Title:
Deep learning for building and validating geometric and semantic maps

dc.contributor.advisor Hays, James
dc.contributor.advisor Dellaert, Frank
dc.contributor.author Lambert, John
dc.contributor.committeeMember Kira, Zsolt
dc.contributor.committeeMember Pradalier, Cedric
dc.contributor.committeeMember Lucey, Simon
dc.contributor.department Interactive Computing
dc.date.accessioned 2022-05-18T19:39:23Z
dc.date.available 2022-05-18T19:39:23Z
dc.date.created 2022-05
dc.date.issued 2022-05-05
dc.date.submitted May 2022
dc.date.updated 2022-05-18T19:39:24Z
dc.description.abstract Mapping the world is an essential tool for making spatial artificial intelligence a reality in our near future. Spatial AI, or embodied intelligence for 3D perception, enables awareness and understanding of our surroundings. Maps serve as a core workhorse of motion prediction and motion planning for modern autonomous vehicles. Maps also enable human users to interact with novel 3D spaces remotely via virtual reality (VR) or convey useful information about an environment through augmented reality (AR). Current methods for building and validating geometric and semantic maps are limited in several ways. For example, floorplan maps constructed from sparse camera views within indoor environments generally suffer from low completeness. In other domains, such as city streets, the world is ever-changing, making online validation of high-definition (HD) maps a requirement for today’s self-driving vehicles; however, many current map change detection methods suffer from high-storage costs or limited accuracy. This dissertation research introduces new algorithms for building and validating geometric and semantic maps using deep learning, with three original contributions. I first develop a new learning-based algorithm, SALVe, for creating complete and accurate 2d geometric maps (floorplans) under very wide baselines and occlusion. Second, I explore the role of the deep "front end" in Structure-from-Motion (SfM), and analyze its use in GTSFM, a new system for global SfM. Finally, I introduce learning-based formulations for solving the HD map change detection task in a bird’s eye view and ego-view. Because real map changes are infrequent and vector maps are easy to synthetically manipulate, we lean on simulated data to train such models. Perhaps surprisingly, we show that such models can generalize to real world distributions. Along the way, in order to satisfy the demands of these data-driven, deep learning approaches, I contribute several large-scale datasets to- wards solving these problems – the Argoverse 1.0 Datasets, the MSeg Dataset, the Trust but Verify (TbV) Dataset, and the Argoverse 2.0 Datasets.
dc.description.degree Ph.D.
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/66670
dc.language.iso en_US
dc.publisher Georgia Institute of Technology
dc.subject Mapping
dc.subject 3d reconstruction
dc.subject Indoor reconstruction
dc.subject HD maps
dc.subject Self-driving
dc.subject Map change detection
dc.subject SfM
dc.subject Structure from motion
dc.subject SLAM
dc.subject Deep learning
dc.subject Autonomous vehicles
dc.subject Autonomous robotics
dc.title Deep learning for building and validating geometric and semantic maps
dc.type Text
dc.type.genre Dissertation
dspace.entity.type Publication
local.contributor.advisor Dellaert, Frank
local.contributor.advisor Hays, James
local.contributor.corporatename College of Computing
local.contributor.corporatename School of Interactive Computing
relation.isAdvisorOfPublication dac80074-d9d8-4358-b6eb-397d95bdc868
relation.isAdvisorOfPublication 5b631b9d-32a1-48bb-887b-c5431096e10d
relation.isOrgUnitOfPublication c8892b3c-8db6-4b7b-a33a-1b67f7db2021
relation.isOrgUnitOfPublication aac3f010-e629-4d08-8276-81143eeaf5cc
thesis.degree.level Doctoral
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
LAMBERT-DISSERTATION-2022.pdf
Size:
82.86 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
LICENSE.txt
Size:
3.86 KB
Format:
Plain Text
Description: