UECP: Uncertainty-Enhanced Collaborative Perception

2026-06-22

AI Summary

This work addresses the lack of an objective, detection-decoupled quality metric in collaborative perception, which is often supervised by physical signals and whose absence leads to biased contribution evaluation. To this end, the authors propose UECP, an uncertainty-enhanced collaborative perception framework that introduces, for the first time, an uncertainty map supervised by LiDAR point density as an unbiased measure of perceptual quality. The framework incorporates an uncertainty-aware pyramid fusion module that implements a coarse-to-fine fusion strategy through two key components: uncertainty-weighted downsampling (UWD) and uncertainty-guided residual fusion (UGRF), enabling high-quality weighting of collaborative features and effective noise suppression. Extensive experiments on real-world datasets demonstrate that the proposed method significantly outperforms existing approaches in both perception accuracy and robustness.

Abstract

Collaborative perception serves as a pivotal solution to enhance the perception capability of individual agents in autonomous driving, where a core challenge lies in seeking reliable evidence to quantify and weight the contribution of each participating agent. Existing methods typically rely on a confidence map, which is co-trained with the detection head, but it is inherently correlated with the detection results and thus fails to provide unbiased physical evidence. Furthermore, how to deeply integrate evidence into the cooperative fusion process remains an open question. To address these issues, this paper first proposes an uncertainty map, a physically grounded and unambiguous metric for evaluating perception quality. This map is directly supervised by real-time sensor signals, i.e., LiDAR point density, ensuring decoupling from detection noise and thereby providing physical scenario-aware evidence for weighting agent contribution. Based on this map, we develop the Uncertainty-Enhanced Collaborative Perception (UECP) framework, centered on the Uncertainty-Aware Pyramid Fusion (UAPF) module. UAPF uses a coarse-to-fine strategy, with two key components: Uncertainty-Weighted Downsampling (UWD) for high-fidelity feature preservation, and Uncertainty-Guided Residual Fusion (UGRF) to reinforce ego features, suppressing noise and ensuring robust fusion. Extensive experiments on real-world datasets show UECP outperforms state-of-the-art methods in effectiveness and robustness by embedding the uncertainty map into fusion. Code will be publicly available.

Problem

• collaborative perception
• uncertainty quantification
• agent contribution weighting
• evidence integration
• perception fusion

Innovation

• uncertainty map
• collaborative perception
• Uncertainty-Aware Pyramid Fusion
• LiDAR point density
• feature fusion