Distributed Data Fusion with Kalman Filters. Simon Julier Computer Science Department University College London

Size: px
Start display at page:

Download "Distributed Data Fusion with Kalman Filters. Simon Julier Computer Science Department University College London"

Transcription

1 Distributed Data Fusion with Kalman Filters Simon Julier Computer Science Department University College London

2 Structure of Talk Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 2

3 Motivation Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 3

4 Wilderness Search and Rescue 4

5 Wilderness Search and Rescue The priority is search which is fast and safe You have to find somebody before you can rescue them Time is often of the essence Safety of searchers must be ensured UAVs are an ideal tool to use: Rapidly collect data from wide area Can go where it s dangerous Automated platforms can operate even faster 5

6 UAV Search Task Fly around the environment Control based on prior distribution of target location Detect potentially interesting objects Localise potentially interesting objects Identify potentially interesting objects 6

7 Autonomous Platforms 7

8 Raw Sensor Data Returned 8

9 Target Localisation Estimate the state of a target in an area of interest using multiple UAVs UCL March

10 Tracking with Multiple UAVs 10

11 Goals of Lecture What causes the algorithms to fail so badly? How can we solve these problems optimally, and what constraints do they place on the solution? How can we solve the problem suboptimally, and what constraints do they pose on the problem? 11

12 Kalman Filters Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 12

13 System Description Let the state of the system at time step i be given by the state space vector Both the process and observation models are linear and are of the form: 13

14 Structure of the State Estimate The estimate consists of the tuple: where: is the mean vector; really a single numerical estimate a bit like MAP is the covariance ; really measure of mean squared error 14

15 Valid Estimates We need to have a criteria which says whether our system works or not Since we only have a state vector and a covariance matrix, our criteria of success is that our state is covariance consistent 15

16 Covariance Consistency We say that an estimate is conservative if it overestimates the actual mean squared error in the estimate, where 16

17 Matched 17

18 Conservative 18

19 Consistent 19

20 Inconsistent 20

21 Biasedness Authors often stipulate that the error needs to be zero-mean However, this is overly restrictive Any system with modelling errors cannot be consistent under this definition Since all models of the real world are wrong, no filter can be consistent 21

22 Biasedness Suppose Then 22

23 Biasedness Therefore, for the estimate to be consistent, 23

24 Matched Biased 24

25 Non-Gaussian Noise Models The definition similarly applies if the distribution is non-gaussian In this case, we just compute the moments of the distribution 25

26 Non-Gaussian Noise Models 26

27 Comparison with Entropy We could argue that instead of covariance consistency, we could use a measure like entropy However: To compute entropy we have to assume a distribution (e.g., Gaussian) Even with this assumption, it won t tell us if our estimate is too small 27

28 Entropy-Matched Distributions 28

29 First Iteration of the Kalman Filter Cycle Initialise Predict Update Observation 29

30 Prediction Step Under the assumption that the errors are small, linearised prediction equations are used 30

31 Kalman Filter Update Step We (arbitrarily) decide a linear update rule of the form where is the innovation vector

32 Kalman Filter Update Step The weight matrix is chosen to minimise the trace of the updated covariance matrix It can be shown that this is and this gives a covariance update equation of the form

33 Debiased Coordinate Conversions A sensor measures the range r and bearing to a target The aim is to estimate the (x, y) coordinates of the target The measurement model is, of course: 33

34 Debiased Coordinate Conversions 34

35 Debiased Coordinate Conversions in Action 35

36 [Mapping Example]

37 Extended Kalman Filter A common assumption is that the errors are small Therefore, the first two moments are approximated as Various kinds of analytical and numerical moment approximations are widely used as well

38 Kalman Filters Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 38

39 Distributed Fusion Kalman Filter Cycle Initialise Predict Update Local Observation Broadcast Estimate Update Remote Estimate Observation Other Nodes Additional steps due to distribution 39

40 Basic Idea of DDF Each platform maintains its own estimate of the target state, Each node runs a Kalman filter locally and fuses locally taken measurements The update is distributed to other nodes which fuse with it 40

41 However, There Is A Slight Complication The state information stored in each node is not independent of the information in other nodes Common process noise Occurs whether or not nodes have exchanged information Common measurement history Occurs when nodes exchange information Assuming that state estimates are independent of one another is bad However, often used in so-called weak coupling of, say, GPS and INS systems 41

42 Dependent Information and Information Sets Each node collects its own set of data, which is independent of the other node

43 Fusion of Information Sets Estimates (information sets) exchanged between nodes

44 Fusion of Independent Information Sets

45 When Do Independent Sets Arise? Independent sets arise when the information set to each node is conditionally independent This can only happen if you can guarantee: The target is stationary The poses of the UAVs are known perfectly The same observation information is only ever used once

46 Multiple Platform Fusion

47 Dependent Information Sets Both sets now contain common information; not conditionally independent

48 Fusion of Dependent Information Sets New information Common information New information

49 Assuming Conditional Independence Double counted term

50 Double Counting in State Space Form Within a Kalman filter, the dependency is through the values of the cross correlations These can be evaluated by considering the state of the entire network, including the joint state of all platforms, all objects being tracked, etc. 50

51 Double Counting in State Space Form The full covariance structure of this estimate is

52 Double Counting in State Space Form However, if we only maintain the marginals for each platform separately,

53 Double Counting in State Space Form The error in the approximate covariance matrix is Therefore, we are using an inconsistent approximation of our network and our system will fail 53

54 Assuming State Estimates Are Independent

55 Optimal Distributed Data Fusion Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 55

56 The Right Way to Solve the Problem Chong and Mori showed that this can be implemented with a modified form of Bayes Rule, Cancel out common information This cancels out the common information between nodes This can only be computed locally with special network topologies

57 Approach 1: Distribute Observations Broadcast all observations to all nodes 57

58 Pros and Cons Advantages: Each node has optimal estimate for all time Distribution provides no additional complexity to fusion algorithm Actually used in practice Disadvantages: Requires all nodes to have the same communication and computational abilities Requires extremely large bandwidth Introduces implicit assumption that all nodes have exactly the same estimate 58

