Robotics. Haslum COMP3620/6320

Similar documents
Robotics. Chapter 25. Chapter 25 1

Robotics/Perception II

Localization and Map Building

Mobile Robots: An Introduction.

Spring Localization II. Roland Siegwart, Margarita Chli, Martin Rufli. ASL Autonomous Systems Lab. Autonomous Mobile Robots

Overview. EECS 124, UC Berkeley, Spring 2008 Lecture 23: Localization and Mapping. Statistical Models

Spring Localization II. Roland Siegwart, Margarita Chli, Juan Nieto, Nick Lawrance. ASL Autonomous Systems Lab. Autonomous Mobile Robots

Robotics. CSPP Artificial Intelligence March 10, 2004

Monte Carlo Localization using Dynamically Expanding Occupancy Grids. Karan M. Gupta

W4. Perception & Situation Awareness & Decision making

Monte Carlo Localization for Mobile Robots

Robotics: Science and Systems II

Probabilistic Robotics

7630 Autonomous Robotics Probabilities for Robotics

Robot Motion Planning

Zürich. Roland Siegwart Margarita Chli Martin Rufli Davide Scaramuzza. ETH Master Course: L Autonomous Mobile Robots Summary

ME 597/747 Autonomous Mobile Robots. Mid Term Exam. Duration: 2 hour Total Marks: 100

Introduction to Autonomous Mobile Robots

Robotics. Chapter 25-b. Chapter 25-b 1

Last update: May 6, Robotics. CMSC 421: Chapter 25. CMSC 421: Chapter 25 1

Introduction to Mobile Robotics

Probabilistic Robotics

Final Exam Practice Fall Semester, 2012

Practical Course WS12/13 Introduction to Monte Carlo Localization

Localization, Where am I?

Machine Learning on Physical Robots

Robotics Tasks. CS 188: Artificial Intelligence Spring Manipulator Robots. Mobile Robots. Degrees of Freedom. Sensors and Effectors

The University of Pennsylvania Robocup 2011 SPL Nao Soccer Team

Probabilistic Robotics

EE565:Mobile Robotics Lecture 3

(W: 12:05-1:50, 50-N202)

COS Lecture 13 Autonomous Robot Navigation

Colorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.

Autonomous Navigation of Nao using Kinect CS365 : Project Report

Robot Mapping. A Short Introduction to the Bayes Filter and Related Models. Gian Diego Tipaldi, Wolfram Burgard

Localization and Map Building

Basics of Localization, Mapping and SLAM. Jari Saarinen Aalto University Department of Automation and systems Technology

Announcements. CS 188: Artificial Intelligence Fall Robot motion planning! Today. Robotics Tasks. Mobile Robots

CS 188: Artificial Intelligence Fall Announcements

Today MAPS AND MAPPING. Features. process of creating maps. More likely features are things that can be extracted from images:

NERC Gazebo simulation implementation

Announcements. CS 188: Artificial Intelligence Spring Advanced Applications. Robot folds towels. Robotic Control Tasks

CS 188: Artificial Intelligence Spring Announcements

Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization. Wolfram Burgard

Autonomous Mobile Robot Design

Simultaneous Localization

Vehicle Localization. Hannah Rae Kerner 21 April 2015

LAIR. UNDERWATER ROBOTICS Field Explorations in Marine Biology, Oceanography, and Archeology

Introduction to robot algorithms CSE 410/510

Autonomous Vehicles:

Jane Li. Assistant Professor Mechanical Engineering Department, Robotic Engineering Program Worcester Polytechnic Institute

Autonomous Vehicles:

Exam in DD2426 Robotics and Autonomous Systems

L10. PARTICLE FILTERING CONTINUED. NA568 Mobile Robotics: Methods & Algorithms

Robotics. Lecture 5: Monte Carlo Localisation. See course website for up to date information.

Humanoid Robotics. Monte Carlo Localization. Maren Bennewitz

Outline Sensors. EE Sensors. H.I. Bozma. Electric Electronic Engineering Bogazici University. December 13, 2017

A New Omnidirectional Vision Sensor for Monte-Carlo Localization

Geometric Path Planning McGill COMP 765 Oct 12 th, 2017

Particle Filters. CSE-571 Probabilistic Robotics. Dependencies. Particle Filter Algorithm. Fast-SLAM Mapping

What is the SLAM problem?

