Learning Isometric Embeddings of Road Networks using Multidimensional Scaling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Pardo, Juan Carlos Climent
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910918033539072
author Pardo, Juan Carlos Climent
author_facet Pardo, Juan Carlos Climent
contents The lack of generalization in learning-based autonomous driving applications is shown by the narrow range of road scenarios that vehicles can currently cover. A generalizable approach should capture many distinct road structures and topologies, as well as consider traffic participants, and dynamic changes in the environment, so that vehicles can navigate and perform motion planning tasks even in the most difficult situations. Designing suitable feature spaces for neural network-based motion planers that encapsulate all kinds of road scenarios is still an open research challenge. This paper tackles this learning-based generalization challenge and shows how graph representations of road networks can be leveraged by using multidimensional scaling (MDS) techniques in order to obtain such feature spaces. State-of-the-art graph representations and MDS approaches are analyzed for the autonomous driving use case. Finally, the option of embedding graph nodes is discussed in order to perform easier learning procedures and obtain dimensionality reduction.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Isometric Embeddings of Road Networks using Multidimensional Scaling
Pardo, Juan Carlos Climent
Machine Learning
Artificial Intelligence
Emerging Technologies
Symbolic Computation
The lack of generalization in learning-based autonomous driving applications is shown by the narrow range of road scenarios that vehicles can currently cover. A generalizable approach should capture many distinct road structures and topologies, as well as consider traffic participants, and dynamic changes in the environment, so that vehicles can navigate and perform motion planning tasks even in the most difficult situations. Designing suitable feature spaces for neural network-based motion planers that encapsulate all kinds of road scenarios is still an open research challenge. This paper tackles this learning-based generalization challenge and shows how graph representations of road networks can be leveraged by using multidimensional scaling (MDS) techniques in order to obtain such feature spaces. State-of-the-art graph representations and MDS approaches are analyzed for the autonomous driving use case. Finally, the option of embedding graph nodes is discussed in order to perform easier learning procedures and obtain dimensionality reduction.
title Learning Isometric Embeddings of Road Networks using Multidimensional Scaling
topic Machine Learning
Artificial Intelligence
Emerging Technologies
Symbolic Computation
url https://arxiv.org/abs/2504.17534