59 Approach 2: Fully-Connected Network Broadcast all updated state estimates to all nodes 59

60 Fully-Connected Networks The easiest way to implement a fully connected network is to use the inverse covariance (or information) form of the Kalman Filter The state space is replaced by the information variables 60

61 Updating in Information Form Using information form, the update simplifies to where the information from the observations is 61

62 Distributed Information Updates Since the information from the observations is independent of the state, i n and I n are independent of previous state estimates and can be safely distributed The update rule simply becomes 62

63 Fully-Connected Network Advantages: Each node has optimal estimate for all time Broadcasting the observation information variables potentially saves bandwidth Disadvantages: Requires all nodes to have the same communication and computational abilities Still requires O(N 2 ) communication links Introduces explicit assumption that all nodes have exactly the same estimate (important if linearising e.g., with an EKF) 63

64 Approach 3: Hierarchical Network Network has master and slave nodes Slaves fuse data locally Estimates sent to master which fuses them together Revised estimate broadcast back to slaves 64

65 Fusion in the Slave The slave updates using the information Kalman filter equations: 65

66 Fusion in the Master The master updates by summing the information from all the slaves To compensate for the prediction which was sent out, the master must subtract out common information, 66

67 Hierarchical Network Advantages: Each node has optimal estimate for all time The number of communication links is O(N) Disadvantages: Additional latency One node is privileged; failure of that node causes the whole network to fail 67

68 Approach 4: Channel Filters Constrain the network to be a tree Single path between any pair of nodes Use channel filters to subtract off common information 68

69 Estimating Common Information Consider a link between a pair of nodes i and j The channel filter maintains common information across the link It has its own information estimate, 69

70 Updating Local Nodes The Channel Filter is a regular Kalman Filter but works with the information exchanged between i and j rather than the observation data directly First, let the update at filter i using the local sensor observations be written as 70

71 Fusing With Nearby Nodes The updated estimate is given by summing all the independent information from a node s neighbours, 71

72 Updating the Channel Filters The channel filter update is given by recursively updating with the difference in information variables from the two nodes, 72

73 Channel Filters in Action 73

74 Advantages and Disadvantages Advantages: The number of communication links is O(N) Optimal in a time-delayed sense Disadvantages: Estimates at all nodes differ Single path of communication; no redundancy If the network is reconfigured, the channel filters have to be recalculated from scratch Global time synchronisation 74

75 Hybrid Architectures Channel filters can be mixed-and-matched with other local topologies like observation distribution or master-slave 75

76 Review of Techniques So Far It is possible to develop optimal algorithms for distributed data fusion using local message passing only However, these techniques rely on special network topologies: Fully connected Tree-connected In general, preserving these topologies can be difficult and undesirable 76

77 Adhoc Network Arbitrary network with loops and cycles Complete flexibility and redundancy 77

78 Distributed Data Fusion in Adhoc Networks However, it has been shown that no local data fusion scheme can be used to develop consistent, optimal estimates in this situation Therefore, it appears that DDF is strongly limited to the case of very particular data fusion architecture Alternative approach: can we develop mathematically rigorous suboptimal solutions? 78

79 Suboptimal Distributed Data Fusion Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 79

80 Double Counting in State Space Form Recall again that the problem is that we want to know the full joint covariance However, we only know the marginalised form 80

81 Double Counting in State Space Form From knowledge of the marginals alone, it is not possible to reconstruct the full joint covariance matrix However, because the joint covariance matrix must be positive semidefinite, we know there are constraints on what the cross correlations look like Therefore, we can exploit these constraints to develop update rules which are consistent for any feasible cross correlation 81

82 The Kalman Filter with Correlated Noise First consider the case that the observation noise is not independent of the filter state, It can be shown that the expectations become

83 Properties of Updated Covariances 83

84 Applying the Results to The update which generates a family of ellipses which circumscribe the intersection region is given by This is the same as a Kalman filter update, but with 84

85 Covariance Intersection 85

86 Choosing The free parameter is used to trade-off between the prediction and the observation It should be chosen to minimise some measure of uncertainty in the estimate Trace Determinant (better) The optimisation is convex and so many simple solver algorithms can be used Some closed form solutions have been developed as well 86

87 Covariance Intersection In Action 87

88 Probabilistic Interpretation of WGMs Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 88

89 Probabilistic Interpretation Great, so this works with means and covariances - but is it actually doing something valid from a probability distribution point of view? It turns out, that a generalisation of CI is equivalent to computing the weighted geometric mean,

90 WGM Does Not Double Count Single counted term

91 Structure of the Fusion Rule The fusion rule has the form where Function of new information Common information single-counted

92 Information Losses and Gains Therefore, we now need to ask what is the effect of We can assess this in several ways: By observation Pointwise bounds Information measures Surprisingly hard; still a work in progress

93 Example Distributions

94 Effect of

95 Effect of

96 Effect of

97 Effect of

98 Effect of

99 Effect of

100 Pointwise Bounds It is possible to establish pointwise bounds which apply at each point in the distribution Although pointwise bounds play no special role in Bayesian statistics, they provide some insight into the behaviour of the fusion rule

101 Bounds for the Unnormalised Distribution Let This is always squeezed between the distributions,

102 Illustration of the Unnormalised Bound

103 Lower Bound Consider the distribution where The WGM obeys the lower bound

104 Illustration of the Lower Bound

105 Interpreting the Lower Bound The minimum value of a distribution plays no special role in Bayesian statistics However, the bound from below Avoids degenerate cases The support has to contain the intersection of the supports of the prior distributions Lower bounds on distributions often play a role in practical filtering algorithms Truncate distributions or modes in MHT if the probability is too small

106 Upper Inequality There can exist an x such that The fact that the distribution can exceed the maximum suggests that fusion can occur The distribution becomes more concentrated

