Che-Wen Chen, Shih-Pang Tseng, Yao-Tsung Hsu, Jhing-Fa Wang
{"title":"智能家居机器人可分全向移动系统人机跟随的设计与实现","authors":"Che-Wen Chen, Shih-Pang Tseng, Yao-Tsung Hsu, Jhing-Fa Wang","doi":"10.1109/ICOT.2017.8336124","DOIUrl":null,"url":null,"abstract":"The paper implements an omnidirectional mobile system that applies to home robots with functions including follow the user, come to the user and path obstacle avoidance. The mobile system can be independently separated or combined with the home robot. In the separation state, the independent mobile system can be remotely control, or switch to make it automatically go forward and avoid obstacles in the path. In the combined state, the mobile system can remotely pull the home robot which weight more than 30 kilograms. In addition, the mobile system can follow or come to the user through the user position information and the results of gesture recognition via Bluetooth from the depth camera Kinect. The gesture recognition allows the robot to receive the message from the user even when speech recognition fails (for example, noisy environment), which improves the usability of user tracking function in actual field. The mobile system uses single-chip control that is specializes in executing specific tasks, while with the delay time sharing reception design, four subsystems can quickly switch their control using Bluetooth and RF 2.4G wireless transmission, therefore achieve a certain degree of multitasking ability. On the other hand, the omnidirectional wheel used by the power subsystem can help the robot to do translation and spin movement that is difficult for the traditional two-wheeled robot. Among them, the translation movement allow the robot to avoid obstacle in the path faster and more flexible, while the spin movement allow the robot to lock user with large angle rotation when user is turning around in a short time, so that the target can always be located within the sight of Kinect camera. Finally, the paper design various experiments in the simulated home environment to verify the mobile system design, including path obstacle avoidance, follow the user and come to the user, and the results show that the mobile system have good performance in home environmental conditions.","PeriodicalId":297245,"journal":{"name":"2017 International Conference on Orange Technologies (ICOT)","volume":"15 3","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Design and implementation of human following for separable omnidirectional mobile system of smart home robot\",\"authors\":\"Che-Wen Chen, Shih-Pang Tseng, Yao-Tsung Hsu, Jhing-Fa Wang\",\"doi\":\"10.1109/ICOT.2017.8336124\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper implements an omnidirectional mobile system that applies to home robots with functions including follow the user, come to the user and path obstacle avoidance. The mobile system can be independently separated or combined with the home robot. In the separation state, the independent mobile system can be remotely control, or switch to make it automatically go forward and avoid obstacles in the path. In the combined state, the mobile system can remotely pull the home robot which weight more than 30 kilograms. In addition, the mobile system can follow or come to the user through the user position information and the results of gesture recognition via Bluetooth from the depth camera Kinect. The gesture recognition allows the robot to receive the message from the user even when speech recognition fails (for example, noisy environment), which improves the usability of user tracking function in actual field. The mobile system uses single-chip control that is specializes in executing specific tasks, while with the delay time sharing reception design, four subsystems can quickly switch their control using Bluetooth and RF 2.4G wireless transmission, therefore achieve a certain degree of multitasking ability. On the other hand, the omnidirectional wheel used by the power subsystem can help the robot to do translation and spin movement that is difficult for the traditional two-wheeled robot. Among them, the translation movement allow the robot to avoid obstacle in the path faster and more flexible, while the spin movement allow the robot to lock user with large angle rotation when user is turning around in a short time, so that the target can always be located within the sight of Kinect camera. Finally, the paper design various experiments in the simulated home environment to verify the mobile system design, including path obstacle avoidance, follow the user and come to the user, and the results show that the mobile system have good performance in home environmental conditions.\",\"PeriodicalId\":297245,\"journal\":{\"name\":\"2017 International Conference on Orange Technologies (ICOT)\",\"volume\":\"15 3\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 International Conference on Orange Technologies (ICOT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICOT.2017.8336124\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Orange Technologies (ICOT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOT.2017.8336124","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Design and implementation of human following for separable omnidirectional mobile system of smart home robot
The paper implements an omnidirectional mobile system that applies to home robots with functions including follow the user, come to the user and path obstacle avoidance. The mobile system can be independently separated or combined with the home robot. In the separation state, the independent mobile system can be remotely control, or switch to make it automatically go forward and avoid obstacles in the path. In the combined state, the mobile system can remotely pull the home robot which weight more than 30 kilograms. In addition, the mobile system can follow or come to the user through the user position information and the results of gesture recognition via Bluetooth from the depth camera Kinect. The gesture recognition allows the robot to receive the message from the user even when speech recognition fails (for example, noisy environment), which improves the usability of user tracking function in actual field. The mobile system uses single-chip control that is specializes in executing specific tasks, while with the delay time sharing reception design, four subsystems can quickly switch their control using Bluetooth and RF 2.4G wireless transmission, therefore achieve a certain degree of multitasking ability. On the other hand, the omnidirectional wheel used by the power subsystem can help the robot to do translation and spin movement that is difficult for the traditional two-wheeled robot. Among them, the translation movement allow the robot to avoid obstacle in the path faster and more flexible, while the spin movement allow the robot to lock user with large angle rotation when user is turning around in a short time, so that the target can always be located within the sight of Kinect camera. Finally, the paper design various experiments in the simulated home environment to verify the mobile system design, including path obstacle avoidance, follow the user and come to the user, and the results show that the mobile system have good performance in home environmental conditions.