AI Autonomous Systems

0.0(0)
studied byStudied by 0 people
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
Card Sorting

1/84

encourage image

There's no tags or description

Looks like no tags are added yet.

Study Analytics
Name
Mastery
Learn
Test
Matching
Spaced

No study sessions yet.

85 Terms

1
New cards

situation

adapting and reacting differently to the changing environment (may include learning)

2
New cards

acting

the ability to bring changes in the world

3
New cards

being useful

the ability to achieve some goals

4
New cards

"learning by building"

the idea that one can truly understand something only by building, creating it

5
New cards

emergent behaviour

complex, often unexpected patterns, actions, and behavior that arise from relatively simple rules and/or architecture

6
New cards

the Tortoises

made by WGW, first electromechanical robots. Emergent behavior: 2 sensors, 2 actuators, programmed reactive control

7
New cards

robot

an autonomous system embodied in the physical world, is able to interact, and sense input from it to achieve goals

8
New cards

autonomous

acting based on its own decisions, not being controlled by humans

9
New cards

teleoperated

controlled externally by humans

10
New cards

embodiment

needs to obey laws of physics, and needs to be capable of maintaining itself in the physical world

11
New cards

Braitenberg Vehicles

14 constructed vehicles with more and more "brainpower". Idea: understanding intelligence by creating it.

12
New cards

Vehicle 1

getting around, likes cold, avoids heat; 1 sensor, 1 motor. In nature: Euglena

13
New cards

Vehicle 2

detecting light, each light sensor is connected to a motor on the same side or the opposite side of the vehicle. It uses 2 sensors and 2 motors.

14
New cards

Vehicle 2 Fear

each sensor is connected directly to the motor on the same side, the vehicle appears "fearful" toward the light

15
New cards

Vehicle 2 Aggression

each sensor is connected to the motor on the opposite side, the vehicle behaves in a way that appears to be "aggressive" towards the light

16
New cards

Vehicle 3

the sensors are connected to the motors with inhibitory wiring, so instead of speeding up the motor in response to stronger sensor input, stronger light input causes the motor to slow down. It also uses 2 sensors and 2 motors

17
New cards

Vehicle 3 Love

each sensor is connected to the motor on the same side with an inhibitory connection, the vehicle appears to "love" the light

18
New cards

Vehicle 3 Explorer

each sensor inhibits the motor on the opposite side, the vehicle moves away from strong light sources but may approach and linger in dimly lit areas

19
New cards

Vehicle 4

combines multiple sensory inputs, each linked to different types of stimuli, resulting in more complex behaviors

20
New cards

Vehicle 1-3

Limited autonomy, purely reactive, yet complex behaviors arise from simple excitatory or inhibitory wiring; shows attraction, avoidance, and exploration.

21
New cards

Vehicle 4-6

Increased adaptability and dynamic response; responds to multiple stimuli, adapts to frequent exposure, and begins storing recent data, showing habituation and anticipation.

22
New cards

Vehicle 7-8

Goal-oriented and spatially aware; follows gradients toward goals and learns paths, suggesting early goal-seeking and path memory.

23
New cards

frame of reference problem

concept in robotics, AI, and cognitive science. It addresses the challenge of understanding how different "observers" (robots, systems, or even people) perceive and interpret the same situation differently depending on their unique position, orientation, or context. 3 main points (in this context): - humans detect human-like motivation/emotion, hereby creating false connections - a behavior of a robot is explained not just by its internal mechanisms, but its interaction with the environment (outside world) - complex behavior doesn't necessarily mean complex (internal) mechanisms

24
New cards

Shakey (1966-72)

early AI-inspired robot, that works in carefully prepared lab conditions. It focuses on reasoning and planning

25
New cards

sensors

to be able to perceive the real world

26
New cards

state

description of a robot and its environment at a given point in time (eg. position, orientation, velocity)

27
New cards

state space

consists of all possible states a robot can be in

28
New cards

sensor space

aka perception space, all possible sensor readings a robot can have

29
New cards

states can be

Observable/Partially observable/Hidden, Continuous/Discrete

30
New cards

effectors & actuators

components of a robot that allow it to move (The effector is the arm, and the actuator is the muscle(s) moving it)

31
New cards

passive activation

only potential energy is used for moving (eg. the stepping robot)

32
New cards

active activation

uses external energy for moving (ex. NEO)

33
New cards

examples of actuators

electronic motors, hydraulics, pneumatics, reactive material

34
New cards

DC motors

the more power it gets, the faster it turns (Fe->Fm)

35
New cards

Servo motors

turn shaft to a specific position, usually made from DC motors

36
New cards

control

("brain") needed for an AS, combines sensory input with actuator output

37
New cards

DOF

Degrees Of Freedom - min nr. of coordinates needed to completely specify the motion of a mechanical system