107 Illustration of the Upper Inequality

108 Updated Distribution

109 Summary Motivation Kalman Filters Double Counting Optimal Distributed Data Fusion Suboptimal Distributed Data Fusion Probabilistic Interpretation of WGMs Summary 109

110 Summary Distributed data fusion is important for many applications However, estimates are not conditionally independent Optimal solutions can be used in just limited circumstances Suboptimal algorithms can be used more widely The KF is more than Bayes with Gaussians! 110

SLAM Techniques and Algorithms. Jack Collier. Canada. Recherche et développement pour la défense Canada. Defence Research and Development Canada

SLAM Techniques and Algorithms. Jack Collier. Canada. Recherche et développement pour la défense Canada. Defence Research and Development Canada SLAM Techniques and Algorithms Jack Collier Defence Research and Development Canada Recherche et développement pour la défense Canada Canada Goals What will we learn Gain an appreciation for what SLAM

More information

Horizontal Integration based upon: Decentralized Data Fusion (DDF), NetCentric Architecture (NCA), and Analysis Collaboration Tools (ACT)

Horizontal Integration based upon: Decentralized Data Fusion (DDF), NetCentric Architecture (NCA), and Analysis Collaboration Tools (ACT) Horizontal Integration based upon: Decentralized Data Fusion (DDF), NetCentric Architecture (NCA), and Analysis Collaboration Tools (ACT) S.B. Gardner Naval Research Laboratory Washington, DC 20375 Horizontal

More information

Introduction p. 1 Fundamental Problems p. 2 Core of Fundamental Theory and General Mathematical Ideas p. 3 Classical Statistical Decision p.

Introduction p. 1 Fundamental Problems p. 2 Core of Fundamental Theory and General Mathematical Ideas p. 3 Classical Statistical Decision p. Preface p. xiii Acknowledgment p. xix Introduction p. 1 Fundamental Problems p. 2 Core of Fundamental Theory and General Mathematical Ideas p. 3 Classical Statistical Decision p. 4 Bayes Decision p. 5

More information

Autonomous Mobile Robot Design

Autonomous Mobile Robot Design Autonomous Mobile Robot Design Topic: Extended Kalman Filter Dr. Kostas Alexis (CSE) These slides relied on the lectures from C. Stachniss, J. Sturm and the book Probabilistic Robotics from Thurn et al.

More information

UAV Navigation: Airborne Inertial SLAM

UAV Navigation: Airborne Inertial SLAM Introduction UAV Navigation: Airborne Inertial SLAM Jonghyuk Kim Faculty of Engineering and Information Technology Australian National University, Australia Salah Sukkarieh ARC Centre of Excellence in

More information

Using the Kalman Filter for SLAM AIMS 2015

Using the Kalman Filter for SLAM AIMS 2015 Using the Kalman Filter for SLAM AIMS 2015 Contents Trivial Kinematics Rapid sweep over localisation and mapping (components of SLAM) Basic EKF Feature Based SLAM Feature types and representations Implementation

More information

Sensor Tasking and Control

Sensor Tasking and Control Sensor Tasking and Control Sensing Networking Leonidas Guibas Stanford University Computation CS428 Sensor systems are about sensing, after all... System State Continuous and Discrete Variables The quantities

More information

CS491/691: Introduction to Aerial Robotics

CS491/691: Introduction to Aerial Robotics CS491/691: Introduction to Aerial Robotics Topic: State Estimation Dr. Kostas Alexis (CSE) World state (or system state) Belief state: Our belief/estimate of the world state World state: Real state of

More information

Lecture Outline. Target Tracking: Lecture 7 Multiple Sensor Tracking Issues. Multi Sensor Architectures. Multi Sensor Architectures

Lecture Outline. Target Tracking: Lecture 7 Multiple Sensor Tracking Issues. Multi Sensor Architectures. Multi Sensor Architectures Lecture Outline Target Tracing: Lecture 7 Multiple Sensor Tracing Issues Umut Orguner umut@metu.edu.tr room: EZ-12 tel: 4425 Department of Electrical & Electronics Engineering Middle East Technical University

More information

The Scaled Unscented Transformation

The Scaled Unscented Transformation The Scaled Unscented Transformation Simon J. Julier, IDAK Industries, 91 Missouri Blvd., #179 Jefferson City, MO 6519 E-mail:sjulier@idak.com Abstract This paper describes a generalisation of the unscented

More information

Introduction to Probabilistic Graphical Models: Exercises

Introduction to Probabilistic Graphical Models: Exercises Introduction to Probabilistic Graphical Models: Exercises Cédric Archambeau Xerox Research Centre Europe cedric.archambeau@xrce.xerox.com Pascal Bootcamp Marseille, France, July 2010 Exercise 1: basics

More information

Here represents the impulse (or delta) function. is an diagonal matrix of intensities, and is an diagonal matrix of intensities.

Here represents the impulse (or delta) function. is an diagonal matrix of intensities, and is an diagonal matrix of intensities. 19 KALMAN FILTER 19.1 Introduction In the previous section, we derived the linear quadratic regulator as an optimal solution for the fullstate feedback control problem. The inherent assumption was that

More information

Decentralized Detection In Wireless Sensor Networks

Decentralized Detection In Wireless Sensor Networks Decentralized Detection In Wireless Sensor Networks Milad Kharratzadeh Department of Electrical & Computer Engineering McGill University Montreal, Canada April 2011 Statistical Detection and Estimation

More information

Planning With Information States: A Survey Term Project for cs397sml Spring 2002

Planning With Information States: A Survey Term Project for cs397sml Spring 2002 Planning With Information States: A Survey Term Project for cs397sml Spring 2002 Jason O Kane jokane@uiuc.edu April 18, 2003 1 Introduction Classical planning generally depends on the assumption that the

