期刊
NEURAL COMPUTATION
卷 25, 期 2, 页码 328-373出版社
MIT PRESS
DOI: 10.1162/NECO_a_00393
关键词
-
资金
- European Commission [AMARSI FP7-ICT-248311]
- National Science Foundation [ECS-0326095, IIS-0535282, CNS-0619937, IIS-0917318, CBET-0922784, EECS-0926052]
- DARPA program on Learning Locomotion
- Okawa Foundation
- ATR Computational Neuroscience Laboratories
- German Research Foundation (DFG) [HO-3771-1]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1017134] Funding Source: National Science Foundation
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [926052] Funding Source: National Science Foundation
- Div Of Information & Intelligent Systems
- Direct For Computer & Info Scie & Enginr [0917318] Funding Source: National Science Foundation
Nonlinear dynamical systems have been used in many disciplines to model complex behaviors, including biological motor control, robotics, perception, economics, traffic prediction, and neuroscience. While often the unexpected emergent behavior of nonlinear systems is the focus of investigations, it is of equal importance to create goal-directed behavior (e.g., stable locomotion from a system of coupled oscillators under perceptual guidance). Modeling goal-directed behavior with nonlinear systems is, however, rather difficult due to the parameter sensitivity of these systems, their complex phase transitions in response to subtle parameter changes, and the difficulty of analyzing and predicting their long-term behavior; intuition and time-consuming parameter tuning play a major role. This letter presents and reviews dynamical movement primitives, a line of research for modeling attractor behaviors of autonomous nonlinear dynamical systems with the help of statistical learning techniques. The essence of our approach is to start with a simple dynamical system, such as a set of linear differential equations, and transform those into a weakly nonlinear system with prescribed attractor dynamics by means of a learnable autonomous forcing term. Both point attractors and limit cycle attractors of almost arbitrary complexity can be generated. We explain the design principle of our approach and evaluate its properties in several example applications in motor control and robotics.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据