Full course · free on YouTube · 42 min

Introduction to SLAM for autonomous vehicles: free, 42 minutes

One recorded webinar of about 42 minutes, presented over slides, from January 2021. It moves from the idea of localization and mapping and the robot pose to online and offline SLAM, three classic methods, a few newer ones, and where SLAM fits in autonomous vehicles.

25 chapters · published 20 Jan 2021 · 2,918 views as of 20 Nov 2026 · by Skill-Lync

Free. We ask for your name and phone once before it plays here · or watch on YouTube ↗

Who is this course for?

Engineering students and early-career engineers who are new to autonomous vehicles or robotics and want a first, non-mathematical picture of what SLAM is and how it is approached.

What will you learn?

  • Define the robot pose as position and heading, and name the sensors (camera, radar, GPS, lidar) a robot uses to read its environment
  • Explain SLAM as localization and mapping done together, and place it before path planning and control commands in a robot pipeline
  • Tell online SLAM (real time) from offline SLAM (map built from collected data) as the speaker presents them
  • Describe in plain terms what a Kalman filter estimates and how a particle filter narrows down a robot's likely position
  • Name the extended Kalman filter, RatSLAM and local bundle adjustment as newer approaches mentioned in this talk
  • Say why localization and mapping matter at each level of driving automation, and how connected vehicles can help

What does each part of the course cover?

7 sections, in watching order. Click a timestamp to jump the player there. The video description has no chapter list, so these chapters and timestamps were written from the video itself.

  1. 0:005 min · 5 chapters

    Why a robot needs SLAM: state, pose and sensors

    The speaker introduces simultaneous localization and mapping, state estimation and corrective action, then environment occupants such as other cars and traffic lights. It defines the robot pose as position and heading and lists camera, radar, GPS and lidar, with sensor fusion.

    Chapters
    • 0:00Introduction: what SLAM stands for and why it matters
    • 0:50Knowing the surroundings and your place in them: state estimation and corrective action
    • 2:00A robot in an environment: environment occupants
    • 2:56The robot pose: position and heading
    • 3:48Reading the environment: camera, radar, GPS, lidar and sensor fusion
  2. 4:519 min · 5 chapters

    What SLAM is: localization, mapping and the generic pipeline

    SLAM is split into localization (placing the robot on a map, with Google Maps and GPS as the example) and mapping (needed indoors, where no ready map exists). The pipeline runs from sensor input to localization and mapping, then path planning from source to destination, then control commands.

    Chapters
    • 4:51What SLAM is: localization plus mapping
    • 5:38Localization: placing yourself on a map, with Google Maps as the example
    • 7:06Mapping an indoor space and the generic SLAM system architecture
    • 10:07After SLAM: path planning from source to destination and control commands
    • 12:15The operating principle: sensor input, localize and map, estimate the pose
  3. 14:034 min · 3 chapters

    Online and offline SLAM, and the methods overview

    Two ways to classify SLAM: online, where the robot maps and localizes in real time, and offline, where data is collected first and a map is built from it. The speaker then introduces three methods, Kalman filter, particle filter and graph-based, as ways of solving a mathematical problem.

    Chapters
    • 14:03Online SLAM versus offline SLAM
    • 15:47Methods used to solve SLAM: an overview
    • 17:10SLAM as a mathematical problem built on sensor measurements
  4. 18:187 min · 2 chapters

    Kalman filter: estimating position and heading

    Introduces the Kalman filter as an estimator that uses a series of noisy measurements. The unknowns are the robot's position and heading, the measurements are distance and heading to objects, and the speaker uses a helicopter's roll, pitch and velocity as an example of a modelled system state.

    Chapters
    • 18:18Kalman filter: unknown position and heading from distance and heading measurements
    • 23:13Kalman filter: system model, sensor noise and a helicopter example
  5. 24:486 min · 3 chapters

    Particle filter, graph-based SLAM and a robot vacuum example

    The particle filter is described as a probabilistic method: a robot that starts unsure of its location narrows its position as it moves and senses. A graph network is then mentioned as a way to represent the map, and a vacuum-cleaning robot promotional video is played as a familiar SLAM product.

