022 Hexapods for robot soccer

Information about 022 Hexapods for robot soccer

Published on December 31, 2007

Author: Flemel

Source: authorstream.com

Content

Research on Robot Soccer and what PSU can do:  Research on Robot Soccer and what PSU can do The perceptions :  The perceptions Three perceptions: see, hear and sense_body. All related to one system of perception. Representation of perceptions: (see 1 (ball …) …) Visual Perception:  Visual Perception see. List of objects recognized: type, direction, distance, speed, number. Lines, gates, boundaries, ball. sense_body:  sense_body Force detection Energy available. Principal actions: dash, kick, turn say. Actions Slide5:  Role level : Determines the roles of each robot. (defender, attacker and goal keeper) Action level : Selects actions of each robot. (shooting, blocking, dribbling, etc) Behavior level : Move and obstacle avoidance Execution level : Motor control Role level Variants of Control structure Classification of Robot Soccer Systems:  Vision-based system Remote brainless system Brain-on-board system Robot-based system Selection guidelines Developer’s interests Computational capabilities of host computer and vision system Capabilities of the robots Cost The system can be classified using the location of intelligence Classification of Robot Soccer Systems Remote-Brainless System:  Centralized system Simple and inexpensive Easy to develop the robot No local sensors. Fast computing time and sampling time Easy to debug and upgrade the program Remote-Brainless System High cost vision system and host computer A type of vision-based system Intelligent part is implemented in the host computer. Remote-Brainless System:  Robots The robots consist of driving mechanism, communication part, and computational part for velocity and for processing the data received from a host computer Host computer All the calculations for vision data processing, strategies, position control of robots and so on, are done in the host computer which controls robots like radio -controlled car Remote-Brainless System Brain-on-board system :  Brain-on-board system Intermediate level between the centralized and the distributed systems / between the remote-brainless and the robot based systems. Robots can use local sensors to move to the goal and to avoid the opponent. Can decompose the system into high level (host computer) and low level (robot systems). Easy to make the system in modular form A type of vision-based system Intelligence is partially implemented in the host computer and robots. Brain-on-board system :  Robots The robots have functions such as velocity control, position control, obstacle avoidance, etc. Host computer The host computer processes vision data and calculates next behaviors of robots according to strategies and sends commands to the robots using RF modem. Brain-on-board system Robot-based system:  Robot-based system Suitable when the large number of agents exist Complex and expensive Need communication among robots Distributed system Intelligent part is implemented in the robots. Robot-based system:  Robots The robots decide their own behavior autonomously using the received vision data, own sensor data and strategies. Host computer The host computer processes only vision data can be considered as a kind of sensor. Robot-based system Main PC:  Main PC Serial Port Select the serial communication port Home Goal Select the home side on the screen Find Objects Check the box of which you like to find on the field Initial Position: tell the vision system the initial position of each object E.g.) for the ball i) turn on the radio button of ‘Ball’ ii) place the mouse on the ball and press the left button Repeat above procedure for another object EXAMPLE Main PC:  Main PC Select Situation The situation in which the game is about to start Command Click ‘Ready’: the vision system starts finding the objects on the field Click ‘Start’ : the vision system starts sending commands to the robots Click ‘Stop’ : the vision system stops finding objects and sending commands EXAMPLE Communication (Infra-red):  Communication (Infra-red) Infra-red Communication Four transmitters are used to cover the whole field EXAMPLE Communication:  Communication Both teams share the same transmitter via a mediator Communication Packet Three 0xFFs: the start of a packet 0x0F (0xF0): Team A (Team B) VLi , VRi: left and right wheel velocity of robot i 0xAA: end of velocity data of each robot EXAMPLE Tough, practical problems to be solved:  Tough, practical problems to be solved Real-Time image processing Sensor fusion (sonar, touch, vision, light, other). Motors, batteries. Sophisticated control strategies Radio communication Agent communication Problems :  Problems Players do not know absolute locations. Points of reference are: boundaries, lines and gates. Conflicts of players Limited visibility Limited communication Software:  Software Real-Time Problem, rule-based, agent behavior. Dynamic planning and execution of plans in real-time. Cooperation and competition. No precise information Non-deterministic behavior: results of actions are uncertain. Software potentials (cont.):  Software potentials (cont.) Voice comunication of players Various players have different rules and behaviors, different strategies and implementations - rule-based, neural nets, fuzzy logic, etc. multi-agents: competition versus collaboration. on-line versus off-line, individual versus group behaviors. FIRA and the ECE 478/ECE 479 class at PSU:  FIRA and the ECE 478/ECE 479 class at PSU Class project and in future Capstone Project (if a company will sponsor) High-School project Portland Cyber Theatre Experience in Visual C++, Basic, Lisp and Prolog programming. A lot of fun. Travel to Japan or Korea? Does PSU team has a chance?:  Does PSU team has a chance? 1. Professor Kim from KAIST in Korea invited us to create a new league of walking robots 2. We have experience with walking robots 3. We will try to propose new competition ideas and have a leverage of knowing them earlier. Besides, our students are smart…..? Let us look to our robots…... What we propose:  What we propose Robot soccer system Intelligent control system Multi-agent system Composition of robot soccer system Mobile robots Host computer Vision system Communication module Sports commentator Walking robots Team One:  Team One Complex robots 8 to 12 servos Our walking quadrupeds and hexapods:  Our walking quadrupeds and hexapods Collaborations: ATR, Japan Technical University of Warsaw, Poland Technical University of Gliwice, Poland KAIST, Korea Multi-national team Quadruped :  Quadruped Basic Radio-Controlled Spider Hexapod with Gripper:  Basic Radio-Controlled Spider Hexapod with Gripper Spider with a camera:  Spider with a camera New soccer-specialized hexapod:  New soccer-specialized hexapod Hexapod’s Soccer Kicker:  Hexapod’s Soccer Kicker Team Two:  Team Two Simple robots - hexapods 2 servos SoccerBot:  SoccerBot Final design of a quadruped walker:  Final design of a quadruped walker Block Diagram of the Simple Robot System:  Block Diagram of the Simple Robot System Logic Power PWM Right PWM Left Motor Driver Motor Driver Motor Motor Voltage Regulator Motor Power Micro-Controller Battery Communication Signal Communication Module Motor Part Sport Commentators:  Sport Commentators Bug Virginia Woolf:  Virginia Woolf Jonas:  Jonas Marvin the Crazy Robot:  Marvin the Crazy Robot Class Projects - Winter/Spring 2002:  Class Projects - Winter/Spring 2002 1. Robot position, orientation and conflict detection using top-mounted camera 2. Ball recognition and vision interface to the server 3. Server and user interface 4. Egoistic soccer-playing strategy 5. Collaborative soccer-playing strategy 6. Recovery from body conflicts such as leg entanglements of robots Class Projects - Winter/Spring 2002:  Class Projects - Winter/Spring 2002 7. Design of robo-head sport commentator: speech and natural language generation. 