Model It Yourself -ADAS

Uncategorized

About Course

“Model It Yourself—ADAS” is a foundational course that you can follow to get acquainted with the world of autonomous vehicles. It starts by introducing you to all important terms in the self-driving car industry and a roadmap for the various roles that can be pursued in this field. You will then get to learn about concepts like perception, localization, prediction, planning, and control. Each module contains fundamental theory, followed by a few assignments and projects, which will give you hands-on exposure.

NOTE: This course is designed as an instruction guide in written format.

Course Content

Path to becoming an ADAS/AV engineer
This section discusses the various paths one can take to enter the field of autonomous vehicles or advanced driver-assist systems (ADAS)

Path to Becoming an ADAS/AV Engineer – Introduction

00:00
Required Skills

00:00
ADAS Features

00:00
Co-simulation: Driving Scenario Creation and Testing

00:00
Communication Protocols

00:00
Hardware and Semiconductors

00:00
Sensor Performance Analysis and Sensor Fusion

00:00
Functional Safety Analysis

00:00
Software and Algorithm Development for Autonomous Vehicles

00:00
Introduction to Perception

00:00
Introduction to State Estimation and Localization

00:00
Introduction to Prediction and Planning

00:00
Introduction to Control in Autonomous Vehicles

00:00
Section 1 Conclusion

00:00

Practicing Tools and Skills
This topic is aimed at giving an introduction to all relevant tools that you will need to follow along the remaining topics. The topic is subdivided into lessons for Python programming, Linux, Git/Github, and Stateflow.

Handling Sensors and Introduction to Robot Operating System
Sensors are the eyes and ears of an autonomous vehicle, and this section is aimed at understanding how to handle sensors, what are the pros and cons of each sensor, and how sensor coverage analysis is crucial. It also includes an introduction to Robot Operating System (ROS), which is an integral tool for autonomous driving systems development.

Handling Sensors and ROS – Introduction

00:00
Introduction to Sensors

00:00
Introduction to ROS

00:00
ROS Assignment 1

00:00
ROS Assignment 2

00:00
ROS Assignment 3

00:00
Using Docker Container with ROS

00:00
Docker Assignment

00:00
Introduction to Carla Simulator

00:00
Section 3 Conclusion

00:00

Controls
The controls module of any self-driving car is like the arms and legs of the vehicle. Based on the computation in the central processing unit, commands are sent to the actuators to execute the right path. For understanding this, it is imperative to understand what are the different types of control systems that can be used. This module covers each of these with an example.

