SA-1 Probabilistic Robotics Probabilistic Sensor Models Beam-based Scan-based Landmarks.

Slides:



Advertisements
Similar presentations
Probabilistic Techniques for Mobile Robot Navigation
Advertisements

Advanced Mobile Robotics
Discussion topics SLAM overview Range and Odometry data Landmarks
Sonar and Localization LMICSE Workshop June , 2005 Alma College.
An appearance-based visual compass for mobile robots Jürgen Sturm University of Amsterdam Informatics Institute.
Integration of sensory modalities
Mapping with Known Poses
Beam Sensor Models Pieter Abbeel UC Berkeley EECS Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics TexPoint fonts used in EMF. Read.
(Includes references to Brian Clipp
Kiyoshi Irie, Tomoaki Yoshida, and Masahiro Tomono 2011 IEEE International Conference on Robotics and Automation Shanghai International Conference Center.
Using Perception for mobile robot. 2D ranging for mobile robot.
Markov Localization & Bayes Filtering 1 with Kalman Filters Discrete Filters Particle Filters Slides adapted from Thrun et al., Probabilistic Robotics.
Simultaneous Localization and Mapping
4-1 Probabilistic Robotics: Motion and Sensing Slide credits: Wolfram Burgard, Dieter Fox, Cyrill Stachniss, Giorgio Grisetti, Maren Bennewitz, Christian.
SA-1 Probabilistic Robotics Probabilistic Sensor Models Beam-based Scan-based Landmarks.
Uncertainty Representation. Gaussian Distribution variance Standard deviation.
Visual Recognition Tutorial
Probabilistic Robotics Bayes Filter Implementations Particle filters.
Sam Pfister, Stergios Roumeliotis, Joel Burdick
Autonomous Robot Navigation Panos Trahanias ΗΥ475 Fall 2007.
Probabilistic Methods in Mobile Robotics. Stereo cameras Infra-red Sonar Laser range-finder Sonar Tactiles.
Graphical Models for Mobile Robot Localization Shuang Wu.
Scan Matching Pieter Abbeel UC Berkeley EECS
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Probability: Review TexPoint fonts used in EMF.
Probabilistic Robotics
A Probabilistic Approach to Collaborative Multi-robot Localization Dieter Fox, Wolfram Burgard, Hannes Kruppa, Sebastin Thrun Presented by Rajkumar Parthasarathy.
SA-1 Probabilistic Robotics Mapping with Known Poses.
Probabilistic Robotics Bayes Filter Implementations Particle filters.
Grid Maps for Robot Mapping. Features versus Volumetric Maps.
HCI / CprE / ComS 575: Computational Perception
Bayesian Filtering for Robot Localization
SLAM: Robotic Simultaneous Location and Mapping
Juhana Leiwo – Marco Torti.  Position and movement  Direction of acceleration (gravity) ‏  Proximity and collision sensing  3-dimensional spatial.
Markov Localization & Bayes Filtering
Juhana Leiwo – Marco Torti.  Position and movement  Direction of acceleration (gravity) ‏  Proximity and collision sensing  3-dimensional spatial.
An Introduction to Robotic Navigation ECE 450 Introduction to Robotics.
오 세 영, 이 진 수 전자전기공학과, 뇌연구센터 포항공과대학교
SA-1 Mapping with Known Poses Ch 4.2 and Ch 9. 2 Why Mapping? Learning maps is one of the fundamental problems in mobile robotics Maps allow robots to.
Probabilistic Robotics: Monte Carlo Localization
Mapping and Localization with RFID Technology Matthai Philipose, Kenneth P Fishkin, Dieter Fox, Dirk Hahnel, Wolfram Burgard Presenter: Aniket Shah.
SLAM: Robotic Simultaneous Location and Mapping With a great deal of acknowledgment to Sebastian Thrun.
SA-1 Probabilistic Robotics Probabilistic Sensor Models Beam-based Scan-based Landmarks.
Forward-Scan Sonar Tomographic Reconstruction PHD Filter Multiple Target Tracking Bayesian Multiple Target Tracking in Forward Scan Sonar.
Mobile Robot Localization (ch. 7)
A Passive Approach to Sensor Network Localization Rahul Biswas and Sebastian Thrun International Conference on Intelligent Robots and Systems 2004 Presented.
1/17/2016CS225B Kurt Konolige Probabilistic Models of Sensing and Movement Move to probability models of sensing and movement Project 2 is about complex.
Probabilistic Robotics
Fast SLAM Simultaneous Localization And Mapping using Particle Filter A geometric approach (as opposed to discretization approach)‏ Subhrajit Bhattacharya.
Probabilistic Robotics Introduction. SA-1 2 Introduction  Robotics is the science of perceiving and manipulating the physical world through computer-controlled.
Particle filters for Robot Localization An implementation of Bayes Filtering Markov Localization.
SLAM Techniques -Venkata satya jayanth Vuddagiri 1.
Autonomous Mobile Robots Autonomous Systems Lab Zürich Probabilistic Map Based Localization "Position" Global Map PerceptionMotion Control Cognition Real.
Line fitting.
Sensors Fusion for Mobile Robotics localization
+ SLAM with SIFT Se, Lowe, and Little Presented by Matt Loper
Probabilistic Robotics
Sensors and Sensing for Reactive Robots
Robot Teknolojisine Giriş Yrd. Doç. Dr. Erkan Uslu, Doç. Dr
Day 32 Range Sensor Models 11/13/2018.
Probabilistic Robotics
Distance Sensor Models
Day 29 Bug Algorithms 12/7/2018.
Day 29 Bug Algorithms 12/8/2018.
Day 33 Range Sensor Models 12/10/2018.
A Short Introduction to the Bayes Filter and Related Models
EE-565: Mobile Robotics Non-Parametric Filters Module 2, Lecture 5
Probabilistic Map Based Localization
Principle of Bayesian Robot Localization.
Presentation transcript:

