1. Dr. Long Tran-Thanh ltt08r@ecs.soton.ac.uk University of Southampton
COMP 2208
Robotics
Dr. Long Tran-Thanh
University of Southampton

2. Robotics in popular culture
One of the most noticeable areas of AI
Many people identify AI as robotics

3. Robotics in popular culture
“Robota” (Czech) = A worker of forced labour
From Czech playwright Karel Čapek's 1921 play “R.U.R” (“Rossum's Universal Robots”)
Originated from the Slavic word “rabot” = labour
“Robot” (old Hungarian) = (forced) service
Before that, the word “automaton” was used instead
Robotics: first coined by Isaac Asimov ( )
The field was also called cybernetics (now cybernetics = applied robotics)

4. Robotics in science and engineering
Japanese Industrial Robot Association (JIRA) :
Definition: “A device with degrees of freedom that can be controlled.”
Class 1 : Manual handling device
Class 2 : Fixed sequence robot
Class 3 : Variable sequence robot
Class 4 : Playback robot
Class 5 : Numerical control robot
Class 6 : Intelligent robot
But how did we get to here?

5. Zhuge Liang: automated ox and horses, used as transporting devices
Legends say …
Many legends about automated machines and artificial creatures in almost every culture
More serious stories:
Archimedes: warfare machines
Zhuge Liang: automated ox and horses, used as transporting devices

6. More serious facts … Al-Jazari’s programmable humanoid robots (1200’s)
Leonardo da Vinci’s mechanical knight (circa 1495)
Farkas Kempelen’s Mechanical Turk (1770)
- proven to be a fake machine

7. Nowadays’ robotics Major contributions were made in the 20th century
Motor driven robots
1928: First motor driven automata
1961: Unimate
First industrial robot
1965: Shakey
Autonomous mobile research robot
1969: Stanford Arm
Dextrous, electric motor driven robot arm

8. Nowadays’ popular view on robotics
Most people identify robotics = humanoid robotics

9. Multi-purpose humanoid robots
Robot categories
Service robots
Industrial robots
Multi-purpose humanoid robots
Assistance robots
Field robots
Distributed robots

10. Robot categories
Industrial robots
Service robots
Assistance robots

11. Robot categories
Field robots
Distributed robots

12. JIRA’s categorisation
Class 1 : Manual handling device
Class 2 : Fixed sequence robot
Class 3 : Variable sequence robot
Class 4 : Playback robot
Class 5 : Numerical control robot
Class 6 : Intelligent robot

13. Autonomous intelligent robots
Autonomy
No need for human input to achieve goals
Make and execute own decisions based on sensor information
Intuitive human-robot Interfaces
Does not require extensive user training
Commands to robots should be natural for inhabitants
Adaptation
Robots have to be able to adjust to changes in the environment

14. But how to build them? Mechanical & electrical engineering Hardware
Low level control
Control theory, optimisation
Architecture
High level control
AI: reasoning, planning, decision making, etc…

15. Deliberative control architectures
The robot first plans a solution for the task by reasoning about the outcome of its actions and then executes it (top down)
Control process goes through a sequence of sensing, model update, and planning steps

16. Deliberative control architectures
Advantages
Reasons about contingencies
Computes solutions to the given task
Goal-directed strategies
Problems
Solutions tend to be fragile in the presence of uncertainty
Requires frequent re-planning
Reacts relatively slowly to changes and unexpected occurrences

17. Behaviour-based control architectures
The robot’s actions are determined by a set of parallel, reactive behaviours which map sensory input and state to actions.

18. Behaviour-based control architectures
Combines relatively simple behaviours, each of which achieves a particular subtask, to achieve the overall task.
Reactive: robot can react fast to changes
System does not depend on complete knowledge of the environment
Emergent behavior (resulting from combining initial behaviours) can make it difficult to predict exact behaviour
Difficult to assure that the overall task is achieved

19. Complex behaviour from simple elements: Braitenberg vehicles
Complex behavior can be achieved using very simple control mechanisms (bottom up)
Braitenberg vehicles: differential drive mobile robots with two light sensors
Complex external behavior does not necessarily require a complex reasoning mechanism + + - -
“Coward”
“Aggressive”
“Love”
“Explore”

20. Behaviour-based architectures: subsumption example
Subsumption architecture is one of the earliest behaviour-based architectures
Behaviours are arranged in a strict priority order where higher priority behaviours subsume lower priority ones as long as they are not inhibited.

21. Behaviour-based control architectures
Advantages
Reacts fast to changes
Does not rely on accurate models
“The world is its own best model”
No need for re-planning
Problems
Difficult to anticipate what effect combinations of behaviours will have
Difficult to construct strategies that will achieve complex, novel tasks
Requires redesign of control system for new tasks

22. Hybrid Control Architectures
Hybrid architectures combine reactive behaviour control with abstract task planning
Abstract task planning layer
Deliberative decisions
Plans goal directed policies
Reactive behaviour layer
Provides reactive actions
Handles sensors and actuators

23. Hybrid Control Architectures
Advantages
Permits goal-based strategies
Ensures fast reactions to unexpected changes
Reduces complexity of planning
Problems
Choice of behaviours limits range of possible tasks
Behaviour interactions have to be well modelled to be able to form plans

24. Robot-human interaction
So what’s next?
Robot-human interaction

25. Human-robot interaction in intelligent environments
Controlled and used by untrained users
Intuitive, easy to use interface
Interface has to “filter” user input
Eliminate dangerous instructions
Find closest possible action
Receive only intermittent commands
Robot requires autonomous capabilities
User commands can be at various levels of complexity
Control system merges instructions and autonomous operation
Interact with a variety of humans
Humans have to feel “comfortable” around robots
Robots have to communicate intentions in a natural way

26. Human to robot: command input
Graphical programming interfaces
Users construct policies form elemental blocks
Problems:
Requires substantial understanding of the robot
Deictic (pointing) interfaces
Humans point at desired targets in the world or
Target specification on a computer screen
How to interpret human gestures ?
Voice recognition
Humans instruct the robot verbally
Speech recognition is very difficult
Robot actions corresponding to words has to be defined

27. Robot to human interaction
The robot has to be able to communicate its intentions to the human
Output has to be easy to understand by humans
Robot has to be able to encode its intention
Interface has to keep human’s attention without annoying her
Robot communication devices:
Easy to understand computer screens
Speech synthesis
Robot “gestures”

28. Human-robot interfaces
Existing technologies
Simple voice recognition and speech synthesis
Gesture recognition systems
On-screen, text-based interaction
Research challenges
How to convey robot intentions ?
How to infer user intent from visual observation (how can a robot imitate a human) ?
How to keep the attention of a human on the robot ?
How to integrate human input with autonomous operation ?

29. Future hot topics within robotics
Human-robot interactions
Distributed robotics
Field robotics
Assistance robotics
Will robots also be ubiquitous in 50 years by now?
Similarity to computers (Moore’s law)

30. Summary Robotics: occurs in many areas of our life
Many control architectures: all have advantages and drawbacks
More of engineering
The future is bright (?)

31. Announcement Interested in AI?
… and interested in doing internship / 3-rd year project in AI?
Contact me:
Long Tran-Thanh

32. Acknowledgement
Some slides were taken from the lecture presentation of Manfred Huber (University of Texas at Arlington) on the same topic.