LIVE: Lidar Informed Visual Search for Multiple Objects with Multiple Robots

TL;DR

This paper presents LIVE, a multi-robot system integrating Lidar and visual detection for efficient multi-object search in indoor environments, with real-world experiments demonstrating its effectiveness.

Contribution

It introduces a novel perception module using Lidar to identify regions for visual inspection and employs Lidar-based coverage path planning for multi-robot coordination.

Findings

Successful real-world multi-robot experiments in indoor settings

Effective detection of multiple objects using combined Lidar and visual methods

Demonstrated efficiency improvements in search planning

Abstract

This paper introduces LIVE: Lidar Informed Visual Search focused on the problem of multi-robot (MR) planning and execution for robust visual detection of multiple objects. We perform extensive real-world experiments with a two-robot team in an indoor apartment setting. LIVE acts as a perception module that detects unmapped obstacles, or Short Term Features (STFs), in Lidar observations. STFs are filtered, resulting in regions to be visually inspected by modifying plans online. Lidar Coverage Path Planning (CPP) is employed for generating highly efficient global plans for heterogeneous robot teams. Finally, we present a data model and a demonstration dataset, which can be found by visiting our project website https://sites.google.com/view/live-iros2023/home.