Yazgan, Melih (FZI Research Center for Information Technology), Arasan, Allen Xavier (Karlsruhe Institute of Technology), Zöllner, J. Marius (FZI Research Center for Information Technology; KIT Karlsruhe In)

EffiComm: Bandwidth Efficient Multi Agent Communication

Scheduled for presentation during the Regular Session "S25c-Cooperative and Connected Autonomous Systems" (TH-LA-T25), Thursday, November 20, 2025, 16:20−16:40, Cooleangata 4

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Collaborative perception allows connected vehicles to exchange sensor information and overcome each vehicle’s blind spots. Yet transmitting raw point clouds or full feature maps overwhelms Vehicle-to-Vehicle (V2V) communications, causing latency and scalability problems. We introduce EffiComm, an end-to-end framework that transmits < 40% of the data required by prior art while maintaining state-of-the-art 3-D object-detection accuracy. EffiComm operates on Bird’s-Eye-View (BEV) feature maps from any modality and applies a two-stage reduction pipeline: (1) Selective Transmission (ST) prunes low-utility regions with a confidence mask; (2) Adaptive Grid Reduction (AGR) uses a Graph Neural Network (GNN) to assign vehicle-specific keep ratios according to role and network load. The remaining features are fused with a soft-gated Mixture-of-Experts (MoE) attention layer, offering greater capacity and specialization for effective feature integration. On the OPV2V benchmark, EffiComm reaches 0.84-mAP@0.7 while sending only an average of ∼ 1.5 MB per frame, outperforming previous methods on the accuracy-per-bit curve. These results highlight the value of adaptive, learned communication for scalable Vehicle-to-Everything (V2X) perception.