Aims

• To give an appreciation of the issues that arise when designing complete, physically embodied autonomous agents.
• To introduce the most popular methods for controlling autonomous mobile robots
• To give hands on experience of engineering design
• To encourage independent thought on possible cognitive architectures for autonomous agents

Objectives

• Design, build and program simple autonomous robots.
• Implement standard signal processing and control algorithms.
• Describe and analyse robot processes using appropriate methods.
• Solve simple control problems by hand using appropriate methods.
• Write a detailed report on a robot project.
• Carry out and write up investigations using appropriate experimental methods.

Prerequisites

Some knowledge of probability theory, basic continuous and discrete maths is an advantage. Some knowledge of C is helpful.

Teaching Methods

18 Lectures approximately
24 Laboratory Sessions approximately

Lectures are interactive with short exercises and games to help the students test their understanding. Class discussion of material is encouraged.

The course work will be based around the construction and programming of Lego robots using Interactive C and a commercially produced microprocessor board. The students will work in pairs. Demonstrators will be on hand to advise on design, programming and debugging of the robots. The final lab session will be a contest between the robots constructed by each team.

There will also be additional take home exercises with answers; and recommended reading assignments to suport the student's understanding of this material.

Assessment

100% For a writeup and demonstration of an autonomous robot project designed and constructed by each team.

It will be expected that the reports relate the theory from the lectures to the robot design and behaviour, and show your ability to place your work in the context of recent work in the field.

Recommended Books

Title	Author(s)	Publisher	Comments
Lecture Notes on Intelligent Robotics, and lab handouts	Jeremy Wyatt	SCS, University of Birmingham	Available to students on the module
Embodied Intelligence	R Brooks and C Ferrell	MIT Press, 1999
The Art of Robotics: An introduction to engineering	F Martin	Addison-Wesley, forthcoming
Vehicles: Experiments in Synthetic Psychology	V Braitenberg	MIT Press, 1984	A copy available with each kit.
Mobile Robotics: A practical introduction	U Nehmzow	Springer Verlag, 2000
Robot Learning	S Mahadevan and J Connell	Kluwer Academic, 1993
Mobile Robots: Inspiration to Implementation	J Jones, B Seiger, and A Flynn	AK Peters, 2nd Ed, 1999
Behavior Based Robotics	R Arkin	MIT Press, 1998

1. Introduction
   • What is robotics?
   • Robotics and AI
   • Embedded Systems
   • Agent-Task-Environment model
   • Embodied Systems
   • Synthetic approaches to science
2. Sensors and signal processing
   • Common sensors and their properties
   • 1D signal processing
   • Vision
3. Planning approaches to robot control
   • STRIPS and SHAKEY
   • Robot manipulator kinematics
   • Limitations of planning approaches
4. Control Theory
   • Feedback, feedforward and open loop control
   • Linear first order lag processes
   • Limitations of control theory
5. Probability Based Approaches
   • Markov Decision Processes (MDPs)
   • Partially Observable Markov Decision Processes
   • Navigation
6. Behaviour-Based Control
   • The subsumption architecture
   • Hybrid architectures
   • Formalising behaviour based control (SMDPs)
7. Adaptive approaches to robot control
   • Reinforcement learning for control
   • Model Based learning approaches to control
   • Learning maps
   • Evolutionary approaches
8. Case studies and applications