8. Mechanical improvements to robots 9. Design of a special soccer player hexapod. Slide42:  Image Processing: find position, orientation and conflicts of a walker Slide43:  Filtering, histogramming, Hough transform, equations Localization, orientation, conflicts (leg entanglements) Robo Soccer - Why is it so cool?:  Robo Soccer - Why is it so cool? Is Robot Soccer useful? Is the result of Robot Soccer useful? Is Robot Soccer the worlds largest playground? Is there money to be made with robots to play sports? Why are Robot Sports so cool? :  Why are Robot Sports so cool? Captures the essence of soccer. (That’s why there can be a lot of people cheering on the teams) ”Hacker-party” more than a dull academic conference….that is, it is a lot of activity. Interesting problem in co-ordinating 11 processes to achieve a common goal. The width of the field, from Robotic-nerds to Sociologists. Why are Robot Sports so cool? :  In the simulator league, you are forced to learn many concepts: for example network communication, multi-threading, agents, hardware, etc. Testbed for AI-algorithms, sociological theories. Fairly simple environment. A limited set of rules (also predefined), but always close to real world problems. Why are Robot Sports so cool? What are the problems with Robot Competitions ? :  What are the problems with Robot Competitions ? Too much work before reaching an interesting research level Too much focus on low level implementation (still) Still focus on competing instead of comparing of strategies. Research:  Research We do research in several areas: Machine learning (constructive induction) Decision theory Social agents walker’s gaits evolution +more In all of the above we plan to use robot sports as a testbed, or applied area. Conclusion:  Conclusion Robot sports areTHE new standard problem within AI. 1500 researchers world-wide. Focuses on interdisciplinary co-operative work between the researchers as well as co-operation between the agents. New experience for PSU Current class:  Current class 4 ME students 3 CS students 3 EE students Using existing robots CS and EE students develop software ME students develop 2 new robot prototypes and kits with good documentation CS and EE students build new robots from kits ME students adopt software to new robots and learn programming 6 robots of two types build and tested in July Current class:  Current class 4 ME students 3 CS students 3 EE students Using existing robots CS and EE students develop software ME students develop 2 new robot prototypes and kits with good documentation CS and EE students build new robots from kits ME students adopt software to new robots and learn programming 6 robots of two types build and tested in July Technical Publications :  Technical Publications Hiroaki Kitano, Masahiro Fujita, Stephane Zrehen , and Koji Kageyama, "Sony Legged Robot for RoboCup Challenge", In Proceedings of the IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, IEEE, 1998, pp.2605-2612 Manuela Veloso, William Uther, Masahiro Fujita, Minoru Asada, and Hiroaki Kitano, "Playing Soccer with Legged Robot", In Proceedings of the INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, 1998, pp.437-442 Let us go deeper How to find more about RoboCup?:  How to find more about RoboCup? Web Pages: http://medialab.di.unipi.it/Project/Robocup http://www.robocup.org http://www.dsv.su.se/~robocup

