首页|Studies from Shandong University Add New Findings in the Area of Robotics (An Ac tive Task Cognition Method for Home Service Robot Using Multi-graph Attention Fu sion Mechanism)
Studies from Shandong University Add New Findings in the Area of Robotics (An Ac tive Task Cognition Method for Home Service Robot Using Multi-graph Attention Fu sion Mechanism)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on Robotics is now availab le. According to news reporting originating from Jinan, People’s Republic of Chi na, by NewsRx correspondents, research stated, “Active Task Cognition (ATC) requ ires the robot to comprehend the current scene using the image within the field of view, enabling them to reason about appropriate and executable tasks, thus al lowing the robot to achieve service task scene discovery capability similar to h umans. This capability is paramount for robots to provide comfort and intelligen t service while performing their tasks.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news editors obtained a quote from the research from Shandong University, “T o enhance home service robots’ ATC capability, a multi-graph fusion mechanism ba sed on Graph Attention Network (GAT) is proposed in this paper to model the sema ntic feature related to the task. First, a multi-graph fusion encoder is propose d to maximally capture the integrated features of objects, tasks, and scenes fro m the images, thereby obtaining a semantic representation related to the home se rvice task from the robot’s perspective. Next, to enhance the interpretability o f the model, we propose a multi-task scene understanding decoder based on the at tention mechanism to utilize the integration features of multi-graph fusion effi ciently. Lastly, we present a loss function for multi-task scene understanding i n the proposed Encoder-Decoder network model for scene comprehension. Furthermor e, a new dataset comprising various daily household tasks is constructed in the experiments.”
JinanPeople’s Republic of ChinaAsiaEmerging TechnologiesMachine LearningNano-robotRobotRoboticsShandong University
NETL
NSTL
