EAGER: Reflection and Diffraction Sound Signals for Non-Field-of-View Target Estimation

EAGER：用于非视场目标估计的反射和衍射声音信号

• 批准号: 1554961
• 负责人: Tomonari Furukawa
• 金额: $ 16.53万
• 依托单位: Virginia Polytechnic Institute and State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-01 至 2017-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1554961&HistoricalAwards=false
• 关键词: EAGER; Reflection; Diffraction; Sound; Signals

This project studies the diffraction and reflection signals in sound source localization. The study could enable the capability of tracking and localizing human partners outside of the robots' Field-Of-View (FOV) to the co-robots for human-robot interaction. The project estimates an object outside of FOV using auditory sensors and enhances perception capabilities of robots. The project integrates research and education by training graduate and undergraduate students and outreach local K-12 students.This research proves the early-stage concept of the project that estimates the location of a Non-FOV (NFOV) target by learning from humans and utilizing the physics of sound wave propagation associated with the NFOV target. The research is to introduce the capability of localizing human partners outside of the robots' FOV to the co-robots for Human-Robot Interaction. The research team approaches the problem by deterministically formulating first-arrival diffraction and reflection signals and identifying signal directions. The project develops an approach that auditorily estimates the location of an NFOV target by learning from humans and utilizing the physics of sound wave propagation associated with the NFOV target. The project further evaluates the approach in unknown indoor environments by using both visual and auditory sensors.

该项目研究声源定位中的衍射和反射信号。该研究可以使协作机器人能够跟踪和定位机器人视野（FOV）之外的人类伙伴，以实现人机交互。 该项目使用听觉传感器估计视场之外的物体，并增强机器人的感知能力。该项目通过培训研究生和本科生以及推广当地 K-12 学生，将研究和教育融为一体。这项研究证明了该项目的早期概念，即通过向人类学习并利用与 NFOV 目标相关的声波传播物理学来估计非 FOV (NFOV) 目标的位置。该研究旨在向协作机器人引入在机器人视野之外定位人类伙伴的能力，以实现人机交互。研究团队通过确定性地制定初至衍射和反射信号并识别信号方向来解决该问题。该项目开发了一种方法，通过向人类学习并利用与 NFOV 目标相关的声波传播物理学，以听觉方式估计 NFOV 目标的位置。该项目通过使用视觉和听觉传感器进一步评估未知室内环境中的方法。