Related presentations


Other presentations created by Flemel

What is a Play
17. 10. 2007
0 views

What is a Play

Jeopardy HIV STD HPV
06. 08. 2007
0 views

Jeopardy HIV STD HPV

Training School Bus Driver
17. 09. 2007
0 views

Training School Bus Driver

semantics
17. 09. 2007
0 views

semantics

philosophy
27. 09. 2007
0 views

philosophy

como rezar rosario
01. 10. 2007
0 views

como rezar rosario

WorldMuslimCongress Mecca
02. 10. 2007
0 views

WorldMuslimCongress Mecca

sentence
03. 10. 2007
0 views

sentence

DHL presentation
11. 10. 2007
0 views

DHL presentation

VIPAR Presentation
15. 10. 2007
0 views

VIPAR Presentation

annee2005
16. 10. 2007
0 views

annee2005

PrÃsentation JBaer 20avr
17. 10. 2007
0 views

PrÃsentation JBaer 20avr

Panel 17 8 Taking the Pulse
17. 10. 2007
0 views

Panel 17 8 Taking the Pulse

tom eddy
17. 09. 2007
0 views

tom eddy

grass
22. 10. 2007
0 views

grass

CXPBrasil June2005
26. 11. 2007
0 views

CXPBrasil June2005

Theor Astrophysics
29. 11. 2007
0 views

Theor Astrophysics

Carnival Brasil
30. 11. 2007
0 views

Carnival Brasil

boon
26. 10. 2007
0 views

boon

kumar eng
26. 10. 2007
0 views

kumar eng

talking freight
07. 11. 2007
0 views

talking freight

LHC Net meet 101205ppt
28. 09. 2007
0 views

LHC Net meet 101205ppt

cmd04 VW
16. 11. 2007
0 views

cmd04 VW

11 OrgsSimAndReal
22. 11. 2007
0 views

11 OrgsSimAndReal

PolComm1
08. 10. 2007
0 views

PolComm1

CAFTA training
03. 01. 2008
0 views

CAFTA training

2 casting forming
04. 01. 2008
0 views

2 casting forming

Sales Training II Final
11. 08. 2007
0 views

Sales Training II Final

Sonnet
11. 08. 2007
0 views

Sonnet

sommers rev oct 19 ppt
11. 08. 2007
0 views

sommers rev oct 19 ppt

Scherrer
11. 08. 2007
0 views

Scherrer

Topic 12 Genetic Disorders 3
11. 08. 2007
0 views

Topic 12 Genetic Disorders 3

Sonnet MLA
11. 08. 2007
0 views

Sonnet MLA

Autism AHistory
05. 01. 2008
0 views

Autism AHistory

Shortage of Girls in China
11. 08. 2007
0 views

Shortage of Girls in China

3 BasicRepro2
07. 12. 2007
0 views

3 BasicRepro2

How Adults Learn
06. 08. 2007
0 views

How Adults Learn

Introversion Turned Inside Out
06. 08. 2007
0 views

Introversion Turned Inside Out

Jenkins
06. 08. 2007
0 views

Jenkins

HCR 107 Overheads
06. 08. 2007
0 views

HCR 107 Overheads

N REG SANIT INT
22. 10. 2007
0 views

N REG SANIT INT

Sung Su Truss Bridge
01. 01. 2008
0 views

Sung Su Truss Bridge

Slides KateSteinbeck
11. 08. 2007
0 views

Slides KateSteinbeck

Senate Hearing 2000
11. 08. 2007
0 views

Senate Hearing 2000

William Graham
23. 11. 2007
0 views

William Graham

truman7
29. 12. 2007
0 views

truman7

231nm02
29. 09. 2007
0 views

231nm02

chpt 1 ppt
24. 02. 2008
0 views

chpt 1 ppt

HIV AIDS in Europe
06. 08. 2007
0 views

HIV AIDS in Europe

Heidtke
29. 02. 2008
0 views

Heidtke

NIBSSep021
28. 12. 2007
0 views

NIBSSep021

07 Uae Profilers in TRMM GV Gage
17. 09. 2007
0 views

07 Uae Profilers in TRMM GV Gage

Protista
26. 03. 2008
0 views

Protista

original
07. 04. 2008
0 views

original

slides prog 71
11. 08. 2007
0 views

slides prog 71

wb english
27. 03. 2008
0 views

wb english

Malaria Blue Sky Final Slideshow
30. 03. 2008
0 views

Malaria Blue Sky Final Slideshow

Session1 Parenteau
10. 04. 2008
0 views

Session1 Parenteau

BS3008w1
13. 04. 2008
0 views

BS3008w1

healthcare
06. 08. 2007
0 views

healthcare

SRM Presentation Jim Hanco
14. 04. 2008
0 views

SRM Presentation Jim Hanco

finnews284 2
16. 04. 2008
0 views

finnews284 2

