发布求助
文献互助 智能选刊 最新文献

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)最新文献

筛选
英文 中文
Kinematic Self-calibration of a 3-DOF Parallel Mechanism with Ill-conditioned Identification Matrix 病态辨识矩阵下三自由度并联机构的运动自标定
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517431
X. Duan, Lixing Jin, Changsheng Li, Rui He, Quanbin Lai, Rui Ma
{"title":"Kinematic Self-calibration of a 3-DOF Parallel Mechanism with Ill-conditioned Identification Matrix","authors":"X. Duan, Lixing Jin, Changsheng Li, Rui He, Quanbin Lai, Rui Ma","doi":"10.1109/RCAR52367.2021.9517431","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517431","url":null,"abstract":"Kinematics calibration is an effective means to improve the accuracy of the mechanism. Parallel mechanisms with redundant actuation have potential for kinematic self-calibration. In this paper, the self-calibration algorithms of a parallel mechanism with 3-DOF are studied. The Jacobian matrix for self-calibration is ill-posed/ill-condition caused by multicollinearity between kinematics parameter, and the calculation with least square method diverges. Truncated singular value decomposition (TSVD), ridge regression (RR) and Liu estimation algorithm are utilized to address this problem, and the identification performances under different error parameters are compared.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115464807","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}
引用次数: 0
A Depthwise Separable Convolution Based 6D Pose Estimation Network by Efficient 2D-3D Feature Fusion 基于深度可分离卷积的高效2D-3D特征融合6D姿态估计网络
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517387
Qi Feng, Chaochen Gu, Jiani Qin, Rui Xu
{"title":"A Depthwise Separable Convolution Based 6D Pose Estimation Network by Efficient 2D-3D Feature Fusion","authors":"Qi Feng, Chaochen Gu, Jiani Qin, Rui Xu","doi":"10.1109/RCAR52367.2021.9517387","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517387","url":null,"abstract":"Precise 6D pose estimation of the target object is an essential prerequisite for robots to understand the real world. Previous 6D pose estimation methods based on 3D data usually have problems such as long model training time, imperfect feature extraction, redundant network model parameters, and complicated follow-up processing steps. This paper proposes a 2D-3D feature fusion module that could enhance feature extraction for the 6D pose estimation network. Furthermore, we compress the size of model parameters by adopting depthwise separable convolution to accelerate training speed and to reduce memory consumption. The experiment results on LineMOD dataset show the effectiveness of our method. Our method achieves on par or better performance than the state-of-art methods for 6D pose estimation and reduces model training time and the number of model parameters simultaneously.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122383871","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}
引用次数: 0
Design of Optimal Tracking Differentiator Based on Particle Swarm Optimization 基于粒子群优化的最优跟踪微分器设计
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517485
Yang Gao, Dapeng Tian
{"title":"Design of Optimal Tracking Differentiator Based on Particle Swarm Optimization","authors":"Yang Gao, Dapeng Tian","doi":"10.1109/RCAR52367.2021.9517485","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517485","url":null,"abstract":"Differential signals are widely used in many systems. Tracking differentiator is an efficient differential estimation method. In general, the parameter design of tracking differentiators is based on experience, it is difficult to achieve optimal performance. In this paper, an optimal parameter design method for tracking differentiators is proposed. The mathematical model between low-pass filter (LPF) and error is established. The objective function to achieve the minimum error is convex and unsolvable. Therefore, an off-line parameter design method based on particle swarm optimization (PSO) is proposed, and a new error evaluation criterion considering phase lag is proposed. Simulation and experimental results show that the optimal parameters of tracking differentiators exist and can be found by the proposed method. The proposed method is practical and can be applied to engineering efficiently.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"678 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122973904","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}
引用次数: 0
Two Stream Dynamic Threshold Network for Weakly-Supervised Temporal Action Localization 弱监督时间动作定位的双流动态阈值网络
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517513
Hao Yan, Jun Cheng, Qieshi Zhang, Ziliang Ren, Shijie Sun, Qin Cheng
