|
|
论文:2016,Vol:34,Issue(6):1082-1087 |
|
|
引用本文： |
|
|
李建良, 杜承烈, 赵晔, 禹科. 一种视觉机器人演示学习的轨迹生成方法[J]. 西北工业大学学报 |
|
|
Li Jianliang, Du Chenglie, Zhao Ye. One Path Generation Method of Visual Robot Based on BLD[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 一种视觉机器人演示学习的轨迹生成方法 |
|
| 李建良1,2, 杜承烈1, 赵晔1,3, 禹科4 |
|
1. 西北工业大学 计算机学院, 陕西 西安 710129;
2. 西北农林科技大学 信息工程学院, 陕西 杨陵 712100;
3. 陕西省人民医院, 陕西 西安 710068;
4. 中航工业自控所 飞行器控制一体化技术重点实验室, 陕西 西安 710065 |
| 摘要: |
| 目前，机器人演示学习已成为机器人学中最为活跃的研究课题之一，而作为演示学习三要点之一的轨迹生成便成为研究热点。轨迹生成是决定演示学习是否成功的重要因素，传统上使用SIFT算法生成轨迹，但是这种方法存在很多局限，例如特征点较多、选择轨迹困难、轨迹存在一定噪声等。为此，提出了一种将SIFT、PCA和UKF等算法相结合的新的轨迹生成方法，通过实验仿真和机器人实体运行，结果表明了算法的有效性。 |
| 关键词:
演示学习
SIFT算法
主成分分析
无迹卡尔曼滤波
|
|
| One Path Generation Method of Visual Robot Based on BLD |
|
| Li Jianliang1,2, Du Chenglie1, Zhao Ye1,3 |
|
1. School of computer science, Northwestern Polytechnical University, Xi'an 710129, China;
2. College of Information Engineering, Northwest A&F University, Xi'an 712100, China;
3. Shaanxi Provincial People's Hospital, Xi'an 710069, China;
4.Science and Technology on Aircraft Control Laboratory, FACRI, Xi'an 710065, China |
| Abstract: |
| Robot learning by demonstration has become one of the most active research topics in robotics, and trajectory generation as one of the three points of demonstration study has become a hot research topic. Trajectory generation is decided to demonstrate learning an important factor in the success, the traditional method using sift tracking direct trajectory generation, but this method exists many shortcomings, such as more feature points selected tracks difficulties, trajectory there are certain noise, and so on. In this paper, a combination of SIFT, PCA and UKF algorithm algorithm based on trajectory generation method, the simulations and experiments with a real robot operation proves the validity of the algorithm. |
| Key words:
learning by demonstration
scale invariant feature transform
principal component analysis
unscented kalman filter
|
|
| 收稿日期: 2016-04-21
修回日期:
|
| DOI: |
| 基金项目: 航空科学基金（20150753011）资助 |
| 通讯作者:
Email： |
| 作者简介: 李建良(1971-),西北工业大学博士研究生,西北农林科技大学副教授,主要从事CPS系统软件工程研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 李建良 在本刊中的所有文章 |
| 杜承烈 在本刊中的所有文章 |
| 赵晔 在本刊中的所有文章 |
| 禹科 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 王田苗,陶永. 我国工业机器人技术现状与产业化发展战略[J]. 机械工程学报,2014(9):1-13 Wang Tianmiao, Tao Yong. Research Status and Industrialization Development Strategy of Chinese Industrial Robot[J]. Journal of Mechanical Engineering, 2014(9):1-13(in Chinese)
[2] 李睿,曲兴华. 工业机器人运动学参数标定误差不确定度研究[J]. 仪器仪表学报,2014(10):2192-2199 Li Rui, Qu Xinghua. Study on Calibration Uncertaintyof Insudtrial Robot Kinematic Parameters[J]. Chinese Journal of Scientific Instrument, 2014(10):2192-2199(in Chinese)
[3] 管贻生,邓休,李怀珠,等. 工业机器人的结构分析与优化[J]. 华南理工大学学报(自然科学版),2013(9):126-131 Guan Yisheng, Deng Xiu, Li Huaizhu, et al. Structural Analysis and Optimization of Industrial Robot[J]. Journal of South China University of Technology(Natural Science Edition), 2013(9):126-131(in Chinese)
[4] Billard A, Calinon S, Dillmann R, et al. Robot Programming by Demonstration, Springer Handbook of Robotics[M]. Springer Berlin Heidelberg, 2008:1371-1394
[5] Rozo Leonel, Jimenez Pablo, Torras Carme. A Robot Learning from Demonstration Framework to Perform Force-Based Manipulation Tasks[J]. Intelligent Service Robotics, 2013,6(1):33-51
[6] Demiris Y, Aziz-Zadeh L, Bonaiuto J. Information Processing in the Mirrorneuron System in Primates and Machines[J]. Neuroinformatics, 2014(12):63-91
[7] Suleman, Khawaja M U, Awais Mian M. Learning from Demonstration in Robots Using the Shared Circuits Model[J]. IEEE Trans on Autonomous Mental Development, 2014,6(4):244-258
[8] Pagliuca Paolo, Nolfi Stefano. Integrating Learning by Experience and Demonstration in Autonomous Robots[J]. Adaptive Behavior, 2015,23(5):300-314
[9] Peters J, Vijayakumar S, Schaal S. Reinforcement Learning for Humanoid Robotics[C]//Proceedings of the 3rd IEEE-RAS International Conference on Humanoid Robots(Humanoids), Karlsruhe, Germany, 2003:1-20
[10] Yoshikawa Y, Shinozawa K, Ishiguro H, et al. Miyamoto. Responsive Robot Gaze to Interaction Partner[C]//Proceedings of the 2006 Robotics Science and Systems Conference, 2006:287-293
[11] Wu Yan, Su Yanyu, Demiris Yiannis. A Morphable Template Framework for Robot Learning by Demonstration:Integrating One-Shot and Incremental Learning Approaches[J]. Robotics and Autonomous Systems, 2014,62(10):1517-1530
[12] Mitic Marko; Miljkovic Zoran. Neural Network Learning from Demonstration and Epipolar Geometry for Visual Control of A Nonholonomic Mobile Robot[J]. Soft Computing, 2014,18(5):1011-1025
[13] Vukovic Najdan, Mitic Marko, Miljkovic Zoran. Trajectory Learning and Reproduction for Differential Drive Mobile Robots Based on Gmm/Hmm and Dynamic Time Warping Using Learning from Demonstration Framework[J]. Engineering Applications of Artificial Intelligence, 2015,45:388-404 |
|
|
|
|
|
|
|
