Results 1  10
of
709
Learning and inferring transportation routines
, 2004
"... This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movements through the community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user’s mode of transportation ..."
Abstract

Cited by 316 (22 self)
 Add to MetaCart
This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movements through the community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user’s mode of transportation or her goal. We apply RaoBlackwellised particle filters for efficient inference both at the low level and at the higher levels of the hierarchy. Significant locations such as goals or locations where the user frequently changes mode of transportation are learned from GPS data logs without requiring any manual labeling. We show how to detect abnormal behaviors (e.g. taking a wrong bus) by concurrently tracking his activities with a trained and a prior model. Experiments show that our model is able to accurately predict the goals of a person and to recognize situations in which the user performs unknown activities.
Bayesian filtering for location estimation
 IEEE Pervasive Computing
, 2003
"... Bayesianfilter techniques provide a powerful statistical tool to help manage measurement uncertainty and perform multisensor fusion and identity estimation. The authors survey Bayes filter implementations and show their application to realworld locationestimation tasks common in pervasive computi ..."
Abstract

Cited by 166 (7 self)
 Add to MetaCart
Bayesianfilter techniques provide a powerful statistical tool to help manage measurement uncertainty and perform multisensor fusion and identity estimation. The authors survey Bayes filter implementations and show their application to realworld locationestimation tasks common in pervasive computing.
Exactly sparse delayedstate filters for viewbased SLAM
 IEEE Transactions on Robotics
, 2006
"... Abstract—This paper reports the novel insight that the simultaneous localization and mapping (SLAM) information matrix is exactly sparse in a delayedstate framework. Such a framework is used in viewbased representations of the environment that rely upon scanmatching raw sensor data to obtain virt ..."
Abstract

Cited by 102 (21 self)
 Add to MetaCart
(Show Context)
Abstract—This paper reports the novel insight that the simultaneous localization and mapping (SLAM) information matrix is exactly sparse in a delayedstate framework. Such a framework is used in viewbased representations of the environment that rely upon scanmatching raw sensor data to obtain virtual observations of robot motion with respect to a place it has previously been. The exact sparseness of the delayedstate information matrix is in contrast to other recent featurebased SLAM information algorithms, such as sparse extended information filter or thin junctiontree filter, since these methods have to make approximations in order to force the featurebased SLAM information matrix to be sparse. The benefit of the exact sparsity of the delayedstate framework is that it allows one to take advantage of the information space parameterization without incurring any sparse approximation error. Therefore, it can produce equivalent results to the fullcovariance solution. The approach is validated experimentally using monocular imagery for two datasets: a testtank experiment with ground truth, and a remotely operated vehicle survey of the RMS Titanic. Index Terms—Information filters, Kalman filtering, machine vision, mobile robot motion planning, mobile robots, recursive estimation, robot vision systems, simultaneous localization and mapping (SLAM), underwater vehicles. I.
Consensus in Ad Hoc WSNs With Noisy Links—Part II: Distributed Estimation and Smoothing of Random Signals
"... Abstract—Distributed algorithms are developed for optimal estimation of stationary random signals and smoothing of (even nonstationary) dynamical processes based on generally correlated observations collected by ad hoc wireless sensor networks (WSNs). Maximum a posteriori (MAP) and linear minimum me ..."
Abstract

Cited by 100 (7 self)
 Add to MetaCart
Abstract—Distributed algorithms are developed for optimal estimation of stationary random signals and smoothing of (even nonstationary) dynamical processes based on generally correlated observations collected by ad hoc wireless sensor networks (WSNs). Maximum a posteriori (MAP) and linear minimum meansquare error (LMMSE) schemes, well appreciated for centralized estimation, are shown possible to reformulate for distributed operation through the iterative (alternatingdirection) method of multipliers. Sensors communicate with singlehop neighbors their individual estimates as well as multipliers measuring how far local estimates are from consensus. When iterations reach consensus, the resultant distributed (D) MAP and LMMSE estimators converge to their centralized counterparts when intersensor communication links are ideal. The DMAP estimators do not require the desired estimator to be expressible in closed form, the DLMMSE ones are provably robust to communication or quantization noise and both are particularly simple to implement when the data model is linearGaussian. For decentralized tracking applications, distributed Kalman filtering and smoothing algorithms are derived for anytime MMSE optimal consensusbased state estimation using WSNs. Analysis and corroborating numerical examples demonstrate the merits of the novel distributed estimators. Index Terms—Distributed estimation, Kalman smoother, nonlinear optimization, wireless sensor networks (WSNs).
Tardós, “Mapping large loops with a single handheld camera
 in Proc. Robotics: Sci. Syst
, 2007
"... Abstract — This paper 1 presents a method for Simultaneous Localization and Mapping (SLAM) relying on a monocular camera as the only sensor which is able to build outdoor, closedloop maps much larger than previously achieved with such input. Our system, based on the Hierarchical Map approach [1], bu ..."
Abstract

Cited by 98 (19 self)
 Add to MetaCart
Abstract — This paper 1 presents a method for Simultaneous Localization and Mapping (SLAM) relying on a monocular camera as the only sensor which is able to build outdoor, closedloop maps much larger than previously achieved with such input. Our system, based on the Hierarchical Map approach [1], builds independent local maps in realtime using the EKFSLAM technique and the inverse depth representation proposed in [2]. The main novelty in the local mapping process is the use of a data association technique that greatly improves its robustness in dynamic and complex environments. A new visual map matching algorithm stitches these maps together and is able to detect large loops automatically, taking into account the unobservability of scale intrinsic to pure monocular SLAM. The loop closing constraint is applied at the upper level of the Hierarchical Map in near realtime. We present experimental results demonstrating monocular SLAM as a human carries a camera over long walked trajectories in outdoor areas with people and other clutter, even in the more difficult case of forwardlooking camera, and show the closing of loops of several hundred meters. I.
Locationbased activity recognition
 In Advances in Neural Information Processing Systems (NIPS
, 2005
"... Learning patterns of human behavior from sensor data is extremely important for highlevel activity inference. We show how to extract and label a person’s activities and significant places from traces of GPS data. In contrast to existing techniques, our approach simultaneously detects and classifies ..."
Abstract

