Closure-guided communication cuts data and boosts vehicle perception
SemRD-V2X: Closure-Guided Communication with Bounded Inference for Cooperative Perception
Artificial IntelligenceInformation Theory
Summary
Vehicles working together to detect objects around them can send lots of data, often repeating what each car already knows. The authors study how to pick only the most crucial shared information that can't be guessed from a vehicle's own sensors. They design a system called SemRD-V2X that smartly compresses and shares only this essential data, letting each car fill in the rest by itself. Tests show this method cuts data sent by over 26 times while improving detection accuracy and only slightly slowing down computation.
What this means in practice
- •For autonomous vehicle engineers: Reduce bandwidth and improve object detection by sharing only essential sensor features among connected cars using SemRD-V2X.
- •For smart city infrastructure teams: Enhance cooperative perception for smart traffic systems by implementing closure-guided communication to lower data load while keeping accuracy.
Authors
Hu Xu, Chun Li, Siyuan Qiu, Zeyan Li, Jianfeng Xu
Abstract
Vehicle-to-Everything (V2X) cooperative perception improves 3-D detection by sharing intermediate features, but dense remote features may repeat context that the ego agent can infer locally. Most communication-efficient designs optimize masks or codes empirically, leaving a more basic question open: which remote evidence is indispensable given the receiver's own observation? We introduce a closure-fidelity perspective on ego conditioned remote perception. Under a finite deductive abstraction and explicit conditions, its rate--distortion function decomposes over an irredundant core, and the exact zero-distortion rate becomes $P_A H(π_A)$. This analysis suggests a concrete design principle: transmit compact evidence and recover derivable context with bounded receiver-side inference. Guided by this principle, SemRD-V2X is an operational neural proxy that combines exact-budget BEV support selection, pointwise channel compression, and masked shared-weight reconstruction before standard fusion. Experiments on simulated V2XSet and real-world DAIR-V2X validate the resulting design. In a controlled five-run V2XSet comparison against a locally reproduced V2X-ViT-v1 baseline on one Tesla V100, SemRD-V2X reduces the analytical feature payload by $26.6\times$ while improving AP@0.5/AP@0.7 by 4.13/8.57 points, with 3.81\% additional mean compute latency. These results position closure fidelity as both an analytical lens and an actionable design principle for communication-efficient cooperative perception.