State Estimation and Localization for Self-Driving Cars from Coursera

What's inside

Syllabus

Module 0: Welcome to Course 2: State Estimation and Localization for Self-Driving Cars

This module introduces you to the main concepts discussed in the course and presents the layout of the course. The module describes and motivates the problems of state estimation and localization for self-driving cars. An accurate estimate of the vehicle state and its position on the road is required at all times to drive safely.

Module 1: Least Squares

The method of least squares, developed by Carl Friedrich Gauss in 1795, is a well known technique for estimating parameter values from data. This module provides a review of least squares, for the cases of unweighted and weighted observations. There is a deep connection between least squares and maximum likelihood estimators (when the observations are considered to be Gaussian random variables) and this connection is established and explained. Finally, the module develops a technique to transform the traditional 'batch' least squares estimator to a recursive form, suitable for online, real-time estimation applications.

Module 2: State Estimation - Linear and Nonlinear Kalman Filters

Any engineer working on autonomous vehicles must understand the Kalman filter, first described in a paper by Rudolf Kalman in 1960. The filter has been recognized as one of the top 10 algorithms of the 20th century, is implemented in software that runs on your smartphone and on modern jet aircraft, and was crucial to enabling the Apollo spacecraft to reach the moon. This module derives the Kalman filter equations from a least squares perspective, for linear systems. The module also examines why the Kalman filter is the best linear unbiased estimator (that is, it is optimal in the linear case). The Kalman filter, as originally published, is a linear algorithm; however, all systems in practice are nonlinear to some degree. Shortly after the Kalman filter was developed, it was extended to nonlinear systems, resulting in an algorithm now called the ‘extended’ Kalman filter, or EKF. The EKF is the ‘bread and butter’ of state estimators, and should be in every engineer’s toolbox. This module explains how the EKF operates (i.e., through linearization) and discusses its relationship to the original Kalman filter. The module also provides an overview of the unscented Kalman filter, or UKF, a more recently developed and very popular member of the Kalman filter family.

Module 3: GNSS/INS Sensing for Pose Estimation

To navigate reliably, autonomous vehicles require an estimate of their pose (position and orientation) in the world (and on the road) at all times. Much like for modern aircraft, this information can be derived from a combination of GPS measurements and inertial navigation system (INS) data. This module introduces sensor models for inertial measurement units and GPS (and, more broadly, GNSS) receivers; performance and noise characteristics are reviewed. The module describes ways in which the two sensor systems can be used in combination to provide accurate and robust vehicle pose estimates.

Module 4: LIDAR Sensing

LIDAR (light detection and ranging) sensing is an enabling technology for self-driving vehicles. LIDAR sensors can ‘see’ farther than cameras and are able to provide accurate range information. This module develops a basic LIDAR sensor model and explores how LIDAR data can be used to produce point clouds (collections of 3D points in a specific reference frame). Learners will examine ways in which two LIDAR point clouds can be registered, or aligned, in order to determine how the pose of the vehicle has changed with time (i.e., the transformation between two local reference frames).

Module 5: Putting It together - An Autonomous Vehicle State Estimator

This module combines materials from Modules 1-4 together, with the goal of developing a full vehicle state estimator. Learners will build, using data from the CARLA simulator, an error-state extended Kalman filter-based estimator that incorporates GPS, IMU, and LIDAR measurements to determine the vehicle position and orientation on the road at a high update rate. There will be an opportunity to observe what happens to the quality of the state estimate when one or more of the sensors either 'drop out' or are disabled.

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Provides a deep dive into state estimation and localization techniques critical for the development of self-driving cars

Taught by instructors Jonathan Kelly and Steven Waslander, renowned experts in robotics and autonomous vehicle research

Designed for learners with a background in engineering or robotics, catering to a specialized audience

Requires strong fundamentals in linear algebra, statistics, calculus, and physics

Includes a practical project involving the implementation of an Error-State Extended Kalman Filter (ES-EKF) in the CARLA simulator

Covers essential sensor models for GPS, IMUs, and LIDAR, ensuring a comprehensive understanding of sensor data

Reviews summary

Kalman filters for self-driving cars

Learners say that this intermediate-level course teaches state estimation for self-driving cars using Kalman filters. They say that the assignments are engaging but difficult, and they recommend that students read supplementary materials to get the most out of the course.

