Pub Date : 2019-05-20DOI: 10.1109/ICRA.2019.8794071
P. Long, Tarik Kelestemur, Aykut Özgün Önol, T. Padır
This paper presents a new method of maximizing the free space for a robot operating in a constrained environment under operator supervision. The objective is to make the resulting trajectories more robust to operator commands and/or changes in the environment. To represent the volume of free space, the constrained manipulability polytopes are used. These polytopes embed the distance to obstacles, the distance to joint limits and the distance to singular configurations. The volume of the resulting Cartesian polyhedron is used in an optimization-based motion planner to create the trajectories. Additionally, we show how fast collision-free inverse kinematic solutions can be obtained by exploiting the pre-computed inequality constraints. The proposed algorithm is validated in simulation and experimentally.
{"title":"optimization-Based Human-in-the-Loop Manipulation Using Joint Space Polytopes","authors":"P. Long, Tarik Kelestemur, Aykut Özgün Önol, T. Padır","doi":"10.1109/ICRA.2019.8794071","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8794071","url":null,"abstract":"This paper presents a new method of maximizing the free space for a robot operating in a constrained environment under operator supervision. The objective is to make the resulting trajectories more robust to operator commands and/or changes in the environment. To represent the volume of free space, the constrained manipulability polytopes are used. These polytopes embed the distance to obstacles, the distance to joint limits and the distance to singular configurations. The volume of the resulting Cartesian polyhedron is used in an optimization-based motion planner to create the trajectories. Additionally, we show how fast collision-free inverse kinematic solutions can be obtained by exploiting the pre-computed inequality constraints. The proposed algorithm is validated in simulation and experimentally.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"20 1","pages":"204-210"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86907130","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8793737
J. Tiemann, Yehya Elmasry, Lucas Koring, C. Wietfeld
The ever increasing need for precise location estimation in robotics is challenging a significant amount of research. Hence, new applications such as wireless localization based aerial robot control or high precision personal safety tracking are developed. However, most of the current developments and research solely focus on the accuracy of the required localization systems. Multi-user scalability, energy efficiency and real-time capabilities are often neglected. This work aims to overcome the technology barrier by providing scalable, high accuracy, real-time localization through energy-efficient, scheduled time-difference of arrival channel access. We could show that simultaneous processing and provisioning of more than a thousand localization results per second with high reliability is possible using the proposed approach. To enable wide-spread adoption, we provide an open source implementation of our system for the robot operating system (ROS). Furthermore, we provide open source access to the raw data created during our evaluation.
{"title":"ATLAS FaST: Fast and Simple Scheduled TDOA for Reliable Ultra-Wideband Localization","authors":"J. Tiemann, Yehya Elmasry, Lucas Koring, C. Wietfeld","doi":"10.1109/ICRA.2019.8793737","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8793737","url":null,"abstract":"The ever increasing need for precise location estimation in robotics is challenging a significant amount of research. Hence, new applications such as wireless localization based aerial robot control or high precision personal safety tracking are developed. However, most of the current developments and research solely focus on the accuracy of the required localization systems. Multi-user scalability, energy efficiency and real-time capabilities are often neglected. This work aims to overcome the technology barrier by providing scalable, high accuracy, real-time localization through energy-efficient, scheduled time-difference of arrival channel access. We could show that simultaneous processing and provisioning of more than a thousand localization results per second with high reliability is possible using the proposed approach. To enable wide-spread adoption, we provide an open source implementation of our system for the robot operating system (ROS). Furthermore, we provide open source access to the raw data created during our evaluation.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"51 1","pages":"2554-2560"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90881867","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8793497
Julius Kümmerle, Marc Sons, Fabian Poggenhans, T. Kühner, M. Lauer, C. Stiller
Highly accurate localization with very limited amount of memory and computational power is one of the big challenges for next generation series cars. We propose localization based on geometric primitives which are compact in representation and further valuable for other tasks like planning and behavior generation. The primitives lack distinctive signature which makes association between detections and map elements highly ambiguous. We resolve ambiguities early in the pipeline by online building up a local map which is key to runtime efficiency. Further, we introduce a new framework to fuse association and odometry measurements based on robust pose graph optimization.We evaluate our localization framework on over 30 min of data recorded in urban scenarios. Our map is memory efficient with less than 8 kB/km and we achieve high localization accuracy with a mean position error of less than 10 cm and a mean yaw angle error of less than 0. 25° at a localization update rate of 50Hz.
