Robotic Mapping and Trajectory Generation

Overview

In this second course of the Introduction to Robotics specialization, "Robotic Mapping and Trajectory Generation", you will learn how to perform basic inverse kinematics of (non-)holonomic systems using a feedback control approach. You will also learn how to process multi-dimensional sensor signals such as laser range scanners for mapping. Additionally, you will apply the overarching focus of mechanisms and sensors as sources of uncertainty and gain techniques to how to model and control them. It is recommended that you complete the first course of this specialization, “Introduction to Robotics: Basic Behaviors”, before beginning this one. This course can be taken for academic credit as part of CU Boulder’s MS in Computer Science degrees offered on the Coursera platform. These fully accredited graduate degrees offer targeted courses, short 8-week sessions, and pay-as-you-go tuition. Admission is based on performance in three preliminary courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: MS in Computer Science: https://coursera.org/degrees/ms-computer-science-boulder

Syllabus

Advanced Sensor: Range finders and Homogeneous transforms

Welcome to Week 1 of the course. You will get started by being introduced to the class of "range finder" devices, which have important applications in mapping, as well as the concept of homogeneous transforms to perform coordinate transformations.

Mapping: Basic Representations

In this week, you will begin to understand basic discrete map representations and their implementation.

Mapping: Probabilistic Representations and Configuration Space

This week introduces simple ways to encode obstacles in terms of probability, the concept of "configuration space", and a simple algorithm for collision checking.

Inverse Kinematics: Trajectory Following

In this week you will learn to define a robot trajectory based on a series of waypoints and implement a basic proportional controller in Webots to navigate in a 2D environment.

Implementing Mapping and Trajectory Generation

In this module you will transfer your mapping and trajectory following skills to a commercial robotic platform in a kitchen environment, introducing you to additional constraints of sensor integration on a real robotic platform.