Initialization of Monocular Visual Navigation for Autonomous Agents Using Modified Structure from Small Motion

TL;DR

This paper introduces a monocular visual SLAM initialization method tailored for space robots, extending SfSM with a robust factor graph approach to handle challenging space inspection conditions.

Contribution

It presents a novel initialization pipeline that improves monocular visual navigation robustness in space environments, addressing issues like weak perspective, planar geometry, and dynamic lighting.

Findings

Effective in simulated satellite inspection scenarios

Outperforms existing monocular initialization methods

Handles challenging space environment conditions

Abstract

We propose a standalone monocular visual Simultaneous Localization and Mapping (vSLAM) initialization pipeline for autonomous space robots. Our method, a state-of-the-art factor graph optimization pipeline, extends Structure from Small Motion (SfSM) to robustly initialize a monocular agent in spacecraft inspection trajectories, addressing visual estimation challenges such as weak-perspective projection and center-pointing motion, which exacerbates the bas-relief ambiguity, dominant planar geometry, which causes motion estimation degeneracies in classical Structure from Motion, and dynamic illumination conditions, which reduce the survivability of visual information. We validate our approach on realistic, simulated satellite inspection image sequences with a tumbling spacecraft and demonstrate the method's effectiveness over existing monocular initialization procedures.