SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception

TL;DR

SlimComm introduces a Doppler-guided sparse communication scheme for cooperative 3D perception in autonomous vehicles, significantly reducing bandwidth while maintaining high perception accuracy through query-driven feature sharing.

Contribution

It presents a novel framework combining Doppler radar data with sparse queries to optimize bandwidth in vehicle cooperation for perception.

Findings

Achieves up to 90% bandwidth reduction compared to full map sharing.

Maintains or surpasses baseline perception accuracy across various traffic conditions.

Introduces new datasets with Doppler radar data for cooperative perception evaluation.

Abstract

Collaborative perception allows connected autonomous vehicles (CAVs) to overcome occlusion and limited sensor range by sharing intermediate features. Yet transmitting dense Bird's-Eye-View (BEV) feature maps can overwhelm the bandwidth available for inter-vehicle communication. We present SlimComm, a communication-efficient framework that integrates 4D radar Doppler with a query-driven sparse scheme. SlimComm builds a motion-centric dynamic map to distinguish moving from static objects and generates two query types: (i) reference queries on dynamic and high-confidence regions, and (ii) exploratory queries probing occluded areas via a two-stage offset. Only query-specific BEV features are exchanged and fused through multi-scale gated deformable attention, reducing payload while preserving accuracy. For evaluation, we release OPV2V-R and Adver-City-R, CARLA-based datasets with per-point Doppler radar. SlimComm achieves up to 90% lower bandwidth than full-map sharing while matching or surpassing prior baselines across varied traffic densities and occlusions. Dataset and code will be available at: https://url.fzi.de/SlimComm.