SwarmDrive: Semantic V2V Coordination for Latency-Constrained Cooperative Autonomous Driving

2026-04-22

AI Summary

This work addresses the high latency and network dependency of cloud-based large-model inference, as well as the performance limitations of purely local edge models in occluded scenarios. To overcome these challenges, the authors propose a lightweight, semantics-driven vehicle-to-vehicle (V2V) cooperative framework that leverages on-device small language models (SLMs). When perceptual uncertainty exceeds a predefined entropy threshold, an event-triggered mechanism enables vehicles to exchange compact intent distributions and reach a consensus. Integrating semantic communication with 6G network simulation, the approach achieves a 94.1% decision success rate in occluded intersection scenarios—representing a 25.2% improvement over a standalone SLM—and reduces end-to-end latency to 151.4 ms, a 358.6 ms reduction compared to cloud-based inference. This effectively balances collaboration scale, communication overhead, and decision accuracy.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Cloud-hosted LLM inference for autonomous driving adds round-trip delay and depends on stable connectivity, while purely local edge models struggle under occlusion. We present SwarmDrive, a semantic Vehicle-to-Vehicle (V2V) coordination framework in which nearby vehicles run local Small Language Models (SLMs), share compact intent distributions only when uncertainty is high, and fuse them through event-triggered consensus. We evaluate SwarmDrive in a 5-seed executable study built around one occluded intersection case, combining matched operating-point comparisons with robustness sweeps. In that setting, SwarmDrive under its 6G communication setting ("Swarm 6G") raises success from 68.9% to 94.1% over a single local SLM while reducing latency from a 510 ms cloud reference to 151.4 ms. However, an increased number of participating vehicles leads to higher communication overhead and packet loss. SwarmDrive also evaluates the impact of swarm-size, packet-loss, and entropy-threshold sweeps and shows that the cooperative gain holds across ablations and is best balanced near an active swarm size of 4 vehicles and an entropy trigger threshold of 0.65 in the current prototype. These results show that semantic edge cooperation can work under tight latency constraints in the targeted intersection case, but they are not a deployment-grade validation of a real 6G stack.

Problem

• autonomous driving
• V2V coordination
• latency-constrained
• occlusion
• cooperative perception

Innovation

• Semantic V2V Coordination
• Small Language Models (SLMs)
• Event-Triggered Consensus
• Latency-Constrained Autonomous Driving
• Cooperative Edge Intelligence