Markerless Robot Detection and 6D Pose Estimation for Multi-Agent SLAM

2026-02-18

AI Summary

This work addresses the challenge of cross-robot data association in multi-robot SLAM, which is often hindered by perceptual aliasing or viewpoint discrepancies, and where conventional methods relying on calibrated markers suffer from limited observation range and sensitivity to lighting conditions. The paper proposes a decentralized multi-robot SLAM framework that, for the first time, integrates markerless deep learning-based 6D pose estimation to enable high-precision relative localization through direct inter-robot observations. By eliminating the need for artificial markers, the approach significantly enhances robustness under challenging illumination and at extended distances. Extensive field experiments in planetary-analog environments demonstrate its effectiveness, yielding substantial improvements in both relative localization accuracy and map consistency across the multi-robot system.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The capability of multi-robot SLAM approaches to merge localization history and maps from different observers is often challenged by the difficulty in establishing data association. Loop closure detection between perceptual inputs of different robotic agents is easily compromised in the context of perceptual aliasing, or when perspectives differ significantly. For this reason, direct mutual observation among robots is a powerful way to connect partial SLAM graphs, but often relies on the presence of calibrated arrays of fiducial markers (e.g., AprilTag arrays), which severely limits the range of observations and frequently fails under sharp lighting conditions, e.g., reflections or overexposure. In this work, we propose a novel solution to this problem leveraging recent advances in Deep-Learning-based 6D pose estimation. We feature markerless pose estimation as part of a decentralized multi-robot SLAM system and demonstrate the benefit to the relative localization accuracy among the robotic team. The solution is validated experimentally on data recorded in a test field campaign on a planetary analogous environment.

Problem

• multi-robot SLAM
• data association
• loop closure detection
• perceptual aliasing
• fiducial markers

Innovation

• markerless detection
• 6D pose estimation
• multi-robot SLAM
• deep learning
• relative localization