Probability in Robotics - PowerPoint PPT Presentation

About This Presentation
Title:

Probability in Robotics

Description:

Probability in Robotics – PowerPoint PPT presentation

Number of Views:141
Avg rating:3.0/5.0
Slides: 123
Provided by: kara218
Category:

less

Transcript and Presenter's Notes

Title: Probability in Robotics


1
Probability in Robotics
2
Trends in Robotics Research
  • Classical Robotics (mid-70s)
  • exact models
  • no sensing necessary
  • Hybrids (since 90s)
  • model-based at higher levels
  • reactive at lower levels
  • Probabilistic Robotics (since mid-90s)
  • seamless integration of models and sensing
  • inaccurate models, inaccurate sensors

3
Advantages of Probabilistic Paradigm
  • Can accommodate inaccurate models
  • Can accommodate imperfect sensors
  • Robust in real-world applications
  • Best known approach to many hard robotics
    problems
  • Pays Tribute to Inherent Uncertainty
  • Know your own ignorance
  • Scalability
  • No need for perfect world model
  • Relieves programmers

4
Limitations of Probability
  • Computationally inefficient
  • Consider entire probability densities
  • Approximation
  • Representing continuous probability
    distributions.

5
Uncertainty Representation
6
Five Sources of Uncertainty
Approximate Computation
Environment Dynamics
Random Action Effects
Inaccurate Models
Sensor Limitations
7
Why Probabilities
  • Real environments imply uncertainty in accuracy
    of
  • robot actions
  • sensor measurements
  • Robot accuracy and correct models are vital for
    successful operations
  • All available data must be used
  • A lot of data is available in the form of
    probabilities

8
What Probabilities
  • Sensor parameters
  • Sensor accuracy
  • Robot wheels slipping
  • Motor resolution limited
  • Wheel precision limited
  • Performance alternates based on
    temperature, etc.

9
Reasons for Motion Errors
and many more
10
What Probabilities
  • These inaccuracies can be measured and modelled
    with random distributions
  • Single reading of a sensor contains more
    information given the prior probability
    distribution of sensor behavior than its actual
    value
  • Robot cannot afford throwing away this additional
    information!

11
What Probabilities
  • More advanced concepts
  • Robot position and orientation (robot pose)?
  • Map of the environment
  • Planning and control
  • Action selection
  • Reasoning...

12
Probabilistic Robotics
  • Falls in between model-based and behavior-based
    techniques
  • There are models, and sensor measurements, but
    they are assumed to be incomplete and
    insufficient for control
  • Statistics provides the mathematical glue to
    integrate models and sensor measurements
  • Basic Mathematics
  • Probabilities
  • Bayes rule
  • Bayes filters

13
Nature of Sensor Data
Odometry Data
14
Sensor inaccuracy
Environmental Uncertainty
15
How do we Solve Localization Uncertainty?
  • Represent beliefs as a probability density
  • Markov assumption
  • Pose distribution at time t conditioned on
  • pose dist. at time t-1
  • movement at time t-1
  • sensor readings at time t
  • Discretize the density by
  • sampling
  • More on this later.

16
Probabilistic Action model
At every time step t UPDATE each samples new
location based on movement RESAMPLE the pose
distribution based on sensor readings
at-1
st-1
st-1
at-1
  • Continuous probability density Bel(st) after
    moving 40m (left figure) and 80m (right figure).
    Darker area has higher probablity.

17
Globalization
  • Localization without knowledge of start location

18
Probabilistic Robotics Basic Idea
  • Key idea Explicit representation of uncertainty
    using probability theory
  • Perception state estimation
  • Action utility optimization

19
Advantages and Pitfalls
  • Can accommodate inaccurate models
  • Can accommodate imperfect sensors
  • Robust in real-world applications
  • Best known approach to many hard robotics
    problems
  • Computationally demanding
  • False assumptions
  • Approximate

20
Axioms of Probability Theory
  • Pr(A) denotes probability that proposition A is
    true.

21
A Closer Look at Axiom 3
22
Using the Axioms
23
Discrete Random Variables
  • X denotes a random variable.
  • X can take on a finite number of values in x1,
    x2, , xn.
  • P(Xxi), or P(xi), is the probability that the
    random variable X takes on value xi.
  • P(? ) is called probability mass function.
  • E.g.