More information

L06. LINEAR KALMAN FILTERS. NA568 Mobile Robotics: Methods & Algorithms

L06. LINEAR KALMAN FILTERS. NA568 Mobile Robotics: Methods & Algorithms L06. LINEAR KALMAN FILTERS NA568 Mobile Robotics: Methods & Algorithms 2 PS2 is out! Landmark-based Localization: EKF, UKF, PF Today s Lecture Minimum Mean Square Error (MMSE) Linear Kalman Filter Gaussian

More information

CIS 390 Fall 2016 Robotics: Planning and Perception Final Review Questions

CIS 390 Fall 2016 Robotics: Planning and Perception Final Review Questions CIS 390 Fall 2016 Robotics: Planning and Perception Final Review Questions December 14, 2016 Questions Throughout the following questions we will assume that x t is the state vector at time t, z t is the

More information

Using covariance intersection for SLAM

Using covariance intersection for SLAM Robotics and Autonomous Systems 55 (2007) 3 20 www.elsevier.com/locate/robot Using covariance intersection for SLAM Simon J. Julier a,, Jeffrey K. Uhlmann b a Department of Computer Science, University

More information

9 Multi-Model State Estimation

9 Multi-Model State Estimation Technion Israel Institute of Technology, Department of Electrical Engineering Estimation and Identification in Dynamical Systems (048825) Lecture Notes, Fall 2009, Prof. N. Shimkin 9 Multi-Model State

More information

Distributed estimation in sensor networks

Distributed estimation in sensor networks in sensor networks A. Benavoli Dpt. di Sistemi e Informatica Università di Firenze, Italy. e-mail: benavoli@dsi.unifi.it Outline 1 An introduction to 2 3 An introduction to An introduction to In recent

More information

Bayesian Machine Learning - Lecture 7

Bayesian Machine Learning - Lecture 7 Bayesian Machine Learning - Lecture 7 Guido Sanguinetti Institute for Adaptive and Neural Computation School of Informatics University of Edinburgh gsanguin@inf.ed.ac.uk March 4, 2015 Today s lecture 1

More information

Communication constraints and latency in Networked Control Systems

Communication constraints and latency in Networked Control Systems Communication constraints and latency in Networked Control Systems João P. Hespanha Center for Control Engineering and Computation University of California Santa Barbara In collaboration with Antonio Ortega

More information

On Scalable Distributed Sensor Fusion

On Scalable Distributed Sensor Fusion On Scalable Distributed Sensor Fusion KC Chang Dept. of SEO George Mason University Fairfax, VA 3, USA kchang@gmu.edu Abstract - The theoretic fundamentals of distributed information fusion are well developed.

More information

EKF and SLAM. McGill COMP 765 Sept 18 th, 2017

EKF and SLAM. McGill COMP 765 Sept 18 th, 2017 EKF and SLAM McGill COMP 765 Sept 18 th, 2017 Outline News and information Instructions for paper presentations Continue on Kalman filter: EKF and extension to mapping Example of a real mapping system:

More information

Bayes Filter Reminder. Kalman Filter Localization. Properties of Gaussians. Gaussians. Prediction. Correction. σ 2. Univariate. 1 2πσ e.

Bayes Filter Reminder. Kalman Filter Localization. Properties of Gaussians. Gaussians. Prediction. Correction. σ 2. Univariate. 1 2πσ e. Kalman Filter Localization Bayes Filter Reminder Prediction Correction Gaussians p(x) ~ N(µ,σ 2 ) : Properties of Gaussians Univariate p(x) = 1 1 2πσ e 2 (x µ) 2 σ 2 µ Univariate -σ σ Multivariate µ Multivariate

More information

Simultaneous Localization and Mapping (SLAM) Corso di Robotica Prof. Davide Brugali Università degli Studi di Bergamo

Simultaneous Localization and Mapping (SLAM) Corso di Robotica Prof. Davide Brugali Università degli Studi di Bergamo Simultaneous Localization and Mapping (SLAM) Corso di Robotica Prof. Davide Brugali Università degli Studi di Bergamo Introduction SLAM asks the following question: Is it possible for an autonomous vehicle

More information

Robotics 2 Data Association. Giorgio Grisetti, Cyrill Stachniss, Kai Arras, Wolfram Burgard

Robotics 2 Data Association. Giorgio Grisetti, Cyrill Stachniss, Kai Arras, Wolfram Burgard Robotics 2 Data Association Giorgio Grisetti, Cyrill Stachniss, Kai Arras, Wolfram Burgard Data Association Data association is the process of associating uncertain measurements to known tracks. Problem

More information

2D Image Processing. Bayes filter implementation: Kalman filter

2D Image Processing. Bayes filter implementation: Kalman filter 2D Image Processing Bayes filter implementation: Kalman filter Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de

More information

Probabilistic Graphical Models

Probabilistic Graphical Models 2016 Robert Nowak Probabilistic Graphical Models 1 Introduction We have focused mainly on linear models for signals, in particular the subspace model x = Uθ, where U is a n k matrix and θ R k is a vector

More information

Robotics. Lecture 4: Probabilistic Robotics. See course website for up to date information.

Robotics. Lecture 4: Probabilistic Robotics. See course website   for up to date information. Robotics Lecture 4: Probabilistic Robotics See course website http://www.doc.ic.ac.uk/~ajd/robotics/ for up to date information. Andrew Davison Department of Computing Imperial College London Review: Sensors

More information

Fusion of Time Delayed Measurements With Uncertain Time Delays

Fusion of Time Delayed Measurements With Uncertain Time Delays Fusion of Time Delayed Measurements With Uncertain Time Delays Simon J. Julier and Jeffrey K. Uhlmann Abstract In this paper we consider the problem of estimating the state of a dynamic system from a sequence

More information

Chapter 1. Root Finding Methods. 1.1 Bisection method

Chapter 1. Root Finding Methods. 1.1 Bisection method Chapter 1 Root Finding Methods We begin by considering numerical solutions to the problem f(x) = 0 (1.1) Although the problem above is simple to state it is not always easy to solve analytically. This

More information

STA 4273H: Statistical Machine Learning

STA 4273H: Statistical Machine Learning STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 11 Project

