AUTONOMOUS SYSTEMS INTRODUCTION

Transcription

1 AUTONOMOUS SYSTEMS INTRODUCTION Pedro Lima, M. Isabel Ribeiro Instituto Superior Técnico/Instituto de Sistemas e Robótica September 2008 Course Handouts All rights reserved

2 Autonomous Systems What is an Autonomous System? 2

3 Autonomous Systems AUTONOMY From Greek αυτονοµία autonomia, noun of quality from αυτόνοµος autonomos independent, living by one s own laws, from αυτο auto- self + νόµος nomos custom, law. In Wikipedia 3

4 Autonomous Systems SYSTEM From late Latin systēma, from Ancient Greek σύστηµα (sustēma), organised whole, body ), from σύν (sun), with, together ) + ἵστηµι (histēmi), I stand ). A collection of organized things. A way of organizing or planning. A whole composed of relationships among the members. In Wikipedia 4

5 Autonomous Systems AUTONOMOUS SYSTEM A collection of organized things, composed of relationships among them, and capable of living independently by its own laws 5

6 Autonomous Systems AUTONOMOUS AGENT An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through effectors (Russel & Norvig, 1995). Jennings and Wooldridge have three key concepts for an agent: situatedness, autonomy, flexibility 6

7 Autonomous Systems AUTONOMOUS AGENT (Jennings & Wooldridge, 1998) Agent is a computer system, situated in some environment, receiving sensory inputs from its environment and performing actions which change the environment in some way. An autonomous agent should be capable of flexible autonomous action in order to meet its design objectives. Flexibility includes that the agent responds to changes it perceives in the environment, takes the initiative where appropriate and is social with other artificial agents and humans. Autonomy means that the agent should be able to act without the direct intervention of humans or other agents and that it should have control over its own actions and internal state. 7

8 Autonomous Systems AUTONOMOUS AGENTS should be able to learn from experience should be able to interact and even cooperate with other autonomous agents should have means of handling the uncertainty associated to its sensor inputs and the effects of its actions over a surrounding, possibly dynamic, environment should have means to take rational decisions, leading to some goal 8

9 Autonomous Systems AUTONOMOUS ROBOTS Autonomous robots are robots (embodied situated agents) which can perform desired tasks in unstructured environments without continuous human guidance. Many kinds of robots have some degree of autonomy. Different robots can be autonomous in different ways. In Wikipedia 9

10 Autonomous Systems AUTONOMOUS ROBOTS have the ability to Gain information about the environment. Work for an extended period without human intervention. Move either all or part of itself throughout its operating environment without human assistance. Avoid situations that are harmful to people, property, or itself. An autonomous robot may also learn or gain new capabilities like adjusting strategies for accomplishing its task(s) or adapting to changing surroundings. In Wikipedia 10

11 Autonomous Systems Examples of Autonomous Systems Autonomous Mobile Robots (individuals or teams) Mobile and Static Sensor Networks Intelligent Homes Autonomous Cars Satellites Spacecraft Software agents Information search Computer viruses Humans, other animals! 11

12 Autonomous Mobile Robots Historical Evolution

13 Autonomous Mobile Robots Historical Evolution Anubis - Ancient Egyptian god of the dead, represented as a jackal or as a man with the head of a jackal. In the Early Dynastic period and the Old Kingdom he was preeminent as lord of the dead, but he was later overshadowed by Osiris. Anubis was associated with the care of the dead and was credited with the invention of embalming, an art he first practiced on the corpse of Osiris. Later assigned the role of conducting souls into the underworld, he was sometimes identified in the Greco-Roman world with Hermes. Karel Capek - He is most famous for coining of the word ``robot'', from the Czech robota, work, in his play (Rossum's Universal Robots RUR) about them taking over the world. The play used to be extremely popular and well-known. The RUR robot which appeared in an adaption of Czech author Karel Capek's Rossum's Universal Robots. Circa 1930s. R.U.R. (Rossum's Universal Robots), which introduced the word robot into the English language, conceives a future in which all workers will be automated. Their ultimate revolt when they acquire souls and the ensuing cotastrophe comprise an exciting, vivid theatrical experience See Le_regne_des_robots_par_Karel_Capek for an explanation of RUR. 13

