Intelligent Robotics: Introduction and Course Overview Intelligent Robotics 06-13520 Intelligent Robotics (Extended) 06-15267 Jeremy Wyatt School of Computer Science University of Birmingham, 2005
Plan • Intellectual aims of the module • Task description • Introduction to hardware and software • Using robots to understand intelligence
Module aims • Give an appreciation of the issues that arise when designing complete, physically embodied autonomous agents. • Introduce some of the most popular methods for controlling autonomous mobile robots. • Give hands on experience of engineering design. • Encourage independent thought on possible cognitive architectures for autonomous agents.
What you will be able to do • Design, build and program simple autonomous robots. • Implement standard signal processing and control algorithms. • Describe and analyse robot processes using appropriate methods. • Write a detailed report on a robot project. • Carry out and write up investigations using appropriate experimental methods.
IR sensors (long, medium, short) Whiskers Microswitches DC motors Servo motors Odometers Sonar Basic Hardware
Additional Hardware • PC104 board + Handyboard Sensors PC104 (Linux) HB USB Motors USB Camera
Coding on the PC104 • Vision routines can be written easily using extensive libraries from Intel • Multiple processes: threads are wrapped • Download and Run Managers • Support on Handyboard for • pulse counting • new compass • new sonars • smooth pwm
Hardware: a warning • Please take extreme care in handling of all hardware • no loose connections • tidy soldering • careful charging • check static • if you are not 100% sure then ASK • We will not be able to replace severely broken kits (you will have to transfer module)
First Week • Handyboard + IC • Aim to build a complete exploring robot by end of week 2 • will familiarise you with sensors and their properties • will give you practice in robot construction
Base Task Description • Robot Rubbish Clear up • arena with four drop zones • bottles (green) • tennis balls (yellow) • pepsi cans (blue) • coke cans (red) • squiggle ball (any) • collect and correctly deliver the rubbish • 2 robots in each bout of 5 mins
Base Task Description • Scoring scheme in assessment handout • Two demos (1 public, 1 private) • Best of two demos • Competition score • influences demo mark • not the only factor • Private demos on the 22nd, 24th and 25th November • Public demo 30th November 2-4pm • Last Year’s results
Assessment Outline • Assessment by demonstration and report • Report must be • 25 pages maximum • 10 pt minimum • Hand in 12 noon on 8th December
Course Team • Jeremy Wyatt • Lecturer • Noel Welsh • Teaching Assistant • Aleem Hossain, Arjun Chandra • Demonstrators • Ben Stone • system software support • Richard Pannell, Bert Dandy • hardware support
What’s Easy is Hard • Easy: expert systems, mathematics, chess • Hard: seeing, language understanding, moving around, making a cup of tea, common sense • What’s easy for humans is hard for computers and vice versa. Why?
The Whole Iguana • AI commonly studies aspects of intelligence separately: narrow domain high performance • In 1976, philosopher Dan Dennett suggested putting it all together, but with a low level of performance
The Whole Iguana “... why not obtain one's simplicity and scaling down by attempting to model a whole cognitive creature of much less sophistication than a human being?... a turtle, perhaps ... [but] considering the abstractness of the problems properly addressed in AI ... one does not want to bogged down in the cognitive eccentricities of turtles if the point of the exercise is to uncover very general, very abstract properties that will apply as well to the cognitive organisation of … human beings. So why not make up a whole cognitive creature, a Martian three-wheeled iguana, say, and an environmental niche for it to cope with? I think such a project could teach us a great deal about the deep principles of human cognitive psychology …”
Experiments with vehicles • Behaviour of agents was more complex than their mechanisms • Behaviour depended on the environment as well as the agent • Hard to infer mechanism from behaviour alone
Experiments with vehicles Valentino Braitenberg - “Law of uphill analysis and downhill invention” My Conclusion: synthesizing agents may have something to offer in understanding our minds
Why build robots to understand minds? • All naturally occuring intelligence is embodied • So robots are in some ways similar systems • Robots, like animals exploit their environments to solve specific tasks “There are no general purpose animals … why should there be general purpose robots?” David MacFarland
Lessons from nature • Gannets – wings half open to control dive • Fold wings to avoid damage • Not at a constant distance, but at a constant time • Birds have detectors that calculate time to impact
Task specific robots • Polly the tour guide exploits assumptions about environment to perform task quickly
Lessons from nature: 2 • Other animals are capable of a surprising degree of manipulative ability e.g. Betty the crow who can make tools • Sometimes we can use robots to test theories of how specific animals work e.g. cricket phonotaxis
Wrap up • By synthesising intelligent robots we can address deep questions about the nature of intelligence • Robots, like animals, are embodied • We can use the task-environment dynamics to constrain our computational problems