arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.00443cs.RO
收藏

虚拟竞赛测试平台的测试框架

Test Framework for a Virtual Competition Testbed

Heriot-Watt University(赫瑞-瓦特大学);University of Edinburgh(爱丁堡大学)

Liam Wellacott, Emilyann Nault, Ioannis Skottis, Alexandre Colle, Shreyank N Gowda, Pierre Nicolay, Emily Rolley-Parnell

摘要:

虚拟环境已被用于机器人研究,作为在现场部署系统之前评估系统的工具。COVID-19大流行为虚拟基准的开发带来了额外的动力,以帮助安全和富有成效的发展。现场机器人竞赛也已停止,从而限制了学生和研究人员的机会范围。我们实现了一个服务机器人比赛的结构到一个可扩展的和适应性强的虚拟评分环境。比赛通过展示机器人完成的现实家庭任务来挑战家庭服务机器人的最新技术。虚拟环境为竞赛团队提供了一个基础,以便在无法访问物理环境时评估其系统。我们相信,利用虚拟环境作为评估手段将带来其他好处,如增加访问和推广。

英文摘要:

Virtual environments have been utilised in robotics research as a tool to assess systems before deploying them in the field. The COVID-19 pandemic has brought about additional motivation for the development of virtual benchmarks in order to aid in safe and productive development. In-person robotics competitions have also halted, thus limiting the scope of opportunities for students and researchers. We implemented the structure of a service robotics competition into an extendable and adaptable virtual scoring environment. The competition challenges the state of the art in home service robotics by presenting realistic household tasks for robots to complete. The virtual environment provides a foundation for competition teams to assess their systems when accessing the physical environment is not possible. We believe that utilising virtual environments as a means of assessment will lead to other benefits such as increased access and generalisation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