{"title":"Accurate and Efficient Self-Localization on Roads using Basic Geometric Primitives","authors":"Julius Kümmerle, Marc Sons, Fabian Poggenhans, T. Kühner, M. Lauer, C. Stiller","doi":"10.1109/ICRA.2019.8793497","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8793497","url":null,"abstract":"Highly accurate localization with very limited amount of memory and computational power is one of the big challenges for next generation series cars. We propose localization based on geometric primitives which are compact in representation and further valuable for other tasks like planning and behavior generation. The primitives lack distinctive signature which makes association between detections and map elements highly ambiguous. We resolve ambiguities early in the pipeline by online building up a local map which is key to runtime efficiency. Further, we introduce a new framework to fuse association and odometry measurements based on robust pose graph optimization.We evaluate our localization framework on over 30 min of data recorded in urban scenarios. Our map is memory efficient with less than 8 kB/km and we achieve high localization accuracy with a mean position error of less than 10 cm and a mean yaw angle error of less than 0. 25° at a localization update rate of 50Hz.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"127 1","pages":"5965-5971"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82635569","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8794420
Xinghong Huang, Zhuang Dai, Weinan Chen, Li He, Hong Zhang
Motivated by the need to improve the performance of visual loop closure verification via multi-view geometry (MVG) under significant illumination and viewpoint changes, we propose a keypoint matching method that uses landmarks as an intermediate image representation in order to leverage the power of deep learning. In environments with various changes, the traditional verification method via MVG may encounter difficulty because of their inability to generate a sufficient number of correctly matched keypoints. Our method exploits the excellent invariance properties of convolutional neural network (ConvNet) features, which have shown outstanding performance for matching landmarks between images. By generating and matching landmarks first in the images and then matching the keypoints within the matched landmark pairs, we can significantly improve the quality of matched keypoints in terms of precision and recall measures. The proposed method is validated on challenging datasets that involve significant illumination and viewpoint changes, to establish its superior performance to the standard keypoint matching method.
{"title":"Improving Keypoint Matching Using a Landmark-Based Image Representation","authors":"Xinghong Huang, Zhuang Dai, Weinan Chen, Li He, Hong Zhang","doi":"10.1109/ICRA.2019.8794420","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8794420","url":null,"abstract":"Motivated by the need to improve the performance of visual loop closure verification via multi-view geometry (MVG) under significant illumination and viewpoint changes, we propose a keypoint matching method that uses landmarks as an intermediate image representation in order to leverage the power of deep learning. In environments with various changes, the traditional verification method via MVG may encounter difficulty because of their inability to generate a sufficient number of correctly matched keypoints. Our method exploits the excellent invariance properties of convolutional neural network (ConvNet) features, which have shown outstanding performance for matching landmarks between images. By generating and matching landmarks first in the images and then matching the keypoints within the matched landmark pairs, we can significantly improve the quality of matched keypoints in terms of precision and recall measures. The proposed method is validated on challenging datasets that involve significant illumination and viewpoint changes, to establish its superior performance to the standard keypoint matching method.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"15 1","pages":"1281-1287"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90468246","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8793824
Philipp S. Schmitt, Florian Wirnshofer, Kai M. Wurm, Georg von Wichert, Wolfram Burgard
In this paper we propose a new model for sequential manipulation tasks that also considers robot dynamics and time-variant environments. From this model we automatically derive constraint-based controllers and use them as steering functions in a kinodynamic manipulation planner. The resulting plan is not a trajectory but a sequence of controllers that react online to disturbances. We validated our approach in simulation and on a real robot. In the experiments our approach plans and executes dual-robot manipulation tasks with online collision avoidance and reactions to estimates of object poses.
{"title":"Modeling and Planning Manipulation in Dynamic Environments","authors":"Philipp S. Schmitt, Florian Wirnshofer, Kai M. Wurm, Georg von Wichert, Wolfram Burgard","doi":"10.1109/ICRA.2019.8793824","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8793824","url":null,"abstract":"In this paper we propose a new model for sequential manipulation tasks that also considers robot dynamics and time-variant environments. From this model we automatically derive constraint-based controllers and use them as steering functions in a kinodynamic manipulation planner. The resulting plan is not a trajectory but a sequence of controllers that react online to disturbances. We validated our approach in simulation and on a real robot. In the experiments our approach plans and executes dual-robot manipulation tasks with online collision avoidance and reactions to estimates of object poses.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"32 1","pages":"176-182"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91502476","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8793876
P. Bhatt, P. Rajendran, K. Mckay, Satyandra K. Gupta
Currently, automatically generated trajectories cannot be directly used on tasks that require high execution accuracies due to errors accused by inaccuracies in the robot model, actuator errors, and controller limitations. These trajectories often need manual refinement. This is not economically viable on low production volume applications. Unfortunately, execution errors are dependent on the nature of the trajectory and end-effector loads, and therefore devising a general purpose automated compensation scheme for reducing trajectory errors is not possible. This paper presents a method for analyzing the given trajectory, executing an exploratory physical run for a small portion of the given trajectory, and learning a compensation scheme based on the measured data. The learned compensation scheme is context-dependent and can be used to reduce the execution error. We have demonstrated the feasibility of this approach by conducting physical experiments.