More information

Distributed Systems. Time, Clocks, and Ordering of Events

Distributed Systems. Time, Clocks, and Ordering of Events Distributed Systems Time, Clocks, and Ordering of Events Björn Franke University of Edinburgh 2016/2017 Today Last lecture: Basic Algorithms Today: Time, clocks, NTP Ref: CDK Causality, ordering, logical

More information

Autonomous Navigation for Flying Robots

Autonomous Navigation for Flying Robots Computer Vision Group Prof. Daniel Cremers Autonomous Navigation for Flying Robots Lecture 6.2: Kalman Filter Jürgen Sturm Technische Universität München Motivation Bayes filter is a useful tool for state

More information

Robotics 2 Target Tracking. Kai Arras, Cyrill Stachniss, Maren Bennewitz, Wolfram Burgard

Robotics 2 Target Tracking. Kai Arras, Cyrill Stachniss, Maren Bennewitz, Wolfram Burgard Robotics 2 Target Tracking Kai Arras, Cyrill Stachniss, Maren Bennewitz, Wolfram Burgard Slides by Kai Arras, Gian Diego Tipaldi, v.1.1, Jan 2012 Chapter Contents Target Tracking Overview Applications

More information

Bayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2016

Bayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2016 Bayesian Networks: Construction, Inference, Learning and Causal Interpretation Volker Tresp Summer 2016 1 Introduction So far we were mostly concerned with supervised learning: we predicted one or several

More information

9 Forward-backward algorithm, sum-product on factor graphs

9 Forward-backward algorithm, sum-product on factor graphs Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science 6.438 Algorithms For Inference Fall 2014 9 Forward-backward algorithm, sum-product on factor graphs The previous

More information

Kalman Filter Computer Vision (Kris Kitani) Carnegie Mellon University

Kalman Filter Computer Vision (Kris Kitani) Carnegie Mellon University Kalman Filter 16-385 Computer Vision (Kris Kitani) Carnegie Mellon University Examples up to now have been discrete (binary) random variables Kalman filtering can be seen as a special case of a temporal

More information

Why Bayesian? Rigorous approach to address statistical estimation problems. The Bayesian philosophy is mature and powerful.

Why Bayesian? Rigorous approach to address statistical estimation problems. The Bayesian philosophy is mature and powerful. Why Bayesian? Rigorous approach to address statistical estimation problems. The Bayesian philosophy is mature and powerful. Even if you aren t Bayesian, you can define an uninformative prior and everything

More information

Linear Dynamical Systems

Linear Dynamical Systems Linear Dynamical Systems Sargur N. srihari@cedar.buffalo.edu Machine Learning Course: http://www.cedar.buffalo.edu/~srihari/cse574/index.html Two Models Described by Same Graph Latent variables Observations

More information

Lecture 6: Multiple Model Filtering, Particle Filtering and Other Approximations

Lecture 6: Multiple Model Filtering, Particle Filtering and Other Approximations Lecture 6: Multiple Model Filtering, Particle Filtering and Other Approximations Department of Biomedical Engineering and Computational Science Aalto University April 28, 2010 Contents 1 Multiple Model

More information

Artificial Intelligence

Artificial Intelligence Artificial Intelligence Roman Barták Department of Theoretical Computer Science and Mathematical Logic Summary of last lecture We know how to do probabilistic reasoning over time transition model P(X t

More information

Practical Polar Code Construction Using Generalised Generator Matrices

Practical Polar Code Construction Using Generalised Generator Matrices Practical Polar Code Construction Using Generalised Generator Matrices Berksan Serbetci and Ali E. Pusane Department of Electrical and Electronics Engineering Bogazici University Istanbul, Turkey E-mail:

More information

Lecture 5: GPs and Streaming regression

Lecture 5: GPs and Streaming regression Lecture 5: GPs and Streaming regression Gaussian Processes Information gain Confidence intervals COMP-652 and ECSE-608, Lecture 5 - September 19, 2017 1 Recall: Non-parametric regression Input space X

More information

6.867 Machine learning, lecture 23 (Jaakkola)

6.867 Machine learning, lecture 23 (Jaakkola) Lecture topics: Markov Random Fields Probabilistic inference Markov Random Fields We will briefly go over undirected graphical models or Markov Random Fields (MRFs) as they will be needed in the context

More information

2D Image Processing. Bayes filter implementation: Kalman filter

2D Image Processing. Bayes filter implementation: Kalman filter 2D Image Processing Bayes filter implementation: Kalman filter Prof. Didier Stricker Dr. Gabriele Bleser Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche

More information

L11. EKF SLAM: PART I. NA568 Mobile Robotics: Methods & Algorithms

L11. EKF SLAM: PART I. NA568 Mobile Robotics: Methods & Algorithms L11. EKF SLAM: PART I NA568 Mobile Robotics: Methods & Algorithms Today s Topic EKF Feature-Based SLAM State Representation Process / Observation Models Landmark Initialization Robot-Landmark Correlation

More information

SLAM for Ship Hull Inspection using Exactly Sparse Extended Information Filters

SLAM for Ship Hull Inspection using Exactly Sparse Extended Information Filters SLAM for Ship Hull Inspection using Exactly Sparse Extended Information Filters Matthew Walter 1,2, Franz Hover 1, & John Leonard 1,2 Massachusetts Institute of Technology 1 Department of Mechanical Engineering

More information

Lecture 2: From Linear Regression to Kalman Filter and Beyond

Lecture 2: From Linear Regression to Kalman Filter and Beyond Lecture 2: From Linear Regression to Kalman Filter and Beyond Department of Biomedical Engineering and Computational Science Aalto University January 26, 2012 Contents 1 Batch and Recursive Estimation

More information

Kalman filtering and friends: Inference in time series models. Herke van Hoof slides mostly by Michael Rubinstein

Kalman filtering and friends: Inference in time series models. Herke van Hoof slides mostly by Michael Rubinstein Kalman filtering and friends: Inference in time series models Herke van Hoof slides mostly by Michael Rubinstein Problem overview Goal Estimate most probable state at time k using measurement up to time

