Brainscape's Knowledge GenomeTM

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


See full index

robotics > test2 > Flashcards

test2 Flashcards

1
Q

what is localization

A

the problem of determining and tracking the robots position relative to a map of its environment

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

what are the two types of localization problems?

A

passive vs active and local vs global

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

what is passive localization

A

Interpret sensor data to determine the robots state, Algorithm on robot provides information on robots localization, but that algorithm does not drive the robot(see this more often)

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

what is active localization

A

choose actions designed to help determine the robots state, Localization algorithm is at the steering wheel

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

what is local localization

A

start with good information about the robots state, keep track of this knowledge as the robot moves around, eyes open at start then closed as moving around

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

what is global localization

A

start with no information about the robots state, try to eliminate this uncertainty

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

what is dudek-romanik-whitesides localization

A

Active global localization, lidar and a compass(can tell between rotated similar polygons) with no sensor noise, range sensor provides a visibility polygon of the robots state x, and if measured correctly there is only one spot where this exact polygon will be seen

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

what are the possible states

A

Set of points you can see from a line of sight from the robots location while staying in the Environment, the process of computing this set is hypothesis generation

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

what is the hypothesis generation algorithm

A

input: environment(n vertices) and visibility(m vertices) polygons, output: set of states that have that visibility polygon, O(mn) time(can be faster but take up more space if there are multiple queries), approx n/2 hypotheses, cant solve shortest path to localize.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

what is visibility cell decomposition

A

divide environment by drawing rays outward from mutual vertices and incident edges

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

what is the hypothesis elimination algorithm

A

create an overlay(visibility cell) for all the candidates, choose a destination that crosses a ray in some but not all of the candidates, get new visibility polygon, eliminate candidates that dont match new reading, repeat until only one candidate remains. if destinations are chosen carefully, should only take more than k(candidates)-1 times as much as the optimal strat

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

what is the Kalman filter

A

a localization algorithm that maintains an estimate of the robots state, expressed as a mean and covariance matrix, is passive, local, and probabilistic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

what is the state transition function associated with Kalman

A

xk+1 = f(xk, uk, thetak(action error))

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

what is the observation or sensing function

A

yk/sensor data = h(xk, observation error)

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

Why a linear gaussian system

A

a special class of robot models that can prove that the probability density over the state space is always a Gaussian no matter what

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

linear gaussian transitions

A

xk+1 = Axk+Buk+Gaction error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

linear gaussian sensing

A

yk = Cxk+Hobs error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

gaussian noise

A

both the action and obs errors are chosen randomly according to independent, zero-mean gaussian identities

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

kalman filter inputs

A

state(muk), square covariance matrix(sumk), action(uk), observation(yk), matrices(A,B,C,G,H), action and obs errors

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

kalman filter outpts

A

state(muk+1) and covariance matrix(sumk+1)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

what is the extended kalman filter

A

takes a linear approximation of the system by taking partial derivatives of f and h which allows for kalman to be used on non linear systems. we do lose the guarantee that the probability is represented exactly, but generally works well in practice if the non-linearities arent too great

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

what is the histogram filter

A

a localization algorithm that maintains an estimate of the robots state, expressed as a collection of probabilities for individual cells, passive, local, and probabilistic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

what is the particle filter

A

a localization algorithm that maintains an estimate of the robots state, expressed as a collection of samples, passive, local, and probabilistic

24
Q

why do we need more algorithms beyond KF/EKF?

A

for if there are multiple likely options/non linear systems

25
Q

what do transition models describe

A

transition models specify the probability distribution over the latest state variables given the previous values

26
Q

what do observation models describe

A

A sensor (observation) model describes how the evidence (observed) variables depend on other variables

27
Q

what is posterior distribution

A

keeping track of a probability distribution over the state space, given a history. provides and answer to the question “where am i”, based on things robot did and saw, where is robot likely to be

28
Q

what is posterior updates

A

the update equation for posterior distribution, the long ass equation, has a scaling factor to ensure the probabilities add up to one

29
Q

histogram filter posterior distribution

A

make a finite collection of cells, track the probability of each cell, use the update equation directly, could take up alot of time and memeory if cells made small to increase accuracy, as have to run equation for every cell(N^2), and most states will be zero

30
Q

particle filter posterior distribution

A

track a finite set of samples, called particles, each with a state x and weight w, dont keep track of the probabilities, only the states that have a better chance of being where the robot is, have stacks where more than one particle has the same state

31
Q

what is the particle filter algorithm

A

For each particle:
Assign weights to random states given the probability that what we saw matched with where we are(how likely is it that we wouldve seen this sensor reading), pretend s is the real state, if so how likely is it that we see what we saw

randomly choose with replacement a sample from the generated set(reinforces the data), with probabilities proportional to the weights. Get rid of particles with low weights, copy particles with higher weights(cliffnotes). add the sample to a new set.

