Robot Lab

Robot Lab

William RegliDepartment of Computer Science

(and Departments of ECE and MEM)Drexel University

Robot Lab “Curiosity, earnest research to learn the hidden laws of nature, gladness akin to rapture,

as they were unfolded to me, are among the earliest sensations I can remember.”– Frankenstein, Mary Shelly

• General objectives for this class…– To explore the interaction between software & information and the physical world

by animating, via software, a robotic “creature”…– To use cyber-infrastructure to obtain and share the information needed to execute

the class

You

YourRoomba

Course Goals and Objectives

• Play with Roombas• Introduction to basic problems in robotics

– Experience them 1st hand with Roombas

• Document experiences in GICL Wiki for– Use by future generations of students– Development of outreach materials (I.e. K-12)– Development of demonstration materials

Topics to be covered in lectures

• Intro to Roomba

• Intro to Robotcs– Basics of robotics systems, sensor, etc– Basics of kinematics/dynamics– Robot Motion Planning & Path Planning

• Intro to multi-agent (multi-robot) coordination– Teamwork, distributed constraints, etc

Assignments

• This is a lab-intensive course, you’ll need to budget time to work on the Roombas

• Roomba assignments– Intro Roomba (what 600 freshman did)– Map making– Roomba coordination– Hunt the Wumpus (tentative)

• (possibly) Non-Roomba assignments– Path planning

Class Structure

• Supervisory Professor: WC Regli

• Recitation Lecturers:– Mr. Michael Grauer– Mr. David Wilkie– Mr. Evan Sultanik

• Teaching Assistant and Hardware Tsar– Ms. Megan Thurber

Grading

• If you finish all of the assignments, you get an “A”– If not, the proportion of finished

assignments will be determined by the class instructor team

What is Cyber-Infrastructure?

• Cyber-Infrastructure: – organized aggregate of technologies that enable us to

access and integrate today’s information technology resources to facilitate science and engineering goals.

• data and storage, computation, communication, visualization, modeling, simulation, networking, scientific instruments, expertise and people

• Analogy to other kinds of “infrastructure”, typically created for the general public good– Interstate Highway System, Power Grid, Panama Canal, etc

• Drexel University is the national leader in CI– Only institution w/ 4 active NSF Cyber-Infrastructure Grants

SCI-0537370, SCI-0537125, OCI-0636273, OCI-0636235

Drexel’s CI-TEAM

• Lead Institution: Drexel University– PI William Regli, co-PI Michael Piasecki

• University of Maryland @ College Park– SK Gupta

• University of North Carolina @ Chapel Hill– Ming Lin and Dinesh Manocha

• University of Wisconsin @ Madison– Nicola Ferrier, Vadim Shapiro, Krishnan Suresh

About the Team

• W. Regli– CS, ECE and Mech E– 1997 NSF CAREER

• M. Piasecki– Civil

• SK Gupta– Mech E– PECASE, CAREER,

and ONR YIP

• M. Lin– CS– CAREER

• D. Manocha– CS– PYI, ONR YIP, Sloan

Fellow

• N. Ferrier– Mech E– NSF CAREER

• V. Shapiro– Mech E, Math & CS– NSF CAREER

• K. Suresh– Mech E

Examples of Cyber-Infrastructure

• Networks– Internet, DragonFly

• Data & Knowledge– IMDB to MedLine

• Software Tools– Firefox, MediaWiki,

Skype, Apache, etc.• Communities/People

– SourceForge, Flickr, discussion boards, email lists, …

• Resources & Repositories– SourceForge, GNU, etc

Role of Cyber-Infrastructure(in this class)

• Class Wiki– http://gicl.cs.drexel.edu/wiki/Robot_Lab_%28Spring_2007%29

• Project materials and “How-To” Wiki– http://gicl.cs.drexel.edu/wiki/Category:Roomba_Design_Lab_%28Winter_2007%29

• “Roomba Questions” email list– Subscribe at

http://face.cs.drexel.edu/mailman/listinfo/spring2007-roomba-lab

• Other web resources– Accessible from the Roomba Wiki

Introducing the Roomba

• Introduced in 2002 by iRobot– Company founded by MIT AI legend

Rodney Brooks

• Roombas manufactured after October 2005 contain an electronic and software interface that allows you to control or modify Roomba's behavior and remotely monitor its sensors– The iRobot Roomba Open Interface is

intended for software programmers and roboticists to create their own enhancements to Roomba.

