Non-Overlap-Aware Egocentric Pose Estimation for Collaborative Perception in Connected Autonomy

TL;DR

This paper introduces NOPE, a novel method for egocentric pose estimation in multi-robot systems that identifies non-overlapping views and operates under limited communication bandwidth, improving accuracy in connected autonomous vehicle perception.

Contribution

The paper presents a hierarchical learning framework combining deep graph matching and cross-attention for non-overlap-aware egocentric pose estimation in multi-robot teams.

Findings

NOPE achieves state-of-the-art performance in simulations and real-world tests.

It effectively identifies non-overlapping views to improve pose estimation accuracy.

The method operates efficiently under communication bandwidth constraints.

Abstract

Egocentric pose estimation is a fundamental capability for multi-robot collaborative perception in connected autonomy, such as connected autonomous vehicles. During multi-robot operations, a robot needs to know the relative pose between itself and its teammates with respect to its own coordinates. However, different robots usually observe completely different views that contains similar objects, which leads to wrong pose estimation. In addition, it is unrealistic to allow robots to share their raw observations to detect overlap due to the limited communication bandwidth constraint. In this paper, we introduce a novel method for Non-Overlap-Aware Egocentric Pose Estimation (NOPE), which performs egocentric pose estimation in a multi-robot team while identifying the non-overlap views and satifying the communication bandwidth constraint. NOPE is built upon an unified hierarchical learning framework that integrates two levels of robot learning: (1) high-level deep graph matching for correspondence identification, which allows to identify if two views are overlapping or not, (2) low-level position-aware cross-attention graph learning for egocentric pose estimation. To evaluate NOPE, we conduct extensive experiments in both high-fidelity simulation and real-world scenarios. Experimental results have demonstrated that NOPE enables the novel capability for non-overlapping-aware egocentric pose estimation and achieves state-of-art performance compared with the existing methods. Our project page at https://hongh0.github.io/NOPE/.