HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception

TL;DR

HyDRA is a unified framework that improves collaborative perception by dynamically handling heterogeneity among agents through domain-aware fusion and pose optimization, achieving scalable, high-performance perception without extra training.

Contribution

We introduce HyDRA, a novel hybrid domain-aware architecture that integrates intermediate and late fusion with dynamic agent classification and pose optimization, enabling scalable heterogeneous collaboration.

Findings

HyDRA achieves performance comparable to state-of-the-art methods without additional training.

HyDRA maintains high performance as the number of agents increases.

HyDRA enables zero-cost scaling in heterogeneous collaborative perception.

Abstract

In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust Architecture), a unified pipeline that integrates intermediate and late fusion within a domain-aware framework. We introduce a lightweight domain classifier that dynamically identifies heterogeneous agents and assigns them to the late-fusion branch. Furthermore, we propose anchor-guided pose graph optimization to mitigate localization errors inherent in late fusion, leveraging reliable detections from intermediate fusion as fixed spatial anchors. Extensive experiments demonstrate that, despite requiring no additional training, HyDRA achieves performance comparable to state-of-the-art heterogeneity-aware CP methods. Importantly, this performance is maintained as the number of collaborating agents increases, enabling zero-cost scaling without retraining.