Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion Approach

This paper presents a bio-inspired, generative Multi-Modal Sensor Fusion (MSF) framework to effectively detecting novel and dynamic situations in the surroundings of Autonomous Vehicle (AV). The MSF framework fuses both proprioceptive (wheel odometry) and exteroceptive (LiDAR point-clouds) sensory i...

Full description

Saved in:
Bibliographic Details
Main Authors: Hafsa Iqbal, Haleema Sadia, Abdulla Al-Kaff, Fernando Garcie
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Intelligent Transportation Systems
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11037519/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849420551122059264
author Hafsa Iqbal
Haleema Sadia
Abdulla Al-Kaff
Fernando Garcie
author_facet Hafsa Iqbal
Haleema Sadia
Abdulla Al-Kaff
Fernando Garcie
author_sort Hafsa Iqbal
collection DOAJ
description This paper presents a bio-inspired, generative Multi-Modal Sensor Fusion (MSF) framework to effectively detecting novel and dynamic situations in the surroundings of Autonomous Vehicle (AV). The MSF framework fuses both proprioceptive (wheel odometry) and exteroceptive (LiDAR point-clouds) sensory inputs. A novel 3-Dimensional Dynamic Variational Auto-Encoder (3D-DVAE) model is employed to learn attention-focused distributions from point-clouds in an unsupervised manner. By fusing the distributions of both modalities (wheel and lidar), modality-specific experts’ distributions are learned, capturing both proprioceptive and exteroceptive information from the surroundings. Bayesian Filtering is then applied to detect novel situations/dynamics by probabilistically inferring future states. The proposed method is validated using the KITTI dataset across diverse and complex urban environments. Both quantitative and qualitative results demonstrate the effectiveness of the proposed approach in detecting novelties through multi-modal fusion.
format Article
id doaj-art-ebaa0562fca143889507ff548a6ecbfe
institution Kabale University
issn 2687-7813
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Intelligent Transportation Systems
spelling doaj-art-ebaa0562fca143889507ff548a6ecbfe2025-08-20T03:31:44ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132025-01-01679981210.1109/OJITS.2025.358027111037519Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion ApproachHafsa Iqbal0https://orcid.org/0000-0002-1773-8066Haleema Sadia1https://orcid.org/0000-0001-8823-2348Abdulla Al-Kaff2https://orcid.org/0000-0003-0212-6400Fernando Garcie3https://orcid.org/0000-0002-6291-5009Departamento de Ingenieria de Sistemas y Automática, Autonomous Mobility and Perception Laboratory, Universidad Carlos III de Madrid, Madrid, SpainDepartment of Electrical and Communication Engineering, United Arab Emirates University, Al Ain, UAEDepartamento de Ingenieria de Sistemas y Automática, Autonomous Mobility and Perception Laboratory, Universidad Carlos III de Madrid, Madrid, SpainDepartamento de Ingenieria de Sistemas y Automática, Autonomous Mobility and Perception Laboratory, Universidad Carlos III de Madrid, Madrid, SpainThis paper presents a bio-inspired, generative Multi-Modal Sensor Fusion (MSF) framework to effectively detecting novel and dynamic situations in the surroundings of Autonomous Vehicle (AV). The MSF framework fuses both proprioceptive (wheel odometry) and exteroceptive (LiDAR point-clouds) sensory inputs. A novel 3-Dimensional Dynamic Variational Auto-Encoder (3D-DVAE) model is employed to learn attention-focused distributions from point-clouds in an unsupervised manner. By fusing the distributions of both modalities (wheel and lidar), modality-specific experts’ distributions are learned, capturing both proprioceptive and exteroceptive information from the surroundings. Bayesian Filtering is then applied to detect novel situations/dynamics by probabilistically inferring future states. The proposed method is validated using the KITTI dataset across diverse and complex urban environments. Both quantitative and qualitative results demonstrate the effectiveness of the proposed approach in detecting novelties through multi-modal fusion.https://ieeexplore.ieee.org/document/11037519/Generative multi-modal sensor fusion frameworkautonomous vehiclesexteroceptive and proprioceptive sensory inputsnovelty detectionBayesian filtering
spellingShingle Hafsa Iqbal
Haleema Sadia
Abdulla Al-Kaff
Fernando Garcie
Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion Approach
IEEE Open Journal of Intelligent Transportation Systems
Generative multi-modal sensor fusion framework
autonomous vehicles
exteroceptive and proprioceptive sensory inputs
novelty detection
Bayesian filtering
title Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion Approach
title_full Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion Approach
title_fullStr Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion Approach
title_full_unstemmed Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion Approach
title_short Novelty Detection in Autonomous Driving: A Generative Multi-Modal Sensor Fusion Approach
title_sort novelty detection in autonomous driving a generative multi modal sensor fusion approach
topic Generative multi-modal sensor fusion framework
autonomous vehicles
exteroceptive and proprioceptive sensory inputs
novelty detection
Bayesian filtering
url https://ieeexplore.ieee.org/document/11037519/
work_keys_str_mv AT hafsaiqbal noveltydetectioninautonomousdrivingagenerativemultimodalsensorfusionapproach
AT haleemasadia noveltydetectioninautonomousdrivingagenerativemultimodalsensorfusionapproach
AT abdullaalkaff noveltydetectioninautonomousdrivingagenerativemultimodalsensorfusionapproach
AT fernandogarcie noveltydetectioninautonomousdrivingagenerativemultimodalsensorfusionapproach