Pub Date : 2017-07-10DOI: 10.1109/ICAR.2017.8023493
M. Durner, Simon Kriegel, Sebastian Riedel, Manuel Brucker, Zoltán-Csaba Márton, Ferenc Bálint-Benczédi, Rudolph Triebel
As the performance of key perception tasks heavily depends on their parametrization, deploying versatile robots to different application domains will also require a way to tune these changing scenarios by their operators. As many of these tunings are found by trial and error basically by experts as well, and the quality criteria change from application to application, we propose a Pipeline Optimization Framework that helps overcoming lengthy setup times by largely automating this process. When deployed, fine-tuning optimizations as presented in this paper can be initiated on pre-recorded data, dry runs, or automatically during operation. Here, we quantified the performance gains for two crucial modules based on ground truth annotated data. We release our challenging THR dataset, including evaluation scenes for two application scenarios.
{"title":"Experience-based optimization of robotic perception","authors":"M. Durner, Simon Kriegel, Sebastian Riedel, Manuel Brucker, Zoltán-Csaba Márton, Ferenc Bálint-Benczédi, Rudolph Triebel","doi":"10.1109/ICAR.2017.8023493","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023493","url":null,"abstract":"As the performance of key perception tasks heavily depends on their parametrization, deploying versatile robots to different application domains will also require a way to tune these changing scenarios by their operators. As many of these tunings are found by trial and error basically by experts as well, and the quality criteria change from application to application, we propose a Pipeline Optimization Framework that helps overcoming lengthy setup times by largely automating this process. When deployed, fine-tuning optimizations as presented in this paper can be initiated on pre-recorded data, dry runs, or automatically during operation. Here, we quantified the performance gains for two crucial modules based on ground truth annotated data. We release our challenging THR dataset, including evaluation scenes for two application scenarios.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125579775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023625
Abeer Imdoukh, A. Shaker, Aya Al-Toukhy, Darin Kablaoui, Mohammed El-Abd
Fire is one of the critical problems that have not been solved yet despite the technological development. Human losses are the most important aspect related to fires. Since it may be impossible to prevent fire from occurring, it would be helpful to minimize its impact in terms of human losses. The fact that unmanned aerial vehicles (UAVs) can handle dangerous and risky tasks as well as their fast and efficient performance allows them to be used in fire related problems such as entering and exploring disastrous zones. Hence, an indoor fireproof unmanned aerial vehicle that enables searching for survivors and locating them in minimal time is developed. The UAV is designed such that it can fly while carrying a fire extinguisher. Cameras are mounted on the UAV such that the person in control of the UAV is able to view the environment. In this way, the safety of firemen is ensured, since they know exactly where to go.
{"title":"Semi-autonomous indoor firefighting UAV","authors":"Abeer Imdoukh, A. Shaker, Aya Al-Toukhy, Darin Kablaoui, Mohammed El-Abd","doi":"10.1109/ICAR.2017.8023625","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023625","url":null,"abstract":"Fire is one of the critical problems that have not been solved yet despite the technological development. Human losses are the most important aspect related to fires. Since it may be impossible to prevent fire from occurring, it would be helpful to minimize its impact in terms of human losses. The fact that unmanned aerial vehicles (UAVs) can handle dangerous and risky tasks as well as their fast and efficient performance allows them to be used in fire related problems such as entering and exploring disastrous zones. Hence, an indoor fireproof unmanned aerial vehicle that enables searching for survivors and locating them in minimal time is developed. The UAV is designed such that it can fly while carrying a fire extinguisher. Cameras are mounted on the UAV such that the person in control of the UAV is able to view the environment. In this way, the safety of firemen is ensured, since they know exactly where to go.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123698316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023650
Fatemah Taqi, Fatima Al-Langawi, H. Abdulraheem, Mohammed El-Abd
The harvesting robot is a robot that is created for harvesting cherry tomatoes in households and greenhouses. For households, the project aims to protect the privacy of people who have their own gardens at home, and do not prefer to have workers coming to their home gardens to harvest the fruits. In addition, the weather in Kuwait is very hot, which makes it difficult for harvesters to work for long periods of time. This creates a problem because if the gardener does not finish harvesting on time; the fruits become rotten causing wastage and loss. Therefore, using a harvesting robot provides an excellent solution for harvesting in such conditions. The developed robot picks out the cherry tomatoes that are ripe enough without causing any damage to the surroundings, and leaves the ones that are not ripe enough. Moreover, the robot identifies the ripe cherry tomatoes by image sensing using a camera. After that, the robot picks the ripe cherry tomato and places it in a basket. The robot repeats the previous steps until there are no cherry tomatoes left on the trees. The robot has additional features, such as picking the rotten cherry tomatoes and placing them in a separate basket. In this paper, we present the design and implementation of this harvesting robot.
