CS7638 FINAL EXAM SOLVED 100%
CORRECT!!
1 of 75
Term
Is the sense function calculated used Bayes Rule or Law of Total
Probability?
Give this one a try later!
Law of Total Probability Cannot be multimodal (Just
(Convolution) unimodal)
Prediction
, Bayes Rule (Normalized
Product)
Don't know?
2 of 75
Term
Can particle filters be used in continuous spaces?
Give this one a try later!
Cannot be multimodal (Just Motion makes entropy go up,
unimodal) measurement makes it go down
The new mean goes towards the Yes, they are usually used for
smaller variance continuous spaces
Don't know?
3 of 75
Term
Which PID term minimizes error?
Give this one a try later!
Exponential Constant
, Inverse Proportional
Don't know?
4 of 75
Definition
No motion noise and no fuzzing will cause particles to be
resampled from existing locations, leading to 2+ particles initialized
at the same exact spot. As time goes on, the less-probable locations
will fall off, and no new locations will be added until all particles are
on top of each other at the same point. This is why fuzzing was
necessary in the particle filter project -- to add exploration.
Give this one a try later!
Does a heuristic need to be less than, equal to, or more than the cost of the goal
to be admissible for A*?
In regards to Kalman Filters, when it comes to scaling in the number of
dimensions of the state space, which of the following is the amount of storage
that must be assigned?
When applied to robots, do you believe the Particle Filter is exact or
approximate?
True or False: A particle filter with no motion noise, no fuzzing, and a
constant number of resampled particles will usually have all
particles converge to a single point
, Don't know?
5 of 75
Term
Does a heuristic need to be less than, equal to, or more than the
cost of the goal to be admissible for A*?
Give this one a try later!
Less than or equal to Dynamic Programming
The new mean is located in
the middle P(A and B) = P(A) * P(B)
Don't know?
6 of 75
Term
When applied to robots, do you believe the Particle Filter is exact or
approximate?
Give this one a try later!
Accurate Exact
CORRECT!!
1 of 75
Term
Is the sense function calculated used Bayes Rule or Law of Total
Probability?
Give this one a try later!
Law of Total Probability Cannot be multimodal (Just
(Convolution) unimodal)
Prediction
, Bayes Rule (Normalized
Product)
Don't know?
2 of 75
Term
Can particle filters be used in continuous spaces?
Give this one a try later!
Cannot be multimodal (Just Motion makes entropy go up,
unimodal) measurement makes it go down
The new mean goes towards the Yes, they are usually used for
smaller variance continuous spaces
Don't know?
3 of 75
Term
Which PID term minimizes error?
Give this one a try later!
Exponential Constant
, Inverse Proportional
Don't know?
4 of 75
Definition
No motion noise and no fuzzing will cause particles to be
resampled from existing locations, leading to 2+ particles initialized
at the same exact spot. As time goes on, the less-probable locations
will fall off, and no new locations will be added until all particles are
on top of each other at the same point. This is why fuzzing was
necessary in the particle filter project -- to add exploration.
Give this one a try later!
Does a heuristic need to be less than, equal to, or more than the cost of the goal
to be admissible for A*?
In regards to Kalman Filters, when it comes to scaling in the number of
dimensions of the state space, which of the following is the amount of storage
that must be assigned?
When applied to robots, do you believe the Particle Filter is exact or
approximate?
True or False: A particle filter with no motion noise, no fuzzing, and a
constant number of resampled particles will usually have all
particles converge to a single point
, Don't know?
5 of 75
Term
Does a heuristic need to be less than, equal to, or more than the
cost of the goal to be admissible for A*?
Give this one a try later!
Less than or equal to Dynamic Programming
The new mean is located in
the middle P(A and B) = P(A) * P(B)
Don't know?
6 of 75
Term
When applied to robots, do you believe the Particle Filter is exact or
approximate?
Give this one a try later!
Accurate Exact
