SELF-DRIVING​ ​CAR​ ​ENGINEER​ ​NANODEGREE

SYLLABUS

Course​ ​1:​ ​Introduction 2

Course​ ​2:​ ​Deep​ ​Learning 3

Course​ ​3:​ ​Computer​ ​Vision 4

Course​ ​4:​ ​Sensor​ ​Fusion 5

Course​ ​5:​ ​Localization 6

Course​ ​6:​ ​Control 7

Course​ ​7:​ ​Path​ ​Planning 8

Course​ ​8:​ ​Elective:​ ​Advanced​ ​Deep​ ​Learning 9

Course​ ​9:​ ​Elective:​ ​Advanced​ ​Deep​ ​Learning 10

Course​ ​10:​ ​System​ ​Integration 11

Course​ ​1:​ ​Introduction
In​ ​this​ ​course,​ ​you​ ​will​ ​learn​ ​about​ ​how​ ​self-driving​ ​cars​ ​work,​ ​and​ ​you’ll​ ​take​ ​a​ ​crack​ ​at​ ​your​ ​very​ ​first
autonomous​ ​vehicle​ ​project​ ​-​ ​finding​ ​lane​ ​lines​ ​on​ ​the​ ​road!​ ​We’ll​ ​also​ ​introduce​ ​the​ ​Nanodegree​ ​Program
and​ ​the​ ​services​ ​we​ ​provide​ ​over​ ​the​ ​course​ ​of​ ​the​ ​journey.

Lesson Title Description

1 Welcome Take​ ​your​ ​first​ ​steps​ ​towards​ ​becoming​ ​a​ ​Self-Driving​ ​Car
Engineer!​ ​In​ ​this​ ​lesson,​ ​we'll​ ​introduce​ ​you​ ​to​ ​the​ ​program,
help​ ​you​ ​discover​ ​the​ ​services​ ​we​ ​provide,​ ​and​ ​show​ ​you
all​ ​the​ ​incredible​ ​projects​ ​you'll​ ​build.​ ​Get​ ​ready​ ​for​ ​an
incredible​ ​9​ ​month​ ​journey!

2 Finding​ ​Lane​ ​Lines In​ ​this​ ​first​ ​lesson,​ ​you'll​ ​get​ ​taste​ ​of​ ​some​ ​basic​ ​computer
vision​ ​techniques​ ​to​ ​find​ ​lane​ ​markings​ ​on​ ​the​ ​road.​ ​ ​We
will​ ​be​ ​diving​ ​much​ ​deeper​ ​into​ ​computer​ ​vision​ ​in​ ​later
lessons,​ ​so​ ​just​ ​relax​ ​and​ ​have​ ​some​ ​fun​ ​in​ ​this​ ​first​ ​week!

Project​ ​0​ ​:​ ​Finding​ ​Lane​ ​Lines​ ​on​ ​a​ ​Road

In​ ​this​ ​project,​ ​you​ ​will​ ​be​ ​writing​ ​code​ ​to​ ​identify​ ​lane​ ​lines​ ​on​ ​the​ ​road,​ ​first​ ​in​ ​an​ ​image,​ ​and​ ​later​ ​in​ ​a
video​ ​stream​ ​(really​ ​just​ ​a​ ​series​ ​of​ ​images).​ ​ ​To​ ​complete​ ​this​ ​project​ ​you​ ​will​ ​use​ ​the​ ​tools​ ​you​ ​learned
about​ ​in​ ​the​ ​lesson,​ ​and​ ​build​ ​upon​ ​them.

Course​ ​2:​ ​Deep​ ​Learning

Deep​ ​learning​ ​has​ ​become​ ​the​ ​most​ ​important​ ​frontier​ ​in​ ​both​ ​machine​ ​learning​ ​and​ ​autonomous​ ​vehicle
development.​ ​Experts​ ​from​ ​NVIDIA​ ​and​ ​Uber​ ​ATG​ ​will​ ​teach​ ​you​ ​to​ ​build​ ​deep​ ​neural​ ​networks​ ​and​ ​train
them​ ​with​ ​data​ ​from​ ​the​ ​real​ ​world​ ​and​ ​from​ ​the​ ​Udacity​ ​simulator.​ ​By​ ​the​ ​end​ ​of​ ​this​ ​course,​ ​you’ll​ ​be
able​ ​to​ ​train​ ​convolutional​ ​neural​ ​networks​ ​to​ ​classify​ ​traffic​ ​signs,​ ​and​ ​to​ ​drive​ ​a​ ​vehicle​ ​in​ ​the​ ​simulator
the​ ​same​ ​way​ ​you​ ​drive​ ​it​ ​yourself!

Lesson Title Description

1 Introduction​ ​to​ ​Neural Learn​ ​to​ ​build​ ​and​ ​train​ ​neural​ ​networks,​ ​starting​ ​with​ ​the
Networks foundations​ ​in​ ​linear​ ​and​ ​logistic​ ​regression,​ ​and
culminating​ ​in​ ​backpropagation​ ​and​ ​multilayer​ ​perceptron
networks.
2 MiniFlow In​ ​this​ ​assignment,​ ​you​ ​will​ ​build​ ​your​ ​own​ ​neural​ ​network
library​ ​from​ ​scratch!​ ​Your​ ​library,​ ​MiniFlow,​ ​will​ ​behave
much​ ​like​ ​TensorFlow,​ ​Google's​ ​deep​ ​learning​ ​library.

3 Introduction​ ​to​ ​TensorFlow Vincent​ ​Vanhoucke,​ ​Principal​ ​Scientist​ ​at​ ​Google​ ​Brain,
introduces​ ​you​ ​to​ ​deep​ ​learning​ ​and​ ​Tensorflow,​ ​Google's
deep​ ​learning​ ​framework.

4 Deep​ ​Neural​ ​Networks Vincent​ ​walks​ ​you​ ​through​ ​how​ ​to​ ​go​ ​from​ ​a​ ​simple​ ​neural
network​ ​to​ ​a​ ​deep​ ​neural​ ​network.​ ​You'll​ ​learn​ ​about​ ​why
additional​ ​layers​ ​can​ ​help​ ​and​ ​how​ ​to​ ​prevent​ ​overfitting.

5 Convolutional​ ​Neural Vincent​ ​explains​ ​the​ ​theory​ ​behind​ ​Convolutional​ ​Neural

Networks Networks​ ​and​ ​how​ ​they​ ​help​ ​us​ ​dramatically​ ​improve
performance​ ​in​ ​image​ ​classification.

6 Traffic​ ​Sign​ ​Classification You​ ​just​ ​finished​ ​getting​ ​your​ ​feet​ ​wet​ ​with​ ​deep​ ​learning.
Now​ ​put​ ​your​ ​skills​ ​to​ ​the​ ​test​ ​by​ ​using​ ​deep​ ​learning​ ​to
classify​ ​different​ ​traffic​ ​signs!

Project​ ​1:​ ​Traffic​ ​Sign​ ​Classifier

You​ ​just​ ​finished​ ​getting​ ​your​ ​feet​ ​wet​ ​with​ ​deep​ ​learning.​ ​Now​ ​put​ ​your​ ​skills​ ​to​ ​the​ ​test​ ​by​ ​using​ ​deep
learning​ ​to​ ​classify​ ​different​ ​traffic​ ​signs!​ ​In​ ​this​ ​project,​ ​you​ ​will​ ​use​ ​what​ ​you've​ ​learned​ ​about​ ​deep
neural​ ​networks​ ​and​ ​convolutional​ ​neural​ ​networks​ ​to​ ​classify​ ​traffic​ ​signs.

Lesson Title Description

7 Keras Take​ ​on​ ​the​ ​neural​ ​network​ ​framework,​ ​Keras.​ ​You'll​ ​be
amazed​ ​how​ ​few​ ​lines​ ​of​ ​code​ ​you'll​ ​need​ ​to​ ​build​ ​and​ ​train
deep​ ​neural​ ​networks!

8 Transfer​ ​Learning Learn​ ​about​ ​some​ ​of​ ​the​ ​most​ ​famous​ ​neural​ ​network
architectures​ ​and​ ​how​ ​you​ ​can​ ​use​ ​them.​ ​By​ ​the​ ​end​ ​of​ ​this
lesson,​ ​you'll​ ​know​ ​how​ ​to​ ​create​ ​new​ ​models​ ​by
leveraging​ ​existing​ ​canonical​ ​networks.

9 Behavioral​ ​Cloning Put​ ​your​ ​deep​ ​learning​ ​skills​ ​to​ ​the​ ​test​ ​with​ ​this​ ​project!
Train​ ​a​ ​deep​ ​neural​ ​network​ ​to​ ​drive​ ​a​ ​car​ ​like​ ​you!

Project​ ​2:​ ​Behavioral​ ​Cloning

Put​ ​your​ ​deep​ ​learning​ ​skills​ ​to​ ​the​ ​test​ ​with​ ​this​ ​project!​ ​Train​ ​a​ ​deep​ ​neural​ ​network​ ​to​ ​drive​ ​a​ ​car​ ​like
you!
Course​ ​3:​ ​Computer​ ​Vision

You’ll​ ​use​ ​a​ ​combination​ ​of​ ​cameras,​ ​software,​ ​and​ ​machine​ ​learning​ ​to​ ​find​ ​lane​ ​lines​ ​on​ ​difficult​ ​roads
and​ ​to​ ​track​ ​vehicles.​ ​You’ll​ ​start​ ​with​ ​calibrating​ ​cameras​ ​and​ ​manipulating​ ​images,​ ​and​ ​end​ ​by​ ​applying
support​ ​vector​ ​machines​ ​and​ ​decision​ ​trees​ ​to​ ​extract​ ​information​ ​from​ ​video.

Lesson Title Description

1 Advanced​ ​Lane​ ​Finding Train​ ​segmentation​ ​networks,​ ​which​ ​paint​ ​each​ ​pixel​ ​of​ ​the
image​ ​a​ ​different​ ​color,​ ​based​ ​on​ ​its​ ​class.​ ​Use​ ​segmented
images​ ​to​ ​find​ ​free​ ​space​ ​on​ ​the​ ​road.

Project​ ​3​ ​:​ ​Advanced​ ​Lane​ ​Finding

In​ ​this​ ​project,​ ​your​ ​goal​ ​is​ ​to​ ​write​ ​a​ ​software​ ​pipeline​ ​to​ ​identify​ ​the​ ​lane​ ​boundaries​ ​in​ ​a​ ​video​ ​from​ ​a
front-facing​ ​camera​ ​on​ ​a​ ​car.

Lesson Title Description

2 Machine​ ​Learning​ ​and Learn​ ​about​ ​classification,​ ​training​ ​and​ ​testing,​ ​and​ ​run​ ​a
Stanley naive​ ​Bayes​ ​classifier​ ​using​ ​Scikit​ ​Learn.

3 Support​ ​Vector​ ​Machines See​ ​how​ ​support​ ​vector​ ​machines​ ​work,​ ​and​ ​code​ ​one
using​ ​Scikit​ ​Learn.

4 Decision​ ​Trees Learn​ ​about​ ​decision​ ​trees,​ ​including​ ​entropy​ ​and

information​ ​gain.

5 Vehicle​ ​Detection​ ​and In​ ​this​ ​lesson​ ​you'll​ ​learn​ ​how​ ​to​ ​detect​ ​and​ ​track​ ​vehicles
Tracking using​ ​color​ ​and​ ​gradient​ ​features​ ​and​ ​a​ ​support​ ​vector
machine​ ​classifier.

Project​ ​4​ ​:​ ​Vehicle​ ​Detection​ ​and​ ​Tracking

In​ ​this​ ​project,​ ​your​ ​goal​ ​is​ ​to​ ​write​ ​a​ ​software​ ​pipeline​ ​to​ ​identify​ ​vehicles​ ​in​ ​a​ ​video​ ​from​ ​a​ ​front-facing
camera​ ​on​ ​a​ ​car.
Course​ ​4:​ ​Sensor​ ​Fusion

Tracking​ ​objects​ ​over​ ​time​ ​is​ ​a​ ​major​ ​challenge​ ​for​ ​understanding​ ​the​ ​environment​ ​surrounding​ ​a​ ​vehicle.
Sensor​ ​fusion​ ​engineers​ ​from​ ​Mercedes-Benz​ ​will​ ​show​ ​you​ ​how​ ​to​ ​program​ ​fundamental​ ​mathematical
tools​ ​called​ ​Kalman​ ​filters.​ ​These​ ​filters​ ​predict​ ​and​ ​determine​ ​with​ ​certainty​ ​the​ ​location​ ​of​ ​other​ ​vehicles
on​ ​the​ ​road.​ ​You’ll​ ​even​ ​learn​ ​to​ ​do​ ​this​ ​with​ ​difficult-to-follow​ ​objects,​ ​by​ ​using​ ​two​ ​advanced​ ​techniques:
the​ ​extended​ ​Kalman​ ​filter​ ​and​ ​the​ ​unscented​ ​Kalman​ ​filter.

Lesson Title Description

1 Introduction​ ​and​ ​Sensors Meet​ ​the​ ​team​ ​at​ ​Mercedes​ ​who​ ​will​ ​help​ ​you​ ​track​ ​objects
in​ ​real-time​ ​with​ ​Sensor​ ​Fusion.

2 Kalman​ ​Filters Learn​ ​from​ ​the​ ​best!​ ​Sebastian​ ​Thrun​ ​will​ ​walk​ ​you​ ​through
the​ ​usage​ ​and​ ​concepts​ ​of​ ​a​ ​Kalman​ ​Filter​ ​using​ ​Python.

3 C++​ ​Checkpoint Are​ ​you​ ​ready​ ​to​ ​build​ ​Kalman​ ​Filters​ ​with​ ​C++?​ ​Take​ ​these
quizzes​ ​to​ ​find​ ​out.

4 Lidar​ ​and​ ​Radar​ ​Fusion In​ ​this​ ​lesson,​ ​you'll​ ​build​ ​a​ ​Kalman​ ​Filter​ ​in​ ​C++​ ​that's
with​ ​Kalman​ ​Filters capable​ ​of​ ​handling​ ​data​ ​from​ ​multiple​ ​sources.​ ​Why​ ​C++?
Its​ ​performance​ ​enables​ ​the​ ​application​ ​of​ ​object​ ​tracking
with​ ​a​ ​Kalman​ ​Filter​ ​in​ ​real-time.

​ ​Project​ ​5:​ ​Extended​ ​Kalman​ ​Filters

In​ ​this​ ​project,​ ​you'll​ ​apply​ ​everything​ ​you've​ ​learned​ ​so​ ​far​ ​about​ ​Sensor​ ​Fusion​ ​by​ ​implementing​ ​an
Extended​ ​Kalman​ ​Filter​ ​in​ ​C++!

Lesson Title Description

5 Unscented​ ​Kalman​ ​Filters While​ ​Extended​ ​Kalman​ ​Filters​ ​work​ ​great​ ​for​ ​linear​ ​motion,
real​ ​objects​ ​rarely​ ​move​ ​linearly.​ ​With​ ​Unscented​ ​Kalman
Filters,​ ​you'll​ ​be​ ​able​ ​to​ ​accurately​ ​track​ ​non-linear​ ​motion!

​ ​Project​ ​6:​ ​Unscented​ ​Kalman​ ​Filters

Put​ ​your​ ​skills​ ​to​ ​the​ ​test!​ ​Use​ ​C++​ ​to​ ​code​ ​an​ ​Unscented​ ​Kalman​ ​Filter​ ​capable​ ​of​ ​tracking​ ​non-linear
motion.
Course​ ​5:​ ​Localization

Localization​ ​is​ ​how​ ​we​ ​determine​ ​where​ ​our​ ​vehicle​ ​is​ ​in​ ​the​ ​world.​ ​GPS​ ​is​ ​great,​ ​but​ ​it’s​ ​only​ ​accurate​ ​to
within​ ​a​ ​few​ ​meters.​ ​We​ ​need​ ​single-digit​ ​centimeter-level​ ​accuracy!​ ​To​ ​achieve​ ​this,​ ​Mercedes-Benz
engineers​ ​will​ ​demonstrate​ ​the​ ​principles​ ​of​ ​Markov​ ​localization​ ​to​ ​program​ ​a​ ​particle​ ​filter,​ ​which​ ​uses
data​ ​and​ ​a​ ​map​ ​to​ ​determine​ ​the​ ​precise​ ​location​ ​of​ ​a​ ​vehicle.

Lesson Title Description

1 Introduction​ ​to​ ​Localization Meet​ ​the​ ​team​ ​that​ ​will​ ​guide​ ​you​ ​through​ ​the​ ​localization
lessons!

2 Localization​ ​Overview Sebastian​ ​Thrun​ ​will​ ​give​ ​you​ ​an​ ​overview​ ​of​ ​the​ ​theory
behind​ ​localization!

3 Markov​ ​Localization In​ ​this​ ​lesson,​ ​you'll​ ​learn​ ​the​ ​math​ ​behind​ ​localization​ ​as
well​ ​as​ ​how​ ​to​ ​implement​ ​Markov​ ​localization​ ​in​ ​C++.

4 Motion​ ​Models Here​ ​you'll​ ​learn​ ​about​ ​vehicle​ ​movement​ ​and​ ​motion
models​ ​to​ ​predict​ ​where​ ​your​ ​car​ ​will​ ​be​ ​at​ ​a​ ​future​ ​time.

5 Particle​ ​Filters Now,​ ​Sebastian​ ​will​ ​teach​ ​you​ ​what​ ​a​ ​particle​ ​filter​ ​is​ ​and
will​ ​teach​ ​the​ ​theory​ ​and​ ​math​ ​behind​ ​the​ ​particle​ ​filter.

6 Implementation​ ​of​ ​a​ ​Particle Now​ ​that​ ​you​ ​understand​ ​how​ ​a​ ​particle​ ​filter​ ​works,​ ​you'll
Filter learn​ ​how​ ​to​ ​code​ ​a​ ​particle​ ​filter.

Project​ ​7​ ​:​ ​Kidnapped​ ​Vehicle

In​ ​this​ ​project,​ ​you'll​ ​build​ ​a​ ​particle​ ​filter​ ​and​ ​combine​ ​it​ ​with​ ​a​ ​real​ ​map​ ​to​ ​localize​ ​a​ ​vehicle!

Course​ ​6:​ ​Control

Ultimately,​ ​a​ ​self-driving​ ​car​ ​is​ ​still​ ​a​ ​car,​ ​and​ ​we​ ​need​ ​to​ ​send​ ​steering,​ ​throttle,​ ​and​ ​brake​ ​commands​ ​to
move​ ​the​ ​car​ ​through​ ​the​ ​world.​ ​Uber​ ​ATG​ ​will​ ​walk​ ​you​ ​through​ ​building​ ​both
proportional-integral-derivative​ ​(PID)​ ​controllers​ ​and​ ​model​ ​predictive​ ​controllers.​ ​Between​ ​these​ ​control
algorithms,​ ​you’ll​ ​become​ ​familiar​ ​with​ ​both​ ​basic​ ​and​ ​advanced​ ​techniques​ ​for​ ​actuating​ ​a​ ​vehicle.

Lesson Title Description

1 PID​ ​Control In​ ​this​ ​lesson​ ​you'll​ ​learn​ ​about​ ​and​ ​how​ ​to​ ​use​ ​PID
 controllers​ ​with​ ​Sebastian!

Project​ ​8:​ ​PID​ ​Controller

In​ ​this​ ​project​ ​you'll​ ​revisit​ ​the​ ​lake​ ​race​ ​track​ ​from​ ​the​ ​Behavioral​ ​Cloning​ ​Project.​ ​This​ ​time,​ ​however,
you'll​ ​implement​ ​a​ ​PID​ ​controller​ ​in​ ​C++​ ​to​ ​maneuver​ ​the​ ​vehicle​ ​around​ ​the​ ​track!

Lesson Title Description

2 Vehicle​ ​Models In​ ​this​ ​lesson,​ ​you'll​ ​learn​ ​about​ ​kinematic​ ​and​ ​dynamic
vehicle​ ​models.​ ​We'll​ ​use​ ​these​ ​later​ ​with​ ​Model​ ​Predictive
Control.

3 Model​ ​Predictive​ ​Control In​ ​this​ ​lesson,​ ​you'll​ ​learn​ ​how​ ​to​ ​frame​ ​the​ ​control​ ​problem
as​ ​an​ ​optimization​ ​problem​ ​over​ ​time​ ​horizons.​ ​This​ ​is
Model​ ​Predictive​ ​Control!

Project​ ​9:​ ​Model​ ​Predictive​ ​Control

In​ ​this​ ​project,​ ​you'll​ ​implement​ ​Model​ ​Predictive​ ​Control​ ​to​ ​drive​ ​the​ ​vehicle​ ​around​ ​the​ ​track​ ​even​ ​with
additional​ ​latency​ ​between​ ​commands!

Course​ ​7:​ ​Path​ ​Planning

Path​ ​planning​ ​routes​ ​a​ ​vehicle​ ​from​ ​one​ ​point​ ​to​ ​another,​ ​and​ ​it​ ​handles​ ​how​ ​to​ ​react​ ​when​ ​emergencies
arise.​ ​The​ ​Mercedes-Benz​ ​Vehicle​ ​Intelligence​ ​team​ ​will​ ​take​ ​you​ ​through​ ​the​ ​three​ ​stages​ ​of​ ​path
planning.​ ​First,​ ​you’ll​ ​apply​ ​model-driven​ ​and​ ​data-driven​ ​approaches​ ​to​ ​predict​ ​how​ ​other​ ​vehicles​ ​on​ ​the
road​ ​will​ ​behave.​ ​Then​ ​you’ll​ ​construct​ ​a​ ​finite​ ​state​ ​machine​ ​to​ ​decide​ ​which​ ​of​ ​several​ ​maneuvers​ ​your
own​ ​vehicle​ ​should​ ​undertake.​ ​Finally,​ ​you’ll​ ​generate​ ​a​ ​safe​ ​and​ ​comfortable​ ​trajectory​ ​to​ ​execute​ ​that
maneuver.

Lesson Title Description

1 Search In​ ​this​ ​lesson​ ​you​ ​will​ ​learn​ ​about​ ​discrete​ ​path​ ​planning
and​ ​algorithms​ ​for​ ​solving​ ​the​ ​path​ ​planning​ ​problem.

2 Prediction In​ ​this​ ​lesson​ ​you'll​ ​learn​ ​how​ ​to​ ​use​ ​data​ ​from​ ​sensor
fusion​ ​to​ ​generate​ ​predictions​ ​about​ ​the​ ​likely​ ​behavior​ ​of
moving​ ​objects.

3 Behavior​ ​Planning In​ ​this​ ​lesson​ ​you'll​ ​learn​ ​how​ ​to​ ​think​ ​about​ ​high​ ​level
behavior​ ​planning​ ​in​ ​a​ ​self​ ​driving​ ​car.

4 Trajectory​ ​Generation In​ ​this​ ​lesson,​ ​you’ll​ ​use​ ​C++​ ​and​ ​the​ ​Eigen​ ​linear​ ​algebra
library​ ​to​ ​build​ ​candidate​ ​trajectories​ ​for​ ​the​ ​vehicle​ ​to
 follow.

Project​ ​10:​ ​Path​ ​Planning

Drive​ ​a​ ​car​ ​down​ ​a​ ​highway​ ​with​ ​other​ ​cars​ ​using​ ​your​ ​own​ ​path​ ​planner.

Course​ ​8:​ ​Elective:​ ​Advanced​ ​Deep​ ​Learning

Students​ ​in​ ​this​ ​elective,​ ​built​ ​with​ ​the​ ​NVIDIA​ ​Deep​ ​Learning​ ​Institute,​ ​will​ ​learn​ ​about​ ​semantic
segmentation,​ ​and​ ​inference​ ​optimization,​ ​active​ ​areas​ ​of​ ​deep​ ​learning​ ​research.​ ​This​ ​course​ ​is​ ​an
elective.​ ​Students​ ​choose​ ​between​ ​completing​ ​either​ ​Advanced​ ​Deep​ ​Learning​ ​or​ ​Functional​ ​Safety​ ​for
graduation.

Lesson Title Description

1 Fully​ ​Convolutional In​ ​this​ ​lesson​ ​you'll​ ​learn​ ​the​ ​motivation​ ​for​ ​Fully
Networks Convolutional​ ​Networks​ ​and​ ​how​ ​they​ ​are​ ​structured.

2 Scene​ ​Understanding In​ ​this​ ​lesson​ ​you'll​ ​be​ ​introduced​ ​to​ ​the​ ​problem​ ​of​ ​Scene
Understanding​ ​and​ ​the​ ​role​ ​FCNs​ ​play.

3 Inference​ ​Performance In​ ​this​ ​lesson​ ​you'll​ ​become​ ​familiar​ ​with​ ​various
optimizations​ ​in​ ​an​ ​effort​ ​to​ ​squeeze​ ​every​ ​last​ ​bit​ ​of
performance​ ​at​ ​inference.

Project​ ​11:​ ​Semantic​ ​Segmentation

Build​ ​a​ ​semantic​ ​segmentation​ ​network​ ​to​ ​identify​ ​free​ ​space​ ​on​ ​the​ ​road.

This​ ​project​ ​is​ ​part​ ​of​ ​an​ ​elective​ ​course.​ ​Students​ ​choose​ ​between​ ​completing​ ​either​ ​Advanced​ ​Deep
Learning​ ​or​ ​Functional​ ​Safety​ ​for​ ​graduation.

Course​ ​9:​ ​Elective:​ ​Functional​ ​Safety

Students​ ​who​ ​select​ ​the​ ​Functional​ ​Safety​ ​specialization,​ ​built​ ​with​ ​Elektrobit,​ ​ ​learn​ ​functional​ ​safety
frameworks​ ​to​ ​ensure​ ​that​ ​vehicles​ ​are​ ​safe,​ ​both​ ​at​ ​the​ ​system​ ​and​ ​component​ ​levels.​ ​This​ ​course​ ​is​ ​an
elective.​ ​Students​ ​choose​ ​between​ ​completing​ ​either​ ​Advanced​ ​Deep​ ​Learning​ ​or​ ​Functional​ ​Safety​ ​for
graduation.

Lesson Title Description

1 Introduction​ ​to​ ​Functional You​ ​will​ ​learn​ ​to​ ​make​ ​safer​ ​vehicles​ ​using​ ​risk​ ​evaluation
Safety and​ ​systems​ ​engineering.
 2 Safety​ ​Plan A​ ​functional​ ​safety​ ​plan​ ​is​ ​critical​ ​to​ ​any​ ​functional​ ​safety
project.​ ​Here​ ​you​ ​will​ ​learn​ ​what​ ​goes​ ​into​ ​a​ ​safety​ ​plan​ ​so
that​ ​you​ ​can​ ​document​ ​your​ ​own.

3 Hazard​ ​Analysis​ ​and​ ​Risk In​ ​a​ ​hazard​ ​analysis​ ​and​ ​risk​ ​assessment,​ ​you​ ​will​ ​identify
Assessment vehicular​ ​malfunctions​ ​and​ ​evaluate​ ​their​ ​risk​ ​levels.​ ​You
can​ ​then​ ​derive​ ​safety​ ​goals​ ​defining​ ​how​ ​your​ ​vehicle​ ​will
remain​ ​safe.

4 Functional​ ​Safety​ ​Concept You​ ​will​ ​derive​ ​functional​ ​safety​ ​requirements​ ​from​ ​the
safety​ ​goals​ ​and​ ​then​ ​add​ ​extra​ ​functionality​ ​to​ ​the​ ​system
diagram.​ ​Finally​ ​you​ ​document​ ​your​ ​work,​ ​a​ ​part​ ​of
functional​ ​safety.

5 Technical​ ​Safety​ ​Concept Once​ ​you​ ​have​ ​derived​ ​functional​ ​safety​ ​requirements,​ ​you
drill​ ​down​ ​into​ ​more​ ​detail.​ ​In​ ​the​ ​technical​ ​safety​ ​concept,
you​ ​refine​ ​your​ ​requirements​ ​into​ ​technical​ ​safety
requirements.

6 Functional​ ​Safety​ ​at​ ​the The​ ​last​ ​step​ ​in​ ​the​ ​vehicle​ ​safety​ ​design​ ​phase​ ​is​ ​to​ ​derive
Software​ ​and​ ​Hardware hardware​ ​and​ ​software​ ​safety​ ​requirements.​ ​In​ ​this​ ​lesson,
Levels you​ ​will​ ​derive​ ​these​ ​requirements​ ​and​ ​refine​ ​a​ ​software
system​ ​architecture.