{"title":"A cherry-tomato harvesting robot","authors":"Fatemah Taqi, Fatima Al-Langawi, H. Abdulraheem, Mohammed El-Abd","doi":"10.1109/ICAR.2017.8023650","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023650","url":null,"abstract":"The harvesting robot is a robot that is created for harvesting cherry tomatoes in households and greenhouses. For households, the project aims to protect the privacy of people who have their own gardens at home, and do not prefer to have workers coming to their home gardens to harvest the fruits. In addition, the weather in Kuwait is very hot, which makes it difficult for harvesters to work for long periods of time. This creates a problem because if the gardener does not finish harvesting on time; the fruits become rotten causing wastage and loss. Therefore, using a harvesting robot provides an excellent solution for harvesting in such conditions. The developed robot picks out the cherry tomatoes that are ripe enough without causing any damage to the surroundings, and leaves the ones that are not ripe enough. Moreover, the robot identifies the ripe cherry tomatoes by image sensing using a camera. After that, the robot picks the ripe cherry tomato and places it in a basket. The robot repeats the previous steps until there are no cherry tomatoes left on the trees. The robot has additional features, such as picking the rotten cherry tomatoes and placing them in a separate basket. In this paper, we present the design and implementation of this harvesting robot.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114143370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023503
A. W. Li, G. S. Bastos
The purpose of this paper is to present a hybrid method of a particle filter for localization in mobile robotics. The main references are the particle filter based on Kullback-Leibler divergence and a self-adaptive particle filter using grid-energy. Gains and drawbacks of each method are discussed and compared with the developed algorithm. This hybrid particle filter explores the best quality of each method and the final result brings a solution to the localization problem: position tracking, global localization and kidnapping in a deterministic environment. This work was developed using the ROS framework (Robot Operating System) and tested with a Pioneer 3DX robot in real and simulation environments.
{"title":"A hybrid self-adaptive particle filter through KLD-sampling and SAMCL","authors":"A. W. Li, G. S. Bastos","doi":"10.1109/ICAR.2017.8023503","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023503","url":null,"abstract":"The purpose of this paper is to present a hybrid method of a particle filter for localization in mobile robotics. The main references are the particle filter based on Kullback-Leibler divergence and a self-adaptive particle filter using grid-energy. Gains and drawbacks of each method are discussed and compared with the developed algorithm. This hybrid particle filter explores the best quality of each method and the final result brings a solution to the localization problem: position tracking, global localization and kidnapping in a deterministic environment. This work was developed using the ROS framework (Robot Operating System) and tested with a Pioneer 3DX robot in real and simulation environments.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131293892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023632
Z. Dong, X. Ye, Jiacai Hong, Zhiwei Liu, Fan Yang
In order to solve the problem of harsh operating condition of the space manipulator, and the problem of not being able to afford great collision Momentum, this paper proposes a new technical method, namely soft-contact technology. According to the proposed method, the dynamic model of space flexible manipulator is built up based on Kane's equations. Then this paper makes a comparison simulation between dynamic models designed by ADAMS using same dynamic parameters. Simulation show that the curves obtained by Kane's equations and ADAMS are basically the same, so the correctness of the dynamic model of the space flexible manipulator based on Kane's equation has been proved.
{"title":"Research on dynamic modeling of soft-contact technology based on Kane's equations","authors":"Z. Dong, X. Ye, Jiacai Hong, Zhiwei Liu, Fan Yang","doi":"10.1109/ICAR.2017.8023632","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023632","url":null,"abstract":"In order to solve the problem of harsh operating condition of the space manipulator, and the problem of not being able to afford great collision Momentum, this paper proposes a new technical method, namely soft-contact technology. According to the proposed method, the dynamic model of space flexible manipulator is built up based on Kane's equations. Then this paper makes a comparison simulation between dynamic models designed by ADAMS using same dynamic parameters. Simulation show that the curves obtained by Kane's equations and ADAMS are basically the same, so the correctness of the dynamic model of the space flexible manipulator based on Kane's equation has been proved.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130837500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023669
R. Raja, A. Dutta
This paper proposes a path planning method for a wheeled mobile robot operating in rough terrain dynamic environments using a combination of A∗ search algorithm and potential field method. In this method, the mobile robot uses the structured light system to extract real terrain data as a discrete points to generate a b-spline surface. The terrain is classified based on the slope and elevation using a fuzzy logic controller and a user defined cost function is generated. A combination of A∗ and potential field method has been introduced to find the path from the start location to goal location according to the cost function. The A∗ algorithm determines the path that globally optimizes terrain roughness, curvature and length of the path, and the potential field method has been used as a local planner which performs an on-line planning to avoid the newly detected obstacles by the sensory information. The developed potential function is found to be able to avoid local minima in the work space. The results shows the effectiveness of the proposed algorithm.
