SD Map Localization: A Deep Learning Approach

Visa enkel post
dc.contributor.authorAbdul Rahuman, Sheik Meeran Rasheed
dc.contributor.authorJathavedan, Sameer
dc.contributor.departmentChalmers tekniska högskola / Institutionen för fysiksv
dc.contributor.departmentChalmers University of Technology / Department of Physicsen
dc.contributor.examinerGranath, Mats
dc.contributor.supervisorGranath, Mats
dc.date.accessioned2024-10-03T10:45:24Z
dc.date.available2024-10-03T10:45:24Z
dc.date.issued2024
dc.date.submitted
dc.description.abstractAccurate localization is critical for the safe and efficient operation of autonomous vehicles, enabling precise navigation and real-time decision-making. This thesis focuses on improving Standard Definition (SD) map based localization, by leveraging deep learning techniques. The research addresses key questions, including how to optimally encode SD map data and sensor data, particularly the Global Navigation Satellite System and Inertial Navigation System sensor, for deep learning, and train models to perform accurate map matching and vehicle localization along the correct road segment. The thesis develops a deep learning-based localization framework for autonomous vehicles, focusing on SD map data. It introduces three main components: a Polyline Encoder using either Graph Neural Networks (GNN) or Transformers, a Map Matching Network based on cross-attention, and a Point Prediction Network consisting of a simple Multi-Layer Perceptron. The model encodes ego trajectories and map links, matches the map data with the vehicle’s trajectory, and predicts precise location. Our results show that the GNN consistently outperforms the Transformer on both map matching and point prediction. The model’s performance varies based on the training and testing data used, with the last point of the trajectory often being sufficient for accurate localization. The study also compares the deep learning model with classical algorithms and finds that the GNN-based localization model significantly improves localization accuracy. Overall, our thesis demonstrates that leveraging deep learning techniques, particularly GNN-based architecture for encoding, along with cross-attention based architecture for map matching, has the potential to significantly enhance SD map localization for autonomous vehicles.
dc.identifier.coursecodeTIFX05
dc.identifier.urihttp://hdl.handle.net/20.500.12380/308843
dc.language.isoeng
dc.setspec.uppsokPhysicsChemistryMaths
dc.subjectDeep Learning, Map Localization, Transformer, Graph Neural Network
dc.titleSD Map Localization: A Deep Learning Approach
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster's Thesisen
dc.type.uppsokH
local.programmeComplex adaptive systems (MPCAS), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
Master Thesis_Sameer Jathavedan_Sheik Meeran_Rasheed.pdf
Storlek:
1.45 MB
Format:
Adobe Portable Document Format
Beskrivning:
Ladda ner
License bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
license.txt
Storlek:
2.35 KB
Format:
Item-specific license agreed upon to submission
Beskrivning:
Ladda ner
Samling
Examensarbeten för masterexamen