动态优化双估计器的多模型自适应混合控制

针对参数子集个数较多导致计算量较大和由于系统参数发生跳变造成系统暂态性能差的问题,本文提出了基于动态优化双估计器的多模型自适应混合控制方法.首先对多个参数子集进行动态优化得到最优参数子集,减少了需要计算的模型数量,提高了系统收敛速度;其次对被控对象设置一个固定初值的估计器和一个可重新赋值的估计器,固定估计器用于初始时刻对参数的估计,可赋值估计器动态调整估计初值用于减小估计误差,提高系统暂态性能.最后的仿真结果表明了该方法的有效性,并给出了系统的稳定性及收敛性分析.     

高斯混合背景模型的方差估计研究

在分析高斯混合背景模型建模机理的基础上,研究了模型参数估计及更新中模型结构稳定性和可塑性两难问题,指出高斯分量方差估计对运动分割的重要性。针对Stauffer算法中高斯分量均值和方差更新公式收敛过慢问题,提出了兼顾适应性和运动分割准确性的均值和方差更新策略。实验结果表明该方法在模态学习的准确性和方差收敛速度方面比原有方法有较大提高。     

一种改进的自适应高斯混合模型实时运动目标检测算法

高斯混合模型被广泛应用于摄像机静止条件下运动目标检测的背景建模。针对传统高斯混合模型中对光照变化适应性差及学习率单一等问题, 提出了一种光照变化检测及学习率更新的方法, 以达到自适应更新背景模型的目的。提出利用颜色直方图匹配算法, 通过引入光照变化因子以及模型参数更新计数器对学习率进行自适应的调整, 并通过对描述模型分量个数的自适应选择减少了计算时间, 增强了系统的实时性。实验结果表明, 该方法能快速有效地适应场景的变化, 比传统高斯混合模型具有更好的鲁棒性与稳定性。     

IMM算法实现非线性状态估计的研究与仿真

研究交互式多模型算法的非线性状态估计性能,按照工作点把非线性系统线性化为多个子模型,建立多模型自适应状态估计器.利用Monte-Carlo仿真法将其与EKF和UKF算法在不同参数下的噪声抑止能力和鲁棒性进行了比较,并分析了马尔可夫参数和模型个数对算法性能的影响.仿真结果表明该算法能达到理想的估计精度、收敛速度、稳定性和鲁棒性,能克服单一估计器由于参数变化和外部扰动所造成的估计误差过大,甚至发散的问题,能覆盖大范围的参数不确定性.     

基于高斯混合模型的粒子滤波时频分析算法

根据有限高斯混合模型可以逼近任意概率分布密度函数的思想,提出了一种基于高斯混合模型的非平稳信号粒子滤波时频分析算法.本方法兼顾了算法在频率缓变时的估计精度和频率突变时的动态性能,并结合一种简化的TVAR模型,通过降低估计量维度,较大幅度地改善了计算性能,满足了对非平稳信号进行在线时频分析的要求.实测数据的时频分析试验证...     

基于贝叶斯通用背景模型的图像标注

在高斯图特征提取过程中,通用背景模型(Universal background model, UBM) 方法常用于根据总体分布估计每一幅图像中特征点分布的高斯混合模型(Gaussian mixture model, GMM)参数. 然而UBM估计的GMM权重参数中有很多接近零的数值,它们所对应的高斯分量对分布估计贡献小却又都参与了计算, 因此UBM的时间复杂度较高. 为解决这个问题,本文提出Bayes UBM方法. 通过引入受限的对称Dirichlet分布来描述GMM权重参数的先验分布,利用Bayes最大后验概率对GMM参数集进行估计. 实验表明Bayes UBM方法不仅有效地降低了时间复杂度,而且提高了Corel数据集上的图像标注精度.     

基于混合微粒群算法的说话人识别

为了解决传统高斯混合模型(GMM)对初值敏感,在实际训练中极易得到局部最优参数的问题,提出了一种采用微粒群算法优化GMM参数的新方法。该方法将最大似然估计融入到微粒群算法迭代过程中,形成了新的混合算法。它利用微粒群算法的全局优化性及最大似然估计的局部寻优性求解高斯混合模型的参数,以提高参数精度。说话人辨认实验表明,与传统的方法相比,新方法可以得到更优的模型参数,使得系统的识别率进一步提高。     

基于混合高斯模型的窄带目标跟踪方法

基于混合高斯模型的轨迹分布融合方法适用于窄带目标跟踪系统.这种算法针对宽带跟踪结果的不精确,目标模糊,窄带跟踪需要依赖人工实现的问题,提出了一种基于混合高斯模型的自动窄带目标跟踪技术.该方法首先将目标方位分布看做是混合高斯模型,利用期望最大化算法估计混合高斯模型中的参数,然后利用混合高斯模型对目标方位进行聚类,最后利用平均加权法对目标方位进行融合,得到清晰稳定的目标跟踪结果.     