More information

Bayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2014

Bayesian Networks: Construction, Inference, Learning and Causal Interpretation. Volker Tresp Summer 2014 Bayesian Networks: Construction, Inference, Learning and Causal Interpretation Volker Tresp Summer 2014 1 Introduction So far we were mostly concerned with supervised learning: we predicted one or several

More information

6196 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 57, NO. 9, SEPTEMBER 2011

6196 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 57, NO. 9, SEPTEMBER 2011 6196 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 57, NO. 9, SEPTEMBER 2011 On the Structure of Real-Time Encoding and Decoding Functions in a Multiterminal Communication System Ashutosh Nayyar, Student

More information

Anytime Planning for Decentralized Multi-Robot Active Information Gathering

Anytime Planning for Decentralized Multi-Robot Active Information Gathering Anytime Planning for Decentralized Multi-Robot Active Information Gathering Brent Schlotfeldt 1 Dinesh Thakur 1 Nikolay Atanasov 2 Vijay Kumar 1 George Pappas 1 1 GRASP Laboratory University of Pennsylvania

More information

Introduction to Unscented Kalman Filter

Introduction to Unscented Kalman Filter Introduction to Unscented Kalman Filter 1 Introdution In many scientific fields, we use certain models to describe the dynamics of system, such as mobile robot, vision tracking and so on. The word dynamics

More information

Probability Propagation in Singly Connected Networks

Probability Propagation in Singly Connected Networks Lecture 4 Probability Propagation in Singly Connected Networks Intelligent Data Analysis and Probabilistic Inference Lecture 4 Slide 1 Probability Propagation We will now develop a general probability

More information

Lecture 9. Time series prediction

Lecture 9. Time series prediction Lecture 9 Time series prediction Prediction is about function fitting To predict we need to model There are a bewildering number of models for data we look at some of the major approaches in this lecture

More information

What is a quantum computer? Quantum Architecture. Quantum Mechanics. Quantum Superposition. Quantum Entanglement. What is a Quantum Computer (contd.

What is a quantum computer? Quantum Architecture. Quantum Mechanics. Quantum Superposition. Quantum Entanglement. What is a Quantum Computer (contd. What is a quantum computer? Quantum Architecture by Murat Birben A quantum computer is a device designed to take advantage of distincly quantum phenomena in carrying out a computational task. A quantum

More information

Probabilistic and Bayesian Machine Learning

Probabilistic and Bayesian Machine Learning Probabilistic and Bayesian Machine Learning Day 4: Expectation and Belief Propagation Yee Whye Teh ywteh@gatsby.ucl.ac.uk Gatsby Computational Neuroscience Unit University College London http://www.gatsby.ucl.ac.uk/

More information

Physics 509: Bootstrap and Robust Parameter Estimation

Physics 509: Bootstrap and Robust Parameter Estimation Physics 509: Bootstrap and Robust Parameter Estimation Scott Oser Lecture #20 Physics 509 1 Nonparametric parameter estimation Question: what error estimate should you assign to the slope and intercept

More information

Sensor Fusion: Particle Filter

Sensor Fusion: Particle Filter Sensor Fusion: Particle Filter By: Gordana Stojceska stojcesk@in.tum.de Outline Motivation Applications Fundamentals Tracking People Advantages and disadvantages Summary June 05 JASS '05, St.Petersburg,

More information

Decentralised Data Fusion with Exponentials of Polynomials

Decentralised Data Fusion with Exponentials of Polynomials Decentralised Data Fusion with Exponentials of Polynomials Bradley Tonkes and Alan D. Blair Abstract We demonstrate applicability of a general class of multivariate probability density functions of the

More information

Parameterized Joint Densities with Gaussian Mixture Marginals and their Potential Use in Nonlinear Robust Estimation

Parameterized Joint Densities with Gaussian Mixture Marginals and their Potential Use in Nonlinear Robust Estimation Proceedings of the 2006 IEEE International Conference on Control Applications Munich, Germany, October 4-6, 2006 WeA0. Parameterized Joint Densities with Gaussian Mixture Marginals and their Potential

More information

Rao-Blackwellized Particle Filter for Multiple Target Tracking

Rao-Blackwellized Particle Filter for Multiple Target Tracking Rao-Blackwellized Particle Filter for Multiple Target Tracking Simo Särkkä, Aki Vehtari, Jouko Lampinen Helsinki University of Technology, Finland Abstract In this article we propose a new Rao-Blackwellized

More information

Mobile Robot Localization

Mobile Robot Localization Mobile Robot Localization 1 The Problem of Robot Localization Given a map of the environment, how can a robot determine its pose (planar coordinates + orientation)? Two sources of uncertainty: - observations

More information

Copyrighted Material. 1.1 Large-Scale Interconnected Dynamical Systems

Copyrighted Material. 1.1 Large-Scale Interconnected Dynamical Systems Chapter One Introduction 1.1 Large-Scale Interconnected Dynamical Systems Modern complex dynamical systems 1 are highly interconnected and mutually interdependent, both physically and through a multitude

More information

PREDICTIVE quantization is one of the most widely-used

PREDICTIVE quantization is one of the most widely-used 618 IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, VOL. 1, NO. 4, DECEMBER 2007 Robust Predictive Quantization: Analysis and Design Via Convex Optimization Alyson K. Fletcher, Member, IEEE, Sundeep

More information

Stat 521A Lecture 18 1

Stat 521A Lecture 18 1 Stat 521A Lecture 18 1 Outline Cts and discrete variables (14.1) Gaussian networks (14.2) Conditional Gaussian networks (14.3) Non-linear Gaussian networks (14.4) Sampling (14.5) 2 Hybrid networks A hybrid

More information

Particle based probability density fusion with differential Shannon entropy criterion

Particle based probability density fusion with differential Shannon entropy criterion 4th International Conference on Information Fusion Chicago, Illinois, USA, July -8, Particle based probability density fusion with differential Shannon entropy criterion Jiří Ajgl and Miroslav Šimandl