    Chapters
    • 24:48Particle filter: a probabilistic estimate of position
    • 26:04Graph-based method and how it relates to online and offline SLAM
    • 27:21Video: a robot vacuum cleaner as a SLAM product
  6. 31:064 min · 4 chapters

    Newer SLAM methods: extended Kalman filter, RatSLAM, bundle adjustment

    Three methods named as state of the art in this January 2021 talk: the extended Kalman filter for non-linear systems, RatSLAM modelled on the rat hippocampus, and local bundle adjustment, a camera-based visual method that builds 3D points. The speaker keeps all three at a high level.

    Chapters
    • 31:06State-of-the-art methods in SLAM (as of this 2021 talk)
    • 31:46Extended Kalman filter for non-linear systems
    • 33:09RatSLAM: a model based on the rat hippocampus
    • 33:54Local bundle adjustment: a camera-based visual method
  7. 34:377 min · 3 chapters

    SLAM in autonomous vehicles, connected features and careers

    Places SLAM in the levels of driving automation, with level 2 and 3 features as the industry focus at the time, and as the core of autonomy. It adds connected vehicles sharing sensor data through the cloud, then lists robotics fields: cars, drones, underwater vehicles, factory robots and farming.

    Chapters
    • 34:37Evolution of SLAM and the levels of driving automation
    • 37:09Connected features: vehicles sharing sensor data to localize better
    • 38:30Where SLAM is used: cars, drones, underwater vehicles, factory and farm robots

Is the Introduction to SLAM for Autonomous Vehicles course really free?

Yes. All 42 min of it is free on Skill-Lync's YouTube channel, with no payment. To watch it on this page with the chapter guide, leave your name and phone number once; you can also watch it directly on YouTube. It was published on 20 Jan 2021 and had 2,918 views as of 20 Nov 2026. This page adds the chapter guide, a study plan and what to learn next.

How long does the Introduction to SLAM for Autonomous Vehicles course take to finish?

The video runs 42 min across 25 chapters. At one hour a day that is about 1 days; plan roughly twice that if you practise each exercise as you go. The longest section is "What SLAM is: localization, mapping and the generic pipeline" (9 min), so give it its own days.

Does the free SLAM course come with a certificate?

The video description has a "claim your certificate" link, which now opens this page. To ask about a certificate for this course, leave your name and phone number in the form below and a Skill-Lync counsellor will call you back. The paid Skill-Lync courses linked here include a certificate along with mentor-reviewed projects.

What should I learn after this course?

The next step is Localization, Mapping, and SLAM using Python (₹40,000). The free course teaches the concepts; the paid Skill-Lync courses add graded projects, mentor feedback and, in the PG programs, placement support.

Do I need to know control systems or maths before this SLAM webinar?

The webinar sets no formal prerequisites. The speaker says a control systems background helps with the Kalman filter section, treats SLAM as a mathematical problem, and keeps every method at a high level, promising more detail only in a full course. No code or derivations are shown.

What is the difference between a Kalman filter and a particle filter in SLAM?

As the speaker explains it, a Kalman filter starts from a mathematical model of the system and corrects its estimate of position and heading using noisy sensor measurements. A particle filter is probabilistic: the robot starts unsure of where it is and the probability narrows to a small area as it moves and senses.

Does the video cover lidar or visual SLAM?

Lidar and camera are listed as sensors, and local bundle adjustment is described as a visual method that builds 3D points from camera images. It is a short mention, not a walkthrough. The video does not compare lidar and visual SLAM or show a specific package.

Last updated 20 Nov 2026 · Course length, chapters, views and dates from the YouTube video on 20 Nov 2026 · Grow by Skill-Lync: free lessons from every course

Finished the course?

Ask about the certificate or your next course.

Leave your name and phone number. A Skill-Lync counsellor calls you back within one working day about the certificate for Introduction to SLAM for Autonomous Vehicles and the course that fits where you want to work.

Talk to a career counsellor

Free 20-minute call. We'll map the right course to where you want to work.

By submitting you agree to our Terms and Privacy Policy.

Free full course · Skill-Lync

Start watching

Free, no payment. Leave your name and phone once and the whole Introduction to SLAM for Autonomous Vehicles course plays here, with every free lesson on Grow. A Skill-Lync counsellor may call you about the certificate or your next course.

By submitting you agree to our Terms and Privacy Policy.

Talk to a career counsellor

Talk to a career counsellor

Free 20-minute call. We'll map the right course to where you want to work.

By submitting you agree to our Terms and Privacy Policy.