14 Autonomous Mobile Robots Historical Evolution Elsie 14

15 Autonomous Mobile Robots Historical Evolution Shakey (Stanford University) it was the first mobile robot to be controlled by vision Shakey was set simple tasks to solve: To recognize an object using vision Find its way to the object Perfom some action on the object (for example, to push it over) 15

16 Autonomous Mobile Robots Historical Evolution Stanford Cart In development since 1967, the Stanford Cart successfully crossed a chair-filled room without human intervention in The "Stanford Cart" and SRI's "Shakey" were the first mobile robots controlled by computers (room-sized, radio linked). Both saw with TV cameras. The Cart followed smudgy white lines seen from a high vantage point in variable illumination quite reliably using adaptation and prediction methods far more complex than Elsie's or the Beast's. Hans Moravec rebuilt the Stanford Cart in 1977, equipping it with stereo vision. A television camera, mounted on a rail on the top of the cart, took pictures from several different angles and relayed them to a computer. The computer gauged the distance between the cart and obstacles in its path. 16

17 Autonomous Mobile Robots Historical Evolution The Hilare Family LAAS - France Hilare I Wheels: 2 driving wheels and a free wheel Batteries: 24V Bus: Multibus Processors: 4 x Intel Operating system: none Communication: serial radio modem (9600 bauds) Sensors: Odometer, 16 US sensors, a Laser Range Finder Dimensions (LxWxH): 80cm x 80cm x 60 cm Weight: 400kg 17

18 Autonomous Mobile Robots Historical Evolution The Hilare Family LAAS - France Hilare II Wheels: 2 driving wheels + 4 free wheels Batteries: 48V Bus: VME Processors: 4 x Motorola Motorola PPC 750 Operating system: VxWorks Communication: Ethernet radio modem (3 Mbit/s) Sensors: odometry, 32 Sonar range sensors, 2D Laser Range Finder, 1 Pan/Tilt/Zoom color camera, 2 Pan/Tilt black and white cameras Dimensions (LxWxH): 130cm x 80cm x 80cm Weight: 450kg 18

19 Autonomous Mobile Robots Historical Evolution Hilare IIbis The Hilare Family LAAS - France Wheels: 2 driving wheels + 4 free wheels Batteries: 48V Bus: 1 VME Rack Processors: 4 x Motorola Motorola PPC 604 Operating system: VxWorks Communication: Ethernet radio modem (3 Mbit/s) Sensors: odometry, 32 Sonar range sensors, 2D Laser Range Finder, 1B&W camera Dimensions (LxWxH): 130cm x 80cm x 80cm Weight: 400kg 19

20 Autonomous Mobile Robots Historical Evolution Ghenghis Legged Robot 20

21 Autonomous Mobile Robots Historical Evolution Dante II legged robot 8 legs Exploration at Antartic and Alaska The first robot to use rapell Communication channel based on optical fiber to a base station and then to a satelite station Colour images, laser and cameras on the legs Gas sensors Computers on VME bus (Sparc and MC68000) The CMU Field Robotics Center (FRC) developed Dante II, a tethered walking robot, which explored the Mt. Spurr (Aleutian Range, Alaska) volcano in July High-temperature, fumaroles gas samples are prized by volcanic science, yet their sampling poses significant challenge. In 1993, eight volcanologists were killed in two separate events while sampling and monitoring volcanoes. The use of robotic explorers, such as Dante II, opens a new era in field techniques by enabling scientists to remotely conduct research and exploration. Using its tether cable anchored at the crater rim, Dante II is able to descend down sheer crater walls in a rappelling-like manner to gather and analyze high temperature gasses from the crater floor. In addition to contributing to volcanic science, a primary objective of the Dante II program is to demonstrate robotic exploration of extreme (i.e., harsh, barren, steep) terrains such as those found on planetary surfaces. 21