24
Continuous Random Variables
  • X takes on values in the continuum.
  • p(Xx), or p(x), is a probability density
    function.
  • E.g.

p(x)
x
25
Joint and Conditional Probability
  • P(Xx and Yy) P(x,y)
  • If X and Y are independent then P(x,y) P(x)
    P(y)
  • P(x y) is the probability of x given y P(x
    y) P(x,y) / P(y) P(x,y) P(x y) P(y)
  • If X and Y are independent then P(x y) P(x)

26
Law of Total Probability
Discrete case
Continuous case
27
Thomas Bayes (1702-1761)
  • Mathematician who first used probability
    inductively and established a mathematical basis
    for probability inference

28
Bayes Formula
29
Normalization
30
Conditioning
  • Total probability
  • Bayes rule and background knowledge

31
Simple Example of State Estimation
  • Suppose a robot obtains measurement z
  • What is P(openz)?

32
Causal vs. Diagnostic Reasoning
  • P(openz) is diagnostic.
  • P(zopen) is causal.
  • Often causal knowledge is easier to obtain.
  • Bayes rule allows us to use causal knowledge to
    calculate diagnostic

33
Example
  • P(zopen) 0.6 P(z?open) 0.3
  • P(open) P(?open) 0.5
  • z raises the probability that the door is open.

34
A Typical Pitfall
  • Two possible locations x1 and x2
  • P(x1)0.99
  • P(zx2)0.09 P(zx1)0.07

35
Combining Evidence
  • Suppose our robot obtains another observation z2.
  • How can we integrate this new information?
  • More generally, how can we estimateP(x z1...zn
    )?

36
Recursive Bayesian Updating
Markov assumption zn is independent of
z1,...,zn-1 if we know x.
37
Example Second Measurement
  • P(z2open) 0.5 P(z2?open) 0.6
  • P(openz1)2/3
  • z2 lowers the probability that the door is open.

38
Localization, Where am I?
  • Odometry, Dead Reckoning
  • Localization base on external sensors, beacons
    or landmarks
  • Probabilistic Map Based Localization

39
Localization Methods
  • Mathematical Background, Bayes Filter
  • Markov Localization
  • Central idea represent the robots belief by a
    probability distribution over possible positions,
    and uses Bayes rule and convolution to update
    the belief whenever the robot senses or moves
  • Markov Assumption past and future data are
    independent if one knows the current state
  • Kalman Filtering
  • Central idea posing localization problem as a
    sensor fusion problem
  • Assumption gaussian distribution function
  • Particle Filtering
  • Central idea Sample-based, nonparametric Filter
  • Monte-Carlo method
  • SLAM (simultaneous localization and mapping)
  • Multi-robot localization

40
Markov Localization
  • Applying probability theory to robot localization
  • Markov localization uses an explicit, discrete
    representation for the probability of all
    position in the state space.
  • This is usually done by representing the
    environment by a grid or a topological graph with
    a finite number of possible states (positions).
  • During each update, the probability for each
    state (element) of the entire space is updated.

41
Markov Localization Example
  • Assume the robot position is one- dimensional

The robot is placed somewhere in the environment
but it is not told its location
The robot queries its sensors and finds out it is
next to a door
42
Markov Localization Example
The robot moves one meter forward. To account for
inherent noise in robot motion the new belief is
smoother
The robot queries its sensors and again it finds
itself next to a door
43
Markov Process
Markov Property The state of the system at
time t1 depends only on the state of the system
at time t
Stationary Assumption Transition probabilities
are independent of time (t)
44
Markov ProcessSimple Example
  • Bumper Sensor
  • hits wall 40 will hit in next position
  • 60 will not hit next position
  • not hit wall 20 will hit in next position
  • 80 will not hit next position

Stochastic FSM
45
Markov ProcessSimple Example
  • Bumper Sensor
  • hits wall 40 will hit in next position
  • 60 will not hit next position
  • not hit wall 20 will hit in next position
  • 80 will not hit next position

The transition matrix
  • Stochastic matrix
  • Rows sum up to 1
  • Double stochastic matrix
  • Rows and columns sum up to 1

46
Markov Processobstacle vs. No-obstacle Example
  • Given that a robots last sonar reading was
    Obstacle, there is a 90 chance that its next
    reading will also be Obstacle.
  • If a robots last sonar reading was No-obstacle,
    there is an 80 chance that its next reading will
    also be No-obstacle.

transition matrix
Obst.
No-obst.
Obst.
No-obst.
47
Markov Process obstacle vs. No-obstacle Example
Given that a robot is currently reading
No-obstacle, what is the probability that it will
read obstacle two readings from now? Pr
no-obstacle???obstacle Pr no-obst?obst?obst
Pr no-obst? no-obst ?obst
0.2 0.9 0.8
0.2 0.34
? ? obst
no-obst? ?
48
Markov Process obstacle vs. No-obstacle Example
Given that a robot is currently reading obstacle,
what is the probability that it will read
no-obstacle three readings from now?
49
Markov Process obstacle vs. No-obstacle Example
  • Assume each sensor makes one reading per second
  • Suppose 60 of all sensors now read obstacle, and
    40 read no-obstacle
  • What fraction of sensors will be reading obstacle
    three seconds from now?

PrX3obs 0.6 0.781 0.4 0.438
0.6438 Qi - the distribution in second
i Q0(0.6,0.4) - initial distribution Q3 Q0 P3
(0.6438,0.3562)
50
Markov Process obstacle vs. No-obstacle Example
Simulation
2/3
PrXi obst
second - i
51
Actions
  • Often the world is dynamic since
  • actions carried out by the robot,
  • actions carried out by other agents,
  • or just the time passing by
  • change the world.
  • How can we incorporate such actions?

52
Typical Actions
  • The robot turns its wheels to move
  • The robot uses its manipulator to grasp an object
  • Actions are never carried out with absolute
    certainty.
  • In contrast to measurements, actions generally
    increase the uncertainty.

53
Modeling Actions
  • To incorporate the outcome of an action u into
    the current belief, we use the conditional pdf
  • P(xu,x)
  • This term specifies the pdf that executing u
    changes the state from x to x.

54
Terminology
  • Robot State (or pose) xt x, y, ?
  • Position and heading
  • x1t x1, , xt
  • Robot Controls ut
  • Robot motion and manipulation
  • u1t u1,..., ut
  • Sensor Measurements zt
  • Range scans, images, etc.
  • z1t z1,..., zt
  • Landmark or Map
  • Landmarks or Map

55
Terminology
  • Observation model or
  • The probability of a measurement zt given that
    the robot is at position xt and map m.
  • Motion Model
  • The posterior probability that action ut carries
    the robot from xt-1 to xt.

56
Terminology
  • Belief
  • Posterior probability
  • Conditioned on available data
  • Prediction
  • Estimate before measurement data

57
Example Closing the door
58
State Transitions
  • P(xu,x) for u close door
  • If the door is open, the action close door
    succeeds in 90 of all cases.

59
Integrating the Outcome of Actions
Continuous case Discrete case
60
Example The Resulting Belief
61
Robot Environment Interaction

State transition probability
measurement probability
62
Bayes Filters Framework
  • Given
  • Stream of observations z and action data u
  • Sensor model P(zx).
  • Action model P(xu,x).
  • Prior probability of the system state P(x).
  • Wanted
  • Estimate of the state X of a dynamical system.
  • The posterior of the state is also called Belief

63
Markov Assumption
  • Underlying Assumptions
  • Static world
  • Independent noise
  • Perfect model, no approximation errors

64
Bayes Filters Framework
  • Given
  • Stream of observations z and action data u
  • Sensor model P(zx).
  • Action model P(xu,x).
  • Prior probability of the system state P(x).
  • Wanted
  • Estimate of the state X of a dynamical system.
  • The posterior of the state is called Belief

measurement probability
State transition probability
65
Bayes Filters The Algorithm
  • Algorithm Bayes_filter ( )
  • for all do
  • endfor
  • return

Action model
Sensor model
66
Bayes Filters
z observation u action x state
Action model
Sensor model
recursion
67
Bayes Filter Algorithm
  • Algorithm Bayes_filter( Bel(x),d )
  • ??0
  • If d is a perceptual data item z then
  • For all x do
  • For all x do
  • Else if d is an action data item u then
  • For all x do
  • Return Bel(x)

68
Bayes Filters are Familiar!
  • Kalman filters (a recursive Bayesian filter for
    multivariate normal distributions)
  • Particle filters (a sequential Monte Carlo (SMC)
    based technique, which models the PDF using a set
    of discrete points)
  • Hidden Markov models (Markov process with unknown
    parameters)
  • Dynamic Bayesian networks
  • Partially Observable Markov Decision Processes
    (POMDPs)?

69
In summary.
  • Bayes rule allows us to compute probabilities
    that are hard to assess otherwise
  • Under the Markov assumption, recursive Bayesian
    updating can be used to efficiently combine
    evidence
  • Bayes filters are a probabilistic tool for
    estimating the state of dynamic systems.

