Thesis work - Learning Robot-Individual Physics-Models from Calibration Data and Test Measurements

Teknik, data och digitalt · Mjukvaru- och webbutveckling · Mjukvaruutveckling · Robotik och automation · Maskininlärning

Gå med för uppdateringar

I korthet

This thesis work focuses on learning individual robot physics models from calibration data and test measurements. The objective is to explore how production data can improve physics-based models using machine-learning techniques for individualized robot representations and future digital twin applications. The internship is for one or two students at ABB Robotics in Västerås, Sweden, from January to June 2027.

Ansvarsområden

Investigate how data and test measurements collected during production can be used to learn robot-specific characteristics and improve modeling of individual robots.
Explore whether robot-specific information can be extracted from existing data and how such information can be integrated with physics-based models using machine-learning techniques.
Establish a framework where data collected during normal production procedures are continuously reused to create and maintain robot-individual models.
Support improved simulation accuracy, automated diagnostics, and future robot-specific control models.

Krav

Studying for a Master of Science, Engineering Physics, Electrical Engineering, Mechanical engineering or Computer Science degree.
Strong interest in machine learning, system identification, physics-based modeling and control theory.
Knowledge of Matlab and/or Python is required.
Basic programming in C/C++ is considered an advantage.

Önskade kvalifikationer

Numerical methods knowledge is considered an advantage.
Basic programming in C/C++ is considered an advantage.

Förmåner

This role sits within ABB's Robotics business, a leading global robotics company.
Opportunity to be part of a pioneering team shaping the future of robotics.
Working alongside world-class experts in a fast-moving, innovation-driven environment.
30 credits for the thesis work.

Färdigheter

Machine LearningSystem IdentificationPhysics-Based ModelingControl TheoryMatlabPythonC++

#robotics#machine learning#physics modeling#calibration#test measurements

Om ABB

We are a technology leader in electrification and automation, enabling a more sustainable and resource-efficient future.

ABB is a technology leader in electrification and automation, enabling a more sustainable and resource-efficient future. The company’s solutions connect engineering know-how and software to optimize how things are manufactured, moved, powered and operated. Building on more than 130 years of excellence, ABB’s ~105,000 employees are committed to driving innovations that accelerate industrial transformation. www.abb.com\nPrivacy notice & house rules: https://social.abb/social-media-information\n\nBefore applying for a job at ABB , please read our Fraud Warning:…

Se alla lediga jobb hos ABB Läs mer om ABB Webbplats