{"title":"Two Stream Dynamic Threshold Network for Weakly-Supervised Temporal Action Localization","authors":"Hao Yan, Jun Cheng, Qieshi Zhang, Ziliang Ren, Shijie Sun, Qin Cheng","doi":"10.1109/RCAR52367.2021.9517513","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517513","url":null,"abstract":"The current mainstream temporal action localization methods are fully-supervised, which needs a lot of time to annotate the required frame-level labels. The emergence of weakly-supervised methods greatly alleviates such problem, as they only require video-level labels to train the models. In order to generate accurate action localization boundary, recent two stream consensus network (TSCN) proposes an attention normalization loss to explicitly force the attention values approach extreme values to avoid ambiguity. However, most previous methods including TSCN use a fixed threshold applied on attention loss to polarize the attention values, which lacks flexibility for different videos. In this paper, we propose a Dynamic Threshold Weakly-supervised action Localization (DH-WTAL) method to address this problem. The proposed DH-WTAL features a dynamic attention threshold decision for the attention mechanism. Specifically, the dynamic threshold can dynamically control the number of snippets selected for different videos, which further adjust the extreme values of the attention mechanism for different videos accordingly. Extensive experiments demonstrate that the proposed DH-WTAL outperforms the TSCN baseline, and ablation study validates the effectiveness of this method.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"60 6-7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114048290","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}
引用次数: 0
Cloud-based Robot Path Planning in Dynamic Environments 动态环境下基于云的机器人路径规划
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517435
Xinquan Chen, Lujia Wang, Xitong Gao, Cheng-Zhong Xu
{"title":"Cloud-based Robot Path Planning in Dynamic Environments","authors":"Xinquan Chen, Lujia Wang, Xitong Gao, Cheng-Zhong Xu","doi":"10.1109/RCAR52367.2021.9517435","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517435","url":null,"abstract":"Most of the current path planning applications only focus on a single agent, without considering the surrounding robots or dynamic obstacles. In safety-critical environments, such as the crowded playground, the robot may have increased difficulty reaching the destination with crowds moving around, sometimes even cause damages. With the development of cloud computing and swarm intelligence, the concept of “cloud robotic” has been followed by more scholars. With collaboration and information sharing between robots, the cluster has better problem-solving skills than the individual. In this paper, we propose a cloud-based multi-agent navigation algorithm in dynamic environments. We propose the concept of pheromones of dynamic obstacles that represent congestion to enable clusters to plan collaboratively. Widespread static sensors are introduced to jointly estimate congestion in the environment with robots. When an agent needs route planning, the cloud provides safe and fast route with intermediate points. The robot uses a simple yet effective local planner based on artificial potential field (APF) to trace the trajectory. We demonstrate this approach's effectiveness compared to traditional A* global planner and APF local planner with traditional repulsion function. Experiments show that our cloud-based method reduces the number of collisions by 92.6%, with only 35% increase in path length. All code for reproducing the experiments is at https://github.com/Asber777/CDPP.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128244153","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}
引用次数: 2
A Novel Underwater Image Synthesis Method Based on a Pixel-Level Self-Supervised Training Strategy 基于像素级自监督训练策略的水下图像合成新方法
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517333
Zhi-zong Wu, Zhengxing Wu, Yue Lu, Jian Wang, Junzhi Yu
{"title":"A Novel Underwater Image Synthesis Method Based on a Pixel-Level Self-Supervised Training Strategy","authors":"Zhi-zong Wu, Zhengxing Wu, Yue Lu, Jian Wang, Junzhi Yu","doi":"10.1109/RCAR52367.2021.9517333","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517333","url":null,"abstract":"With the rapid development of deep neural networks, underwater vision plays an increasingly important role in the underwater robotic operation. However, the scarce underwater datasets greatly limit the performance of deep learning on underwater visual tasks, further hindering the applications of underwater operation. To solve this problem, we propose an underwater image synthesis method, which can directly convert the natural light image into the synthetic underwater image end-to-end. Particularly, a pixel-level self-supervised training strategy is designed to maximize the structural similarity between the synthesized and real images, through training the real underwater images. Finally, extensive experiments are carried out, and the obtained results demonstrate the effectiveness and superiority of our methods by quantitative and qualitative comparisons. The proposed underwater image synthesis method offers a valuable sight for underwater vision and manipulating control.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128736168","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}
引用次数: 2
Hysteresis Compensation of an Elbow Joint Rehabilitation Robot Featuring Flexible Pneumatic Artificial Muscle Actuation 柔性气动人工肌肉驱动肘关节康复机器人的滞后补偿
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517399
Y. Xu, Yanding Qin, Jianda Han
