COSM2IC: Optimizing real-time multi-modal instruction comprehension

• Main Authors: WEERAKOON MUDIYANSELAGE DULANGA KAVEESHA WEERAKOON, SUBBARAJU, Vigneshwaran, TRAN, Minh Anh Tuan, MISRA, Archan
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2022
• 主題: Deep Learning for Visual Perception; Data Sets for Robotic Vision; Embedded Systems for Robotic andAutomation; Human-Robot Collaboration; RGB-D Perception; Artificial Intelligence and Robotics; Databases and Information Systems
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/7618; https://ink.library.smu.edu.sg/context/sis_research/article/8621/viewcontent/iros_final.pdf

Supporting real-time, on-device execution of multi-modal referring instruction comprehension models is an important challenge to be tackled in embodied Human-Robot Interaction. However, state-of-the-art deep learning models are resource-intensive and unsuitable for real-time execution on embedded de...