– “Roombatics”: the general science of modifying or programming your Roomba

Highlights from the History of Robotics

Fiction:– Jewish folklore, a golem ( גולם ) is

an animated being created from inanimate matter.

– “Robot”, from the Czech/Slovak word robota, labor or work.

– The word robot first appeared in Karel Čapek's science fiction play R.U.R. (Rossum's Universal Robots) in 1921.

– Fritz Lang’s Metropolis (1926)– Word was brought into use by Isaac

Asimov.– Patron Saint: the HAL 9000

Non-Fiction– Tesla’s remote

controlled boat– SRI’s Shakey– NASA

• Voyager• Pathfinder• Spirit/Opportunity

– Sony Aibo– Honda ASIMO– DARPA Grand Challenge

http://robotics.megagiant.com/history.htmlhttp://en.wikipedia.org/wiki/Robotics

The Future for Robotics

• Existing Applications– Exploration

• Space, undersea

– Haz-Mat Duties• Disaster recovery, inspection

• Nuclear waste management

– Manufacturing• Mining, assembly, welding

– Military• Unmanned Ground, Aerial,

Sea, Undersea Vehicles

• Emerging Applications– Aging Societies

• Over the last century, the age distribution of the U.S. population changed from relatively young to relatively old.

– Medical• Surgical robotics• Tele-medicine• Prosthetics

– Consumer• Electronics, automotive,

entertainment, toys, games

Sprawl robot: SprawlitaMulti-University Research InitiativePI: Mark R. Cutkosky (Stanford University)

JPL Serpentine Robot

Tuna robot: VCUUVDraper Laboratory, Cambridge, MA

Tour of the Roomba

Tour of the Roomba: The Vitals

• Roomba Serial Port• MiniDIN male-male

cable• USB adapter

Tour of the Roomba: The Vitals

• IR Wall Sensors

– You may want to use these to implement wall following behavior

The Roomba Challenges

1. The Chutes

2. The Maze

3. The Great Escape

4. Name that Tune

NIST Rescue Robot LeagueMaze (2004)

Roomba Challenge #1:The Chutes

“The legal and philosophic aspects of obedience are of enormous importance.”

--- "The Perils of Obedience”, Stanley Milgram

• Problem: Given a detailed and exact layout of the world, with single exit path and no possible wrong turns or shortcuts, implement a set of instructions (i.e. a path) for the Roomba so it can navigate the start to the finish

• Objective: minimize time, minimize distance to finish line

Roomba Challenge #1:The Chutes Example

ST

AR

T

FIN

ISH

10m.

3m.

1m

.

3m

6.0508m1m

.

3m

3m

.

3m.

1m.

1.5

m

Roomba Challenge #1:Implementation Challenges

• Getting Roomba/computer set up working• The path/world is explicit; you are doing manual path

planning with complete information---how will you get the robot to follow the path you select?

• Could solve this without the use of sensors by– Dead reckoning– Hard coding (bump-turn-bump-turn etc)

• Error will be introduced by the movement of the vehicle, friction, uncertainty in orientation and initial set up

Roomba Challenge #2:The Maze

"You are in a maze of twisty little passages, all alike“--Colossal Cave Adventure Game, 1976

• Problem: – The night before the competition, we will release the

dimensions/configuration for a different maze of chutes– The Roomba is placed in a maze in a pre-determined starting

location; there will be only one path out, but there may be dead-ends and detours

– Your job: implement an algorithm to find a path out of the maze• Modify existing code for pre-set maze that night OR• Write code for general maze solving

• Objective: minimize time and minimize distance within the maze to the finish line

Roomba Challenge #2:The Maze Example

ST

AR

T

FIN

ISH

How to find the

shortcut?


