Using Lidar Intensity for Robot Navigation

TL;DR

This paper introduces Multi-Layer Intensity Maps derived from lidar data to improve robot perception and navigation, enabling differentiation of obstacle types and adaptive obstacle inflation for better navigation success.

Contribution

The paper presents a novel 3D object representation called Multi-Layer Intensity Map, enhancing obstacle differentiation and navigation in complex environments.

Findings

Significant increase in navigation success rates (>50%)

Up to 9.5% reduction in trajectory length

Up to 22.6% improvement in F-score

Abstract

We present Multi-Layer Intensity Map, a novel 3D object representation for robot perception and autonomous navigation. Intensity maps consist of multiple stacked layers of 2D grid maps each derived from reflected point cloud intensities corresponding to a certain height interval. The different layers of intensity maps can be used to simultaneously estimate obstacles' height, solidity/density, and opacity. We demonstrate that intensity maps' can help accurately differentiate obstacles that are safe to navigate through (e.g. beaded/string curtains, pliable tall grass), from ones that must be avoided (e.g. transparent surfaces such as glass walls, bushes, trees, etc.) in indoor and outdoor environments. Further, to handle narrow passages, and navigate through non-solid obstacles in dense environments, we propose an approach to adaptively inflate or enlarge the obstacles detected on intensity maps based on their solidity, and the robot's preferred velocity direction. We demonstrate these improved navigation capabilities in real-world narrow, dense environments using a real Turtlebot and Boston Dynamics Spot robots. We observe significant increases in success rates to more than 50%, up to a 9.5% decrease in normalized trajectory length, and up to a 22.6% increase in the F-score compared to current navigation methods using other sensor modalities.