Cited by 79 (8 self)
 Add to MetaCart
Learning patterns of human behavior from sensor data is extremely important for highlevel activity inference. We show how to extract and label a person’s activities and significant places from traces of GPS data. In contrast to existing techniques, our approach simultaneously detects and classifies the significant locations of a person and takes the highlevel context into account. Our system uses relational Markov networks to represent the hierarchical activity model that encodes the complex relations among GPS readings, activities and significant places. We apply FFTbased message passing to perform efficient summation over large numbers of nodes in the networks. We present experiments that show significant improvements over existing techniques. 1
Exactly sparse delayedstate filters
 in IEEE Intl. Conf. on Robotics and Automation (ICRA
, 2005
"... Abstract — This paper presents the novel insight that the SLAM information matrix is exactly sparse in a delayedstate framework. Such a framework is used in viewbased representations of the environment which rely upon scanmatching raw sensor data. Scanmatching raw data results in virtual observati ..."
Abstract

Cited by 76 (11 self)
 Add to MetaCart
(Show Context)
Abstract — This paper presents the novel insight that the SLAM information matrix is exactly sparse in a delayedstate framework. Such a framework is used in viewbased representations of the environment which rely upon scanmatching raw sensor data. Scanmatching raw data results in virtual observations of robot motion with respect to a place its previously been. The exact sparseness of the delayedstate information matrix is in contrast to other recent featurebased SLAM information algorithms like Sparse Extended Information Filters or Thin Junction Tree Filters. These methods have to make approximations in order to force the featurebased SLAM information matrix to be sparse. The benefit of the exact sparseness of the delayedstate framework is that it allows one to take advantage of the information space parameterization without having to make any approximations. Therefore, it can produce equivalent results to the “fullcovariance ” solution. Index Terms — Delayed states, EIF, SLAM. I.
Visually navigating the RMS Titanic with SLAM information filters
 in Proceedings of Robotics: Science and Systems
, 2005
"... Abstract — This paper describes a visionbased, largearea, simultaneous localization and mapping (SLAM) algorithm that respects the lowoverlap imagery constraints typical of underwater vehicles while exploiting the inertial sensor information that is routinely available on such platforms. We prese ..."
Abstract

Cited by 74 (12 self)
 Add to MetaCart
(Show Context)
Abstract — This paper describes a visionbased, largearea, simultaneous localization and mapping (SLAM) algorithm that respects the lowoverlap imagery constraints typical of underwater vehicles while exploiting the inertial sensor information that is routinely available on such platforms. We present a novel strategy for efficiently accessing and maintaining consistent covariance bounds within a SLAM information filter, thereby greatly increasing the reliability of data association. The technique is based upon solving a sparse system of linear equations coupled with the application of constanttime Kalman updates. The method is shown to produce consistent covariance estimates suitable for robot planning and data association. Realworld results are presented for a visionbased 6DOF SLAM implementation using data from a recent ROV survey of the wreck of the RMS Titanic. I.
Hybrid Bayesian Networks for Reasoning about Complex Systems
, 2002
"... Many realworld systems are naturally modeled as hybrid stochastic processes, i.e., stochastic processes that contain both discrete and continuous variables. Examples include speech recognition, target tracking, and monitoring of physical systems. The task is usually to perform probabilistic inferen ..."
Abstract

Cited by 71 (0 self)
 Add to MetaCart
Many realworld systems are naturally modeled as hybrid stochastic processes, i.e., stochastic processes that contain both discrete and continuous variables. Examples include speech recognition, target tracking, and monitoring of physical systems. The task is usually to perform probabilistic inference, i.e., infer the hidden state of the system given some noisy observations. For example, we can ask what is the probability that a certain word was pronounced given the readings of our microphone, what is the probability that a submarine is trying to surface given our sonar data, and what is the probability of a valve being open given our pressure and flow readings. Bayesian networks are
A practical, decisiontheoretic approach to multirobot mapping and exploration
 In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS
, 2003
"... An important assumption underlying virtually all approaches to multirobot exploration is prior knowledge about their relative locations. This is due to the fact that robots need to merge their maps so as to coordinate their exploration strategies. The key step in map merging is to estimate the rela ..."
Abstract

Cited by 71 (5 self)
 Add to MetaCart
(Show Context)
An important assumption underlying virtually all approaches to multirobot exploration is prior knowledge about their relative locations. This is due to the fact that robots need to merge their maps so as to coordinate their exploration strategies. The key step in map merging is to estimate the relative locations of the individual robots. This paper presents a novel approach to multirobot map merging under global uncertainty about the robot’s relative locations. Our approach uses an adapted version of particle filters to estimate the position of one robot in the other robot’s partial map. The risk of falsepositive map matches is avoided by verifying match hypotheses using a rendezvous approach. We show how to seamlessly integrate this approach into a decisiontheoretic multirobot coordination strategy. The experiments show that our samplebased technique can reliably find good hypotheses for map matches. Furthermore, we present results obtained with two robots successfully merging their maps using the decisiontheoretic rendezvous strategy. 1