Faculty/School

Faculty of Engineering

School of Electrical Engineering and Robotics

Topic status

We're looking for students to study this topic.

Research centre

Supervisors

Dr Maryam Haghighat
Position
Lecturer
Division / Faculty
Faculty of Engineering

Overview

Navigating through forests where every path looks the same poses a challenge for robot localisation in these natural environments. Robot localisation, i.e. determining position and orientation, is crucial for autonomous tasks like monitoring, exploration and critical search and rescue operations in GPS-degraded areas. Lack of distinctive features and environmental changes lead to potential errors and often failures if relying on model-based techniques. To address these issues, this project aims to incorporate deep-learning based approaches that combine information from different sources, such as Google Map and satellite imagery with lidar point clouds.

Research engagement

  • In this project you will be working as a member of a team to process Lidar 3D point clouds using advanced machine learning algorithms.
  • You will participate in developing a data integration framework, designing training algorithms and running experimental setups.

Outcomes

Collaboration on developing a cutting-edge localisation system to improve navigation and understanding of natural environments both in terms of accuracy and reliability.

Skills and experience

  • Strong programming background (preferably in Python).
  • Machine learning experience preferred but not mandatory.
  • Understanding of computer vision and deep learning concepts is beneficial.

Start date

1 November, 2024

End date

28 February, 2025

Location

School of Electrical Engineering and Robotics

Keywords

Contact

maryam.haghighat@qut.edu.au