Clear and engaging

"A well-taught course by Prof. Jonathan Kelly.I accumulated huge amount of knowledge after undergoing his teachings.The supplementary readings proved to be of great help to ace the final project."

"Firstly, I would like to start thanking Prof. Jonathan Kelley for making good illustration."

Helpful and in-depth

"The supplementary material provided really helped me to strengthen my concepts."

"This course provides a lot of insights in various sensors used for pose estimation and also delves into multi sensor fusion which gives the knowledge and importance about the sensor calibration. Overall a very well taught course and the most important one for who want to pursue a career in self driving cars."

Challenging but rewarding

"Very challenging, nevertheless excelent for learning automation concepts, python programming, sensor fusion, probability & statistics"

"The programming assignments given tested us on how well we understood the fundamentals of localization"

"The last assignment for this module is very challenging."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in State Estimation and Localization for Self-Driving Cars with these activities:

Review previous coursework

Show steps

Review previously learned material in Linear Algebra, Statistics, Calculus and Physics to prepare for the course.

Browse courses on State Estimation

Show steps

Review lecture notes from previous courses
Go through practice problems and assignments
Take practice quizzes and tests

Form a study group with classmates

Show steps

Enhance learning by collaborating with peers through a study group, where you can discuss course material, share insights, and work through problems together.

Browse courses on Self-Driving Cars

Show steps

Find a group of classmates who are interested in forming a study group
Set up regular meeting times
Prepare for each meeting by reading the assigned material and completing any homework
Discuss the material, ask questions, and work through problems together

Gather resources on sensor fusion

Show steps

Compile a collection of resources (e.g., articles, videos, datasets) on sensor fusion, which will expand knowledge and understanding of how different sensors are combined for state estimation.

Browse courses on Sensor Fusion

Show steps

Search for relevant resources online
Organize the resources into a logical structure
Share the compilation with other students or online communities

Five other activities

Expand to see all activities and additional details

Show all eight activities

Attend a workshop on self-driving car technology

Show steps

Deepen understanding and gain insights into the latest advancements in self-driving car technology by attending a workshop led by experts in the field.

Browse courses on Self-Driving Cars

Show steps

Find relevant workshops and conferences
Register and attend the workshop
Take notes and actively participate in discussions

Review 'Autonomous Vehicle Technology' by James M. Anderson

Show steps

Gain a comprehensive overview of the field by reading 'Autonomous Vehicle Technology', which provides a thorough examination of the key concepts, technologies, and challenges in self-driving car development.

Show steps

Read the book thoroughly
Take notes and highlight important passages
Discuss the book's concepts with other students or experts

Follow tutorials on Kalman filters

Show steps

Reinforce understanding of Kalman filters by following online tutorials, which will provide step-by-step guidance and examples.

Browse courses on Kalman Filter

Show steps

Find online tutorials on the Kalman filter
Go through the tutorials at your own pace
Complete the exercises and practice problems

Practice least squares estimation

Show steps

Practice applying the method of least squares to estimate parameters in various scenarios, which will strengthen foundational skills in parameter estimation.

Browse courses on Least Squares

Show steps

Find practice problems and datasets online
Solve the problems using the least squares method
Compare your results to the expected values

Build a simple state estimator for a moving object

Show steps

Apply course concepts by building a simple state estimator for a moving object, which will provide practical experience in implementing and evaluating state estimation algorithms.

Browse courses on State Estimation

Show steps

Choose an appropriate state estimation algorithm
Define the state space model for the moving object
Implement the algorithm and test it using simulated data
Evaluate the performance of the estimator

Career center

Learners who complete State Estimation and Localization for Self-Driving Cars will develop knowledge and skills that may be useful to these careers:

Sensor Engineer

A Sensor Engineer is responsible for designing, developing, and testing sensors used in a variety of applications, including self-driving cars. This course would be particularly useful for Sensor Engineers who want to learn more about the specific challenges of state estimation and localization for autonomous vehicles. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing accurate and reliable sensors for self-driving cars.

