Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Autonomous Systems > Lecture 6 - Control Architectures > Flashcards

Lecture 6 - Control Architectures Flashcards

1
Q

Control Architecture

  1. definition
  2. what does it enable?
A
  1. A control architecture provides guiding principles and constraints for organizing a robot’s control system (its brain)
  2. To program a robot in such a way that it will produce the desired result
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

4 Control Architectures

1. Deliberative Control

A
  • grew out of early AI (playing chess)
    -> does not have conflicting outputs
    Involves long term planning and therefore thoughtfulness in decision and action
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Planning (2)

A

Process of (1) looking ahead at outcomes of possible actions and (2) searching for the sequence of actions that will reach the goal (shortest path in maze)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Planning
Where does searching happen?
Why not somewhere else?

A

In robot’s head as a representation

Not in physical world bc robot can search from the goal backwards

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

4 Control Architectures

  1. Deliberative Control
    - SPA architecture (3)
A
  1. Sensing
  2. Planning
  3. Acting (executing the plan) -> actuators
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q 
4 Control Architectures
1. Deliberative Control
Drawbacks
- Time scale 
-> When a problem (2)?
A
  1. Many sensors + large internal models = large state space
    - > slows down the search
  2. hard if states are partially observable (i.e. location is not completely known)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

4 Control Architectures
1. Deliberative Control
Drawbacks
- Space

A

Memory space

-> robot’s representations must contain all information needed for localizing the robot and planning (distance, images)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

4 Control Architectures
1. Deliberative Control
Drawbacks
- Information

A
  • inaccurate representation leads to errors

- > representations must be checked often

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

4 Control Architectures
1. Deliberative Control

Only useful if..

  1. The environment..
  2. The robot knows..
  3. The robot’s…
A
  1. The environment is completely known and does not change during the execution of the plan
  2. The robot knows what the state of the world is and what the state of the plan is
  3. The robot’s effectors are accurate enough to execute each step of the plan.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

4 Control Architectures

  1. Reactive Control
    - What does it remove?
    - What does it use (2)?
A
  • Removes planning component to get fast response
  • Uses (1) direct mapping between sensors and effectors. (2) A set of reactive rules couple specific situations to specific actions
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

4 Control Architectures

  1. Reactive Control
    - When is it used?
A
  • In a dynamic environment
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q 
4 Control Architectures
2. Reactive Control
Action Selection
1. When needed?
2. Command arbitration
3. Command fusion
A
  1. In situations where multiple actions are triggered
  2. Select one action from multiple candidates
  3. Combine multiple candidates into a single output action/behavior.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q 
4 Control Architectures
3. Hybrid Control
Disadvantages 
1. Deliberative Control
2. Reactive Control
  1. Which need does Hybrid control satisfy?
A
  1. Smart but slow
  2. Fast but inflexible
  3. Need for effective solutions for different time-scales and representation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Synonym for Hybrid System
and explanation (3)
example

A

Three-layer system because they consist of three layers

  1. Reactive layer
  2. Planning layer
  3. Middle layer (links 1. & 2.)

example: medicine delivery robot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

4 Control Architectures
3. Hybrid Control
What if map changes?
Computing path multiple times?

A

The planning layer should update the representation

Nah, store the plans!

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

4 Control Architectures

  1. Hybrid Control
  2. Offline planning
  3. Online planning
A
  1. Preplanned plan, for situations that might arise

2. Planning while task is performed

17
Q

4 Control Architectures

  1. Hybrid Control
  2. Why not plan everything?
  3. Universal plan
A
  1. changes in environment/task & too many plans

2. set of all plans, initial states and all goals within state space

18
Q

4 Control Architectures

  1. Behavior-Based Control
  2. What is it?
  3. Drawback Hybrid System
A
  1. Network of internal behaviors which interact in order to produce the desired external behavior (close to reactionism)
  2. Hybrid has too complex interaction of components
19
Q

4 Control Architectures

  1. Behavior-Based Control
  2. What do behaviors do?
  3. examples
  4. What can behaviors do?
A
  1. they maintain a goal, executed in parallel
  2. find object, follow target
  3. can take inputs from sensors and behaviors AND can send outputs to other behaviors AND can store (decentralized) representations
20
Q

4 Control Architectures

  1. Behavior-Based Control
  2. When should it be used?
A
  1. When behaviors in subsystem operate with similar time-scales
    - > else: hybrid
21
Q

4 Control Architectures

  1. Behavior-Based Control
  2. Hierarchy of behaviors three layer example
    - > what is it called
A 
Layer 0: move around
Layer 1: avoid-obstacles
Layer 3: find-doors
-> subsumption architecture
-> bottom up

Autonomous Systems (10 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions