NAVIGATION MAP CREATION AND UPDATE

Background of thesis project


Volvo Construction Equipment (VCE) is one of the world's largest manufacturers of construction equipment. With enhancing the artificial intelligent area and learning-based approaches, there is a big trend for shifting towards autonomous vehicles that can localize themselves in the environment, perceive it and be able to safely navigate and plan. In the context of construction domain where the environment is of high dynamicity in nature, for the vehicle to be able to navigate safely and efficiently a map of the environment is required that can provide relevant information about the surrounding. Hence it is essential for Volvo to develop proper navigation map solution for safe and energy efficient autonomous vehicle navigation.


Suitable background


This master thesis is suitable for one student that is completing their studies in computer science. The thesis will be lead by Volvo Construction Equipment. Desired start date is Jan 2023.

Description of thesis work


Prior studies such as [1, 2] have looked into the spatial representation of the environment using the Normal Distributions Transform (NDT) approach. Our aim is to identify the state-of-the-art solutions for creating navigation map and updating it and customize the identified solution to our construction environments where we deal with highly dynamic environment.
Dataset will be provided by VCE containing point cloud video frames obtained by the LiDAR sensor. The student is preferably knowledgeable in deep learning, and Python is meriting. The main activities are:
Reviewing related studies in map creation and update criteria for outdoor applications.
Select the state of the art solutions in map creation and update criteria for outdoor applications.
Implementation of the selected solution on real hardware.
Evaluating the performance of the proposed solution.

A full report of the work carried out will be prepared and presented to staff at Volvo CE. It will be required for the student to perform the thesis at Volvo CE facilities in Eskilstuna.


References


[1] Saarinen, J., Andreasson, H., Stoyanov, T., Ala-Luhtala, J., & Lilienthal, A. J. (2013, May). Normal distributions transform occupancy maps: Application to large-scale online 3D mapping. In 2013 ieee international conference on robotics and automation (pp. 2233-2238). IEEE.
[2] Saarinen, J. P., Andreasson, H., Stoyanov, T., & Lilienthal, A. J. (2013). 3D normal distributions transform occupancy maps: An efficient representation for mapping in dynamic environments. The International Journal of Robotics Research, 32(14), 1627-1644.


Thesis Level: Master

Language: English


Starting date: January 2023


Number of students: One student


Tutor


Name, title, phone
Sara Afshar, Research Owner at Emerging Technologies, +46 1654 15707
Mohammad Loni, Research Engineer AI at Emerging Technologies, +46 165414570