See salaries and explore the career path for Sensor Engineer

Controls Engineer

A Controls Engineer is responsible for designing, developing, and testing control systems for a variety of applications, including self-driving cars. This course would be particularly useful for Controls Engineers who want to learn more about the specific challenges of state estimation and localization for autonomous vehicles. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing robust and reliable control systems for self-driving cars.

See salaries and explore the career path for Controls Engineer

Software Engineer

Software Engineers design, develop, and test software for a variety of applications, including self-driving cars. This course would be helpful for Software Engineers who want to learn more about the specific challenges of state estimation and localization for autonomous vehicles. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing robust and reliable software for self-driving cars.

See salaries and explore the career path for Software Engineer

Robotics Engineer

Robotics Engineers design, build, and maintain robots, which are becoming increasingly important in a variety of industries, including the automotive industry. This course would be helpful for Robotics Engineers who want to learn more about the specific challenges of state estimation and localization for self-driving cars. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing robots that can navigate safely and autonomously.

See salaries and explore the career path for Robotics Engineer

Systems Engineer

A Systems Engineer is responsible for designing, developing, and testing systems that integrate hardware and software, including self-driving cars. This course would be helpful for Systems Engineers who want to learn more about the specific challenges of state estimation and localization for autonomous vehicles. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing safe and reliable systems for self-driving cars.

See salaries and explore the career path for Systems Engineer

Artificial Intelligence Engineer

Artificial Intelligence Engineers design, develop, and test AI systems, which are becoming increasingly important in a variety of industries, including the automotive industry. This course would be helpful for Artificial Intelligence Engineers who want to learn more about the specific challenges of state estimation and localization for self-driving cars. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing safe and reliable AI systems for self-driving cars.

See salaries and explore the career path for Artificial Intelligence Engineer

Data Scientist

Data Scientists use data to solve problems and make predictions, which is becoming increasingly important in a variety of industries, including the automotive industry. This course would be helpful for Data Scientists who want to learn more about the specific challenges of state estimation and localization for self-driving cars. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing data-driven solutions for self-driving cars.

See salaries and explore the career path for Data Scientist

Automotive Engineer

Automotive Engineers design, develop, and test automobiles, including self-driving cars. This course would be helpful for Automotive Engineers who want to learn more about the specific challenges of state estimation and localization for autonomous vehicles. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing safe and reliable self-driving cars.

See salaries and explore the career path for Automotive Engineer

Mechanical Engineer

Mechanical Engineers design, develop, and test mechanical systems, including those used in self-driving cars. This course would be helpful for Mechanical Engineers who want to learn more about the specific challenges of state estimation and localization for autonomous vehicles. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing safe and reliable mechanical systems for self-driving cars.

See salaries and explore the career path for Mechanical Engineer

Electrical Engineer

Electrical Engineers design, develop, and test electrical systems, including those used in self-driving cars. This course would be helpful for Electrical Engineers who want to learn more about the specific challenges of state estimation and localization for autonomous vehicles. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing robust and reliable electrical systems for self-driving cars.

See salaries and explore the career path for Electrical Engineer

Project Manager

Project Managers plan, execute, and close projects, which is becoming increasingly important in a variety of industries, including the automotive industry. This course would be helpful for Project Managers who want to learn more about the specific challenges of state estimation and localization for self-driving cars. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing and managing successful self-driving car projects.

See salaries and explore the career path for Project Manager

Business Analyst

Business Analysts gather and analyze data to help businesses make better decisions, which is becoming increasingly important in a variety of industries, including the automotive industry. This course would be helpful for Business Analysts who want to learn more about the specific challenges of state estimation and localization for self-driving cars. The course covers topics such as Kalman filtering, LIDAR sensing, and GPS/INS sensing, which are all essential for developing data-driven solutions for self-driving cars.

See salaries and explore the career path for Business Analyst

Sales Engineer

Sales Engineers sell products and services to businesses, including self-driving cars.

See salaries and explore the career path for Sales Engineer

Technical Writer

Technical Writers create documentation for a variety of products and services, including self-driving cars.

See salaries and explore the career path for Technical Writer

Product Manager

Product Managers plan, develop, and launch products, which is becoming increasingly important in a variety of industries, including the automotive industry.

See salaries and explore the career path for Product Manager