SA-1 Probabilistic Robotics Probabilistic Sensor Models Beam-based Scan-based Landmarks

2 Sensors for Mobile Robots Contact sensors: Bumpers Internal sensors Accelerometers (spring-mounted masses) Gyroscopes (spinning mass, laser light) Compasses, inclinometers (earth magnetic field, gravity) Proximity sensors Sonar (time of flight) Radar (phase and frequency) Laser range-finders (triangulation, tof, phase) Infrared (intensity) Visual sensors: Cameras Satellite-based sensors: GPS

3 Proximity Sensors The central task is to determine P(z|x), i.e., the probability of a measurement z given that the robot is at position x. Question: Where do the probabilities come from? Approach: Let’s try to explain a measurement.

4 Beam-based Sensor Model Scan z consists of K measurements. Individual measurements are independent given the robot position.

5 Beam-based Sensor Model

6 Typical Measurement Errors of an Range Measurements 1.Beams reflected by obstacles 2.Beams reflected by persons / caused by crosstalk 3.Random measurements 4.Maximum range measurements

7 Proximity Measurement Measurement can be caused by … a known obstacle. cross-talk. an unexpected obstacle (people, furniture, …). missing all obstacles (total reflection, glass, …). Noise is due to uncertainty … in measuring distance to known obstacle. in position of known obstacles. in position of additional obstacles. whether obstacle is missed.

8 Beam-based Proximity Model Measurement noise z exp z max 0 Unexpected obstacles z exp z max 0

9 Beam-based Proximity Model Random measurementMax range z exp z max 0 z exp z max 0

10 Resulting Mixture Density How can we determine the model parameters?

11 Raw Sensor Data Measured distances for expected distance of 300 cm. SonarLaser

12 Approximation Maximize log likelihood of the data Search space of n-1 parameters. Hill climbing Gradient descent Genetic algorithms … Deterministically compute the n-th parameter to satisfy normalization constraint.

13 Learn Intrinsic Parameters

14 Approximation Results Sonar Laser 300cm 400cm

15 Example zP(z|x,m)

16 Likelihood Fields for Range Finders

17

18 Likelihood Fields for Range Finders - Algorithm

19 Likelihood of a Landmark Measurement

20 Sampling Poses from a Landmark Measurement

21 Discrete Model of Proximity Sensors Instead of densities, consider discrete steps along the sensor beam. Consider dependencies between different cases. Laser sensor Sonar sensor

22 Approximation Results Laser Sonar

23 Influence of Angle to Obstacle

24 Influence of Angle to Obstacle

25 Influence of Angle to Obstacle

26 Influence of Angle to Obstacle

27 Summary Beam-based Model Assumes independence between beams. Justification? Overconfident! Models physical causes for measurements. Mixture of densities for these causes. Assumes independence between causes. Problem? Implementation Learn parameters based on real data. Different models should be learned for different angles at which the sensor beam hits the obstacle. Determine expected distances by ray-tracing. Expected distances can be pre-processed.

28 Additional Models of Proximity Sensors Map matching (sonar,laser): generate small, local maps from sensor data and match local maps against global model. Scan matching (laser): map is represented by scan endpoints, match scan into this map. Features (sonar, laser, vision): Extract features such as doors, hallways from sensor data.