Salvatore Gaglio

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.

Method fragments for agent design methodologies: from standardisation to research

The method engineering paradigm enables designers to reuse portions of design processes (called method fragments or chunks in literature) to build processes that are expressly tailored for realising a system that is specific for some problem or development context. This paper initially reports on the standardisation attempt carried out by the FIPA Methodology Technical Committee (TC) and then presents the research activities we did starting from that work; these resulted in a slightly different definition of some of the most important elements of the approach in order to support a multiview representation of the fragment (the views are process, reuse, storing and implementation). The paper also describes the documents we used for representing a fragment and concludes with an example.

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.

Human Activity Recognition Process Using 3-D Posture Data

In this paper, we present a method for recognizing human activities using information sensed by an RGB-D camera, namely the Microsoft Kinect. Our approach is based on the estimation of some relevant joints of the human body by means of the Kinect; three different machine learning techniques, i.e., K-means clustering, support vector machines, and hidden Markov models, are combined to detect the postures involved while performing an activity, to classify them, and to model each activity as a spatiotemporal evolution of known postures. Experiments were performed on Kinect Activity Recognition Dataset, a new dataset, and on CAD-60, a public dataset. Experimental results show that our solution outperforms four relevant works based on RGB-D image fusion, hierarchical Maximum Entropy Markov Model, Markov Random Fields, and Eigenjoints, respectively. The performance we achieved, i.e., precision/recall of 77.3% and 76.7%, and the ability to recognize the activities in real time show promise for applied use.

A conversational agent based on a conceptual interpretation of a data driven semantic space

In this work we propose an interpretation of the LSA framework which leads to a data-driven “conceptual” space creation suitable for an “intuitive” conversational agent. The proposed approach allows overcoming the limitations of traditional, rule-based, chat-bots, leading to a more natural dialogue.

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.

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.

Using and Extending the SPEM Specifications to Represent Agent Oriented Methodologies

Situational Method Engineering used for constructing ad-hoc agent oriented design processes is grounded on a well defined set of phases that are principally based on reuse of components coming from existing agent design processes; these components have to be stored in a repository. The identification and extraction of these components could take large advantages from the existence of a standardized representation of the design processes they come from. In this paper we illustrate our solution based on SPEM 2.0 specifications for modelling agent design processes and extending them when necessary to meet the specific needs we faced in our experiments.

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.