• You need to use the Roomba sensors– Develop a different strategy because robots may

encounter dead-ends, non-right-angled walls, etc– There may be short cuts that are hard to ‘sense’

• Might not be able to get out without some additional info from sensors or a combination of sensing and hard-coding

• Should be able to get most of the way with hard-coding and dead reckoning

Roomba Challenge #3:The Great Escape

"I'm making this up as I go.“--Indiana Jones, 1936.

• Problem: – The Roomba is placed in an arbitrary maze in an arbitrary

starting location; there will be only one path out, but there may be dead-ends and detours; the maze may be reconfigured between trials

– Your job: implement an algorithm to find a path out of the arbitrary maze

• You will not have time to modify existing code, you’ll need to write code for general maze solving and test it

• Objective: simply exit the maze

Roomba Challenge #3:Escape Example

ST

AR

T

FIN

ISH

x


• This is a tricky assignment– We will not give you the maze; maze config may

change between trials; starting point may change

• You need to implement some kind of maze exit strategy– This will take some work…

• You will not be able to hard-code• Mazes will change

– Hence, cannot change code during the day

Roomba Challenge #4:Name That Tune

“I sing the Body electric;”--Walt Whitman (1819–1892), Leaves of Grass.

• Problem: Program the Roomba to play one or more of the following tunes– The Drexel Ode– Fanfare for the Common Man, A. Copeland– Thus Spake Zarathustra, R. Strauss– The Imperial March (Darth Vader's Theme), John Williams

• Objective: Play the tune– Bonus!!: a chorus of many Roomba doing the Drexel Ode together!! Get your lab-mates together…


• Find the sequence of notes/keys– The set of notes can be shared, posted to the

discussion board, etc.– MIDI files, sheet music are available on the web

• Setting up the Roomba-Midi encoder– http://todbot.com/blog/2006/05/03/roombamidi-

roomba-as-midi-instrument/

• This one shouldn’t be that hard and should be a lot of fun– Feel free to get carried away!

Implementation Tools

• Hacking Roomba: ExtremeTech – by Tod E. Kurt

• Published Dec 2006!• Exercises are derivative of

those in this book• A mere $17! • All code, examples, etc are

available at http://hackingroomba.com/NOTE: you don’t really need the

book, all info is available via the cyber-infrastructure…

Everything is on the Wiki!http://gicl.cs.drexel.edu/wiki/Category:Roomba_Design_Lab_%28Winter_2007%29

Summary of Module Instructions

• Subscribe to mailing list• Connect the Roomba to Your Computer

– Cable, bluetooth, etc• Set up Processing

– An open source programming language and environment for people who want to program images, animation, and sound. Simple programming, no compiling; cut-and-paste examples.

• Install RoombaComm– RoombaComm is a Java library created by Tod E. Kurt that

allows users to communicate with Roomba through a high-level language (Java); Processing uses it.

• Roomba Program 1– A “Hello Roomba” program

Summary of Module Instructions

• Subscribe to mailing list• Connect the Roomba to Your Computer






DO

BE

FO

RE

YO

U C

OM

E T

O

RE

CIT

AT

ION

Processing• What it is

– A simple, interactive, programming language, with full access to Java & Java classes and class libraries

– Simple IDE (Integrated Development Environment), with source code editor, compiler, debugger

– It’s free and open source (if you don’t like it you can modify it)

• Why use it– Quick implementation and testing, perfect for trying out ideas– Lightweight programming environment, just edit source and run– Look ma, No Compiling!– Cross Platform Capability

• Assures same version Java VM– Produces applications for OSX, Windows, Linux

• Note: you are welcome not to use it in favor of C/C++/Java/C#/Perl/Python... etc… but you are on your own.– Tools do exist for roomba hacking in these other languages

Processing: Example Commands

• spinRight(float "degrees") • spinLeft() • goForward() • goBackward() • updateSensors() • playNote() • bump() • bumpLeft() • bumpRight() • wall()