Simultaneous Localization and Mapping (SLAM)

Turning an Automated System into an Autonomous system using Model-Based Design Autonomous Tech Conference 2018

Vision-based Mobile Robot Localization and Mapping using Scale-Invariant Features

Introduction to Multi-Agent Programming

CS283: Robotics Fall 2016: Sensors

L17. OCCUPANCY MAPS. NA568 Mobile Robotics: Methods & Algorithms

Visual Perception for Robots

This chapter explains two techniques which are frequently used throughout

Autonomous Navigation of Humanoid Using Kinect. Harshad Sawhney Samyak Daga 11633

ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space

Functional Discretization of Space Using Gaussian Processes for Road Intersection Crossing

Revising Stereo Vision Maps in Particle Filter Based SLAM using Localisation Confidence and Sample History

3D Simultaneous Localization and Mapping and Navigation Planning for Mobile Robots in Complex Environments

Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization

CSE-571. Deterministic Path Planning in Robotics. Maxim Likhachev 1. Motion/Path Planning. Courtesy of Maxim Likhachev University of Pennsylvania

Introduction to Mobile Robotics

Introduction to Information Science and Technology (IST) Part IV: Intelligent Machines and Robotics Planning

Adapting the Sample Size in Particle Filters Through KLD-Sampling

Particle Filter in Brief. Robot Mapping. FastSLAM Feature-based SLAM with Particle Filters. Particle Representation. Particle Filter Algorithm

Particle-Filter-Based Self-Localization Using Landmarks and Directed Lines

Statistical Techniques in Robotics (16-831, F10) Lecture#06(Thursday September 11) Occupancy Maps

ZJUCyber Team Description for ROBOCUP 2013

Practical Extensions to Vision-Based Monte Carlo Localization Methods for Robot Soccer Domain

SLAM: Robotic Simultaneous Location and Mapping

Kaijen Hsiao. Part A: Topics of Fascination

Navigation and Metric Path Planning

CSE-571 Robotics. Sensors for Mobile Robots. Beam-based Sensor Model. Proximity Sensors. Probabilistic Sensor Models. Beam-based Scan-based Landmarks

Local Search Methods. CS 188: Artificial Intelligence Fall Announcements. Hill Climbing. Hill Climbing Diagram. Today

L15. POSE-GRAPH SLAM. NA568 Mobile Robotics: Methods & Algorithms

Solid State LiDAR for Ubiquitous 3D Sensing

Pattern Recognition for Autonomous. Pattern Recognition for Autonomous. Driving. Freie Universität t Berlin. Raul Rojas

Sensor technology for mobile robots

Planning in Mobile Robotics

ROBOTICS AND AUTONOMOUS SYSTEMS

Adapting the Sample Size in Particle Filters Through KLD-Sampling

Introduction to Mobile Robotics

AUTONOMOUS SYSTEMS. PROBABILISTIC LOCALIZATION Monte Carlo Localization

Navigation methods and systems

Big Picture: Overview of Issues and Challenges in Autonomous Robotics + Impact on Practical Implementation Details

Transcription:

Robotics P@trik Haslum COMP3620/6320

Introduction Robotics Industrial Automation * Repetitive manipulation tasks (assembly, etc). * Well-known, controlled environment. * High-power, high-precision, very expensive. Mobile Robots * Acting in environments that are dangerous or difficult to access (Fire/rescue, mine clearing, Mars, deep oceans) * Domestic (vaccuum cleaners, guides, toys) * Unknown & dynamic environment. * Uncertain sensors & imprecise actuators. * Hard power/size/weight/cost limits.

Introduction

Introduction Hardware Sensors * Range finders: Sonar, laser, contact sensors. * Imaging: Cameras. * Proprioceptive: shaft encoders, odometers / tachometers, inertial sensors (gyro, accelerometer), compass, force/torque sensors. * External: GPS, beacons, fixed cameras. Effectors * Mobility: Wheels, tracks, legs, rotors / propellers, rudders. * Manipulators: Arm joints, grippers (mechanical, vaccuum, magnetic), attached tools. * Speakers, light signals, etc.

Basic Problems & Techniques Localisation & Mapping Two Basic Problems Localisation & Mapping * How does the world look, and where in it am I? * Localisation: Determining the robots position/pose w.r.t. a known environment. * Mapping (SLAM): Constructing a map of the environment. Path/Motion Planning * Knowing the world and where I am in it, how do I get from here to there? * Path planning: Finding a path from A to B free of collisions with the environment (obstacles). * Motion planning: Finding a sequence of motions that take the robot from A to B without collision.

Basic Problems & Techniques Localisation & Mapping Localisation Filtering Approach * P(x t ) = P(z t x t ) P(x t x t 1, a t 1 )P(x t 1 ) * Motion model (P(x t x t 1, a t 1 )): deterministic prediction + noise. * Sensor model (P(z t x t )): likelihood of making observation z if state is x. * Common assumption: Noise is Gaussian.

Basic Problems & Techniques Localisation & Mapping Representation of the Estimate * Gaussian ( EKF ): - Compact and fast. - Unimodal, assumes linear models. * Probability Grid ( Markov Loc. ): - Discretize configuration space, assign probability to each cell. - Computationally expensive. * Particle Filter ( Monte Carlo Loc. ): - Approximate distribution by a finite sample of configurations. - Computationally expensive (somewhat).