{"title":"Path planning in dynamic environment for a rover using A∗ and potential field method","authors":"R. Raja, A. Dutta","doi":"10.1109/ICAR.2017.8023669","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023669","url":null,"abstract":"This paper proposes a path planning method for a wheeled mobile robot operating in rough terrain dynamic environments using a combination of A∗ search algorithm and potential field method. In this method, the mobile robot uses the structured light system to extract real terrain data as a discrete points to generate a b-spline surface. The terrain is classified based on the slope and elevation using a fuzzy logic controller and a user defined cost function is generated. A combination of A∗ and potential field method has been introduced to find the path from the start location to goal location according to the cost function. The A∗ algorithm determines the path that globally optimizes terrain roughness, curvature and length of the path, and the potential field method has been used as a local planner which performs an on-line planning to avoid the newly detected obstacles by the sensory information. The developed potential function is found to be able to avoid local minima in the work space. The results shows the effectiveness of the proposed algorithm.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"52 18","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133655851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023664
Guang-ming Xiong, Hao Li, Y. Jin, Jian-wei Gong, Huiyan Chen
Although efforts have been done to solve collision avoidance using either environment recognition sensors or vehicle-to-vehicle (V2V) communication information, it is still a challenging problem in some specific scene, e.g. highway entrance ramp. In this paper, we propose a new cooperative adaptive cruise control (CACC) method which combines information of environment recognition sensors and V2V communication. A collision detection system of CACC will work based on the information of V2V communication before environment recognition sensors detecting obstacles accurately. Co-simulation experiment using PreScan and Simulink is conducted. The experimental results show that the intelligent vehicle with our method can pass the freeway entrance ramp more safely.
{"title":"Collision avoidance system with cooperative adaptive cruise control in highway entrance ramp environment","authors":"Guang-ming Xiong, Hao Li, Y. Jin, Jian-wei Gong, Huiyan Chen","doi":"10.1109/ICAR.2017.8023664","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023664","url":null,"abstract":"Although efforts have been done to solve collision avoidance using either environment recognition sensors or vehicle-to-vehicle (V2V) communication information, it is still a challenging problem in some specific scene, e.g. highway entrance ramp. In this paper, we propose a new cooperative adaptive cruise control (CACC) method which combines information of environment recognition sensors and V2V communication. A collision detection system of CACC will work based on the information of V2V communication before environment recognition sensors detecting obstacles accurately. Co-simulation experiment using PreScan and Simulink is conducted. The experimental results show that the intelligent vehicle with our method can pass the freeway entrance ramp more safely.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115267951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a new form of space system construction and space operation, cellular space robot has the advantages of standardization, reconfiguration and system flexibility. The system flexibility depends on the flexibility of the configuration of the cellular space robot. In order to accomplish different tasks, cellular space robot needs to change its configuration by self-reconfiguration. However, since the variety types of cells, heterogeneous self-configuration problem of the cellular space robot constitutes a formidable technical challenge. In the process of self-reconfiguration, frequent cell disassembly operations will waste time and might bring additional risks. To solve the above-mentioned problems, a reconfiguration algorithm for heterogeneous cellular space robot is proposed to reduce the times of cell disassembly operations. Firstly, all cells for reconfiguration are divided into different levels. Then the cells are moved to the corresponding level of the intermediate configuration. Finally, the cells in the intermediate configuration are reconstructed to form the target configuration. The applicability of this algorithm is proven. The amount of cell disassembly of this algorithm is O(n). 3D simulations validate that the algorithm can realize the self-reconfiguration of the cellular space robot.
