SemAgent: Semantic-Driven Agentic AI Empowered Trajectory Prediction in Vehicular Networks

2025-11-30

AI Summary

Traditional V2X communication suffers from high overhead and latency, while existing trajectory prediction models lack environmental awareness and logical reasoning capabilities. To address these issues, this paper proposes a multi-agent collaborative framework integrating semantic communication and Agentic AI. The framework deploys feature extraction agents and semantic analysis agents at roadside units and onboard units, respectively, enabling environment perception, semantic compression, contextual reasoning, and multi-source information fusion in both V2I and V2V scenarios. Semantic-driven information exchange significantly reduces communication load while enhancing prediction interpretability and robustness. Experimental results demonstrate consistent superiority over baseline methods across diverse channel conditions; notably, prediction accuracy improves by up to 47.5% under low signal-to-noise ratio (SNR) conditions.

Technology Category

• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Efficient information exchange and reliable contextual reasoning are essential for vehicle-to-everything (V2X) networks. Conventional communication schemes often incur significant transmission overhead and latency, while existing trajectory prediction models generally lack environmental perception and logical inference capabilities. This paper presents a trajectory prediction framework that integrates semantic communication with Agentic AI to enhance predictive performance in vehicular environments. In vehicle-to-infrastructure (V2I) communication, a feature-extraction agent at the Roadside Unit (RSU) derives compact representations from historical vehicle trajectories, followed by semantic reasoning performed by a semantic-analysis agent. The RSU then transmits both feature representations and semantic insights to the target vehicle via semantic communication, enabling the vehicle to predict future trajectories by combining received semantics with its own historical data. In vehicle-to-vehicle (V2V) communication, each vehicle performs local feature extraction and semantic analysis while receiving predicted trajectories from neighboring vehicles, and jointly utilizes this information for its own trajectory prediction. Extensive experiments across diverse communication conditions demonstrate that the proposed method significantly outperforms baseline schemes, achieving up to a 47.5% improvement in prediction accuracy under low signal-to-noise ratio (SNR) conditions.

Problem

• Enhances trajectory prediction using semantic communication and Agentic AI
• Reduces transmission overhead and latency in V2X networks
• Improves environmental perception and logical inference for vehicles

Innovation

• Integrates semantic communication with Agentic AI
• Uses feature-extraction and semantic-analysis agents at RSU
• Combines received semantics with local data for prediction