More information

A NOVEL OPTIMAL PROBABILITY DENSITY FUNCTION TRACKING FILTER DESIGN 1

A NOVEL OPTIMAL PROBABILITY DENSITY FUNCTION TRACKING FILTER DESIGN 1 A NOVEL OPTIMAL PROBABILITY DENSITY FUNCTION TRACKING FILTER DESIGN 1 Jinglin Zhou Hong Wang, Donghua Zhou Department of Automation, Tsinghua University, Beijing 100084, P. R. China Control Systems Centre,

More information

p L yi z n m x N n xi

p L yi z n m x N n xi y i z n x n N x i Overview Directed and undirected graphs Conditional independence Exact inference Latent variables and EM Variational inference Books statistical perspective Graphical Models, S. Lauritzen

More information

STA 4273H: Statistical Machine Learning

STA 4273H: Statistical Machine Learning STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 3 Linear

More information

Lecture 7: Optimal Smoothing

Lecture 7: Optimal Smoothing Department of Biomedical Engineering and Computational Science Aalto University March 17, 2011 Contents 1 What is Optimal Smoothing? 2 Bayesian Optimal Smoothing Equations 3 Rauch-Tung-Striebel Smoother

More information

Probabilistic Graphical Models Lecture 17: Markov chain Monte Carlo

Probabilistic Graphical Models Lecture 17: Markov chain Monte Carlo Probabilistic Graphical Models Lecture 17: Markov chain Monte Carlo Andrew Gordon Wilson www.cs.cmu.edu/~andrewgw Carnegie Mellon University March 18, 2015 1 / 45 Resources and Attribution Image credits,

More information

Delayed-State Information Filter for Cooperative Decentralized Tracking

Delayed-State Information Filter for Cooperative Decentralized Tracking 29 IEEE International Conference on Robotics and Automation Kobe International Conference Center Kobe, Japan, May 12-17, 29 Delayed-State Information Filter for Cooperative Decentralized Tracking J. Capitán,

More information

13 : Variational Inference: Loopy Belief Propagation and Mean Field

13 : Variational Inference: Loopy Belief Propagation and Mean Field 10-708: Probabilistic Graphical Models 10-708, Spring 2012 13 : Variational Inference: Loopy Belief Propagation and Mean Field Lecturer: Eric P. Xing Scribes: Peter Schulam and William Wang 1 Introduction

More information

Recap. CS514: Intermediate Course in Operating Systems. What time is it? This week. Reminder: Lamport s approach. But what does time mean?

Recap. CS514: Intermediate Course in Operating Systems. What time is it? This week. Reminder: Lamport s approach. But what does time mean? CS514: Intermediate Course in Operating Systems Professor Ken Birman Vivek Vishnumurthy: TA Recap We ve started a process of isolating questions that arise in big systems Tease out an abstract issue Treat

More information

(W: 12:05-1:50, 50-N201)

(W: 12:05-1:50, 50-N201) 2015 School of Information Technology and Electrical Engineering at the University of Queensland Schedule Week Date Lecture (W: 12:05-1:50, 50-N201) 1 29-Jul Introduction Representing Position & Orientation

More information

Lecture 9: Bayesian Learning

Lecture 9: Bayesian Learning Lecture 9: Bayesian Learning Cognitive Systems II - Machine Learning Part II: Special Aspects of Concept Learning Bayes Theorem, MAL / ML hypotheses, Brute-force MAP LEARNING, MDL principle, Bayes Optimal

More information

Stochastic Processes, Kernel Regression, Infinite Mixture Models

Stochastic Processes, Kernel Regression, Infinite Mixture Models Stochastic Processes, Kernel Regression, Infinite Mixture Models Gabriel Huang (TA for Simon Lacoste-Julien) IFT 6269 : Probabilistic Graphical Models - Fall 2018 Stochastic Process = Random Function 2

More information

Discrete Probability and State Estimation

Discrete Probability and State Estimation 6.01, Fall Semester, 2007 Lecture 12 Notes 1 MASSACHVSETTS INSTITVTE OF TECHNOLOGY Department of Electrical Engineering and Computer Science 6.01 Introduction to EECS I Fall Semester, 2007 Lecture 12 Notes

More information

Stochastic Analogues to Deterministic Optimizers

Stochastic Analogues to Deterministic Optimizers Stochastic Analogues to Deterministic Optimizers ISMP 2018 Bordeaux, France Vivak Patel Presented by: Mihai Anitescu July 6, 2018 1 Apology I apologize for not being here to give this talk myself. I injured

More information

Clock Synchronization

Clock Synchronization Today: Canonical Problems in Distributed Systems Time ordering and clock synchronization Leader election Mutual exclusion Distributed transactions Deadlock detection Lecture 11, page 7 Clock Synchronization

More information

ESTIMATOR STABILITY ANALYSIS IN SLAM. Teresa Vidal-Calleja, Juan Andrade-Cetto, Alberto Sanfeliu

ESTIMATOR STABILITY ANALYSIS IN SLAM. Teresa Vidal-Calleja, Juan Andrade-Cetto, Alberto Sanfeliu ESTIMATOR STABILITY ANALYSIS IN SLAM Teresa Vidal-Calleja, Juan Andrade-Cetto, Alberto Sanfeliu Institut de Robtica i Informtica Industrial, UPC-CSIC Llorens Artigas 4-6, Barcelona, 88 Spain {tvidal, cetto,

More information

Mobile Robot Localization

Mobile Robot Localization Mobile Robot Localization 1 The Problem of Robot Localization Given a map of the environment, how can a robot determine its pose (planar coordinates + orientation)? Two sources of uncertainty: - observations

More information

12 : Variational Inference I

12 : Variational Inference I 10-708: Probabilistic Graphical Models, Spring 2015 12 : Variational Inference I Lecturer: Eric P. Xing Scribes: Fattaneh Jabbari, Eric Lei, Evan Shapiro 1 Introduction Probabilistic inference is one of

