Mobile Robots

Course dates – HT – week beginning Monday 04th March 2019 – for Year 1 students
Paul Newman and Ingmar Posner

Introduction

In the future, autonomous vehicles will play an important part in our lives. They will come in a variety of shapes and sizes and undertake a diverse set of tasks on our behalf. We want smart vehicles to carry, transport, labour for and defend us. We want them to be flexible, reliable and safe. This course will to introduce you to the key components of mobile robotics in a very real sense (you will end up in field with one)

Objectives
  • To understand the interplay between localisation, planning and control in an embedded system and to execute the design of such a system
  • To understand and experience the pros and cons of infrastructure dependent and infrastructure free localisation
  • To gain practical experience in safely operating autonomous vehicles in the field and debugging errant behaviour
  • To understand the theoretical underpinnings of planning-by-search, visual odometry and visual localisation, lidar based navigation and obstacle detection
Prerequisites
  • Ability to program in C++
  • CDT-gleaned knowledge on computer vision and estimation
Lecture Notes
  • each day will begin with a brief lecture  before carrying on with the practical
  • the practical will be supported by 5 members of the robotics research group to ensure you have the attention and problem solving resource you will need.

 

Other Sources

The mobile robotics group will provide you with a working robot (a Husky or  Kuku Youbot) and some key software and hardware components for example a visual odometry system, a low level controller, a communications manager and a visualisation tool kit, a dense stereo library and a location sensing device.

 

Exercises

The course will be built around a single extensive practical (long days of great enjoyment). You will be split into two teams, each given a mobile robot (100kg) and at the end of the week you will compete against each other in a mobile robot challenge (for example finding an object in the University Parks).

Assessment Mode

You will give a presentation of your results and critique of your system to the mobile robotics research group on the last day of the week. Each team member will be asked to write a 3 page report on their contribution and evaluate the overall performance of their implementation.