Control

Question 1

What are some aspects used to deal with the hardware that control a robot?

Answer 1

• Drive motors

* Read sensors

Question 2

What are some basic functionalities that control a robot?

Answer 2

• Drive around
• Grasping / object manipulation.
• Processing sensor data.

Question 3

What are some cognitive functions of robots?

Answer 3

• Task and path planning
• Mapping / world model updates
• Communication / coordination with other entities.
• Learning.

Question 4

What is the classical control approach?

Answer 4

*Given a current and desired world state, choose the control inputs that produce the goal state.

Question 5

How many types of control systems do we have for classical control?

Answer 5

*Open loop and closed loop.

Question 6

How does the open loop control work?

Answer 6

Inputs are computed based on inverted know control law, assumed system states and desired goal states.
*It does not rely in real-world settings.

Question 7

How does a closed loop control work?

Answer 7

It dynamically adjust control input.

Question 8

What is the main used of control theory for robotics?

Answer 8

To control actuators.

Question 9

What are some uses for robot control architectures (RCA)?

Answer 9

• Sense the environment.
• Compute desired state change.
• Drive actuators toward desired state change.

Question 10

What are the three main types of RCA?

Answer 10

• Hierarchical: Sense - Plan - Act
• Reactive: Sense - Act
• Hybrid : Sense - |Plan| - Act

Question 11

What is a horizontal RCA?

Answer 11

Data flows through all parts in sequence

Question 12

What is a vertical RCA?

Answer 12

Data flows through some parts in parallel, typically reactive architectures.

Question 13

What are deliberative RCA?

Answer 13

Explicit planning and modeling. Use internal state representations.

Question 14

What are reactive RCA?

Answer 14

Sensor data goes directly to the actuators.

Question 15

What are behavior-base RCA?

Answer 15

• Typically used in vertical or reactive architectures.

* Basic function implemented as “behaviors”, small modules doing a specific task.

Question 16

What is the deliberative RCA?

Answer 16

• Classic approach of AI.
• sensors -> Perception -> Modeling -> Planning -> Plan execution -> Motor control -> Effectors -> Sensors
• Perception - cognition - action cycle.

Question 17

What does modeling know?

Answer 17

• What exists in the world
• Relation between entities
• Properties of entities in the world.

Question 18

What are examples of logic-based modeling?

Answer 18

• First order logic FOL
• Predicate logics
• Temporal logics
• Spatial logics
• Dynamic logics.

Question 19

What are examples of non-logic based?

Answer 19

• Procedural representations
• Analogical representations
• Sematic networks
• Action theories
• Frames and scripts.

Question 20

Common problems of plan execution?

Answer 20

• Incomplete world model
• Effectors fail
• Sensors produce misreadings
• Modification of the world by other agents.

Question 21

What are the weakness of deliberate RCA?

Answer 21

• Slow turnaround cycle
• Re-planning often necessary due to failures, or unexpected events.
• Reactivity hard to achieve
• Extension of control architecture often difficult.
• Long response time in failure situations
• Limited ability to adapt to environmental changes
• Potential paralysis in highly dynamic environments.

Question 22

What could be an example of a behavior-based control?

Answer 22

s -> Follow Path -> E
e -> Look for food -> + f
n -> Avoid danger -> f
s -> Wander -> e
o c
r t
^ o
| ————————————– r

Question 23

How does the behavior-based control work?

Answer 23

• Sensor data goes to all behaviors simultaneuosly
• Each behavior decides on an action
• Behaviors are independent

Question 24

What is the most simple implementation of a behavior-based control?

Answer 24

Braitenberg vehicle

Question 25

How is the behavior of a braitenberg vehicle controled?

Answer 25

based on geometrical arrangement of sensors, motors or by a cross connection between sensors.

Question 26

What are the types of braitenberg vehicles?

Answer 26

• Sensors stimulate same-side motors (Obstacle avoiding)
• Sensors stimulate opposite side motors (Light seeking)
• Sensors go to both motors, some stimulating, some inhibiting. (Depends on weights to achieve behaviors.)

Question 27

What is a subsumption architecture?

Answer 27

• Layered behavior networks.
• In each layer we define elementary behaviors, aggregate behaviors, continuously select behaviors based on sensor data.
• Limited value of look ahead planning

Question 28

What are some requirements for behavior-based control?

Answer 28

• Multiple goals
• Robustness
• Extensibility
• Variety of sensors

Question 29

What are two main reactive architecture styles?

Answer 29

Subsumption architecture

Potential fields

Question 30

What are the basic vector fields?

Answer 30

• Uniform directional field
• Perpendicular field
• Attraction field
• Repulsion field
• Tangential field

Question 31

What are the advantages of potential fields?

Answer 31

• Easy to visualize
• Easy to build up software libraries
• Fields can be parameterized
• Combination mechanism is fixed.

Question 32

What are the disadvantages of potential fields?

Answer 32

• Local minima

* Jerky motion

Question 33

What is the arbitration via action selection?

Answer 33

The behavior with highest activation level is selected.

Question 34

What is the voting-based coordination behavior selection?

Answer 34

• A number of committee members receive activation levels.
• Each committee member selects one behavior
• Behavior with most votes wins

Question 35

What is the behavioral fusion via vector summation?

Answer 35

• Each behavior produces an action vector

* Vectors are summed up