Project​ ​11:​ ​Functional​ ​Safety​ ​of​ ​a​ ​Lane​ ​Assistance​ ​System

You’ll​ ​use​ ​the​ ​guidance​ ​from​ ​your​ ​lessons​ ​to​ ​construct​ ​part​ ​of​ ​a​ ​safety​ ​case​ ​for​ ​a​ ​lane​ ​departure
warning​ ​feature.​ ​You’ll​ ​begin​ ​with​ ​the​ ​hazard​ ​analysis​ ​and​ ​risk​ ​assessment,​ ​and​ ​create​ ​further
documentation​ ​for​ ​functional​ ​and​ ​technical​ ​safety​ ​concepts,​ ​and​ ​finally​ ​software​ ​and​ ​hardware
requirements.​ ​Analyzing​ ​and​ ​documenting​ ​system​ ​safety​ ​is​ ​critical​ ​for​ ​autonomous​ ​vehicle
development.​ ​These​ ​are​ ​skills​ ​that​ ​often​ ​only​ ​experienced​ ​automotive​ ​engineers​ ​possess!

This​ ​project​ ​is​ ​part​ ​of​ ​an​ ​elective​ ​course.​ ​Students​ ​choose​ ​between​ ​completing​ ​either​ ​Advanced​ ​Deep
Learning​ ​or​ ​Functional​ ​Safety​ ​for​ ​graduation.

Course​ ​10:​ ​System​ ​Integration

This​ ​is​ ​capstone​ ​of​ ​the​ ​entire​ ​Self-Driving​ ​Car​ ​Engineer​ ​Nanodegree​ ​Program!​ ​We’ll​ ​introduce​ ​Carla,​ ​the
Udacity​ ​self-driving​ ​car,​ ​and​ ​the​ ​Robot​ ​Operating​ ​System​ ​that​ ​controls​ ​her.​ ​You’ll​ ​work​ ​with​ ​a​ ​team​ ​of​ ​othe
Nanodegree​ ​students​ ​to​ ​combine​ ​what​ ​you’ve​ ​learned​ ​over​ ​the​ ​course​ ​of​ ​the​ ​entire​ ​Nanodegree​ ​Program
to​ ​drive​ ​Carla,​ ​a​ ​real​ ​self-driving​ ​car,​ ​around​ ​the​ ​Udacity​ ​test​ ​track!

Lesson Title Description

1 Autonomous​ ​Vehicle Learn​ ​about​ ​the​ ​system​ ​architecture​ ​for​ ​Carla,​ ​Udacity's
Architecture autonomous​ ​vehicle.
2 Introduction​ ​to​ ​ROS Obtain​ ​an​ ​architectural​ ​overview​ ​of​ ​the​ ​Robot​ ​Operating
System​ ​Framework​ ​and​ ​setup​ ​your​ ​own​ ​ROS​ ​environment
on​ ​your​ ​computer.

3 Packages​ ​and​ ​Catkin Learn​ ​about​ ​ROS​ ​workspace​ ​structure,​ ​essential​ ​command
Workspaces line​ ​utilities,​ ​and​ ​how​ ​to​ ​manage​ ​software​ ​packages​ ​within
a​ ​project.​ ​Harnessing​ ​these​ ​will​ ​be​ ​key​ ​to​ ​building
shippable​ ​software​ ​using​ ​ROS.

4 Writing​ ​ROS​ ​Nodes ROS​ ​Nodes​ ​are​ ​a​ ​key​ ​abstraction​ ​that​ ​allows​ ​a​ ​robot
system​ ​to​ ​be​ ​built​ ​modularly.​ ​In​ ​this​ ​lesson,​ ​ ​you'll​ ​learn
how​ ​to​ ​write​ ​them​ ​using​ ​Python.

Project​ ​12:​ ​Programming​ ​a​ ​Real​ ​Self-Driving​ ​Car

Run​ ​your​ ​code​ ​on​ ​Carla,​ ​Udacity's​ ​autonomous​ ​vehicle!