FX Hedging Strategies1
17. 04. 2008
0 views

FX Hedging Strategies1

ioko times showreel
22. 04. 2008
0 views

ioko times showreel

23 Practice Problems
07. 11. 2007
0 views

23 Practice Problems

PE2 U6 R
14. 02. 2008
0 views

PE2 U6 R

ASUD
18. 06. 2007
0 views

ASUD

armi leggere
18. 06. 2007
0 views

armi leggere

apq
18. 06. 2007
0 views

apq

apicorso
18. 06. 2007
0 views

apicorso

aeipres
18. 06. 2007
0 views

aeipres

901059 Kids Share ppt
18. 06. 2007
0 views

901059 Kids Share ppt

Sporting tips
18. 06. 2007
0 views

Sporting tips

semi2
18. 06. 2007
0 views

semi2

Saker Motorports USALLC
18. 06. 2007
0 views

Saker Motorports USALLC

Running on Fumes
18. 06. 2007
0 views

Running on Fumes

FBranca Luxembourg 3mar
26. 11. 2007
0 views

FBranca Luxembourg 3mar

Sisvalsoc
18. 06. 2007
0 views

Sisvalsoc

Shalom Auschwitz Ginocchio
18. 06. 2007
0 views

Shalom Auschwitz Ginocchio

scrittura
18. 06. 2007
0 views

scrittura

scheda unipol
18. 06. 2007
0 views

scheda unipol

satzherstellung
18. 06. 2007
0 views

satzherstellung

uss presentation
02. 01. 2008
0 views

uss presentation

HandsOnWMS nov
16. 10. 2007
0 views

HandsOnWMS nov

hatikvah E2 short
22. 10. 2007
0 views

hatikvah E2 short

amer deadlocks
17. 09. 2007
0 views

amer deadlocks

deadlocks
17. 09. 2007
0 views

deadlocks

L14 Deadlock
17. 09. 2007
0 views

L14 Deadlock

Chapter 03
17. 09. 2007
0 views

Chapter 03

Slides Egidi
18. 06. 2007
0 views

Slides Egidi

Ballanti Diagramaps 070704
18. 06. 2007
0 views

Ballanti Diagramaps 070704

1111 123080220071234
24. 10. 2007
0 views

1111 123080220071234

Dr Tom Sparrow
17. 09. 2007
0 views

Dr Tom Sparrow

amiland gesetze
18. 06. 2007
0 views

amiland gesetze

Gen Micro130 ch1
16. 10. 2007
0 views

Gen Micro130 ch1

bus safety
15. 06. 2007
0 views

bus safety

xo Overheads 2
15. 06. 2007
0 views

xo Overheads 2

Wandering
15. 06. 2007
0 views

Wandering

walker ssm
15. 06. 2007
0 views

walker ssm

spelling
15. 06. 2007
0 views

spelling

spanish american humor
15. 06. 2007
0 views

spanish american humor

research paper checklist
15. 06. 2007
0 views

research paper checklist

Phil Logic 2000 1
15. 06. 2007
0 views

Phil Logic 2000 1

merchant
15. 06. 2007
0 views

merchant

Love 3
15. 06. 2007
0 views

Love 3

jewish humor
15. 06. 2007
0 views

jewish humor

oef 9 opl
15. 06. 2007
0 views

oef 9 opl

oef 2 opl
15. 06. 2007
0 views

oef 2 opl

obscenity andc ensorship
15. 06. 2007
0 views

obscenity andc ensorship

intro to personality psych
06. 08. 2007
0 views

intro to personality psych

Neorev
24. 02. 2008
0 views

Neorev

session 3b cogdell
18. 06. 2007
0 views

session 3b cogdell

jurors
06. 08. 2007
0 views

jurors

Hyde
06. 08. 2007
0 views

Hyde

Reunion Burgos
18. 06. 2007
0 views

Reunion Burgos

JSOBasic
06. 08. 2007
0 views

JSOBasic

sipf050405ih
23. 10. 2007
0 views

sipf050405ih

419 banks 051
10. 03. 2008
0 views

419 banks 051

pries vortraege
14. 11. 2007
0 views

pries vortraege

scar slides
17. 11. 2007
0 views

scar slides

Item 2 Mercury in Terns
06. 08. 2007
0 views

Item 2 Mercury in Terns

The new obesity guidance
11. 08. 2007
0 views

The new obesity guidance

Socrates IIa
11. 08. 2007
0 views

Socrates IIa

ID3 MedhaPradhan
26. 10. 2007
0 views

ID3 MedhaPradhan

AeroSpace Workshop JK mods
22. 10. 2007
0 views

AeroSpace Workshop JK mods

tritroph
30. 12. 2007
0 views

tritroph

Trick or Treaters
18. 06. 2007
0 views

Trick or Treaters

Saviez vous que
11. 08. 2007
0 views

Saviez vous que