{"title":"Reconfiguration planning for heterogeneous cellular space robot","authors":"Yifei Zhang, Panfeng Huang, Yizhai Zhang, Haitao Chang","doi":"10.1109/ICAR.2017.8023516","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023516","url":null,"abstract":"As a new form of space system construction and space operation, cellular space robot has the advantages of standardization, reconfiguration and system flexibility. The system flexibility depends on the flexibility of the configuration of the cellular space robot. In order to accomplish different tasks, cellular space robot needs to change its configuration by self-reconfiguration. However, since the variety types of cells, heterogeneous self-configuration problem of the cellular space robot constitutes a formidable technical challenge. In the process of self-reconfiguration, frequent cell disassembly operations will waste time and might bring additional risks. To solve the above-mentioned problems, a reconfiguration algorithm for heterogeneous cellular space robot is proposed to reduce the times of cell disassembly operations. Firstly, all cells for reconfiguration are divided into different levels. Then the cells are moved to the corresponding level of the intermediate configuration. Finally, the cells in the intermediate configuration are reconstructed to form the target configuration. The applicability of this algorithm is proven. The amount of cell disassembly of this algorithm is O(n). 3D simulations validate that the algorithm can realize the self-reconfiguration of the cellular space robot.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114069301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023518
C. S. Wieghardt, Bernardo Wagner
Rising automation requirements in manufacturing lead to an increasing demand for robot self-calibration. Self-calibration becomes a challenging task for mobile robots since the environment is dynamic, at least from the perspective of moving robots. This paper proposes a new self-calibration method by tracking the end-effector with the help of a head-mounted projector (see Fig. 1). Pseudorandom coded light is projected into the environment and single images are decoded. The pattern consists of checkerboard-like corner-primitives, which are detected by a camera-pair, mounted on the robot base. Triangulation yields the primitives' positions. The projector can be described as an inverse camera model, so its pose is determinable by taking the primitive points as reference. The extrinsic hand-projector and camera-robot transformations are given by the commonly known formula AX = ZB. Further optimization and the incorporation of the joint parameters allow the calibration of the manipulator. Self-calibration means that no sort of calibration object like a checkerboard is needed. Since the decoding is applied to single images, the environment is permitted to change, and the robot is allowed to move around freely during calibration. Experimental results of this method show a submillimeter accuracy of the proposed projector tracking as well as improvements of the robot's accuracy in its typical workspace.
{"title":"Self-calibration of a mobile manipulator using structured light","authors":"C. S. Wieghardt, Bernardo Wagner","doi":"10.1109/ICAR.2017.8023518","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023518","url":null,"abstract":"Rising automation requirements in manufacturing lead to an increasing demand for robot self-calibration. Self-calibration becomes a challenging task for mobile robots since the environment is dynamic, at least from the perspective of moving robots. This paper proposes a new self-calibration method by tracking the end-effector with the help of a head-mounted projector (see Fig. 1). Pseudorandom coded light is projected into the environment and single images are decoded. The pattern consists of checkerboard-like corner-primitives, which are detected by a camera-pair, mounted on the robot base. Triangulation yields the primitives' positions. The projector can be described as an inverse camera model, so its pose is determinable by taking the primitive points as reference. The extrinsic hand-projector and camera-robot transformations are given by the commonly known formula AX = ZB. Further optimization and the incorporation of the joint parameters allow the calibration of the manipulator. Self-calibration means that no sort of calibration object like a checkerboard is needed. Since the decoding is applied to single images, the environment is permitted to change, and the robot is allowed to move around freely during calibration. Experimental results of this method show a submillimeter accuracy of the proposed projector tracking as well as improvements of the robot's accuracy in its typical workspace.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130252029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023652
Ming Chen, Lujia Wang, Cheng-Zhong Xu, Renfa Li
Intelligent human robot interaction are becoming popular in both industry and academia. However, amongst current techniques, speech recognition is a challenging topic, including real-time translation with high accuracy, amicability and the support for recognizing minor languages or sophisticated dialects. In this paper, we propose a human-friendly prototype deployed on NAO robots in a real-life scenario through daily speech commands and NAO would act accordingly. We primarily adopt HMM-GMM, the combination of HMMs (Hidden Markov Models) and GMMs (Gaussian Mixtures Models). The experimental results show that the proposed prototype achieves high accuracy and well-received by experiment subjects.
{"title":"A novel approach of system design for dialect speech interaction with NAO robot","authors":"Ming Chen, Lujia Wang, Cheng-Zhong Xu, Renfa Li","doi":"10.1109/ICAR.2017.8023652","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023652","url":null,"abstract":"Intelligent human robot interaction are becoming popular in both industry and academia. However, amongst current techniques, speech recognition is a challenging topic, including real-time translation with high accuracy, amicability and the support for recognizing minor languages or sophisticated dialects. In this paper, we propose a human-friendly prototype deployed on NAO robots in a real-life scenario through daily speech commands and NAO would act accordingly. We primarily adopt HMM-GMM, the combination of HMMs (Hidden Markov Models) and GMMs (Gaussian Mixtures Models). The experimental results show that the proposed prototype achieves high accuracy and well-received by experiment subjects.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129281057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：