Home // International Journal On Advances in Software, volume 18, numbers 3 and 4, 2025 // View article
Relevance-Aware Semantic Communication for Intelligent Collective Perception System
Authors:
Romain Tessier
Bruno Monsuez
Oyunchimeg Shagdar
Keywords: Collaborative Perception; V2X; Ontology; Context-aware; Semantic-Communication
Abstract:
Autonomous vehicles face critical limitations when navigating dynamic environments where occlusions or sensor range constraints prevent full situational awareness. Cooperative Intelligent Transport Systems (C-ITS) offer a solution by enabling vehicles to share perception data. However, the uncontrolled volume of exchanged messages leads to congestion and interpretation challenges. This paper proposes a context-aware approach to collaborative perception that transmits only semantically relevant information. By leveraging ontologies to build a knowledge graph of the driving scene, vehicles can reason over their environment, identify safety-critical events, and generate Semantic Collective Perception Messages (S-CPMs). These messages encode not just raw data, but meaningful, situationally prioritized insights, improving decision-making and communication efficiency. A hidden pedestrian use case demonstrates the frameworkâs ability to anticipate and communicate high-risk interactions even in the absence of direct visibility. This semantic approach lays the groundwork for intelligent V2X systems that communicate with precision, relevance, and safety in mind.
Pages: 169 to 180
Copyright: Copyright (c) to authors, 2025. Used with permission.
Publication date: December 30, 2025
Published in: journal
ISSN: 1942-2628