基于交叉熵优化的高斯混合模型运动编码
Encoding Motor Skills with Gaussian Mixture Models Optimized by the Cross Entropy Method
查看参考文献24篇
文摘
|
针对模仿学习中运动的表征和泛化问题,提出了交叉熵优化算法,用于混合模型参数的推断.该算法易于实施、计算效率高.更重要的是,它能够自动确定混合模型中最优成分的个数.为了产生泛化的运动轨迹,提出了交叉熵回归算法.为了进一步提高这种算法对动态环境的适应能力,引入了任务参数化的概念并提出了任务参数交叉熵回归算法.最后设计了一个新颖的锤击任务,验证了所提出的算法在理论上的正确性和优越性.基于机器人物理仿真软件Gazebo的仿真实验表明了算法在实际应用中的可行性. |
其他语种文摘
|
Aiming at the movement representation and generalization problems in imitation learning,a cross entropy optimization algorithm is proposed to infer parameters in mixture models. The proposed algorithm is easy to implement and computationally efficient. More importantly, it can automatically determine the optimal component number in the mixture models. In order to produce generalized motion trajectories,a cross entropy regression algorithm is proposed. To further improve the adaptability of the algorithm in dynamic environments,the concept of task parametrization is introduced and a task-parameterized cross entropy regression algorithm is proposed. Finally,a novel hammer- over- a - nail task is designed, which verifies the theoretical correctness and superiority of the proposed methods. Simulation experiments based on robot physical simulation software Gazebo show the feasibility of the proposed algorithms in piratical applications. |
来源
|
机器人
,2018,40(4):569-576 【核心库】
|
DOI
|
10.13973/j.cnki.robot.180146
|
关键词
|
技能学习
;
模仿学习
;
交叉熵
;
任务参数
;
运动表征
;
混合模型
|
地址
|
1.
中国科学院沈阳自动化研究所, 机器人学国家重点实验室, 辽宁, 沈阳, 110016
2.
中国科学院大学, 北京, 100049
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1002-0446 |
学科
|
自动化技术、计算机技术 |
文献收藏号
|
CSCD:6292386
|
参考文献 共
24
共2页
|
1.
Argall B D. A survey of robot learning from demonstration.
Robotics and Autonomous Systems,2009,57(5):469-483
|
被引
44
次
|
|
|
|
2.
Billard A G. Learning from humans.
Springer Handbook of Robotics,2016:1995-2014
|
被引
3
次
|
|
|
|
3.
Liu S. Teaching and learning of deburring robots using neural networks.
IEEE International Conference on Robotics and Automation,1993:339-345
|
被引
1
次
|
|
|
|
4.
Billard A. Learning motor skills by imitation: A biologically inspired robotic model.
Cybernetics and Systems,2001,32(1/2):155-193
|
被引
1
次
|
|
|
|
5.
Kaiser M. Building elementary robot skills from human demonstration.
IEEE International Conference on Robotics and Automation,1996:2700-2705
|
被引
1
次
|
|
|
|
6.
Dillmann R. Acquisition of elementary robot skills from human demonstration.
International Symposium on Intelligent Robotics Systems,1995:185-192
|
被引
1
次
|
|
|
|
7.
Vakanski A. Trajectory learning for robot programming by demonstration using hidden Markov model and dynamic time warping.
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2012,42(4):1039-1052
|
被引
4
次
|
|
|
|
8.
Nguyen-Tuong D. Local Gaussian process regression for real time online model learning.
Advances in Neural Information Processing Systems,2009:1193-1200
|
被引
1
次
|
|
|
|
9.
Vijayakumar S. Locally weighted projection regression: An O(n) algorithm for incremental real time learning in high dimensional space.
Proceedings of the Seventeenth International Conference on Machine Learning,2000:1079-1086
|
被引
1
次
|
|
|
|
10.
Calinon S. A tutorial on task-parameterized movement learning and retrieval.
Intelligent Service Robotics,2016,9(1):1-29
|
被引
9
次
|
|
|
|
11.
Ijspeert A J. Learning attractor landscapes for learning motor primitives.
Advances in Neural Information Processing Systems,2003:1547-1554
|
被引
4
次
|
|
|
|
12.
Schaal S. Dynamic movement primitives-A framework for motor control in humans and humanoid robotics.
Adaptive Motion of Animals and Machines,2006:261-280
|
被引
5
次
|
|
|
|
13.
Ijspeert A J. Dynamical movement primitives: Learning attractor models for motor behaviors.
Neural Computation,2013,25(2):328-373
|
被引
44
次
|
|
|
|
14.
Nakanishi J. Learning from demonstration and adaptation of biped locomotion.
Robotics and Autonomous Systems,2004,47(2/3):79-91
|
被引
4
次
|
|
|
|
15.
Park D H. Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields.
IEEE-RAS International Conference on Humanoid Robots,2008:91-98
|
被引
1
次
|
|
|
|
16.
Gams A. Coupling movement primitives: Interaction with the environment and bimanual tasks.
IEEE Transactions on Robotics,2014,30(4):816-830
|
被引
5
次
|
|
|
|
17.
Paraschos A. Probabilistic movement primitives.
Advances in Neural Information Processing Systems,2013:2616-2624
|
被引
5
次
|
|
|
|
18.
Gribovskaya E. Learning nonlinear multivariate dynamics of motion in robotic manipulators.
International Journal of Robotics Research,2011,30(1):80-117
|
被引
11
次
|
|
|
|
19.
Wang Z G. Incremental multiple instance outlier detection.
Neural Computing and Applications,2015,26(4):957-968
|
被引
5
次
|
|
|
|
20.
Tabor J. Cross-entropy clustering.
Pattern Recognition,2014,47(9):3046-3059
|
被引
2
次
|
|
|
|
|