{"title":"Context-Dependent Compensation Scheme to Reduce Trajectory Execution Errors for Industrial Manipulators","authors":"P. Bhatt, P. Rajendran, K. Mckay, Satyandra K. Gupta","doi":"10.1109/ICRA.2019.8793876","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8793876","url":null,"abstract":"Currently, automatically generated trajectories cannot be directly used on tasks that require high execution accuracies due to errors accused by inaccuracies in the robot model, actuator errors, and controller limitations. These trajectories often need manual refinement. This is not economically viable on low production volume applications. Unfortunately, execution errors are dependent on the nature of the trajectory and end-effector loads, and therefore devising a general purpose automated compensation scheme for reducing trajectory errors is not possible. This paper presents a method for analyzing the given trajectory, executing an exploratory physical run for a small portion of the given trajectory, and learning a compensation scheme based on the measured data. The learned compensation scheme is context-dependent and can be used to reduce the execution error. We have demonstrated the feasibility of this approach by conducting physical experiments.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"9 1","pages":"5578-5584"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91142064","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8793751
H. Karaoğuz, P. Jensfelt
In this paper, we focus on the robot grasping problem with parallel grippers using image data. For this task, we propose and implement an end-to-end approach. In order to detect the good grasping poses for a parallel gripper from RGB images, we have employed transfer learning for a Convolutional Neural Network (CNN) based object detection architecture. Our obtained results show that, the adapted network either outperforms or is on-par with the state-of-the art methods on a benchmark dataset. We also performed grasping experiments on a real robot platform to evaluate our method’s real world performance.
{"title":"Object Detection Approach for Robot Grasp Detection","authors":"H. Karaoğuz, P. Jensfelt","doi":"10.1109/ICRA.2019.8793751","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8793751","url":null,"abstract":"In this paper, we focus on the robot grasping problem with parallel grippers using image data. For this task, we propose and implement an end-to-end approach. In order to detect the good grasping poses for a parallel gripper from RGB images, we have employed transfer learning for a Convolutional Neural Network (CNN) based object detection architecture. Our obtained results show that, the adapted network either outperforms or is on-par with the state-of-the art methods on a benchmark dataset. We also performed grasping experiments on a real robot platform to evaluate our method’s real world performance.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"6 1","pages":"4953-4959"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76448136","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8794430
Qianwen Chao, Xiaogang Jin, Hen-Wei Huang, S. Foong, L. Yu, Sai-Kit Yeung
Recent failures in real-world self-driving tests have suggested a paradigm shift from directly learning in real-world roads to building a high-fidelity driving simulator as an alternative, effective, and safe tool to handle intricate traffic environments in urban areas. To date, traffic simulation can construct virtual urban environments with various weather conditions, day and night, and traffic control for autonomous vehicle testing. However, mutual interactions between autonomous vehicles and pedestrians are rarely modeled in existing simulators. Besides vehicles and pedestrians, the usage of personal mobility devices is increasing in congested cities as an alternative to the traditional transport system. A simulator that considers all potential road-users in a realistic urban environment is urgently desired. In this work, we propose a novel, extensible, and microscopic method to build heterogenous traffic simulation using the force-based concept. This force-based approach can accurately replicate the sophisticated behaviors of various road users and their interactions through a simple and unified way. Furthermore, we validate our approach through simulation experiments and comparisons to the popular simulators currently used for research and development of autonomous vehicles.
