Robot ics J uly 26, 2005 CS 486/ 686 Universit y of Wat erloo - PowerPoint PPT Presentation

Robot ics J uly 26, 2005 CS 486/ 686 Universit y of Wat erloo

Out line • Robot ics – Percept ion – Planning • Reading: R&N Sect . 25.1-25.4 2 CS486/686 Lecture Slides (c) 2005 P. Poupart

Robot s • Manipulat ors – Physically anchored – Most indust r ial robot s • Assembly lines 3 CS486/686 Lecture Slides (c) 2005 P. Poupart

Robot s • Mobile r obot s – Shakey t he robot (SRI 1968) • First mobile robot – Service robot s (CMU’s Minerva) • Museum t our guide robot – Unmanned land vehicle (NavLab) • Aut onomous highway driving – Unmanned air vehicles • Surveillance, crop-spraying, milit ary operat ions – Aut onomous underwat er vehicles • Deep see explorat ion – Planet ary rovers (Nasa’s Soj ourner) 4 CS486/686 Lecture Slides (c) 2005 P. Poupart

Shakey t he robot • First mobile robot (SRI 1968) 5 CS486/686 Lecture Slides (c) 2005 P. Poupart

Nasa’s Soj ourner • Planet ary rover 6 CS486/686 Lecture Slides (c) 2005 P. Poupart

Honda’s P3 and Asimo • Humanoid robot s 7 CS486/686 Lecture Slides (c) 2005 P. Poupart

Robot Hardware • Sensors – Range f inder s (sonar s, laser s) – Tact ile sensors – GPS – I maging (video cameras) – Propriocept ive sensors (odomet ry) – Microphones 8 CS486/686 Lecture Slides (c) 2005 P. Poupart

Range scan example 9 CS486/686 Lecture Slides (c) 2005 P. Poupart

Robot ic Percept ion • Challenge: noisy sensors • What st at ist ical model should we use t o inf er t he st at e of t he world? • HMMs (or DBNs) s 0 s 1 s 2 s 4 s 3 o 1 o 2 o 3 o 4 10 CS486/686 Lecture Slides (c) 2005 P. Poupart

Robot Localisat ion • Sebast ian Thrun • ht t p:/ / robot s.st anf ord.edu/ movies/ sca80a0.avi 11 CS486/686 Lecture Slides (c) 2005 P. Poupart

Simult aneous mapping and localisat ion • ht t p:/ / robot s.st anf ord.edu/ movies/ mapping1-new.avi • Sebast ian Thrun 12 CS486/686 Lecture Slides (c) 2005 P. Poupart

Robot Hardware • Ef f ect ors – Revolut e j oint s and prismat ic j oint s – Gripper s – Wheels – Legs – Speaker s 13 CS486/686 Lecture Slides (c) 2005 P. Poupart

Degrees of Freedom • A robot has one degree of f reedom f or each independent direct ion of movement P R R R R R 6 degrees of freedom 14 CS486/686 Lecture Slides (c) 2005 P. Poupart

Degrees of Freedom • How many degrees of f reedom (DOF) does a car have? – 3 ef f ect ive DOF: x, y, orient at ion – 2 cont rollable DOF θ (x,y) 15 CS486/686 Lecture Slides (c) 2005 P. Poupart

Degrees of Freedom • Holonomic robot s: – # ef f ect ive DOF = # cont rollable DOF – Most robot arms – Easy t o cont rol – Complex mechanics • Non-holonomic robot s – # ef f ect ive DOF > # cont rollable DOF – Most mobile robot s – Harder t o cont rol – Simple mechanics 16 CS486/686 Lecture Slides (c) 2005 P. Poupart

Planning • Challenge: – Noisy sensors – Uncert ain act ion ef f ect s • What st at ist ical model can we use? – Par t ially observable Markov decision process (POMDP) – Dynamic decision net work (DDN) 17 CS486/686 Lecture Slides (c) 2005 P. Poupart

POMDP (or DDN) • Graphical Represent at ion o 2 o 3 o o o 1 a 3 a 2 a 0 a 1 s 0 s 1 s 2 s 4 s 3 r 2 r 3 r 4 r 1 18 CS486/686 Lecture Slides (c) 2005 P. Poupart

Greedy Pat ient Finding • Sebast ian Thrun • ht t p:/ / robot s.st anf ord.edu/ movies/ bad.people.avi 19 CS486/686 Lecture Slides (c) 2005 P. Poupart

POMDP Pat ient Finding • Sebast ian Thrun • ht t p:/ / robot s.st anf ord.edu/ movies/ good.people.avi 20 CS486/686 Lecture Slides (c) 2005 P. Poupart

Ot her subf ields of Robot ics • Mechanics – Hardware engineering • Cont rol – Form of planning – Mainly concerned wit h “st abilit y” 21 CS486/686 Lecture Slides (c) 2005 P. Poupart

Next Class • Next Class: •Course wrap up •Final exam inf o •Ot her AI courses 22 CS486/686 Lecture Slides (c) 2005 P. Poupart