70
How all of this relates to Sensors and navigation?
Sensor fusion
71
Basic statistics Statistical representation
Stochastic variable
Travel time, X 5hours 1hour X can have many
different values
Continous The variable can have any value
within the bounds
Discrete The variable can have specific
(discrete) values
72
Basic statistics Statistical representation
Stochastic variable
Another way of describing the stochastic
variable, i.e. by another form of bounds
Probability distribution
In 68 x11 lt X lt x12 In 95 x21 lt X lt x22 In
99 x31 lt X lt x32 In 100 -? lt X lt ?
The value to expect is the mean value gt Expected
value
How much X varies from its expected value gt
Variance
73
Expected value and Variance
The standard deviation ?X is the square root of
the variance
74
Gaussian (Normal) distribution
By far the mostly used probability distribution
because of its nice statistical and mathematical
properties
Normal distribution 68.3 95 99 etc.
What does it means if a specification tells that
a sensor measures a distance mm and has an
error that is normally distributed with zero mean
and ? 100mm?
75
Estimate of the expected value and the variance
from observations
76
Linear combinations (1)
X2 N(m2, s2)
X1 N(m1, s1)
Y N(m1 m2, sqrt(s1 s2))
Since linear combination of Gaussian variables is
another Gaussian variable, Y remains Gaussian if
the s.v. are combined linearly!
77
Linear combinations (2)
We measure a distance by a device that have
normally distributed errors,
Do we win something of making a lot of
measurements and use the average value instead?
What will the expected value of Y be? What will
the variance (and standard deviation) of Y be? If
you are using a sensor that gives a large error,
how would you best use it?
78
Linear combinations (3)
With ?d and ?a un-correlated gt V?d, ?a 0
(co-variance is zero)
di is the mean value and ?d N(0, sd)
ai is the mean value and ?a N(0, sa)
79
Linear combinations (4)
D The total distance is calculated as before
as this is only the sum of all ds
The expected value and the variance become
80
Linear combinations (5)
? The heading angle is calculated as before
as this is only the sum of all ?s, i.e. as the
sum of all changes in heading
The expected value and the variance become
What if we want to predict X and Y from our
measured ds and ?s?
81
Non-linear combinations (1)
X(N) is the previous value of X plus the latest
movement (in the X direction)
The estimate of X(N) becomes
This equation is non-linear as it contains the
term
and for X(N) to become Gaussian distributed, this
equation must be replaced with a linear
approximation around . To do
this we can use the Taylor expansion of the first
order. By this approximation we also assume that
the error is rather small!
With perfectly known ?N-1 and ?N-1 the equation
would have been linear!
82
Non-linear combinations (2)
Use a first order Taylor expansion and linearize
X(N) around .
This equation is linear as all error terms are
multiplied by constants and we can calculate the
expected value and the variance as we did before.
83
Non-linear combinations (3)
The variance becomes (calculated exactly as
before)
Two really important things should be noticed,
first the linearization only affects the
calculation of the variance and second (which is
even more important) is that the above equation
is the partial derivatives of
with respect to our uncertain parameters squared
multiplied with their variance!
84
Non-linear combinations (4)
This result is very good gt an easy way of
calculating the variance gt the law of error
propagation
The partial derivatives of
become
85
Non-linear combinations (5)
The plot shows the variance of X for the time
step 1, , 20 and as can be noticed the variance
(or standard deviation) is constantly increasing.
?d 1/10 ?? 5/360
86
The Error Propagation Law
87
The Error Propagation Law
88
The Error Propagation Law
89
Multidimensional Gaussian distributions MGD (1)
The Gaussian distribution can easily be extended
for several dimensions by replacing the variance
(?) by a co-variance matrix (?) and the scalars
(x and mX) by column vectors.
The CVM describes (consists of) 1) the
variances of the individual dimensions gt
diagonal elements 2) the co-variances between the
different dimensions gt off-diagonal elements
! Symmetric ! Positive definite
90
(No Transcript)
91
MGD (2)
Eigenvalues gt standard deviations Eigenvectors
gt rotation of the ellipses
92
MGD (3)
The co-variance between two stochastic variables
is calculated as
Which for a discrete variable becomes
And for a continuous variable becomes
93
MGD (4) - Non-linear combinations
The state variables (x, y, ?) at time k1 become
94
MGD (5) - Non-linear combinations
We know that to calculate the variance (or
co-variance) at time step k1 we must linearize
Z(k1) by e.g. a Taylor expansion - but we also
know that this is done by the law of error
propagation, which for matrices becomes
With ?fX and ?fU are the Jacobian matrices
(w.r.t. our uncertain variables) of the state
transition matrix.
95
MGD (6) - Non-linear combinations
The uncertainty ellipses for X and Y (for time
step 1 .. 20) is shown in the figure.
96
Circular Error Problem
If we have a map We can localize!
NOT THAT SIMPLE!
If we can localize We can make a map!
97
Expectation-Maximization (EM)
Algorithm
  • Initialize Make random guess for lines
  • Repeat
  • Find the line closest to each point and group
    into two sets. (Expectation Step)
  • Find the best-fit lines to the two sets
    (Maximization Step)
  • Iterate until convergence
  • The algorithm is guaranteed to converge to some
    local optima