38
New cards

Transitional DOF

x,y,z

39
New cards

Rotational DOF

roll, pitch, yaw

40
New cards

holonomic

controllable DOF

41
New cards

non-holonomic

controllable DOF < Total DOF (eg. car - 2DOF (x,z))

42
New cards

redundant

controllable DOF > Total DOF (human arm - 7 DOF)

43
New cards

robot locomotion

the way a robot moves from one place to another

44
New cards

static stability

stands still without falling (spider, tripod)

45
New cards

dynamic stability

needs to actively balance to not fall (pogo stick)

46
New cards

COG

center of gravity (a body is stable when the COG lies within the polygon of support)

47
New cards

gait

particular way a robot moves, characterized by the sequence of lifting and lowering legs and placing feet on the ground (eg. tripod, ripple) (possible gaits depend on the number of legs.)

48
New cards

robot perception

senses the environment (exteroception), and itself (proprioception)

49
New cards

active sensor

emits signal that interacts with its environment (sonar sensor)

50
New cards

passive sensor

measures physical properties without direct interaction (thermometer)

51
New cards

simple sensor

provides 1D input, that needs little to no processing (switch)

52
New cards

complex sensor

usually provides multidimensional input that requires sophisticated processing (camera)

53
New cards

sensor fusion

improving the usefulness of a sensor by combining it with other sensors

54
New cards

filtered sensing

applying knowledge about the world when processing a signal perceived by a sensor, resulting in simpler processing, and more accurate signal detection

55
New cards

Genetic algorithm (GA)

an approach to learning that is based on simulated evolution (unlike other ML algorithms)

56
New cards

GA processes

  1. random solution, 2. evaluation, ranking 3. creating crossovers, offspring, 4. iterating this process until some goal is achieved

57
New cards

GA components

problem, fitness func., initial pool, evolution strategy (eg. MAXONE)

58
New cards

elitism

ensuring that the solution quality obtained will not decrease, and that the best solutions of a generation will carry over to the next

59
New cards

Genetic Operations

the operations that recombine and mutate selected members of generation Gx

60
New cards

crossovers

trying to simulate biological reproduction

61
New cards

mutation

adding randomness, noise, in hopes of creating a better solution when creating children

62
New cards

natural selection

probabilistic approach is used to decide which solution to keep (trying to resemble natural selection)

63
New cards

Genetic programming (GP)

extension of GAs for creating computer programs

64
New cards

controller

the robot's brain, that's what allows it to be autonomous

65
New cards

optimization

finding the best solution

66
New cards

control architecture

makes it possible to program a robot in such a way that it will produce the desired behavior

67
New cards

deliberate control

"Thinking hard" (eg. Mr. Vogt preparing for the lecture)

68
New cards

SPA architecture

3 steps of deliberate architect; Sense, Plan, Act

69
New cards

reactive control

"Don't think, react!" planning is removed to get fast results (eg. Braitenberg vehicles)

70
New cards

hybrid control

"Think and act separately, in parallel" combines deliberate and reactive control (eg. medicine delivery robot)

71
New cards

offline planning

prepare for situations that might come up (eg. preparing for an exam)

72
New cards

online planning

planning while task is performed (eg. writing the exam)

73
New cards

behavior-based control (BBC)

"Think the way you act!" biologically inspired (eg. humanoid robot)

74
New cards

subsumption architecture

hierarchical system, uses bottom-up design. The best-known architecture for BBC and reactive control

75
New cards

centralized representation

used by deliberative and hybrid control (global map), and centralized reasoning is used to solve the problem (planner to find path)

76
New cards

decentralized representation

it's distributed over behaviors' structure (reasoning is also distributed)

77
New cards

neural network controllers (NN controllers)

can be used by all types of control architectures

78
New cards

Robotic Operating System (ROS)

it consists of many systems, devices, and users that need to interact reliably

79
New cards

ways to organize computer systems

Distributed, parallel, hardware defines this choice

80
New cards

node

a single-purpose program that publishes or subscribes to information on a certain topic (eg. bumper message)

81
New cards

message

timestamped piece of information on a certain topic (eg. bool bumper_pressed)

82
New cards

Symbol grounding problem

symbols must be grounded in robot-environment interaction (eg. beer) (Newell & Simon '76 PSSH). It highlights the need for robots to have a robust mechanism to link abstract symbols to tangible objects and actions in the real world, enabling them to understand and execute commands accurately.

83
New cards

Referential uncertainty

everyone learning word-meaning mappings needs to deal with referential uncertainty (eg. Gavagai!)

84
New cards

effectors

components of a robot that allow it to interact with the physical world (eg. the arm)

85
New cards

actuator

the mechanisms that enable the effectors to execute an action or movement