ICAI 2004 presentation

Learning serious knowledge while “playing” with robots: 

Learning serious knowledge while “playing” with robots Zoltán ISTENES ELTE – IK - PSZT

Introduction: 

Introduction Building and programming robots seem to be just a „game” but : Programming robots requires the use of knowledge from different parts of informatics Robotics can be used as a reduced test environment Students learn and experiment without the feeling of studying Presentation summary : The material and the programming 3 different projects The educational benefits

The material : Lego Mindstorm: 

The material : Lego Mindstorm RCX Microprocessor (H8, 16MHz) ROM (16K) power on program RAM (32K) firmware, user programs Infra red (IR) port 3 input sensors touch, light intensity, rotation, … 3 output motors, lamps, … IR tower (attached to a computer) Lots of Lego bricks, gears, …

Controlling / programming possibilities: 

Controlling / programming possibilities

The „line following” project: 

The „line following” project Objectives : Build a mobile robot and program it to follow a line Make the robot go „as fast as possible” Challenges : Different lines (large, thin, continuous, with gaps, sharp turns, line crossings, etc…) Control algorithms for 1, 2 and 3 sensors Real time, changing environment Learning, adaptation Fault tolerance, error recovery

Different control algorithms for different lines (large and thin line): 

Different control algorithms for different lines (large and thin line)

Different control algorithms for 1 and 3 sensors…: 

Different control algorithms for 1 and 3 sensors…

The used techniques and knowledge (1): 

The used techniques and knowledge (1) Real time constraints appear when the robot goes „as fast as possible” : Sensor reading and information processing speed Motor-robot inertia, wheel slipping… Fault tolerant, error recovery techniques are used when : Unreliable sensor values Inaccurate surface Loosing the line…

The used techniques and knowledge (2): 

The used techniques and knowledge (2) Initial calibration and adaptation are used in the „changing environment” : Changes in the light intensity of the line (room lamps, robot shade, …) Battery’s charge… „Learning” techniques can be used to determine : How fast the robot can go (acceleration on long straight lines) How sharply the robot should turn How to avoid endless repetitions

Educational benefits of the „line following” project: 

Educational benefits of the „line following” project Students confronted, used and learned : Real time constraints Robust, fault tolerant control algorithms Error „recovery” techniques Robot’s learning and adaptation to the changing environment

Game playing projects: 

Game playing projects Project objectives : Two or three RCX is playing with each other Games : Number guessing Battleship Tic-tac-toe Challenges : Game playing logic Inter RCX communication „Server” Visualisation „Client” Player 1 „Client” Player 2 „on turn”

Educational benefitsof the „game playing” projects: 

Educational benefits of the „game playing” projects Students learned and practiced : Communication protocols Broadcast, peer-to-peer Client-server architecture, game master election Game logic algorithms

Experiments with “discovering robots”: 

Experiments with “discovering robots” 1. Capturing the camera image 2. Image processing : Identification of the robot and the target 3. Constructing an internal representation of the environment, searching for a path 4. Sending control information to the robot Web camera Mobil robot Target object IR comm. port

Slide15: 

The robot must find, turn and go to the target object

Educational benefitsof the “discovering robots” project: 

Educational benefits of the “discovering robots” project Students learned and practiced : Image processing, image/pattern recognition Computer graphics Path (graph) search Artificial Intelligence Control information’s sending Communication

Educational benefits of programming and using robots (1): 

Educational benefits of programming and using robots (1) Building and programming a robot require knowledge from several different fields of informatics, such as : programming languages and techniques, communication and networks, artificial intelligence and agents, pattern recognition, computer graphics, etc… „Students learn to apply these knowledge.”

Educational benefitsof programming and using robots (2): 

Educational benefits of programming and using robots (2) Building and programming a robot can be seen as a reduced test environment of the real world : Robotics facilitate to model real world’s problems Problems arise faster, since the hardware and software limits are reached sooner „Students learn to find out and apply solutions, and they acquire a large experience in solving problems for the future.”

Educational benefitsof programming and using robots (3): 

Educational benefits of programming and using robots (3) Building and programming a robot - during the courses - seem to be motivating and interesting, such as : Working in a team Using creativity to construct a project and to realize it Producing a tangible, working result „Students enjoy this kind of thinking, programming and learning.”

Conclusion: 

Conclusion Robot programming facilitates to think, to apply, to combine and to practice : How to use knowledge from different fields of informatics. How to take advantage of a reduced test environment. How to enjoy learning. Students have the feeling of “just playing with robots”, but in the reality, they learn serious knowledge.

Slide21: 

Thank you for your attention ! istenes@inf.elte.hu http://people.inf.elte.hu/istenes