{"title":"Human robot interaction for agricultural Tele-Operation, using virtual Reality: A feasibility study","authors":"Daniel Udekwe, Hasan Seyyedhasani","doi":"10.1016/j.compag.2024.109702","DOIUrl":null,"url":null,"abstract":"<div><div>With the increasing demand for efficient and sustainable agricultural practices, the automation of tasks such as crop inspection and harvesting has become a critical endeavor. However, the complex and dynamic nature of agricultural environments poses challenges for conventional methods that are fully autonomous or those relying on traditional interfaces. To address these challenges, we propose a solution that leverages the capabilities of Virtual Reality (VR) to provide operators with an intuitive and immersive control experience. This paper introduces a novel method for tele-operating a robotic system in agriculture using VR technology. By integrating a VR device with SteamVR and Unity 3D, users can control a mobile robotic module over a local network or the internet using VR hand controllers and a headset. In order to validates the system feasibility, we case studied two agricultural operations in lab settings: leaf inspection and crop harvesting.</div><div>The results of this study were evaluated based on the cycle completion time (CCT) and the success rate of robot-plant interaction (RPI). For fruit harvesting, with a sample size (N) = 5, the mean CCT was approximately 18 s, with a standard deviation of nearly 5 s, indicating an improvement compared to existing autonomous systems in the literature. Additionally, in the leaf inspections, the mean CCT resulted in approximately 26 s with the standard deviation of nearly 6 s with the same sample size. The RPI success rate reached up to 90 % in the fruit harvesting practices. And in leaf inspection practices, this metric averaged two attempts per diseased leaf, 50 %, to grasp it and bring it to the operator’s attention. Through this study, the combination of consumer-grade VR technologies with a mobile robotic manipulation system highlights the system’s promise in improving remote agricultural tasks, especially in response to labor scarcity and improving farmworker efficiency.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"228 ","pages":"Article 109702"},"PeriodicalIF":7.7000,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers and Electronics in Agriculture","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0168169924010937","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
With the increasing demand for efficient and sustainable agricultural practices, the automation of tasks such as crop inspection and harvesting has become a critical endeavor. However, the complex and dynamic nature of agricultural environments poses challenges for conventional methods that are fully autonomous or those relying on traditional interfaces. To address these challenges, we propose a solution that leverages the capabilities of Virtual Reality (VR) to provide operators with an intuitive and immersive control experience. This paper introduces a novel method for tele-operating a robotic system in agriculture using VR technology. By integrating a VR device with SteamVR and Unity 3D, users can control a mobile robotic module over a local network or the internet using VR hand controllers and a headset. In order to validates the system feasibility, we case studied two agricultural operations in lab settings: leaf inspection and crop harvesting.
The results of this study were evaluated based on the cycle completion time (CCT) and the success rate of robot-plant interaction (RPI). For fruit harvesting, with a sample size (N) = 5, the mean CCT was approximately 18 s, with a standard deviation of nearly 5 s, indicating an improvement compared to existing autonomous systems in the literature. Additionally, in the leaf inspections, the mean CCT resulted in approximately 26 s with the standard deviation of nearly 6 s with the same sample size. The RPI success rate reached up to 90 % in the fruit harvesting practices. And in leaf inspection practices, this metric averaged two attempts per diseased leaf, 50 %, to grasp it and bring it to the operator’s attention. Through this study, the combination of consumer-grade VR technologies with a mobile robotic manipulation system highlights the system’s promise in improving remote agricultural tasks, especially in response to labor scarcity and improving farmworker efficiency.
期刊介绍:
Computers and Electronics in Agriculture provides international coverage of advancements in computer hardware, software, electronic instrumentation, and control systems applied to agricultural challenges. Encompassing agronomy, horticulture, forestry, aquaculture, and animal farming, the journal publishes original papers, reviews, and applications notes. It explores the use of computers and electronics in plant or animal agricultural production, covering topics like agricultural soils, water, pests, controlled environments, and waste. The scope extends to on-farm post-harvest operations and relevant technologies, including artificial intelligence, sensors, machine vision, robotics, networking, and simulation modeling. Its companion journal, Smart Agricultural Technology, continues the focus on smart applications in production agriculture.