Basic Problems & Techniques Localisation & Mapping Simultaneous Localisation and Mapping (SLAM) * Filtering approach like localisation, but landmark positions part of the state. * Problem: Dimensionality of state changes dynamically as new landmarks detected. * Need to (reliably) reidentify landmarks. Demos by S. Thrun (http://robots.stanford.edu/)

Basic Problems & Techniques Path & Motion Planning Two Basic Problems Localisation & Mapping * How does the world look, and where in it am I? * Localisation: Determining the robots position/pose w.r.t. a known environment. * Mapping (SLAM): Constructing a map of the environment. Path/Motion Planning * Knowing the world and where I am in it, how do I get from here to there? * Path planning: Finding a path from A to B free of collisions with the environment (obstacles). * Motion planning: Finding a sequence of motions that take the robot from A to B without collision.

Basic Problems & Techniques Path & Motion Planning Degree-of-Freedom (DOF) * Degree-of-Freedom (DOF): Independent direction of robot movement. * Configuration (state/ pose ) specified by value for each DOF. * Holonomic: # controllable DOF = # effective DOF. - Non-holonomic robot: Harder planning/control problem.

Basic Problems & Techniques Path & Motion Planning Work & Configuration Space * Work space (W ): 3D world Robot & environment have simple geometry Collision checking is easy. * Configuration space (C): Space of robot states/poses (dimension = # DOF) Robot is a point, obstacles have complex shapes. * Free space: Configurations robot can reach/occupy. * C W easy, W C hard & often ill-posed.

Basic Problems & Techniques Path & Motion Planning Path Planning * Search for a path in free space: Continuous space need to discretize. * Cell decomposition: - Regular grid, subdivision, exact From incomplete to optimal. - Computationally expensive with many dimensions. * Skeletonisation methods. * Probailistic roadmap: - Scales to high-dof problems. - Probabilistically complete, can yield large detours.

Basic Problems & Techniques System Architechture Robot System Architechtures Traditional/Hierarchical * Sense Plan Act : Build high-level world model, reason/plan in model, execute. * Too slow, too brittle (sensing/acting failures). Hybrid Reactive * Sense Act : No explicit internal model. * Intelligence emerges from combination of simple behaviours. *...only sometimes, it doesn t (inflexible, dumb ). * Sense Act & Monitor/Learn/(Re-)Plan/Adapt. * 3-layer architectures (deliberative, reactive, control).

Applications & Success Stories RHINO & Minerva: Robotic Museum Guides * Demonstrated over 3 days in 1997 at Deutsches Museum in Bonn, and 2 weeks in 1998 at the Smithsonian Museum in Washington. * Navigation in an uncontrolled and crowded environment. * Interaction with untrained users: Clearing the way, attracting attention, interpreting requests. http://www.informatik. uni-bonn.de/ rhino/ http://www.cs.cmu.edu/ minerva/

Applications & Success Stories RoboCup * Robot soccer competition, held (almost) annually since 1997. In 2008, 70+ teams, in 4 leagues (+ other events/challenges). - Small (5/team, external camera/computers). - Midsize (4/team, all sensors/computers on-board). - Standard platform (Sony AIBO, Aldebaran NAO). - Humanoid (3/team, kid & teen sizes). * Contributed to advancing s.o.t.a. in mobile robotics hardware and programming from I see the ball to real teamplay. * By the year 2050, a team of fully autonomous humanoid robots that can win against the human world soccer champion team. http://robocup.org/

Applications & Success Stories Mars Exploration Rovers * 2 Rovers, on Mars for over 5 years, have travelled over 7.7 km / 15 km still going! * Daily targets, autonomous navigation & odometry, using stereo vision. * Some autonomous science (rare events captured in nav. cam images). http://marsrovers.nasa.gov/home/

Applications & Success Stories DARPA Grand Challenge 2005 * Challenge: Autonomously driving a course of 212km, * Route defined by coordinates (1 point / 72m). * Dirt road, including some tricky spots. * 5 vehicles finished the course (18 didn t), the fastest in < 7 hours (average of 30 kph). http://www.darpa.mil/grandchallenge/

Applications & Success Stories 1 1 7 2 v1.0 N 5 1 6 6 7 8 14 9 11 12 5 10 8 3 4 9 4 1 2 10 11 * Note: The southern 6 waypoints in the Parking Lot (Zone 14) are Checkpoints 12 17 3 13 DARPA Urban Challenge 2007 * Challenge: Autonomously driving a 38 checkpoint course on urban streets, given network map, with traffic, obeying road rules. * 11 autonomous and 30 human-driven vehicles simultaneously on the track 6 finished the course. Sample RNDF Waypoint Lane Zone Stop Sign Segment / Zone ID Checkpoint ID Parking Lot* Traffic Circle 4-way Stop http://www.darpa.mil/grandchallenge/