Loading [MathJax]/extensions/MathMenu.js
AutowareV2X: Reliable V2X Communication and Collective Perception for Autonomous Driving | IEEE Conference Publication | IEEE Xplore

AutowareV2X: Reliable V2X Communication and Collective Perception for Autonomous Driving


Abstract:

For cooperative intelligent transport systems (C-ITS), vehicle-to-everything (V2X) communication is utilized to allow autonomous vehicles to share critical information wi...Show More

Abstract:

For cooperative intelligent transport systems (C-ITS), vehicle-to-everything (V2X) communication is utilized to allow autonomous vehicles to share critical information with each other. We propose AutowareV2X, an implementation of a V2X communication module that is integrated into the autonomous driving (AD) software, Autoware. AutowareV2X provides external connectivity to the entire AD stack, enabling the end-to-end (E2E) experimentation and evaluation of connected autonomous vehicles (CAV). The Collective Perception Service was also implemented, allowing the transmission of Collective Perception Messages (CPMs). A dual-channel mechanism that enables wireless link redundancy on the critical object information shared by CPMs is also proposed. Performance evaluation in field experiments has indicated that the CPM-based perception information can be transmitted in around 30 ms, and shared object data can be used by the AD software to conduct collision avoidance maneuvers. The dual-channel delivery of CPMs transmits perception information through two different wireless technologies. The receiver-side CAV can then dynamically select the best CPM from CPMs received from both links, depending on the freshness of their information.
Date of Conference: 20-23 June 2023
Date Added to IEEE Xplore: 14 August 2023
ISBN Information:

ISSN Information:

Conference Location: Florence, Italy

Funding Agency:


I. Introduction

Autonomous vehicles are one of the key components for the development and deployment of next-generation mobility services. It presents a combination of technical challenges that extend into multiple domains of cyber-physical systems, from accurate and reliable sensing, accelerated computation, and versatile planning algorithms, to fail-safe actuation systems. Open-source implementations of autonomous driving (AD) software stacks such as Autoware [1] and Baidu Apollo [2] provide implementations for necessary functions and modules for standalone autonomous vehicles (AVs). Standalone AVs have their set of limitations, and for cooperative intelligent transport systems (C-ITS), vehicle-to-everything (V2X) communication is utilized to realize connected autonomous vehicles (CAVs). This allows CAVs to share critical information with each other in order to enhance environmental awareness and reinforce cooperative decision-making. This additional layer of previously exclusive information allows CAVs to achieve a level of safety and efficiency that is impossible by stand-alone AVs. The proliferation of C-ITS technology and V2X communication heavily relies on the set of standards that are widely accepted either globally or regionally. The ITS station architecture [3], [4] proposed by the European Telecommunications Standards Institute (ETSI) and International Organization for Standardization (ISO) provides a common set of principles, guidelines, and standards for designing and implementing various ITS applications and services. Here, a physical node where the ITS systems and applications are installed is expressed as an ITS Station (ITS-S), and both CAVs and roadside units (RSUs) can be considered ITS-Ss. The Cooperative Awareness Message (CAM) [5] provides basic safety-oriented information about an ITS-S to nearby ITS-Ss within the broadcasting range. In the United States, the Basic Safety Message (BSM) [6] provides similar functionalities. To cooperatively improve environmental awareness, discussions for new standards such as the Collective Perception Service (CPS) [7] are underway, allowing ITS-Ss to share the objects they have perceived with others.

Contact IEEE to Subscribe

References

References is not available for this document.