Fabiano Rogerio Corrêa

Semantic mapping with a probabilistic description logic

Semantic mapping employs explicit labels to deal with sensor data in robotic mapping processes. In this paper we present a method for boosting performance of spatial mapping, through the use of a probabilistic ontology, expressed with a probabilistic description logic. Reasoning with this ontology allows segmentation and tagging of sensor data acquired by a robot during navigation; hence a robot can construct metric maps topologically. We report experiments with a real robot to validate our approach, thus moving closer to the goal of integrating mapping and semantic labeling processes.

Omnidirectional stereovision system for occupancy grid

Vision systems provide large amount of data to robots about its environment. Particularly, an omnidirectional vision system provides information in all directions in just one image. By processing a pair of omnidirectional images it is possible to obtain distances between the robot and the objects in its working environment. Using only an omnidirectional stereovision system as source of information to create a stochastic representation of the environment, known as occupancy grids, a robot can determine the probability of occupation of the space and navigate autonomously. This article shows a stereo algorithm with a matching restricted by geometrical properties of the vision system using directly the omnidirectional image and a model of that sensor to update an occupancy grid

Is BIM Big Enough to Take Advantage of Big Data Analytics

As the Architecture, Engineering, Construction, and Facilities Management industry undergoes a profound change with Building Information Modeling (BIM), it seems the right moment to properly re-structure the inherent processes to promote a new wave of innovation. To leverage digital information from each individual project into business value for the whole industry, researchers must borrow knowledge and solutions from computational fields, such as Machine Learning, Artificial Intelligence, Data Mining and Data Science. They will provide a guide to the development, and even transformation of current BIM processes, with potential for development of new tools and automation of many tasks. What is not entirely clear is if BIM could take advantage also from Big Data Analytics, as some professionals are been advocating. In this paper, the author analyzes Big Data problems and the BIM context, and argues that BIM could not immediately take advantage from Big Datainfrastructure. Nevertheless, a route of development is suggested, which extends BIM from its predominantly building-focused models to models that encompass an entire city, which certainly will demand Big Data Analytics. Thus, a new City Information Modeling seems to be the right path of development for BIM as it turns to be integrated with Geographic Information Systems and will lead to tools that would be adequate for future Smart Cities planning and management.

Semi-automatic Codification of Economical Activities with Support Vector Machines

The correct attribution of codes to economical activities is of ultimate importance for fiscal and administrative purposes. In a joint effort involving federal, state and city business regulating offices, the unification and automation of this codification process is in progress. As the input information is in the form of free textual entries, techniques used in multi-class, multi-label text categorization are well suited. Due to the fact that the possible codes are in the order of one thousand, this problem is under investigation through an approach based on a hierarchical use of Support Vector Machines (SVM). The hierarchical organization of several SVMs split the problem into smaller ones and allows a fine tuning of the code attribution obeying the very hierarchy present in the table describing the codes. This paper will introduce the problem, describe the proposed approach based on SVMs and show some results that validate the approach.

CORBA-BASED ARCHITECTURE FOR COOPERATIVE PERCEPTION

Abstract In these networked days cooperative perception means that multiple robots with multiple sensors can share their data creating a common knowledge base so that they can plan and interact with the environment in a more appropriate and efficient way. We propose in this work an architecture for cooperative perception for mobile robots based on distributed objects in a network. The implementation follow the CORBA specification, created to facilitate development of distributed applications in heterogeneous network. Objects could be the sensors and actuators of a robot or processes that treat common sensor data. An implementation of an image acquisition and distribution service is presented and others are proposed to compose the architecture.