Early vision algorithms often have a first stage of linear-filtering that 'extracts' from the image information at multiple scales of resolution and multiple orientations. A common difficulty in the design and implementation of such schemes is that one feels compelled to discretize coarsely the space of scales and orientations in order to reduce computation and storage costs. This discretizatio...

Human-centered computation is characterized by at least three features: it must be adaptive, reactive, and it must empower the user to configure and extend the behavior of the systems using her natural modes of interaction. In our previous work we have proposed systems that address the first two features. In this paper we present Alfred – a natural end user programming interface for Intelligent...

The mobile agent paradigm has been developed to solve problems in dynamic and heterogeneous environment [8]. The agent model of this paper is quite general. It is based on the concepts of agents, communication links and places. An agent is an entity which executes an algorithm: it can move from place to place (with some data and its algorithm) through communication links and it can make local c...

This paper describes Probabilistic Bias Evaluation (PBE), a method for evaluating learning biases formally analyzing the tradeoff between the expected accuracy and complexity of alternative biases. Intelligent agents must filter out irrelevant aspects of the environment, in order to minimize the costs of learning. In PBE, probabilistic background knowledge about relevance is used to compute exp...

Intelligent agents are powerful tools for complex and dynamic problems. Belief Desire Intension (BDI) is one of the most popular agent architectures for reactive goal directed agents. Planning is intrinsic for intelligent behaviour. But planning from first principle is costly in terms of computation time and resources. BDI agents retain their reactive property by avoiding planning from real-tim...

The importance of mutual monitoring in recommender systems based on learning agents derives from the consideration that a learning agent needs to interact with other agents in its environment in order to improve its individual performances. In this paper we present a novel framework, called EVA, that introduces a strategy to improve the performances of recommender agents based on a dynamic comp...

This paper presents a principled way to think about articulated movement for artificial agents and a measurement of platforms that produce such movement. In particular, in human-facing scenarios, the shape evolution of robotic platforms will become essential in creating systems that integrate – and communicate – with human counterparts. This paper provides a tool to measure the expressive capac...

Autonomous systems must operate in dynamic, unpredictable environments in real time. The task of ying a plane is an example of an environment in which the agent must respond quickly to unexpected events while pursuing goals at di erent levels of complexity and granularity. We present a system, Air-Soar, that achieves intelligent control through fully symbolic reasoning in a hierarchy of simulta...

The evolution of SAT technology over the last decade has motivated its application in model checking, initially through the utilization of SAT in bounded model checking (BMC) and, more recently, in unbounded model checking (UMC). This paper addresses the utilization of interpolants in UMC and proposes two techniques for improving the original interpolant-based UMC algorithm. These techniques in...

In this paper we present intelligent visibility-based techniques allowing efficient processing of 3D scenes in order to be used in real time in computer games. The presented techniques allow real time use of 3D scenes either by simplifying the scene models (by suppressing useless details or by using improved image-based modelling) or by off-line automatic camera path pre-computation allowing fa...