Introduction to Controls

00:00
DC Motor Simulation

00:00
Control System Designer – Algorithm

00:00
PID Tuner App

00:00
Linear Quadratic Regulator – Introduction

00:00
Linear Quadratic Regulator – Algorithm

00:00
Model Predictive Control – Introduction & Theory

00:00
MPC Hands-On Example

00:00
MPC – Further Learning

00:00
Section 4 Conclusion

00:00

Sensor Fusion and Tracking

Introduction to Sensor Fusion

00:00
Types of Sensor Fusion Methods

00:00
Sensor Fusion Algorithms

00:00
Understanding Filters for Sensor Fusion and Tracking

00:00
Kalman Filter

00:00
Variants of Kalman Filters

00:00
Tracking

00:00
Sensor Fusion – Mini Project

00:00
Section 5 Conclusion

00:00

Prediction

Introduction to Prediction

00:00
Predication Problem Formulation

00:00
Model-Based Approach for Prediction

00:00
Data-Driven Approach for Prediction

00:00
Classification of Prediction Methods for Data-Driven Approach

00:00
Challenges in Data-Driven Approach

00:00
Hybrid Approach for Prediction

00:00
Types of Naïve Bayes Classifiers

00:00
Project: Building the Scenario

00:00
Project: Building the Model

00:00
Project: Defining the Functions

00:00
Project: Analyzing the Results

00:00
Section 6 Conclusion

00:00

Mapping, Localization & SLAM

Introduction to Mapping, Localization & SLAM

00:00
Occupancy Grid Mapping

00:00
Mapping: Assignment 1

00:00
Mapping: Assignment 2

00:00
Introduction to Localization

00:00
Types of Localization

00:00
Introduction to SLAM

00:00
SLAM Algorithms

00:00
Front-End Processing in SLAM

00:00
Common Challenges in SLAM

00:00
Localization – Mini Project

00:00
Section 7 Conclusion

00:00

Motion Planning

Introduction to Motion Planning

00:00
Dijkstra’s Algorithm

00:00
A* Algorithm

00:00
A* Algorithm – Assignment

00:00
RRT* Algorithm

00:00
RRT* Algorithm – Assignment

00:00
Behavior Planning

00:00
Local Planning

00:00
Local Planning Project

00:00
Section 8 Conclusion

00:00

Perception

DIY Project – Lane Keeping Assist

Student Ratings & Reviews

4.0

Total 2 Ratings

0 Rating

2 Ratings

0 Rating

Mohammed Tazeem Khan

7 months ago

Nice Course

Bala Naga Bharath Chinni

8 months ago

It was a good course to understand the basics of ADAS. But having some support and opportunities to have doubts clarified would have been very fruitful.

Dorle Controls

About Course

What Will You Learn?

Course Content

Path to becoming an ADAS/AV engineer This section discusses the various paths one can take to enter the field of autonomous vehicles or advanced driver-assist systems (ADAS)

Path to Becoming an ADAS/AV Engineer – Introduction

Required Skills

ADAS Features

Co-simulation: Driving Scenario Creation and Testing

Communication Protocols

Hardware and Semiconductors

Sensor Performance Analysis and Sensor Fusion

Functional Safety Analysis

Software and Algorithm Development for Autonomous Vehicles

Introduction to Perception

Introduction to State Estimation and Localization

Introduction to Prediction and Planning

Introduction to Control in Autonomous Vehicles

Section 1 Conclusion

Practicing Tools and Skills This topic is aimed at giving an introduction to all relevant tools that you will need to follow along the remaining topics. The topic is subdivided into lessons for Python programming, Linux, Git/Github, and Stateflow.

Practicing Tools and Skills – Introduction

Instructions

Virtual Environment for OpenCV Project

Introduction to Linux

Introduction to Git and Github

Introduction to Stateflow

Section 2 Conclusion

Handling Sensors and ROS – Introduction

Introduction to Sensors

Introduction to ROS

ROS Assignment 1

ROS Assignment 2

ROS Assignment 3

Using Docker Container with ROS

Docker Assignment

Introduction to Carla Simulator

Section 3 Conclusion

Introduction to Controls

DC Motor Simulation

Control System Designer – Algorithm

PID Tuner App

Linear Quadratic Regulator – Introduction

Linear Quadratic Regulator – Algorithm

Model Predictive Control – Introduction & Theory

MPC Hands-On Example

MPC – Further Learning

Section 4 Conclusion

Sensor Fusion and Tracking

Introduction to Sensor Fusion

Types of Sensor Fusion Methods

Sensor Fusion Algorithms

Understanding Filters for Sensor Fusion and Tracking

Kalman Filter

Variants of Kalman Filters

Tracking

Sensor Fusion – Mini Project

Section 5 Conclusion

Prediction

Introduction to Prediction

Predication Problem Formulation

Model-Based Approach for Prediction

Data-Driven Approach for Prediction

Classification of Prediction Methods for Data-Driven Approach

Challenges in Data-Driven Approach

Hybrid Approach for Prediction

Types of Naïve Bayes Classifiers

Project: Building the Scenario

Project: Building the Model

Project: Defining the Functions

Project: Analyzing the Results

Section 6 Conclusion

Mapping, Localization & SLAM

Introduction to Mapping, Localization & SLAM

Occupancy Grid Mapping

Mapping: Assignment 1

Mapping: Assignment 2

Introduction to Localization

Types of Localization

Introduction to SLAM

SLAM Algorithms

Path to becoming an ADAS/AV engineer
This section discusses the various paths one can take to enter the field of autonomous vehicles or advanced driver-assist systems (ADAS)

Practicing Tools and Skills
This topic is aimed at giving an introduction to all relevant tools that you will need to follow along the remaining topics. The topic is subdivided into lessons for Python programming, Linux, Git/Github, and Stateflow.