A Motion Planning Strategy for the Active Vision-Based Mapping of Ground-Level Structures

TL;DR

This paper introduces a motion planning strategy for ground robots with vision sensors to autonomously map 3D structures, focusing on accurate reconstruction without prior models, suitable for architecture and inspection tasks.

Contribution

It presents a novel, initialization-free motion planning algorithm that optimizes viewpoint selection for 3D mapping with integrated localization, outperforming traditional frontier-based methods.

Findings

Effective in mapping structures of moderate size

Compatible with vision-based localization without external systems

Validated through real-world experiments

Abstract

This paper presents a strategy to guide a mobile ground robot equipped with a camera or depth sensor, in order to autonomously map the visible part of a bounded three-dimensional structure. We describe motion planning algorithms that determine appropriate successive viewpoints and attempt to fill holes automatically in a point cloud produced by the sensing and perception layer. The emphasis is on accurately reconstructing a 3D model of a structure of moderate size rather than mapping large open environments, with applications for example in architecture, construction and inspection. The proposed algorithms do not require any initialization in the form of a mesh model or a bounding box, and the paths generated are well adapted to situations where the vision sensor is used simultaneously for mapping and for localizing the robot, in the absence of additional absolute positioning system. We analyze the coverage properties of our policy, and compare its performance to the classic frontier based exploration algorithm. We illustrate its efficacy for different structure sizes, levels of localization accuracy and range of the depth sensor, and validate our design on a real-world experiment.