WareVR: Virtual Reality Interface for Supervision of Autonomous Robotic System Aimed at Warehouse Stocktaking

TL;DR

WareVR introduces a virtual reality interface enabling warehouse workers to remotely supervise and control heterogeneous robotic systems, including ground and aerial vehicles, for efficient inventory management during pandemic conditions.

Contribution

This paper presents a novel VR-based human-robot interface that allows non-expert users to supervise and control autonomous warehouse robots remotely, integrating digital twin visualization and real-time video streaming.

Findings

Effective remote supervision demonstrated in user study

Enhanced inspection capabilities via UAV teleoperation

Improved safety and efficiency in warehouse stocktaking

Abstract

WareVR is a novel human-robot interface based on a virtual reality (VR) application to interact with a heterogeneous robotic system for automated inventory management. We have created an interface to supervise an autonomous robot remotely from a secluded workstation in a warehouse that could benefit during the current pandemic COVID-19 since the stocktaking is a necessary and regular process in warehouses, which involves a group of people. The proposed interface allows regular warehouse workers without experience in robotics to control the heterogeneous robotic system consisting of an unmanned ground vehicle (UGV) and unmanned aerial vehicle (UAV). WareVR provides visualization of the robotic system in a digital twin of the warehouse, which is accompanied by a real-time video stream from the real environment through an on-board UAV camera. Using the WareVR interface, the operator can conduct different levels of stocktaking, monitor the inventory process remotely, and teleoperate the drone for a more detailed inspection. Besides, the developed interface includes remote control of the UAV for intuitive and straightforward human interaction with the autonomous robot for stocktaking. The effectiveness of the VR-based interface was evaluated through the user study in a "visual inspection" scenario.