{"title":"Force-based Heterogeneous Traffic Simulation for Autonomous Vehicle Testing","authors":"Qianwen Chao, Xiaogang Jin, Hen-Wei Huang, S. Foong, L. Yu, Sai-Kit Yeung","doi":"10.1109/ICRA.2019.8794430","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8794430","url":null,"abstract":"Recent failures in real-world self-driving tests have suggested a paradigm shift from directly learning in real-world roads to building a high-fidelity driving simulator as an alternative, effective, and safe tool to handle intricate traffic environments in urban areas. To date, traffic simulation can construct virtual urban environments with various weather conditions, day and night, and traffic control for autonomous vehicle testing. However, mutual interactions between autonomous vehicles and pedestrians are rarely modeled in existing simulators. Besides vehicles and pedestrians, the usage of personal mobility devices is increasing in congested cities as an alternative to the traditional transport system. A simulator that considers all potential road-users in a realistic urban environment is urgently desired. In this work, we propose a novel, extensible, and microscopic method to build heterogenous traffic simulation using the force-based concept. This force-based approach can accurately replicate the sophisticated behaviors of various road users and their interactions through a simple and unified way. Furthermore, we validate our approach through simulation experiments and comparisons to the popular simulators currently used for research and development of autonomous vehicles.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"36 1","pages":"8298-8304"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75177771","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 : 2019-05-20DOI: 10.1109/ICRA.2019.8794063
Congying Sui, Kejing He, C. Lyu, Zerui Wang, Yunhui Liu
Three-dimensional vision plays an important role in robotics. In this paper, we present a 3D surface reconstruction scheme based on combination of stereo matching and pattern projection. A two-step matching scheme is proposed to establish reliable correspondence between stereo images with high computation efficiency and accuracy. The first step (coarse matching) can quickly find the correlation candidates, and the second step (precise matching) is responsible for determining the most precise correspondence within the candidates. Two phase maps serve as codewords and are utilized in the two-step stereo matching, respectively. The phase maps are derived from phase-shifting patterns to provide robustness to the background noises. Only five patterns are required, which reduces the image acquisition time. Moreover, the precision is further enhanced by applying a correspondence refinement algorithm. The precision and accuracy are validated by experiments on standard objects. Furthermore, various experiments are conducted to verify the capability of the proposed method, which includes the complex object reconstruction, the high-resolution reconstruction, and the occlusion avoidance. The real-time experimental results are also provided.
{"title":"3D Surface Reconstruction Using A Two-Step Stereo Matching Method Assisted with Five Projected Patterns","authors":"Congying Sui, Kejing He, C. Lyu, Zerui Wang, Yunhui Liu","doi":"10.1109/ICRA.2019.8794063","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8794063","url":null,"abstract":"Three-dimensional vision plays an important role in robotics. In this paper, we present a 3D surface reconstruction scheme based on combination of stereo matching and pattern projection. A two-step matching scheme is proposed to establish reliable correspondence between stereo images with high computation efficiency and accuracy. The first step (coarse matching) can quickly find the correlation candidates, and the second step (precise matching) is responsible for determining the most precise correspondence within the candidates. Two phase maps serve as codewords and are utilized in the two-step stereo matching, respectively. The phase maps are derived from phase-shifting patterns to provide robustness to the background noises. Only five patterns are required, which reduces the image acquisition time. Moreover, the precision is further enhanced by applying a correspondence refinement algorithm. The precision and accuracy are validated by experiments on standard objects. Furthermore, various experiments are conducted to verify the capability of the proposed method, which includes the complex object reconstruction, the high-resolution reconstruction, and the occlusion avoidance. The real-time experimental results are also provided.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"440 ","pages":"6080-6086"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72555769","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}
There are two difficulties to utilize state-of-the-art object recognition/detection/segmentation methods to robotic applications. First, most of the deep learning models heavily depend on large amounts of labeled training data, which are expensive to obtain for each individual application. Second, the object categories must be pre-defined in the dataset, thus not practical to scenarios with varying object categories. To alleviate the reliance on pre-defined big data, this paper proposes a customized object recognition and segmentation method. It aims to recognize and segment any object defined by the user, given only one annotation. There are three steps in the proposed method. First, the user takes an exemplar video of the target object with the robot, defines its name, and mask its boundary on only one frame. Then the robot automatically propagates the annotation through the exemplar video based on a proposed data generation method. In the meantime, a segmentation model continuously updates itself on the generated data. Finally, only a lightweight segmentation net is required at testing stage, to recognize and segment the user-defined object in any scenes.
{"title":"Customized Object Recognition and Segmentation by One Shot Learning with Human Robot Interaction","authors":"Ping Guo, Lidan Zhang, Lu Cao, Yingzhe Shen, Xuesong Shi, Haibing Ren, Yimin Zhang","doi":"10.1109/ICRA.2019.8793845","DOIUrl":"https://doi.org/10.1109/ICRA.2019.8793845","url":null,"abstract":"There are two difficulties to utilize state-of-the-art object recognition/detection/segmentation methods to robotic applications. First, most of the deep learning models heavily depend on large amounts of labeled training data, which are expensive to obtain for each individual application. Second, the object categories must be pre-defined in the dataset, thus not practical to scenarios with varying object categories. To alleviate the reliance on pre-defined big data, this paper proposes a customized object recognition and segmentation method. It aims to recognize and segment any object defined by the user, given only one annotation. There are three steps in the proposed method. First, the user takes an exemplar video of the target object with the robot, defines its name, and mask its boundary on only one frame. Then the robot automatically propagates the annotation through the exemplar video based on a proposed data generation method. In the meantime, a segmentation model continuously updates itself on the generated data. Finally, only a lightweight segmentation net is required at testing stage, to recognize and segment the user-defined object in any scenes.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"15 1","pages":"4356-4361"},"PeriodicalIF":0.0,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74750686","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：