32
Q

what is SLAM

A

Simultaneous localization and mapping, the problem of using a mobile robot to build a map of its environment, since maps are hard to get

33
Q

whats the basic idea of SLAM

A

a particle filter where each particle represents both a possible robot path and a possible map

34
Q

what are the two steps of SLAM

A

-probabilistic mapping
-SLAM based on particle filters

35
Q

why is SLAM hard?

A

you cannot separate localization and mapping, as localization usually requires a map agaisnt which to match the robots observations, and mapping usually requires the robot to be localized, so the locations of observed obstacles can be recorded

36
Q

what does mapping look like with known robot locations?

A

you have an occupancy grid, where ml = 1 if cell l is an obstacle, and ml = 0 if cell l is free, and we want the probability that each cell is occupied, given the robots hostory of observations and states

37
Q

how do you update the occupancy grid probabilities?

A

use the update rule, which depends on the likelihood of a given cell being free or an obstacle, given the robots current location and observation(left side), and the occupancy probability, given the history at the previous stage

38
Q

what is an observation model?

A

for an ultrasonic range sensor, depends on the measured distance, and the angle and distance between occupancy grid and sensors emitter

39
Q

what is rao-blackwellization?

A

Factoring the state space into one part we sample(path) and one part we derive(map). Instead of maintaining particles for the whole space, which would require an insane amount of memory, maintain particles for the space of robot paths, and given this path we can compute the most likely map

40
Q

what is the Rao-Blackwellized particle filter?

A

-for each particle, compute the most likely map
-use this map along with the observation model to compute the weight for each particle
-resample using these weights as in the standard particle filter

41
Q

why are cameras good for robots?

A

provide lots of information, small, light, cheap, energy efficient, many aspects of human environment designed with vision in mind.

42
Q

why are cameras a challenge for robots?

A

can be challenging and computation intensive to extrat useful info from camera data, such as depth and correspondence

43
Q

what is the intensity matrix

A

each image is an array of intensity values, either a single value at each position(greyscale) or different values for a small number of channels(rgb)

44
Q

what is the main issue with cameras?

A

losing a dimension, fe the pinhole camera takes a 3d place and produces a 2d image

45
Q

what is the purpose of camera callibration

A

to determine the projection matrix for a given camera, common to use a flat checkerboard with known square sizes that provide constraints on the matrix, want to find a matrix that minimizes the error of these constraints

46
Q

what is stereopsis?

A

use multiple cameras(or views from same camera) then find one or more pairs of points that correspond between the two images

47
Q

what is the baseline in stereopsis?

A

the distance between the cameras, comes with a tradeoff: if cameras are closer together, correspondence is easier(images are similar) but positioning errors are magnified, if they are farther apart, correspondence is harder but results may be more accurate

48
Q

what is ground plane knowledge?

A

if we know that a certain plane(the ground) contains the point we are interested in, enough to use one camera to recover depth

49
Q

other hardware for recovering depth

A

rgbd sensor(project infrared dots and measure distortion)

50
Q

what problem does correspondence try to solve

A

matching objects from different images to one another

51
Q

correspondence with histograms

A

represent an object by the histogram of its colors, useful when objects are distinguished by their combination of colors

52
Q

correspondence with features

A

a feature is an image location that is stable under small changes to the image and in the viewpoint, a feature detector is an algorithm that finds a small, manageable number of features in a given image. dont always need to know what they are as long as they are consistent

53
Q

what is a ros parameter

A

a configuration value of a node. You can think of parameters as node settings

54
Q

what is a ros service

A

another method of node communication, call and response method, many clients only one server

55
Q

what is ros bag

A

records and can play data published from topics in your system

robotics (3 decks)

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