Keila Lima, Eduardo R. B. Marques, J. Pinto, J. Sousa
{"title":"使用海豚编程网络车辆系统- REP'17现场测试","authors":"Keila Lima, Eduardo R. B. Marques, J. Pinto, J. Sousa","doi":"10.1109/OCEANSKOBE.2018.8559474","DOIUrl":null,"url":null,"abstract":"The increasing availability and use of autonomous vehicles for real operational scenarios has led to the need for tools that allow human operators to interact with multiple systems effectively, taking into account their capabilities, limitations and environmental constraints. Multiple vehicles, deployed together in order to accomplish a common goal, impose a high burden on a human operator for specifying and executing coordinated behavior, particularly in mixed-initiative systems where humans are part of the control loop. In this paper, we describe experimental field tests for Dolphin, a domain-specific language that allows a single program to define the joint behaviour of multiple vehicles over a network. Using the language, it is possible to accomplish an orchestrated execution of single-vehicle tasks according to several patterns such as sequential, concurrent, or event-based program flow. With this aim, Dolphin has been integrated modularly with a software toolchain for autonomous vehicles developed by Laboratório de Sistemas e Tecnologia Subaquática (LSTS). The tests we describe made use of LSTS unmanned underwater vehicles (UUVs) at open sea during the 2017 edition of Rapid Environment Picture (REP), an annual exercise jointly organised by LSTS and the Portuguese Navy.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Programming Networked Vehicle Systems Using Dolphin - Field Tests at REP'17\",\"authors\":\"Keila Lima, Eduardo R. B. Marques, J. Pinto, J. Sousa\",\"doi\":\"10.1109/OCEANSKOBE.2018.8559474\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The increasing availability and use of autonomous vehicles for real operational scenarios has led to the need for tools that allow human operators to interact with multiple systems effectively, taking into account their capabilities, limitations and environmental constraints. Multiple vehicles, deployed together in order to accomplish a common goal, impose a high burden on a human operator for specifying and executing coordinated behavior, particularly in mixed-initiative systems where humans are part of the control loop. In this paper, we describe experimental field tests for Dolphin, a domain-specific language that allows a single program to define the joint behaviour of multiple vehicles over a network. Using the language, it is possible to accomplish an orchestrated execution of single-vehicle tasks according to several patterns such as sequential, concurrent, or event-based program flow. With this aim, Dolphin has been integrated modularly with a software toolchain for autonomous vehicles developed by Laboratório de Sistemas e Tecnologia Subaquática (LSTS). The tests we describe made use of LSTS unmanned underwater vehicles (UUVs) at open sea during the 2017 edition of Rapid Environment Picture (REP), an annual exercise jointly organised by LSTS and the Portuguese Navy.\",\"PeriodicalId\":441405,\"journal\":{\"name\":\"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)\",\"volume\":\"2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-05-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/OCEANSKOBE.2018.8559474\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/OCEANSKOBE.2018.8559474","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
摘要
在实际操作场景中,自动驾驶汽车的可用性和使用越来越多,这导致了对工具的需求,使人类操作员能够有效地与多个系统进行交互,同时考虑到它们的能力、局限性和环境约束。为了实现一个共同的目标而部署在一起的多辆汽车,在指定和执行协调行为方面给人类操作员带来了很高的负担,特别是在混合主动系统中,人类是控制回路的一部分。在本文中,我们描述了Dolphin的实验现场测试,Dolphin是一种特定于领域的语言,允许单个程序定义网络上多个车辆的联合行为。使用该语言,可以根据顺序、并发或基于事件的程序流等多种模式,完成单车辆任务的编排执行。为此,Dolphin与Laboratório de Sistemas e tecologia Subaquática (LSTS)开发的自动驾驶汽车软件工具链进行了模块化集成。我们描述的测试是在2017年版快速环境图片(REP)期间在公海使用LSTS无人水下航行器(uuv)进行的,这是由LSTS和葡萄牙海军联合组织的年度演习。
Programming Networked Vehicle Systems Using Dolphin - Field Tests at REP'17
The increasing availability and use of autonomous vehicles for real operational scenarios has led to the need for tools that allow human operators to interact with multiple systems effectively, taking into account their capabilities, limitations and environmental constraints. Multiple vehicles, deployed together in order to accomplish a common goal, impose a high burden on a human operator for specifying and executing coordinated behavior, particularly in mixed-initiative systems where humans are part of the control loop. In this paper, we describe experimental field tests for Dolphin, a domain-specific language that allows a single program to define the joint behaviour of multiple vehicles over a network. Using the language, it is possible to accomplish an orchestrated execution of single-vehicle tasks according to several patterns such as sequential, concurrent, or event-based program flow. With this aim, Dolphin has been integrated modularly with a software toolchain for autonomous vehicles developed by Laboratório de Sistemas e Tecnologia Subaquática (LSTS). The tests we describe made use of LSTS unmanned underwater vehicles (UUVs) at open sea during the 2017 edition of Rapid Environment Picture (REP), an annual exercise jointly organised by LSTS and the Portuguese Navy.