EffiComm: Bandwidth Efficient Multi Agent Communication

TL;DR

EffiComm is an efficient multi-agent communication framework for connected vehicles that reduces data transmission by over 60% while maintaining high 3D object detection accuracy, enhancing scalability in V2X perception.

Contribution

It introduces a novel two-stage data reduction pipeline with adaptive and selective mechanisms, enabling scalable V2V communication without sacrificing detection performance.

Findings

Achieves 0.84 mAP@0.7 on OPV2V benchmark.

Transmits approximately 1.5 MB per frame, over 60% less data than prior methods.

Maintains state-of-the-art detection accuracy with significantly reduced bandwidth.

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 less than 40% of the data required by prior art while maintaining state-of-the-art 3D 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 approximately 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.