Robo Cloud: augmenting robotic visions for open environment modeling using Internet knowledge

作     者：Yiying LI Huaimin WANG Bo DING Wei ZHOU 

作者机构：College of Computer National University of Defense Technology 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2018年第61卷第5期

页      面：19-34页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by National Natural Science Foundation of China (Grant Nos. 91118008, 61202117, 61772030) Special Program for the Applied Basic Research of National University of Defense Technology (Grant No. ZDYYJCYJ20140601) Jiangsu Future Networks Innovation Institute Prospective Research Project on Future Networks (Grant No. BY2013095-2-08) 

主　　题：Internet-augmented environment modeling uncertainty robotic visions semantic mapping robotic software cloud robotics 

摘      要：Modeling an open environment that contains unpredictable objects is a challenging problem in the field of robotics. In traditional approaches, when a robot encounters an unknown object, a mistake will inevitably be added to the robot’s environmental model, severely constraining the robot’s autonomy,and possibly leading to disastrous consequences in certain settings. The abundant knowledge accumulated on the Internet has the potential to remedy the uncertainties that result from encountering with unknown objects. However, robotic applications generally pay considerable attention to quality of service(Qo S).For this reason, directly accessing the Internet, which can be unpredictable, is generally not acceptable.Robo Cloud is proposed as a novel approach to environment modeling that takes advantage of the Internet without sacrificing the critical properties of Qo S. Robo Cloud is a mission cloud–public cloud layered cloud organization model in which the mission cloud provides Qo S-available environment modeling capability with built-in prior knowledge while the public cloud is the existing services provided by the Internet. The cloud phase transition mechanism seeks help from the public cloud only when a request is outside the knowledge of the mission cloud and the Qo S cost is acceptable. We have adopted semantic mapping, a typical robotic environment modeling task, to illustrate and substantiate our approach and key mechanism. Experiments using open 2 D and 3 D datasets with real robots have demonstrated that Robo Cloud is able to augment robotic visions for open environment modeling.