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

TL;DR

SemAgent introduces a semantic-driven AI framework for vehicle trajectory prediction in V2X networks, improving accuracy and reducing communication overhead by integrating semantic reasoning with agentic AI in vehicular environments.

Contribution

It presents a novel semantic communication and agentic AI-based trajectory prediction framework that enhances predictive accuracy and efficiency in vehicular networks.

Findings

Achieves up to 47.5% improvement in prediction accuracy under low SNR conditions.

Effectively combines semantic reasoning with feature extraction for better trajectory prediction.

Outperforms baseline schemes across diverse communication scenarios.

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.