MétaCan
Menu
Back to cohort
Record W4389192220 · doi:10.22215/etd/2023-15731

Towards Full Deep Learning-based SLAM

2023· dissertation· en· W4389192220 on OpenAlexaff
Abhishek Khoyani

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldEngineering
TopicRobotics and Sensor-Based Localization
Canadian institutionsCarleton University
Fundersnot available
KeywordsSimultaneous localization and mappingComputer scienceArtificial intelligenceGraphDeep learningFalse positive paradoxMatching (statistics)Process (computing)RobotMachine learningTheoretical computer scienceMobile robotMathematics

Abstract

fetched live from OpenAlex

Applications of the robots are increasing in routine for shop floor activity, transportation, and many other areas.Simultaneous localization and mapping (SLAM) is one of the algorithm that gives a comprehensive understanding of robot's environment in form of map to perform various operation like navigation, and space reconstruction along with current state of estimation of robot i.e., localization in form of pose and orientation.Deep learning-based SLAM can be employed to overcome challenges faced by conventional SLAM algorithms, such as dynamic environments (moving objects, lighting variations) and long-scale mapping scenarios.In absence of fully deep learning-based SLAM system, this thesis presents a loop closure approach with constructing a real-time graph that can be developed further in fully SLAM system.The proposed approach involves constructing a real-time graph using features extracted from deep learning-based backbone models to achieve robust loop closure detection.This modularized parameter-free system framework extracts features from input images, calculates matching scores between the features, and generates a graph structure that represents the connectivity of nodes based on the matching criteria.The proposed framework is evaluated using various deep learning-based feature extractors on 11 sequences from the 5 open-source dataset.The results show that the proposed framework achieves faster processing times whereas achieving higher precision-recall i Firstly, I would like to express my heartfelt appreciation to my supervisor, Dr. Marzieh Amini, for placing her trust in my abilities and affording me the opportunity to pursue my MASc degree.This important milestone would not have been attainable without her unwavering guidance, encouragement, and motivation.I am profoundly grateful for my wonderful family.To my late father, whose numerous sacrifices have paved the way for my current achievements, I owe a debt of gratitude.To my mother

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0010.002
Open science0.0020.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.226
Teacher spread0.217 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicRobotics and Sensor-Based LocalizationFrench-language works237,207