Processing: Example Program

// **WALL FINDING** // - Simple loop that reiterates until it sees a wall // - When it hits left bump sensor, it turn 45 degrees right, and// - vice versa; When it finds a wall, it exits loop, and code can// - be implemented afterwards for another behavior while( ! roombacomm.wall()) // while its not seen a wall { roombacomm.goForward(); // keep going forward until… if (roombacomm.bumpLeft()) { roombacomm.spinRight(45); } else if (roombacomm.bumpRight()) { roombacomm.spinLeft(45); } roombacomm.updateSensors(); }

Processing: Example Program

// **WAGGLE** // - This is a behavior used by the roomba when it is search for// - something. It is seen when roomba is wall-following in// - cleaning mode. roombacomm.drive(velocity, radius) -->// - measurements in millimeters done = false; while ( ! done ) {

roombacomm.drive(200,600); roombacomm.pause(250); roombacomm.drive(200,-600); roombacomm.pause(250);

}

Suggested Approach

• Read the Wiki before you come to recitation• Review the Hacking Roomba website

– Many useful things there• Have software set up on your laptops and ready to go• Familiarize yourself with editing the program elements

– Some basic ‘bump-then-turn’ code may be useful• Be prepared to debug issues such as

– Port conflicts, I/O issues, can’t talk to USB devices, etc.– These will all be situation dependent, and specific to your individual laptop– Suggestion: bring more than one laptop

• You may want to build a test-rig for work outside of class• TAs and Co-ops will be available to help set up

and configure BUT … getting skills in downloadand configuring hardware-software systems is one of the goals of this module!

To Do Before Recitation

• Subscribe to mailing list • Connect the Roomba to Your Computer






DO

BE

FO

RE

YO

U C

OM

E T

O

RE

CIT

AT

ION

Expected Module Pitfalls

• Computer-Roomba configuration– Getting software installed, talking to the Roomba, getting “hello world” to work– This is very environment centric, part of the assignment is for teams to work

this out for at least one machine in your group• Program construction

– Format or syntax problems, unexplained errors, understanding commands– Give yourself time to learn, explore, test & debug. You will not succeed if

you try everything the night before!• Roomba anomalies

– Roomba doesn’t go exactly straight, commands not exact, etc– Welcome to the real world! Dealing with these problems is part of the

assignment.• Software/Algorithm Design

– Don’t make matters too complex. Most of the credit can be gotten via brute force hard coding. However, to fully solve the challenges will require some more sophistication and use of the sensors on the robot.

Suggested Ways to Handle Pitfalls

• Use the mailing list and post questions– At least one member per-team should subscribehttp://face.cs.drexel.edu/mailman/listinfo/roomba-07-questions

• Share insights and information with others– You are scored based on the competition, not based on

configuration of your laptop

• Post hacks, tricks, suggestions and ideas to the list and message board– Major issues will be addressed by the faculty, most

problems are going to be configuration-related

• Use the web and the wiki

The First Assignments

• The Chutes– Fixed maze, in the recitation room

• The Maze– Fixed maze, availability TBD

• The Great Escape– Not a fixed maze, but a family of reconfigurable

ones, set up on the day of the contest and periodically changed during the day

• i.e. you’ll need to implement a maze solver (wall follower or similar) to get out of this

Contest Scoring

• All about time to completion• You must complete the event

– Partial completions will not count (unlike for grading)

• Roomba’s will be timed• No remote control allowed• Objective:

– Complete all the events – Have the lowest cumulative time

Questions?

Unsuccessful Project Successful Project

OK, Great, so we get to program robots to exit mazes… where is the Science and Engineering?

Roomba Challenges #3 & #4:General Maze Solving Algorithms

http://en.wikipedia.org/wiki/Maze#Solving_mazes• Wall Follower• Pledge algorithm• Random mouse• Tremaux's algorithm

Roomba Challenges #3 & #4:General Maze Solving Algorithms

http://en.wikipedia.org/wiki/Maze#Solving_mazes• Wall Follower (a.k.a. Depth First Search)• Pledge algorithm• Random mouse• Tremaux's algorithm

Graph Theory

• History– Leonhard Euler and the

Seven Bridges of Königsberg (1736)

• Problem areas– Subgraphs– Graph Coloring– Network Routing– Network Flow– Visibility– Covering, Embedding

The Bridges of Königsberg

Graph Theory Today

• Graphs are everywhere!• Examples:

– Google’s PageRank algorithm was developed by Page and Brin in an undergrad CS class

– Network communications is about least-cost paths

– Logistics plans for WalMart, FedEx, UPS rely on route planning and map data

– Recommender systems, social networks, etc … all graphs!

