© sebastian thrun, cmu, 20001 16-899c statistical techniques in robotics sebastian thrun and...

© sebastian thrun, CMU, 2000 1

16-899C Statistical Techniques In Robotics

Sebastian Thrun and Geoffrey GordonCarnegie Mellon University

www.cs.cmu.edu/~thrunwww.cs.cmu.edu/~ggordon

© sebastian thrun, CMU, 2000 2

notes

Pointer to Larry’s material

© sebastian thrun, CMU, 2000 3

Administrative Information

Sebastian Thrun thrun@cs.cmu.edu Geoffrey Gordon ggordon@cs.cmu.edu Web: http://www.cs.cmu.edu/~16899 Email list: 16-899@cs.cmu.edu Time: Mon/Wed, 10:30-11:50am Location: NSH 3302 TA: n/a Appointments: send Email!

© sebastian thrun, CMU, 2000 4

© sebastian thrun, CMU, 2000 5

Goals

Enable you to program robots and embedded systems in a robust fashion

Enable you to understand the intrinsic assumptions in your robot software

Enable you to pursue original research in probabilistic robotics

Sway you into joining a young and fascinating research field: probabilistic robotics

© sebastian thrun, CMU, 2000 6

What this course is not

Intro to robotics Little work Low on math

© sebastian thrun, CMU, 2000 7

Course Schedule

LocalizationSept 4-16

MappingSept 30-Oct 16

Decision MakingOct 21-30

Multi-AgentNov 4-11

Advanced PerceptionNov 13-25

© sebastian thrun, CMU, 2000 8

What You Should Do

Think

Think differently

Be critical

Come up with Original Research

© sebastian thrun, CMU, 2000 9

What Is A Good Project

Mine Mapping Multi-Agent Control

© sebastian thrun, CMU, 2000 10

Requirements

In teams of three:• Warm-up project (mobile robot localization)• Written assignment(s)• Research Project

Class Presence: all but two sessions (send me email) Quizzes (all but at most two) No exams

© sebastian thrun, CMU, 2000 11

Your next tasks

Check out Web site• Read assigned paper• Download map+sensor data and program robot

localization algorithm

Send Sebastian mail with your name and names of team mates (for warm-up project)

Come to class on Sept 9th (10:30am-11:50am)

© sebastian thrun, CMU, 2000 12

© sebastian thrun, CMU, 2000 13

© sebastian thrun, CMU, 2000 14

© sebastian thrun, CMU, 2000 15

© sebastian thrun, CMU, 2000 16

Five Sources of Uncertainty

EnvironmentDynamics

RandomAction Effects

SensorLimitations

InaccurateModels

ApproximateComputation

© sebastian thrun, CMU, 2000 17

Trends in Robotics

Reactive Paradigm (mid-80’s)• no models• relies heavily on good sensing

Probabilistic Robotics (since mid-90’s)• seamless integration of models and sensing• inaccurate models, inaccurate sensors

Hybrids (since 90’s)• model-based at higher levels• reactive at lower levels

Classical Robotics (mid-70’s)• exact models• no sensing necessary

© sebastian thrun, CMU, 2000 18

© sebastian thrun, CMU, 2000 19

Rhino

© sebastian thrun, CMU, 2000 20

Minerva

© sebastian thrun, CMU, 2000 21

The CMU/Pitt Nursebot Initiative

© sebastian thrun, CMU, 2000 22

People Detection

Mike Montemerlo

© sebastian thrun, CMU, 2000 23

Learning Models of People

Maren Bennewitz

© sebastian thrun, CMU, 2000 24

3D Mapping Result

With: Christian Martin

© sebastian thrun, CMU, 2000 25

Multi-Robot Exploration

© sebastian thrun, CMU, 2000 26

Mine Mapping (brand new)

© sebastian thrun, CMU, 2000 27

What are interesting problems?

Mapping, automatic, manual, guided? Probabilistic localization, landmarks?, odometer!, Route planning, collision avoidance Mine Mapping?

© sebastian thrun, CMU, 2000 28

How can we solve them?

© sebastian thrun, CMU, 2000 29

© sebastian thrun, CMU, 2000 30

Where Am I/?

© sebastian thrun, CMU, 2000 31

Nature of Sensor Data: Uncertainty

Odometry Data Range Data

© sebastian thrun, CMU, 2000 32

© sebastian thrun, CMU, 2000 33

Warm-Up Assignment: Localization,Due Sept 23

© sebastian thrun, CMU, 2000 34

Warm-Up Assignment: Localization

© sebastian thrun, CMU, 2000 35

Warm-Up Assignment: Localization