3/11/2016CS225B Kurt Konolige Probabilistic Models of Sensing and Movement Move to probability models of sensing and movement Project 2 is about complex.

Slides:



Advertisements
Similar presentations
Mobile Robot Localization and Mapping using the Kalman Filter
Advertisements

Odometry Error Modeling Three noble methods to model random odometry error.
Mapping with Known Poses
Robot Localization Using Bayesian Methods
Lab 2 Lab 3 Homework Labs 4-6 Final Project Late No Videos Write up
Probabilistic Robotics Course Presentation Outline 1. Introduction 2. The Bayes Filter 3. Non Parametric Filters 4. Gausian Filters 5. EKF Map Based Localization.
Probabilistic Robotics Probabilistic Motion Models.
1 Slides for the book: Probabilistic Robotics Authors: Sebastian Thrun Wolfram Burgard Dieter Fox Publisher: MIT Press, Web site for the book & more.
Bayesian Robot Programming & Probabilistic Robotics Pavel Petrovič Department of Applied Informatics, Faculty of Mathematics, Physics and Informatics
Probabilistic Robotics Probabilistic Motion Models.
Probabilistic Robotics Probabilistic Motion Models.
4-1 Probabilistic Robotics: Motion and Sensing Slide credits: Wolfram Burgard, Dieter Fox, Cyrill Stachniss, Giorgio Grisetti, Maren Bennewitz, Christian.
Uncertainty Representation. Gaussian Distribution variance Standard deviation.
Bayes Filters Pieter Abbeel UC Berkeley EECS Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics TexPoint fonts used in EMF. Read the.
Autonomous Robot Navigation Panos Trahanias ΗΥ475 Fall 2007.
Robotic Mapping: A Survey Sebastian Thrun, 2002 Presentation by David Black-Schaffer and Kristof Richmond.
Particle Filters Pieter Abbeel UC Berkeley EECS Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics TexPoint fonts used in EMF. Read.
CS 547: Sensing and Planning in Robotics Gaurav S. Sukhatme Computer Science Robotic Embedded Systems Laboratory University of Southern California
Probability: Review TexPoint fonts used in EMF.
Part 2 of 3: Bayesian Network and Dynamic Bayesian Network.
Probabilistic Robotics: Motion Model/EKF Localization
Probabilistic Robotics Introduction Probabilities Bayes rule Bayes filters.
Probabilistic Robotics Bayes Filter Implementations Particle filters.
Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University.
Particle Filters++ TexPoint fonts used in EMF.
HCI / CprE / ComS 575: Computational Perception
ROBOT MAPPING AND EKF SLAM
Bayesian Filtering for Robot Localization
Mobile Robot controlled by Kalman Filter
Markov Localization & Bayes Filtering
/09/dji-phantom-crashes-into- canadian-lake/
From Bayesian Filtering to Particle Filters Dieter Fox University of Washington Joint work with W. Burgard, F. Dellaert, C. Kwok, S. Thrun.
1 Robot Motion and Perception (ch. 5, 6) These two chapters discuss how one obtains the motion model and measurement model mentioned before. They are needed.
Probabilistic Robotics: Monte Carlo Localization
Probabilistic Robotics Probabilistic Motion Models.
Computer Vision Group Prof. Daniel Cremers Autonomous Navigation for Flying Robots Lecture 2.3: 2D Robot Example Jürgen Sturm Technische Universität München.
Visibility Graph. Voronoi Diagram Control is easy: stay equidistant away from closest obstacles.
Probabilistic Robotics Bayes Filter Implementations Gaussian filters.
SLAM: Robotic Simultaneous Location and Mapping With a great deal of acknowledgment to Sebastian Thrun.
1 Robot Environment Interaction Environment perception provides information about the environment’s state, and it tends to increase the robot’s knowledge.
Where’s the Robot? Ross Mead April 3 rd, Where’s the Robot? Given an initial estimate P(0) of the robot’s location in the configuration space, maintain.
Recursive Bayes Filters and related models for mobile robots.
Lecture 22 Dimitar Stefanov.
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.
Robotics Club: 5:30 this evening
CARLOC: Precisely Tracking Automobile Position
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
CS 547: Sensing and Planning in Robotics Gaurav S. Sukhatme Computer Science Robotic Embedded Systems Laboratory University of Southern California
Trends in Robotics Research Classical AI Robotics (mid-70’s) Sense-Plan-Act Complex world model and reasoning Reactive Paradigm (mid-80’s) No models: “the.
Probabilistic Robotics Introduction Probabilities Bayes rule Bayes filters.
Robust Localization Kalman Filter & LADAR Scans
Probabilistic Robotics Probability Theory Basics Error Propagation Slides from Autonomous Robots (Siegwart and Nourbaksh), Chapter 5 Probabilistic Robotics.
Autonomous Mobile Robots Autonomous Systems Lab Zürich Probabilistic Map Based Localization "Position" Global Map PerceptionMotion Control Cognition Real.
Probabilistic Robotics Bayes Filter Implementations Gaussian filters.
Probabilistic Robotics
Simultaneous Localization and Mapping
Trends in Robotics Research
Markov ó Kalman Filter Localization
State Estimation Probability, Bayes Filtering
Probabilistic Robotics
A Short Introduction to the Bayes Filter and Related Models
Motion Models (cont) 2/16/2019.
Probabilistic Map Based Localization
Introduction to Sensor Interpretation
Introduction to Sensor Interpretation
Velocity Motion Model (cont)
Velocity Motion Model (cont)
Presentation transcript:

