A Novel Trajectory Generation Method for Robot Control

被引：0

作者：

KeJun Ning

Tomas Kulvicius

Minija Tamosiunaite

Florentin Wörgötter

机构：

[1] University of Göttingen,Bernstein Center for Computational Neuroscience, Inst. of Physics III

[2] Research & Technology,undefined

[3] Lenovo,undefined

来源：

Journal of Intelligent & Robotic Systems | 2012年 / 68卷

关键词：

Trajectory generation; Dynamic trajectory joining; Control theory; Machine learning;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

This paper presents a novel trajectory generator based on Dynamic Movement Primitives (DMP). The key ideas from the original DMP formalism are extracted, reformulated and extended from a control theoretical viewpoint. This method can generate smooth trajectories, satisfy position- and velocity boundary conditions at start- and endpoint with high precision, and follow accurately geometrical paths as desired. Paths can be complex and processed as a whole, and smooth transitions can be generated automatically. Performance is analyzed for several cases and a comparison with a spline-based trajectory generation method is provided. Results are comparable and, thus, this novel trajectory generating technology appears to be a viable alternative to the existing solutions not only for service robotics but possibly also in industry.

引用

页码：165 / 184

页数：19

共 61 条

[1]

Atkeson CG(2000)Using humanoid robots to study human behavior IEEE Intell. Syst. 15 46-56

[2]

Hale JG(1984)An on-line dynamic trajectory generator Int. J. Rob. Res. 3 68-72

[3]

Pollick F(1999)The three-cubic method: an optimal online robot joint trajectory generator under velocity, acceleration, and wandering constraints Int. J. Rob. Res. 18 893-901

[4]

Riley M(1987)Formulation of joint trajectories for industrial robots using B-splines IEEE Trans. Ind. Electron. IE-34 192-199

[5]

Kotosaka S(1985)On-line polynomial trajectories for robot manipulators Int. J. Rob. Res. 4 38-48

[6]

Schaal S(1979)Straight line manipulator trajectories IBM J. Res. Dev. 23 424-436

[7]

Shibata T(1995)A theory for cursive handwriting based on the minimization principle Biol. Cybern. 73 3-13

[8]

Tevatia G(2008)Reinforcement learning of motor skills with policy gradients Neural Netw. 21 682-697

[9]

Ude A(2007)Dynamics systems vs. optimal control - a unifying view Prog. Brain Res. 165 425-445

[10]

Vijayakumar S(2012)Joining movement sequences: modified dynamic movement primitives for robotics applications exemplified on handwriting IEEE Trans. Robot. 28 145-157

← 1 2 3 4 5 6 7 →