BEVCooper: Accurate and Communication-Efficient Bird's-Eye-View Perception in Vehicular Networks

2025-12-22

AI Summary

To address low accuracy, high communication overhead, and excessive latency in multi-vehicle bird’s-eye view (BEV) construction for vehicle-infrastructure cooperative driving, this paper proposes a dynamic collaborative BEV perception framework. The method introduces (1) an online-learning-based dynamic vehicle selection mechanism that adaptively identifies optimal collaboration nodes according to real-time environmental conditions and V2V channel quality; and (2) an environment- and channel-aware adaptive feature compression and fusion scheme that jointly optimizes quantization granularity and fusion weights. We theoretically prove the asymptotic optimality of the proposed framework under dynamic network topologies and non-ideal wireless channels. Experimental results demonstrate that, compared with baseline approaches, the framework improves BEV perception accuracy by 63.18%, reduces end-to-end latency by 67.9%, and incurs only 1.8% additional computational overhead.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Bird's-Eye-View (BEV) is critical to connected and automated vehicles (CAVs) as it can provide unified and precise representation of vehicular surroundings. However, quality of the raw sensing data may degrade in occluded or distant regions, undermining the fidelity of constructed BEV map. In this paper, we propose BEVCooper, a novel collaborative perception framework that can guarantee accurate and low-latency BEV map construction. We first define an effective metric to evaluate the utility of BEV features from neighboring CAVs. Then, based on this, we develop an online learning-based collaborative CAV selection strategy that captures the ever-changing BEV feature utility of neighboring vehicles, enabling the ego CAV to prioritize the most valuable sources under bandwidth-constrained vehicle-to-vehicle (V2V) links. Furthermore, we design an adaptive fusion mechanism that optimizes BEV feature compression based on the environment dynamics and real-time V2V channel quality, effectively balancing feature transmission latency and accuracy of the constructed BEV map. Theoretical analysis demonstrates that, BEVCooper achieves asymptotically optimal CAV selection and adaptive feature fusion under dynamic vehicular topology and V2V channel conditions. Extensive experiments on real-world testbed show that, compared with state-of-the-art benchmarks, the proposed BEVCooper enhances BEV perception accuracy by up to $63.18%$ and reduces end-to-end latency by $67.9%$, with only $1.8%$ additional computational overhead.

Problem

• Enhances BEV map accuracy in occluded or distant regions
• Optimizes CAV selection for efficient V2V communication under bandwidth constraints
• Balances feature transmission latency and BEV map accuracy adaptively

Innovation

• Online learning-based collaborative CAV selection strategy
• Adaptive fusion mechanism optimizing BEV feature compression
• Asymptotically optimal selection and fusion under dynamic conditions