Course overview
Localisation & Mapping algorithms are the essential skill set for any engineer who would like to explore career opportunities in the areas of mobile robots. You may have already witnessed self-driving vehicles such as Google’s Waymo, Tesla, autonomous floor cleaning robots such as Roomba and Irobot. All these autonomous systems use localisation and mapping technology to understand the environment to move and to reach the required destination.
Robot localisation is the process of determining where a mobile robot is located with respect to its environment. The knowledge of the robot's own location is an essential precursor to making decisions about future actions. Robotic mapping is a discipline related to computer vision and cartography. With the help of Localisation & Mapping, the goal for an autonomous robot is to be able to construct a map or floor plan and to localise itself.
 |
 |
This course on Robot Localisation and Mapping helps you to practically build projects to gain confidence on algorithms such as, 1D bayes filter & 2D bayes filter localisation, Monte Carlo Localisation and Occupancy grid mapping. By the end of this course, you will have the confidence to build projects & troubleshoot the issues.
Mobile Robots, Sensors & 1D Bayes filter localisation algorithm
Learning overview: Week 1
Introduction to mobile robots, types of mobile robots (Wheeled, Tracked, Legged, AIr-based & Water based robot), types of wheeled robots and their locomotion (Single wheeled, two wheeled, three wheeled, Four wheeled & Five or more wheeled robots), Types of wheels (Standard/Fixed, Orientable Ball and Omni wheel).
Introduction to a sensors and its types (Active and Passive), Introduction to Odometry sensor, It’s need, working and error propagation. Introduction to a Laser sensor, it’s need, working, Laser parameters (Maximum, Minimum, Accuracy, Resolution, Scan Area) and Laser gaussian error (1D and 2D). Introduction to Localization and need for localization. Basics of probability (Joint Distribution & Conditional Probability).
Introduction Baye's filter, hand calculation to estimate if a door Is open or closed using Baye’s filter . Baye's filter 1D localization algorithm. Programming 1D robot localization based on robot sensing and movement and Analysis of robot localization accuracy based on the grid size.
2D Bayes filter localisation algorithm
Learning overview: Week 2
Introduction to 2D Baye's filter localization, 2D Baye's filter algorithm, Grid based representation of the environment and Robot orientation pose representation (x, y, theta). Programming 2D Baye's filter localization algorithm to estimate robots position based on robot’s movement and Observation and Visualization of robot position tracking based on given tag position. Introduction to ROS bag file and creating ROS bag file for the given ROS topics.
Monte Carlo localisation algorithms
Learning overview: Week 3
Introduction to particle filter or Monte Carlo localization, Robot localization based on particle sampling, resampling, motion update, estimate robot’s new belief, given the previous belief and Particle filter localization algorithm. Programming robot with Monte Carlo localization, odometry noise, laser noise, number of particles and particle weights. Analysis of robot position estimation based on number of particles and robot motion to understand the time taken and error value of the algorithm.
Robot mapping & occupancy grid mapping algorithm
Learning overview: Week 4
Introduction to robot mapping and application of robot mapping in real world scenarios. Introduction to occupancy grid mapping, Occupancy grid mapping algorithm, Laser scan method of identifying free and occupied spaces, Bresenham's line algorithm to convert laser scan data to obstacle representation.
Introduction to Quaternion coordinate system and conversion of Quaternion coordinate system to Euler angles. Programming occupancy grid mapping algorithm to estimate to scan the environment and calculate the robot’s map. Analysis of accuracy, resolution and time of occupancy grid mapping algorithm. Analysis of number of messages, simulation and size of the data generated based on occupancy grid mapping algorithm.
Course notes
Course name |
Localisation & Mapping Algorithms for Autonomous Robots |
Mode of delivery |
Online & Self paced with support |
Start & end date |
Immediately |
Course duration |
15+ hours |
Software used |
ROS, Rviz, Gazebo & Python (+HTML) |
Applicable for |
This course is for engineers who would like to align & prepare themselves to be the part of autonomous robotics industry. The application may be cars, self driving taxis, drones, flights, ships, floor cleaning bots, inspection & surveillance bots, medical bots & more. |
Certification by & Host details |
Decibels Lab Pvt Ltd
(Recognised as Start-up by Department for Promotion of Industry and Internal Trade Ministry of Commerce & Industry Government of India) (Certificate Number: DIPP45372) |
Prerequisites & hardware |
Mandatory to complete Decibels course on Building Industrial Robots using Python & ROS. |
Batch size |
15 participants only |
Selection criteria |
First, come registration basis |
Session formats |
Enrolled participants will get access to pre-recorded course lectures In decibels LMS. You can learn the courses as per your time planning. |
Doubt clarification |
Addressed during via Discussions option available at each lesson In our LMS. If the query needs a detailed discussion, we will support you through the zoom meeting + Dedicated support for queries. |
Certification |
Participants will receive a Linkedin shareable digital Course completion certificate. (Verifiable certificate)
*** Students can opt for this course as a 6-week Internship |
Course enrolment
-
Localisation & Mapping Algorithms for Autonomous Robots
₹4,999.00
Buy Now
Feedback from participants
 |
 |
 |
 |