of conceptual spaces for many of the crucial tasks of anchorin…

Conceptual spaces for anchoring