Results 1 
8 of
8
Visual Place Recognition for Autonomous Robots
, 1998
"... The problem of place recognition is central to robot map learning. A robot needs to be able to recognize when it has returned to a previously visited place, or at least to be able to estimate the likelihood that it has been at a place before. Our approach is to compare images taken at two places, us ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
The problem of place recognition is central to robot map learning. A robot needs to be able to recognize when it has returned to a previously visited place, or at least to be able to estimate the likelihood that it has been at a place before. Our approach is to compare images taken at two places, using a stochastic model of changes due to shift, zoom, and occlusion to predict the probability that one of them could be a perturbation of the other. We have performed experiments to gather the value of a Ø 2 statistic applied to image matches from a variety of indoor locations. Image pairs gathered from nearby locations generate low Ø 2 values, and images gathered from different locations generate high values. The rate of false positive and false negative matches is low. I. Introduction This paper presents a new visual place recognition algorithm. The algorithm accepts two images taken from two poses, and tests whether they the two poses are (probably) close to each other. The success...
Fusion of Symbolic Knowledge and Uncertain Information in Robotics
 International Journal of Intelligent Systems
, 2001
"... The interpretation of data coming from the real world may require different and often complementary uncertainty models: some are better described by possibility theory, others are intrinsically probabilistic. A logic for belief functions is introduced to axiomatize both semantics as special cases. A ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
(Show Context)
The interpretation of data coming from the real world may require different and often complementary uncertainty models: some are better described by possibility theory, others are intrinsically probabilistic. A logic for belief functions is introduced to axiomatize both semantics as special cases. As it properly extends classical logic, it also allows the fusion of data with different semantics and symbolic knowledge. The approach has been applied to the problem of mobile robot localization. For each place in the environment, a set of logical propositions allows the system to calculate the belief of the robot's presence as a function of the partial evidences provided by the individual sensors.
LogicBased Algorithms for Data Interpretation With Application to Robotics
, 1998
"... We present a formal method, based on possibilistic logic, to fuse uncertain sensory information. The basic concepts underlying the approach are summarized and discussed. The method has been applied to a realworld problem of noisy sensordata fusion: the position estimation of an autonomous mobile r ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
We present a formal method, based on possibilistic logic, to fuse uncertain sensory information. The basic concepts underlying the approach are summarized and discussed. The method has been applied to a realworld problem of noisy sensordata fusion: the position estimation of an autonomous mobile robot navigating in an approximately and partially known o#ce environment, using a topological map. Each place in the map is characterized by a set of logical formulae axiomatizing both abstract knowledge and uncertain information from the sensors. At each time instant during navigation, the necessity value for each place is calculated using a purely syntactical method, based on sequent calculus. Several test runs on a real robot have evidenced the adequacy of the approach in interpreting and disambiguating the information coming from independent perceptual sources, in combination with abstract knowledge. Keywords: Reasoning with Uncertainty, Possibilistic Logic, Sequent Calculus, Sensor Fus...
Merging Probability and Possibility for Robot Localization
 In Proceedings of the Workshop on Reasoning with Uncertainty in Robot Navigation (RUR99
, 1999
"... A mobile robot localization system based on sensor fusion is described. Data coming from various sensors can require di#erent and often complementary uncertainty models: some are better described by possibility theory, others are intrinsically probabilistic. A logic for belief functions is int ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
A mobile robot localization system based on sensor fusion is described. Data coming from various sensors can require di#erent and often complementary uncertainty models: some are better described by possibility theory, others are intrinsically probabilistic. A logic for belief functions is introduced to axiomatize both semantics as special cases. For each place in a map of the environment, a set of logical rules allows to calculate the belief of the robot's presence, as a function of the partial evidences provided by the individual sensors. Various experimental runs have shown promising results. 1 Introduction The aim of this work is to apply to robotics a logical framework where di#erent uncertainty models, like belief functions, possibilities (i.e. consonant belief functions) and probabilities (i.e. additive belief functions) can be uniformly axiomatized. 1.1 Uncertainty models Although probability theory has a leading position in the description of uncertainty, in th...
A Hybrid Mapping Approach For Mobile Robots
 In The Third IASTED International Conference on Artificial Intelligence and Applications  AIA 2003, Benalmdena
, 2003
"... In this paper we describe a mapping strategy for a mobile robot. The environment is represented by a graph relating locations of particular places. ..."
Abstract
 Add to MetaCart
In this paper we describe a mapping strategy for a mobile robot. The environment is represented by a graph relating locations of particular places.
A Categorical Approach to Data Fusion
"... Abstract Using suitable topoi of presheaves, a categorical definition of measure is given. When the general definition is specialized to particular categories made of sets of possibility, probability or imprecise probability measures, the internal language of the corresponding topos gives a valid a ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract Using suitable topoi of presheaves, a categorical definition of measure is given. When the general definition is specialized to particular categories made of sets of possibility, probability or imprecise probability measures, the internal language of the corresponding topos gives a valid and complete proof system for the corresponding semantics. An application of this method to data fusion in mobile robotics is presented.
Reactive Sensing for Autonomous Mobile Robots
"... This article presents an overview of our ongoing research in reactive sensing. Reactive sensing allows sensing processes at both the behavioral and deliberative levels to act as autonomous specialists in maintaining the most robust and efficient perception for the given behavior, state of the robot, ..."
Abstract
 Add to MetaCart
This article presents an overview of our ongoing research in reactive sensing. Reactive sensing allows sensing processes at both the behavioral and deliberative levels to act as autonomous specialists in maintaining the most robust and efficient perception for the given behavior, state of the robot, and state of the world. Two basic reactive sensing mechanisms are presented. One is a method for identifying and employing a satisfactory recovery strategy after a sensing failure. The recoverycentered method shows an improvement of between 39% and 99.4% over previous methods. The second mechanism is an alternative to Dempster's rule of combination of belief used to opportunistically reduce sensing without sacrificing certainty. The method dynamically projects whether belief in an object will decay below an unsatisfactory threshold if an observation is missed. These mechanisms were implemented on two mobile robots within the SFX architecture, and demonstrated for indoor, outdoor, and space...
Fuzzy control and coherent functions
"... A fuzzy controller can be seen as an algorithm that, given a fuzzy set (input) and a set of linguistic rules, computes the degree of possibility of every control value. Using a valid and complete proof system for possibilistic logic, we prove that fuzzy controllers enjoy the following property: ever ..."
Abstract
 Add to MetaCart
(Show Context)
A fuzzy controller can be seen as an algorithm that, given a fuzzy set (input) and a set of linguistic rules, computes the degree of possibility of every control value. Using a valid and complete proof system for possibilistic logic, we prove that fuzzy controllers enjoy the following property: every possibility measure that satisfies the degrees of possibility of input and linguistic rules also satisfies, for every control value, the degree of possibility computed by the fuzzy controller. We call such a property coherence between input, task description and output. We give a general definition of coherent function and we show that coherent functions form a class of functions that properly contains fuzzy controllers. Moreover, we present an application of coherent functions to a task different from control, namely localization in mobile robotics. 1