Biological Inspired Machine Learning Based Mobile Robot Velocity Estimation

By

Acknowledgement

I would take this opportunity to thank my research supervisor, family and friends for their support and guidance without which this research would not have been possible.

DECLARATION

I [type your full first names and surname here], declare that the contents of this dissertation/thesis represent my own unaided work, and that the dissertation/thesis has not previously been submitted for academic examination towards any qualification. Furthermore, it represents my own opinions and not necessarily those of the University.

Signed __________________ Date _________________

Abstract

In this study we try to explore the concept of “Biological Inspired Machine” in a holistic context. The main focus of the research is on “Biological Inspired Machine” and its relation with “learning based mobile robot velocity estimation”. The research also analyzes many aspects of “Biological Inspired Machine” and tries to gauge its effect on “learning based mobile robot velocity estimation”. Finally the research describes various factors which are responsible for “Biological Inspired Machine” and tries to describe the overall effect of “Biological Inspired Machine” on “learning based mobile robot velocity estimation”.

Dissertation title:

Biological inspired Machine learning based mobile robot velocity estimation

Chapter 1:

Introduction

1.1.1 Ego-velocity Estimation

Motion analysis is concerned with the estimation of the relative motion between an observer and objects (environments). The relative motion is derived from the movement of the observer, the objects (environments), or both.

This thesis focuses on the estimation of observer motion, more commonly known as ego-motion, “an active or passive environmental displacement of the observer” [].

Ego-motion is calculated through the information regarding observer rotation and direction of translation at a given instant of time, as the observer moves through the environment.

The need for healthy and reliable estimation of ego-motion is still an interesting and important problem. Knowledge about the relative motion of a camera (robot) with respect to the static environment represents a cornerstone for subsequent dynamic scene (environment) analysis and future development for different mobile robot applications: Obstacle navigation, collision avoidance, autonomous vision-based vehicle guidance [], shift command (speed and heading), [T1] steering and localization, route mapping planning ,mapping[T2], localization, shift command, following vehicles schemes navigation, and navigation[T3]

The literature and related works regarding state of the art of the robot velocity estimation show that many techniques based on different kinds of sensors that have been developed []. Among the most common methods used behind sensors are odometer encoders (or shaft encoders) [], inertial measurement units (IMU) [], sonar/ultrasonic sensors [], infrared laser radiation [], and global-positioning-systems (GPS) []. Each has its own unique merits; however, they also have inevitable shortcomings that lead to the production of non-robust and unreliable robot motion information in real world situations. For example, odometer-based mobile robots that employ differential wheel drives for estimating velocity and steering depend on very exact measurements of the robot's wheels and wheelbase. However, they are easily prone to high degrees of wheel slippage and suffer from precision errors, especially when moving over extreme terrain surfaces, such as rubble, gravel, grass, sand and ...