98
Example
99
Example
100
Example
101
Example
102
Example
Converged!
103
Probabilistic Mapping
Maximum Likelihood Estimation
  • E-Step Use current best map and data to find
    belief probabilities
  • M-step Compute the most likely map based on the
    probabilities computed in the E-step.
  • Alternate steps to get better map and
    localization estimates
  • Convergence is guaranteed as before.

104
The E-Step
  • P(std,m) P(st o1, a1 ot,m) . P(st atoT,m)

105
The M-Step
  • Updates occupancy grid
  • P(mxyl d)

106
Probabilistic Mapping
  • Addresses the Simultaneous Mapping and
    Localization problem (SLAM)
  • Robust
  • Hacks for easing computational and processing
    burden
  • Caching
  • Selective computation
  • Selective memorization

107
(No Transcript)
108
(No Transcript)
109
(No Transcript)
110
Markov Assumption
Future is Independent of Past Given Current State
Assume Static World
111
Probabilistic Model
112
Derivation Markov Localization
113
  • Mobile Robot Localization
  • Proprioceptive Sensors (Encoders, IMU) -
    Odometry, Dead reckoning
  • Exteroceptive Sensors (Laser, Camera) - Global,
    Local Correlation
  • Scan-Matching
  • Correlate range measurements to estimate
    displacement
  • Can improve (or even replace) odometry
    Roumeliotis TAI-14
  • Previous Work - Vision community and Lu Milios
    97

114
Weighted Approach
  • Explicit models of uncertainty noise sources
    for each scan point
  • Sensor noise errors
  • Range noise
  • Angular uncertainty
  • Bias
  • Point correspondence uncertainty

Combined Uncertanties
  • Improvement vs. unweighted method
  • More accurate displacement estimate
  • More realistic covariance estimate
  • Increased robustness to initial conditions
  • Improved convergence

115
Weighted Formulation
Goal Estimate displacement (pij ,fij )
Measured range data from poses i and j
sensor noise
bias
true range
Error between kth scan point pair
rotation of fij
Correspondence Error
Bias Error
Noise Error
116
Covariance of Error Estimate
Covariance of error between kth scan point pair
  • Sensor Noise

Pose i
  • Sensor Bias
  • neglect for now

117
  • Correspondence Error cijk
  • Estimate bounds of cijk from the geometry
  • of the boundary and robot poses

Max error
  • Assume uniform distribution

where
118
Finding incidence angles aik and ajk Hough
Transform -Fits lines to range data -Local
incidence angle estimated from line tangent and
scan angle -Common technique in vision community
(Duda Hart 72) -Can be extended to fit simple
curves
aik
119
Maximum Likelihood Estimation
Likelihood of obtaining errors eijk given
displacement
Non-linear Optimization Problem
  • Position displacement estimate obtained in closed
    form
  • Orientation estimate found using 1-D numerical
  • optimization, or series expansion
    approximation methods

120
Experimental Results
Weighted vs. Unweighted matching of two poses
512 trials with different initial displacements
within /- 15 degrees of actual angular
displacement /- 150 mm of actual spatial
displacement
Initial Displacements Unweighted
Estimates Weighted Estimates
  • Increased robustness to inaccurate initial
    displacement guesses
  • Fewer iterations for convergence

121
Unweighted Weighted
122
Eight-step, 22 meter path
  • Displacement estimate errors at end of path
  • Odometry 950mm
  • Unweighted 490mm
  • Weighted 120mm
  • More accurate covariance estimate
  • Improved knowledge of
  • measurement uncertainty
  • - Better fusion with other sensors

123
Uncertainty From Sensor Noise
Write a Comment
User Comments (0)
About PowerShow.com