Study of non-Gaussian probability distributions and experimental characterization of error distribution on sensors

Project Description

Non-Gaussian distribution refers to a class of probability distributions that differ from the symmetric and bell-shaped pattern of the Gaussian distribution, also known as the normal distribution. Understanding and analyzing non-Gaussian distributions is crucial in data analysis and modeling, as they faithfully represent real-world data, capture intricate patterns, and effectively handle outliers. This project seeks to experimentally characterize the error distributions that affect the sensing set of IRMA L@B cable-robot prototype, which includes load cells, incremental encoders and an XSens inclinometer.

Prerequisites

• Sound knowledge of basic mathematics
• Basic knowledge of Matlab
• Keen on studying complex new theory
• Strong will to cope with demanding challenges
• Foundation of measurement theory

Target Objectives

• Study of Non-Gaussian distributions
• Acquire competence in bibliography analysis
• Strength the knowledge of Matlab and acquire the capability to use it to simulate the behavior of real sensors
• Acquire competence in experimental research activities

Expected Results

• Analysis of the literature regarding non-Gaussian distributions
• Development of a method enabling the characterization of error distributions, followed by method verification through simulation
• Characterization of the error distributions that affect the sensing set of IRMA L@B cable-robot prototype

Apply Now