Multi-Resolution 3D Mapping with Explicit Free Space Representation for Fast and Accurate Mobile Robot Motion Planning

TL;DR

This paper presents an efficient multi-resolution 3D mapping system using adaptive octree structures and explicit free space representation, enabling fast and accurate robot motion planning.

Contribution

It introduces a real-time multi-scale resolution selection method and a free space mapping approach that enhances planning speed and accuracy over existing methods.

Findings

Improved mapping accuracy and memory efficiency.

Faster collision queries for robot planning.

Enhanced performance in high-resolution mapping scenarios.

Abstract

With the aim of bridging the gap between high quality reconstruction and mobile robot motion planning, we propose an efficient system that leverages the concept of adaptive-resolution volumetric mapping, which naturally integrates with the hierarchical decomposition of space in an octree data structure. Instead of a Truncated Signed Distance Function (TSDF), we adopt mapping of occupancy probabilities in log-odds representation, which allows to represent both surfaces, as well as the entire free, i.e. observed space, as opposed to unobserved space. We introduce a method for choosing resolution -- on the fly -- in real-time by means of a multi-scale max-min pooling of the input depth image. The notion of explicit free space mapping paired with the spatial hierarchy in the data structure, as well as map resolution, allows for collision queries, as needed for robot motion planning, at unprecedented speed. We quantitatively evaluate mapping accuracy, memory, runtime performance, and planning performance showing improvements over the state of the art, particularly in cases requiring high resolution maps.