Piggyback Camera: Easy-to-Deploy Visual Surveillance by Mobile Sensing on Commercial Robot Vacuums

TL;DR

Piggyback Camera offers an easy, hardware-modification-free visual surveillance system by mounting smartphones on commercial robot vacuums, utilizing neural inertial navigation and novel data augmentation for accurate localization and object mapping.

Contribution

The paper introduces a novel smartphone-based mounting system and a rotation-augmented ensemble method for improved neural inertial navigation in robot vacuums.

Findings

Achieves 0.83 m pose error in robot localization

Attains 0.97 m positional accuracy in object mapping

Demonstrates effectiveness in retail environment scenarios

Abstract

This paper presents Piggyback Camera, an easy-to-deploy system for visual surveillance using commercial robot vacuums. Rather than requiring access to internal robot systems, our approach mounts a smartphone equipped with a camera and Inertial Measurement Unit (IMU) on the robot, making it applicable to any commercial robot without hardware modifications. The system estimates robot poses through neural inertial navigation and efficiently captures images at regular spatial intervals throughout the cleaning task. We develop a novel test-time data augmentation method called Rotation-Augmented Ensemble (RAE) to mitigate domain gaps in neural inertial navigation. A loop closure method that exploits robot cleaning patterns further refines these estimated poses. We demonstrate the system with an object mapping application that analyzes captured images to geo-localize objects in the environment. Experimental evaluation in retail environments shows that our approach achieves 0.83 m relative pose error for robot localization and 0.97 m positional error for object mapping of over 100 items.