More information

Exact Inference I. Mark Peot. In this lecture we will look at issues associated with exact inference. = =

Exact Inference I. Mark Peot. In this lecture we will look at issues associated with exact inference. = = Exact Inference I Mark Peot In this lecture we will look at issues associated with exact inference 10 Queries The objective of probabilistic inference is to compute a joint distribution of a set of query

More information

Conditions for Suboptimal Filter Stability in SLAM

Conditions for Suboptimal Filter Stability in SLAM Conditions for Suboptimal Filter Stability in SLAM Teresa Vidal-Calleja, Juan Andrade-Cetto and Alberto Sanfeliu Institut de Robòtica i Informàtica Industrial, UPC-CSIC Llorens Artigas -, Barcelona, Spain

More information

Gaussian Process Approximations of Stochastic Differential Equations

Gaussian Process Approximations of Stochastic Differential Equations Gaussian Process Approximations of Stochastic Differential Equations Cédric Archambeau Centre for Computational Statistics and Machine Learning University College London c.archambeau@cs.ucl.ac.uk CSML

More information

Markov localization uses an explicit, discrete representation for the probability of all position in the state space.

Markov localization uses an explicit, discrete representation for the probability of all position in the state space. Markov Kalman Filter Localization Markov localization localization starting from any unknown position recovers from ambiguous situation. However, to update the probability of all positions within the whole

More information

LARGE-SCALE TRAFFIC STATE ESTIMATION

LARGE-SCALE TRAFFIC STATE ESTIMATION Hans van Lint, Yufei Yuan & Friso Scholten A localized deterministic Ensemble Kalman Filter LARGE-SCALE TRAFFIC STATE ESTIMATION CONTENTS Intro: need for large-scale traffic state estimation Some Kalman

More information

Please bring the task to your first physics lesson and hand it to the teacher.

Please bring the task to your first physics lesson and hand it to the teacher. Pre-enrolment task for 2014 entry Physics Why do I need to complete a pre-enrolment task? This bridging pack serves a number of purposes. It gives you practice in some of the important skills you will

More information

CS 6820 Fall 2014 Lectures, October 3-20, 2014

CS 6820 Fall 2014 Lectures, October 3-20, 2014 Analysis of Algorithms Linear Programming Notes CS 6820 Fall 2014 Lectures, October 3-20, 2014 1 Linear programming The linear programming (LP) problem is the following optimization problem. We are given

More information

Mark Gales October y (x) x 1. x 2 y (x) Inputs. Outputs. x d. y (x) Second Output layer layer. layer.

Mark Gales October y (x) x 1. x 2 y (x) Inputs. Outputs. x d. y (x) Second Output layer layer. layer. University of Cambridge Engineering Part IIB & EIST Part II Paper I0: Advanced Pattern Processing Handouts 4 & 5: Multi-Layer Perceptron: Introduction and Training x y (x) Inputs x 2 y (x) 2 Outputs x

More information

Track-to-track Fusion for Multi-target Tracking Using Asynchronous and Delayed Data

Track-to-track Fusion for Multi-target Tracking Using Asynchronous and Delayed Data Track-to-track Fusion for Multi-target Tracking Using Asynchronous and Delayed Data Master s thesis in Systems, Control and Mechatronics ALEXANDER BERG ANDREAS KÄLL Department of Signals and Systems CHALMERS

More information

STATE ESTIMATION IN COORDINATED CONTROL WITH A NON-STANDARD INFORMATION ARCHITECTURE. Jun Yan, Keunmo Kang, and Robert Bitmead

STATE ESTIMATION IN COORDINATED CONTROL WITH A NON-STANDARD INFORMATION ARCHITECTURE. Jun Yan, Keunmo Kang, and Robert Bitmead STATE ESTIMATION IN COORDINATED CONTROL WITH A NON-STANDARD INFORMATION ARCHITECTURE Jun Yan, Keunmo Kang, and Robert Bitmead Department of Mechanical & Aerospace Engineering University of California San

More information

Memory, Latches, & Registers

Memory, Latches, & Registers Memory, Latches, & Registers 1) Structured Logic Arrays 2) Memory Arrays 3) Transparent Latches 4) How to save a few bucks at toll booths 5) Edge-triggered Registers L13 Memory 1 General Table Lookup Synthesis

More information

STAT 302 Introduction to Probability Learning Outcomes. Textbook: A First Course in Probability by Sheldon Ross, 8 th ed.

STAT 302 Introduction to Probability Learning Outcomes. Textbook: A First Course in Probability by Sheldon Ross, 8 th ed. STAT 302 Introduction to Probability Learning Outcomes Textbook: A First Course in Probability by Sheldon Ross, 8 th ed. Chapter 1: Combinatorial Analysis Demonstrate the ability to solve combinatorial

More information

LQR, Kalman Filter, and LQG. Postgraduate Course, M.Sc. Electrical Engineering Department College of Engineering University of Salahaddin

LQR, Kalman Filter, and LQG. Postgraduate Course, M.Sc. Electrical Engineering Department College of Engineering University of Salahaddin LQR, Kalman Filter, and LQG Postgraduate Course, M.Sc. Electrical Engineering Department College of Engineering University of Salahaddin May 2015 Linear Quadratic Regulator (LQR) Consider a linear system

More information

Tutorial on Mathematical Induction

Tutorial on Mathematical Induction Tutorial on Mathematical Induction Roy Overbeek VU University Amsterdam Department of Computer Science r.overbeek@student.vu.nl April 22, 2014 1 Dominoes: from case-by-case to induction Suppose that you

More information

5682 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 55, NO. 12, DECEMBER /$ IEEE

5682 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 55, NO. 12, DECEMBER /$ IEEE 5682 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 55, NO. 12, DECEMBER 2009 Hyperplane-Based Vector Quantization for Distributed Estimation in Wireless Sensor Networks Jun Fang, Member, IEEE, and Hongbin

More information