An application of Lyapunov stability analysis to improve the performance of NARMAX models
An application of Lyapunov stability analysis to improve the performance of NARMAX models
复制标题
DOI：
10.1016/j.robot.2009.11.001
复制
发表时间：
2010-03-31
影响因子：
4.3
通讯作者：
Billings, S. A.
中科院分区：
文献类型：
--
作者：
Akanyeti, Otar;Rano, Inaki;Billings, S. A.
在此之前，我们提出了一种基于系统辨识和机器人训练技术的机器人控制器编程的新方法。所提出的方法分两个阶段工作：首先，程序员通过在目标环境中手动驱动机器人来向机器人演示期望的行为。在此运行期间，机器人的感官感知和所需的速度命令被记录下来。在获得训练数据后，我们使用ARMAX/NARMAX模型和系统辨识技术对机器人的感官读数和运动命令之间的关系进行建模。NARMAX模型的数学分析可以用来理解机器人的控制行为，提出假设，并改进机器人的行为。这种方法背后的一个主要目标是避免对机器人代码进行反复试验和改进。相反，我们寻求获得可靠的设计过程，其中程序设计决策基于对描述机器人如何与环境交互以实现预期行为的模型的数学分析。我们通过分析移动机器人中的一项特殊任务--门遍历来演示这一过程。(C)2009爱思唯尔B.V.保留所有权利。
Previously we presented a novel approach to program a robot controller based on system identification and robot training techniques. The proposed method works in two stages: first, the programmer demonstrates the desired behaviour to the robot by driving it manually in the target environment. During this run, the sensory perception and the desired velocity commands of the robot are logged. Having thus obtained training data we model the relationship between sensory readings and the motor commands of the robot using ARMAX/NARMAX models and system identification techniques. These produce linear "traditional robot" or non-linear polynomials which can be formally analysed, as well as used in place of control code.In this paper we focus our attention on how the mathematical analysis of NARMAX models can be used to understand the robot's control actions, to formulate hypotheses and to improve the robot's behaviour. One main objective behind this approach is to avoid trial-and-error refinement of robot code. Instead, we seek to obtain a reliable design process, where program design decisions are based on the mathematical analysis of the model describing how the robot interacts with its environment to achieve the desired behaviour. We demonstrate this procedure through the analysis of a particular task in mobile robotics: door traversal. (C) 2009 Elsevier B.V. All rights reserved.