– Molecular modeling, computational pharmacology, protein folding all use graphs as their basic data structure

An example

Graph Theory and Mazes: A Change of the Representation

• The physical topology of the maze can mapped into a Graph

• A Graph G can be represented as an ordered pair of setsG = <V, E> where V is the set of vertices and E is the set of edges

• Note that each edge is really a pair as well– i.e. ei = <vk, vj > means that there is an edge

between vertices vk and vj

The Basic DFS Algorithm

dfs( v ) process( v ) /* do what needs to get done*/mark v as visitedfor all vertices i adjacent to v not visited

dfs( i )

• Typical application questions– How to traverse the successor vertices?– How to order/process vertices in your output

• Pre-order (Polish notation) … the above is pre-order.• Post-order (reverse Polish notation)

Depth First Search

Depth First Search

Recurse back up the tree…

Depth First Search

Properties of DFS: Time

• DO NOT measure time with a clock!

• Doing DFS on a graph G with vertices v1, v2, … vn and edges e1, e2, … em

– What is the Time Complexity? (i.e. # of discrete computational steps)

• Best Case?• Worst Case?• Average Case?



– What is the Time Complexity? (i.e. # of computational steps)

• Best Case: you go right to the solution, no backtracking, and the solution is close by

– d steps, where d is the length (i.e. depth) of the shortest path to the soln from the start state

• Worst Case?• Average Case?




• Best Case: d• Worst Case: check every node in the tree

– n steps

• Average Case?




• Best Case: d• Worst Case: n• Average Case: … depends on the structure of the

“tree”…. Not answerable without more info.– Theoretically very difficult problem involving graph theory,

combinatorics and statistics

Properties of DFS: Space

• How much computer memory is needed?• Doing DFS on a graph G with vertices

v1, v2, … vn and edges e1, e2, … em

– What is the Space Complexity? (i.e. how many nodes in memory?)

• Need to store – All nodes on the longest path

– All nodes that “branch” from that path

• This is path-independent– Best Case Scenario and Worst Case Scenario are the same!

Properties of DFS: Space

• One needs Best Case Scenario and Worst Case Scenario are the same– Storage needs,

where d is the longest path and b is the “branching factor” (i.e. the maximum # of edges or degree for a vertex), are d·b

….

“width” of the tree is named b, for “branching factor” b

d

Other Applications/Assignments

• Mapping

• Navigation

• Hunt the Wumpus

Example: MappingThe CMU Millibots

• Modular DesignPlanning & Control

Computation

Motor control

Localization

IR obstacle detection

Communication

Payload:• sonar• camera

• Plug & Play interface

Common Bus:• communications• power12x7x14 cm

Communication

Localization

Motor control

IR

Interface

Interface

Interface

Interface

Interface

...

• Occupancy certainty grids with Bayesian integration:

• Integration of multiple sensor readings

• Integration of multiple local maps

T

T SSFS2

1 ).(Prob),.(Prob).(Prob

0% (Free)

50% (Unknown)

100% (Occupied)

Application: Collaborative Mapping

OccupancyProbability

new sensorreading

Integration of multiple readings

Accumulating Knowledge

• ‘bots communicate to commander agents to create view of the world

• View is propagated back to ‘bots

• ‘bots coordinate their activities to refine world view

Collaborative Exploration

• Robot Agents store global map and determines exploration frontiers

• Robots Agents explore nearest frontier that is not yet being explored by other robots

• Exploration finishes when no more unexplored frontiers exist

Explorationfrontier

Currentgoal

Questions?

Unsuccessful Project Successful Project

Robot Lab

Documents

Transcript of Robot Lab