{"title":"Hysteresis Compensation of an Elbow Joint Rehabilitation Robot Featuring Flexible Pneumatic Artificial Muscle Actuation","authors":"Y. Xu, Yanding Qin, Jianda Han","doi":"10.1109/RCAR52367.2021.9517399","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517399","url":null,"abstract":"A pneumatic artificial muscle (PAM) actuated robot is developed for the elbow joint rehabilitation and assisted movement of the arm in this paper. The PAM utilized has the characteristics of flexible actuation, making it user-friendly and safe during the user-robot collaboration. However, its hysteresis nonlinearity significantly affects the motion accuracy of the robot. Offline parameter identification and model inversion are the two main steps of common model-based hysteresis compensation strategies, whereas the robustness against the variation of the system's configuration is low. This paper presents a hysteresis compensation strategy based on the direct inverse modeling method and a modified adaptive projection algorithm. The inverse PI model is adopted as the hysteresis compensator, and a modified adaptive projection algorithm is utilized to adjust the parameters of the inverse PI model online. It has been verified by experiments that the proposed method is effective in hysteresis compensation, and the transient performance of the system has been improved. In the meantime, the performance of the closed-loop system on tracking different types of trajectories is experimentally tested.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129644574","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}
引用次数: 1
Experimental Study on Dynamic Characteristics and Fatigue of McKibben Pneumatic Artificial Muscles McKibben气动人造肌肉动态特性及疲劳试验研究
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517361
Wenlin Chen, Tian Ma, Y. Zhang, Lina Hao, Shuopeng Wang, Meng Liu, Rixin Wang
{"title":"Experimental Study on Dynamic Characteristics and Fatigue of McKibben Pneumatic Artificial Muscles","authors":"Wenlin Chen, Tian Ma, Y. Zhang, Lina Hao, Shuopeng Wang, Meng Liu, Rixin Wang","doi":"10.1109/RCAR52367.2021.9517361","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517361","url":null,"abstract":"Pneumatic artificial muscles (PAMs), as a type of actuators in soft robots, have been attracted in the past few decades. Because of their higher power density ratio and flexibility, PAMs are now widely used as a flexible actuator. When PAMs are applied to different robot systems, their dynamic output characteristics are influenced by the amplitude and frequency of input signals and external loads. The experimental results show that with the increase of input signals frequency, the width of PAMs dynamic hysteresis loop increases and the height decreases. Meanwhile, in order to verify that the fatigue life of the Mckibben PAMs made in the laboratory can meet the use requirements, this paper has completed the fatigue tests of them.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121494348","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}
引用次数: 1
Robotic arm grasping through 3D point clouds recognition 基于三维点云识别的机械臂抓取
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517680
Suhui Ji, Wentao Li, Zhen Zhang, Shijun Zhou, Zhiyuan Cai, Jiandong Tian
{"title":"Robotic arm grasping through 3D point clouds recognition","authors":"Suhui Ji, Wentao Li, Zhen Zhang, Shijun Zhou, Zhiyuan Cai, Jiandong Tian","doi":"10.1109/RCAR52367.2021.9517680","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517680","url":null,"abstract":"The combination of 2D cameras and robots usually can no longer meet manufacturing production requirements. With the emergence of cheap 3D cameras, robot research based on 3D vision has become mainstream. In this paper, the Kinect camera is combined with the Fanuc manipulator to build an intelligent robot grasping system. First, we have proposed a new pentagonal positioning method, which can reduce errors in position conversion. Next, we designed our point cloud models for the model-based point clouds matching method. In the pose estimation process, we used a voxel grid to speed up the calculation, established a hash table that stores point pair features, and used Hough voting and pose Clustering to perform point cloud matching and output poses. Finally, we conducted several grasping experiments, and the experimental results met the requirements of grasping accuracy in our system.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121637452","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}
引用次数: 2
FPGA-based Deep Learning Acceleration for Visual Grasping Control of Manipulator
2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517666
Haibin Yin, Haiqing Hong, Jing Liu
{"title":"FPGA-based Deep Learning Acceleration for Visual Grasping Control of Manipulator","authors":"Haibin Yin, Haiqing Hong, Jing Liu","doi":"10.1109/RCAR52367.2021.9517666","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517666","url":null,"abstract":"The vision-based robotic arm control system is an important solution for intelligent production, and the robotic arm visual grasping system based on deep learning is an important branch. Aiming at the requirements of fast visual recognition speed, low power consumption and high precision of mobile visual grasping robot, a deep learning target detection scheme based on FPGA hardware acceleration is proposed. Use Vivado and Petalinux development kit to build the software and hardware system, then deploy YOLOv3 model in the system. Experiments show that the solution meets the demand of robotic arm visual grasping, and the real-time performance is better. The recognition speed is 18 times that of the CPU, the power consumption is 1/13 of the GPU, and the cost is lower.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127667133","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}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信