2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)最新文献_第9页

Programming by Visual Demonstration for Pick-and-Place Tasks using Robot Skills 使用机器人技能的拾取任务的可视化演示编程

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961481

Peng Hao, Tao Lu, Yinghao Cai, Shuo Wang

{"title":"Programming by Visual Demonstration for Pick-and-Place Tasks using Robot Skills","authors":"Peng Hao, Tao Lu, Yinghao Cai, Shuo Wang","doi":"10.1109/ROBIO49542.2019.8961481","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961481","url":null,"abstract":"In this paper, we present a vision-based robot programming system for pick-and-place tasks that can generate programs from human demonstrations. The system consists of a detection network and a program generation module. The detection network leverages convolutional pose machines to detect the key-points of the objects. The network is trained in a simulation environment in which the train set is collected and auto-labeled. To bridge the gap between reality and simulation, we propose a design method of transform function for mapping a real image to synthesized style. Compared with the unmapped results, the Mean Absolute Error (MAE) of the model completely trained with synthesized images is reduced by 23% and the False Negative Rate FNR (FNR) of the model fine-tuned by the real images is reduced by 42.5% after mapping. The program generation module provides a human-readable program based on the detection results to reproduce a real-world demonstration, in which a longshort memory (LSM) is designed to integrate current and historical information. The system is tested in the real world with a UR5 robot on the task of stacking colored cubes in different orders.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131417193","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: 3

Lightweight 10-DOF Robotic Hand With Built-In Wire-Driven Mechanism 内置线驱动机构的轻量级10自由度机械手

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961530

T. Shimura, Yuta Murai, Shunta Togo, Yinlai Jiang, H. Yokoi

引用次数: 0

Clutter Filtering Algorithm in Dense Clutter Environment 密集杂波环境下的杂波滤波算法

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961873

Sheng Mou, Jianhui Guo

引用次数: 0

An Attention Module for Multi-Person Pose Estimation 一种多人姿态估计的注意模块

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961623

Daxing Chen, Xinghao Song, Shixi Fan, Hongpeng Wang

引用次数: 0

Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition 机器人电梯按钮识别中视角畸变的自主去除

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961720

Delong Zhu, Jianbang Liu, Nachuan Ma, Z. Min, M. Meng

{"title":"Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition","authors":"Delong Zhu, Jianbang Liu, Nachuan Ma, Z. Min, M. Meng","doi":"10.1109/ROBIO49542.2019.8961720","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961720","url":null,"abstract":"Elevator button recognition is considered an indispensable function for enabling the autonomous elevator operation of mobile robots. However, due to unfavorable image conditions and various image distortions, the recognition accuracy remains to be improved. In this paper, we present a novel algorithm that can autonomously correct perspective distortions of elevator panel images. The algorithm first leverages the Gaussian Mixture Model (GMM) to conduct a grid fitting process based on button recognition results, then utilizes the estimated grid centers as reference features to estimate camera motions for correcting perspective distortions. The algorithm performs on a single image autonomously and does not need explicit feature detection or feature matching procedure, which is much more robust to noises and outliers than traditional feature-based geometric approaches. To verify the effectiveness of the algorithm, we collect an elevator panel dataset of 50 images captured from different angles of view. Experimental results show that the proposed algorithm can accurately estimate camera motions and effectively remove perspective distortions.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128062419","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: 5

Spin-up Control of Tethered Space Station for Artificial Gravity Task* 用于人工重力任务的系留空间站的自旋控制*

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961375

Zhengyuan Li, Zhongjie Meng, Panfeng Huang

引用次数: 0

An Modified Real-time Photometric Calibration Algorithm Based on ORB Features* 一种改进的基于ORB特征的实时光度校正算法*

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961503

Chuanzheng Liu, Jiahui Qi, Cheng-jin Zhang, Peixin Liu, Xianfeng Yuan

引用次数: 0

A Global Path Planning Algorithm for Robots Using Reinforcement Learning 基于强化学习的机器人全局路径规划算法

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961753

Penggang Gao, Zihan Liu, Zongkai Wu, Donglin Wang

引用次数: 17

Sensorless Hybrid Normal-Force Controller With Surface Prediction 具有表面预测的无传感器混合法向力控制器

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961532

Yingjie Qian, Jianjun Yuan, Sheng Bao, Liming Gao

{"title":"Sensorless Hybrid Normal-Force Controller With Surface Prediction","authors":"Yingjie Qian, Jianjun Yuan, Sheng Bao, Liming Gao","doi":"10.1109/ROBIO49542.2019.8961532","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961532","url":null,"abstract":"In this paper, an improved sensorless hybrid controller for constant force control along normal direction is proposed for applications including polishing, milling and deburring. No additional sensors are involved. External joint torques of all joints can be calculated from their electric current, dynamic model and friction model. With the help of dynamically consistent generalized inverse matrix, they can be converted to external force/torque at the end-effector. The underlying force control strategy is the integration of impedance control model and explicit force control. The novel improvement is the real-time prediction algorithm of surface’s shape profile and normal direction without any prior knowledge. So, this force controller has great adaptiveness to arbitrary unknown surfaces. Experiments were performed on a 7 degrees-of-freedom (DOFs) robot to test the controller’s capability and utility on an inclined plane and curved surface. Results prove the credibility of external force estimation. The normal force tracking accuracy is adequate for targeted applications. Real-time prediction is functional as the robot adjusts its orientation accordingly.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133906263","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: 5

Trans Humeral Prosthesis Based on sEMG and SSVEP-EEG Signals* 基于sEMG和SSVEP-EEG信号的经肱骨假体*

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961453

Kangshuai Chen, Yanan Zhang, Zhen Zhang, Yu-xian Yang, Hailiang Ye

{"title":"Trans Humeral Prosthesis Based on sEMG and SSVEP-EEG Signals*","authors":"Kangshuai Chen, Yanan Zhang, Zhen Zhang, Yu-xian Yang, Hailiang Ye","doi":"10.1109/ROBIO49542.2019.8961453","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961453","url":null,"abstract":"The loss of forearm muscle in amputees above elbow joint make it impossible to control the prosthesis of elbow joint and upper limb only by using surface electromyography (sEMG) signals. Electroencephalogram (EEG) signals can be used as input signal to control the motion of the upper limb prosthetic hand for it can reflect the user's motion intention. This paper introduces a method of controlling the trans humeral prosthesis by combining sEMG and EEG signals. In this method, the control of elbow flexion and extension motions are based on sEMG signals of biceps and triceps. Combined with the collected elbow angles, the elbow angle of prosthetic arm is predicted by back propagation neural network after training and then the angle can be used to control the elbow joint. In order to control the motion of the prosthetic hand, a control method based on EEG is proposed. The EEG control method is named as steady state visual evoked potential (SSVEP). User can use his EEG signals to control the motion of hand prosthesis. Canonical correlation analysis (CCA) algorithm is used to classify SSVEP signals, then different SSVEP signals can be used to control different motions of prosthetic hands. Some experiments were carried out on healthy subjects to verify the performance of the proposed system.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132348846","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