22 Autonomous Mobile Robots Historical Evolution Cog MIT (USA) Rodney Brooks Protothype of a humanoid robot. 22

23 Autonomous Mobile Robots Historical Evolution Planetary Robotics NASA JPL Rovers 23

24 Autonomous Mobile Robots Historical Evolution Mars rovers: Spirit and Opportunity In Mars since

25 Autonomous Mobile Robots Examples AGV, Efacec Fábrica de Transformadores LGV, Soporcel Fábrica de Papel

26 Autonomous Mobile Robots Examples ATRV-Jr Robot Alice, EPFL, Suíça Wheelesley-cadeira de rodas robotizada Helpmate Aspirador Roomba

27 Autonomous Mobile Robots Examples PackBot, irobot, EUA RAPOSA, ISR/IST + IdMind, Portugal Shrimp, EPFL, Suíça

28 Autonomous Mobile Robots Examples Passarola, ISR/IST, Portugal Robots for Non-Land Environments AIR Helicopter UNDERWATER OCEAN Infante ISR/IST, Portugal Delfim ISR/IST, Portugal

29 Autonomous Mobile Robots Examples AIBO, Sony ASIMO, Honda QRIO, Sony P3, Honda PARO, Japão

30 Historical Evolution Present, Near Future Reconfigurable Robots Small-Micro Robots Robot Collectives (e.g., Swarms) EPFL, Zurich 30

31 Historical Evolution Present, Near Future Robotic Assistant/ Cognitive humanoids Bio-inspired Cognitive Systems Antropomorphic Robotics and Neurosciences icub, FP6 RobotCub project BALTAZAR, ISR/IST, Portugal 31

32 Autonomous Robots - Applications Support to medical services SERVICE ROBOTS Transportation of food, medication, medical exams, Automation of pharmacy service Automatic cleaning of (large) areas Supermarkets, airports, industrial sites Glass cleaning Domestic vacuum-cleaner Client support Museum tours, exhibitions guides Agricultural Fruit and vegetable picking, fertilization, planting Forests Cleaning, fire preventing, tree cuting 32

33 Autonomous Robots - Applications Hazard Environments Inspection of hazard environments (catastrofic areas, vulcanos, nuclear power plants, oil tanks) Inspection of gas or oil pipes, and power transmission lines Oil tank cleaning Construction and demolishing Space Space exploration Remote inspection of space stations Military Surveilance vehicles Monitoring vehicles Forests Cleaning, fire preventing, tree cuting 33

34 Autonomous Robots - Applications Material Handling AGVs, SGVs, LGVs Safety Surveillance of large areas, buildings, airports, car parking lots Civil Transportation Inspection of airplanes, trains, Elderly and Handicapped Assistance to handicapped or elderly people, helping in tansportation, health care, Entertainment RobotDog Aibo Robot dog from Sony Telepresence 34

35 Robot Networks 35

36 Robot Networks Soccer Robots 36

37 Spacecraft Formations 37

38 Static + Mobile Sensor Networks 38

39 Static + Mobile Sensor Networks distributed sensors (cameras) ubiquitous comms networked personal assistants Robot assistants (cognitive, social) 39

40 Home Sensor Networks Autonomous Systems Pedro Lima, Isabel Ribeiro Introduction

41 Home Sensor Networks

42 Robots + Sensors in Urban Scenarios EC FP6 URUS (Ubiquitous Networking Robotics in Urban Settings) Project

43 Static + Mobile Sensor Networks - Applications Environment mapping and monitoring Spatial exploration Surveillance Search and rescue Intelligent homes Intelligent clothes Helping people in urban spaces 43

44 Autonomous Systems New Challenges Growing robots, inspired in humans cognition Bio-inspired robot collectives Robot societies using social sciences concepts 44

45 Components of an Autonomous System Classical cycle: SENSING PROCESSING - ACTING 45