3/11/2016CS225B Kurt Konolige Probabilistic Models of Sensing and Movement Move to probability models of sensing and movement Project 2 is about complex behavior using sensing Sensor interpretation is difficult – simple interpretation in this section Artifacts [goal-directed motion] and reactive behaviors Lectures Probabilistic sensor models Probabilistic representation of uncertain movement Particle filter implementation Project PF for motion model Markov localization with PF Stretch – feature-based localization Slides thanks to Steffen Gutmann

3/11/2016CS225B Kurt Konolige Robot Motion Robot motion is inherently uncertain. How can we model this uncertainty?

3/11/2016CS225B Kurt Konolige Dynamic Bayesian Network for Controls, States, and Sensations

3/11/2016CS225B Kurt Konolige Probabilistic Motion Models To implement the Bayes Filter, we need the transition model p(x | x’, u). The term p(x | x’, u) specifies a posterior probability, that action u carries the robot from x’ to x. In this section we will specify, how p(x | x’, u) can be modeled based on the motion equations. We concentrate on wheel-based robots; for legged ones, similar equations hold.

3/11/2016CS225B Kurt Konolige Coordinate Systems In general the configuration of a robot can be described by six parameters. Three-dimensional Cartesian coordinates plus three Euler angles pitch, roll, and tilt. Throughout this section, we consider robots operating on a planar surface. The state space of such systems is three- dimensional (x,y,).

3/11/2016CS225B Kurt Konolige Typical Motion Models In practice, one often finds two types of motion models: Odometry-based Velocity-based (dead reckoning) Odometry-based models are used when systems are equipped with encoders that can measure the actual path traveled. Velocity-based models have to be applied when no encoders are given. They calculate the new pose based on the velocities and the time elapsed.

3/11/2016CS225B Kurt Konolige Example Wheel Encoders These modules require +5V and GND to power them, and provide a 0 to 5V output. They provide +5V output when they "see" white, and a 0V output when they "see" black. These disks are manufactured out of high quality laminated color plastic to offer a very crisp black to white transition. This enables a wheel encoder sensor to easily see the transitions. Source:

3/11/2016CS225B Kurt Konolige Dead Reckoning Derived from “ deduced reckoning. ” Mathematical procedure for determining the present location of a vehicle. Achieved by calculating the current pose of the vehicle based on its velocities and the time elapsed, over small time intervals

3/11/2016CS225B Kurt Konolige Reasons for Motion Errors bump ideal case different wheel diameters carpet and many more …

3/11/2016CS225B Kurt Konolige Odometry Model Robot moves from to. Odometry information.

3/11/2016CS225B Kurt Konolige The atan2 Function Extends the inverse tangent and correctly copes with the signs of x and y.

3/11/2016CS225B Kurt Konolige Noise Model for Odometry The measured motion is given by the true motion corrupted with noise.

3/11/2016CS225B Kurt Konolige Variances and Deviations For independent errors, variances add. If errors are specified using std, the length over which the error occurs must be given: 6 cm in 1 m => 36 cm 2 in 1 m 3 deg in 360 deg => 9 deg 2 in 360 deg Consider to specify a variance s2s2 s2s2 2s 2

3/11/2016CS225B Kurt Konolige Typical Distributions for Probabilistic Motion Models Normal distributionTriangular distribution

3/11/2016CS225B Kurt Konolige Calculating the Posterior given x, x ’, and u 1.Algorithm motion_model_odometry(x,x’,u) return p 1 · p 2 · p 3 odometry values (u) values of interest (x,x’)

3/11/2016CS225B Kurt Konolige Application Typical banana-shaped distributions obtained for 2d-projection of 3d posterior. x’ u p(x|u,x’) u x’