Fusion or Confusion? Potential and Challenges in Fusion of Onboard Sensors and V2X Data in Cooperative Perception

Jul 16, 2026

Upload by Miles

Connected and Automated Vehicles rely on onboard sensors for perception, but performance degrades under adverse weather and non-line-of-sight conditions. Cooperative perception improves sensing by exchanging V2X data so vehicles collectively enhance perception. Prior work highlights cooperative perception potential, yet limited attention has focused on how to fuse received V2X messages with onboard sensor information. The study shows higher V2X penetration can improve perception while introducing false positives and ghost objects, affecting safety and driving efficiency.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

Abstract

Keywords

I. Introduction

© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. A. Mohammadisarab, M. Sepulcre, L. Lusvarghi, S. S. Avedisov, M. I. Khan, T. Shimizu, O. Altintas, and J. Gozálvez, "Fusion or Confusion? Potential and Challenges in Fusion of Onboard Sensors and V2X Data in Cooperative Perception", IEEE CSCN, 15-17 September, 2025, Bologna, Italy. Online: [https://ieeexplore.ieee.org/abstract/document/11230764](https://ieeexplore.ieee.org/abstract/document/11230764) Fusion or Confusion? Potential and Challenges in Fusion of Onboard Sensors and V2X Data in Cooperative Perception Amir Mohammadisarab1, Miguel Sepulcre 1, Luca Lusvarghi1, Sergei S. Avedisov2, Mohammad Irfan Khan2, Takayuki Shimizu2, Onur Altintas2, Javier Gozalvez 1 1 Universidad Miguel Hernández de Elche (UMH), Spain, {amohammadisarab, msepulcre, llusvarghi, [j.gozalvez}@umh.es](j.gozalvez}@umh.es) 2Toyota Motor North America R&D, InfoTech Labs, Mountain View, California, USA, {sergei.avedisov, mohammad.irfan.khan, takayuki.shimizu, [onur.altintas}@toyota.com](onur.altintas}@toyota.com) Abstract—Connected Automated Vehicles (CAVs) utilize their onboard sensors to perceive the environment. The perception range and accuracy can be affected by adverse weather or non-line-of-sight conditions. Cooperative perception or sensor sharing can overcome these limitations by enabling CAVs to exchange sensor data, thus collectively enhancing their perception capabilities. Previous studies have shown the potential of cooperative perception, but limited attention has been given to the fusion of V2X data received through cooperative perception messages with onboard sensor information. The fusion process can be influenced by the quantity and quality of the V2X data. An increased volume of V2X data can reduce uncertainty in the perceived environment; however, when the data is noisy, it may compromise the accuracy of the fusion results. This study investigates the fusion of onboard sensor and V2X data in cooperative perception, and demonstrates that while perception can significantly improve asthe V2X penetration rate increases, it can introduce a significant number of false positives if V2X data is not highly accurate. False positives result in the detection of ghost objects that do not actually exist. These ghost objects can, in turn, compromise safety and driving efficiency. Our analysis found that false positives or ghost objects can appear even with accurate V2X data. These findings highlight the challenges in cooperative perception and the importance of developing robust data fusion methods to enhance the reliability of cooperative perception. This is particularly relevant in light of ongoing standardization efforts, such as ETSI TS 103 324 on collective perception. Keywords— V2X, cooperative perception, collective perception, sensor sharing, fusion, association, penetration rate, advanced driver assistance systems, ADAS, V2V. I. INTRODUCTION Cooperative (or collective) perception or sensor data sharing is a key enabler to enhance the perception of Connected and Automated Vehicles (CAVs) as well as human-driven vehicles using Vehicle-to-Everything (V2X) communication. Cooperative perception enables the exchange of information acquired by onboard sensors, which helps mitigate sensor limitations in terms of occlusion and field of view [1] . The standardization of cooperative perception by ETSI and SAE enables CAVs to exchange object-or tracklevel data (e.g., position, speed, and size) via V2X in cooperative perception messages. The received V2X data must be fused with onboard sensor data to enhance the perception capabilities of the CAVs. This ty

FAQs

What limitation motivates cooperative perception in connected automated vehicles?

Adverse weather and non-line-of-sight conditions can reduce perception range and accuracy. Cooperative perception mitigates these limitations by enabling vehicles to exchange sensor-derived information via V2X.

Why does fusing V2X data with onboard sensor data affect results?

The fusion outcome depends on the quantity and quality of the received V2X data. Larger volumes can reduce uncertainty, but noisy V2X data can degrade fusion accuracy.

What are ghost objects and what impact do they have?

Ghost objects are false positives—detections of objects that do not actually exist. They can compromise safety and reduce driving efficiency, and the analysis indicates they may appear even when V2X data is accurate.

Jul 16, 2026

Upload by Miles