基于动态系统的机器人模仿学习方法研究

针对当前机器人模仿学习过程中,运动模仿存在无法收敛到目标点以及泛化能力差的问题,引入一种基于动态系统（dynamical system,DS）的模仿学习方法。该方法通过高斯混合模型（gaussian mixture model,GMM）将示教运动数据建模为一非线性动态系统;将DS全局稳定的充分条件作为约束,以保证DS所生成的所有轨迹收敛到目标点;将动态系统模型的参数学习问题转化为求解一个约束优化问题,从而得到模型参数。以7bot机械臂为实验对象,进行仿真实验和机器人实验,实验结果表明:该方法学习的DS模型从不同起点生成的所有轨迹都收敛到目标点,轨迹平滑,泛化能力好。     

基于动态MFCC的说话人识别算法

提出了一种基于动态MFCC特征的说话人识别算法.该算法根据说话人的基音频率随语境变化的特点,通过动态构建基于说话人基音频率的Mel-滤波器组,以抽取可以表征说话人身份特征的动态MFCC参数,提高说话人辨识的准确性和鲁棒性.此外,本文还讨论了基于高斯混合模型的分类器设计问题,给出了一个通过聚类分析获得高斯混合模型的最优混合度与相关模型参数的初始估计的方法.实验证明,本文所提出的方法在实际中能够获得较好的识别结果.     

Incremental online sparsification for model learning in real-time robot control

For many applications such as compliant, accurate robot tracking control, dynamics models learned from data can help to achieve both compliant control performance as well as high tracking quality. Online learning of these dynamics models allows the robot controller to adapt itself to changes in the dynamics (e.g., due to time-variant nonlinearities or unforeseen loads). However, online learning in real-time applications - as required in control - cannot be realized by straightforward usage of off-the-shelf machine learning methods such as Gaussian process regression or support vector regression. In this paper, we propose a framework for online, incremental sparsification with a fixed budget designed for fast real-time model learning. The proposed approach employs a sparsification method based on an independence measure. In combination with an incremental learning approach such as incremental Gaussian process regression, we obtain a model approximation method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques. Implementation on a real Barrett WAM robot demonstrates the applicability of the approach in real-time online model learning for real world systems.     

基于GPR和深度强化学习的分层人机协作控制

提出了一种基于高斯过程回归与深度强化学习的分层人机协作控制方法, 并以人机协作控制球杆系统为例检验该方法的高效性. 主要贡献是: 1)在模型未知的情况下, 采用深度强化学习算法设计了一种有效的非线性次优控制策略, 并将其作为顶层期望控制策略以引导分层人机协作控制过程, 解决了传统控制方法无法直接应用于模型未知人机协作场景的问题; 2)针对分层人机协作过程中人未知和随机控制策略带来的不利影响, 采用高斯过程回归拟合人体控制策略以建立机器人对人控制行为的认知模型, 在减弱该不利影响的同时提升机器人在协作过程中的主动性, 从而进一步提升协作效率; 3)利用所得认知模型和期望控制策略设计机器人末端速度的控制律, 并通过实验对比验证了所提方法的有效性.     

Model Learning with Local Gaussian Process Regression

Precise models of robot inverse dynamics allow the design of significantly more accurate, energy-efficient and compliant robot control. However, in some cases the accuracy of rigid-body models does not suffice for sound control performance due to unmodeled nonlinearities arising from hydraulic cable dynamics, complex friction or actuator dynamics. In such cases, estimating the inverse dynamics model from measured data poses an interesting alternative. Nonparametric regression methods, such as Gaussian process regression (GPR) or locally weighted projection regression (LWPR), are not as restrictive as parametric models and, thus, offer a more flexible framework for approximating unknown nonlinearities. In this paper, we propose a local approximation to the standard GPR, called local GPR (LGP), for real-time model online learning by combining the strengths of both regression methods, i.e., the high accuracy of GPR and the fast speed of LWPR. The approach is shown to have competitive learning performance for high-dimensional data while being sufficiently fast for real-time learning. The effectiveness of LGP is exhibited by a comparison with the state-of-the-art regression techniques, such as GPR, LWPR and ν-support vector regression. The applicability of the proposed LGP method is demonstrated by real-time online learning of the inverse dynamics model for robot model-based control on a Barrett WAM robot arm.     

基于改进高斯混合模型的机器人运动状态估计

针对复杂环境下机器人运动状态估计的精度改善问题, 提出一种面向非线性非高斯系统的改进高斯和容积卡尔曼滤波估计方法. 首先, 引入加权信息量概念来改进期望最大化算法目标函数惩罚项, 使得在优化过程中能考虑更全面的参数信息, 以达到减少期望最大化算法的迭代次数和提高收敛速度的目的. 此外, 以基于马氏距离和Kullback-Leibler (KL)距离的高斯项合并方法为基础, 提出一种能有效联合两类高斯项合并方式的融合模式. 先单独使用马氏距离和KL距离进行高斯混合项合并, 再对获得的高斯混合项进行加权融合处理, 以改善高斯和滤波中多高斯项的合并性能和保真度. 最后, 应用非线性非高斯系统的高斯和容积卡尔曼滤波框架实现对复杂环境下机器人的运动状态估计. 理论分析与仿真结果表明, 该方法能实现对机器人运动更好的状态估计精度, 并具有更强的鲁棒性能.     

Prediction of the Posture-Dependent Tool Tip Dynamics in Robotic Milling Based on Multi-Task Gaussian Process Regressions

Chatter vibration is one of the main factors that limit the productivity and quality of the robotic milling process. To predict the robotic milling stability, it is essential to obtain the tool tip frequency response function (FRF). The tool tip dynamics of a robot heavily depend on its postures and used tools. A state-of-art methodology of combining the regression model with the Receptance Coupling Substructure Analysis (RCSA) method is proved to be effective in predicting tool tip FRFs of machine tools for different positions and tools. However, for the milling robot, the cross coupling FRFs have an obvious influence on the dynamic property of the milling robot, thereby greatly affecting the milling stability boundary. It is of great challenge to directly integrate the effect of the cross coupling FRFs into the state-of-art approach to predict the tool tip dynamics. To tackle this challenge, in this paper, we propose an approach to predict the posture-dependent tool tip dynamics for different tools in robotic milling considering the cross coupling FRFs. First, a more comprehensive RCSA procedure is adopted to include the cross coupling FRFs. Then, the impact test is designed to measure the required FRF matrix. By fitting the measured FRF matrix with the multiple-degree-of-freedom (MDOF) model, the number of modal parameters is significantly reduced. Next, the Multi-Task Gaussian Process (MTGP) regression model is employed to mine the physical correlations between different modal parameters. Compared to the ordinary Gaussian Process regression model, the number of required regression models in MTGP is reduced and the prediction performance is improved in terms of accuracy and robustness. Furthermore, the effectiveness of the proposed approach is validated by the impact test and milling experiment on an industrial robot.     

Balance Control of a Biped Robot on a Rotating Platform Based on Efficient Reinforcement Learning

In this work, we combined the model based reinforcement learning (MBRL) and model free reinforcement learning (MFRL) to stabilize a biped robot (NAO robot) on a rotating platform, where the angular velocity of the platform is unknown for the proposed learning algorithm and treated as the external disturbance. Nonparametric Gaussian processes normally require a large number of training data points to deal with the discontinuity of the estimated model. Although some improved method such as probabilistic inference for learning control (PILCO) does not require an explicit global model as the actions are obtained by directly searching the policy space, the overfitting and lack of model complexity may still result in a large deviation between the prediction and the real system. Besides, none of these approaches consider the data error and measurement noise during the training process and test process, respectively. We propose a hierarchical Gaussian processes (GP) models, containing two layers of independent GPs, where the physically continuous probability transition model of the robot is obtained. Due to the physically continuous estimation, the algorithm overcomes the overfitting problem with a guaranteed model complexity, and the number of training data is also reduced. The policy for any given initial state is generated automatically by minimizing the expected cost according to the predefined cost function and the obtained probability distribution of the state. Furthermore, a novel Q(λ) based MFRL method scheme is employed to improve the policy. Simulation results show that the proposed RL algorithm is able to balance NAO robot on a rotating platform, and it is capable of adapting to the platform with varying angular velocity.      

基于多源信息融合的协作机器人演示编程及优化方法

为解决现有机器人装配学习过程复杂且对编程技术要求高等问题,提出一种基于前臂表面肌电信号和惯性多源信息融合的隐式交互方式来实现机器人演示编程.在通过演示学习获得演示人的装配经验的基础上,为提高对装配对象和环境变化的自适应能力,提出了一种多工深度确定性策略梯度算法（M-DDPG）来修正装配参数,在演示编程的基础上,进行强化学习确保机器人稳定执行任务.在演示编程实验中,提出一种改进的PCNN（并行卷积神经网络）,称作1维PCNN（1D-PCNN）,即通过1维的卷积与池化过程自动提取惯性信息与肌电信息特征,增强了手势识别的泛化性和准确率;在演示再现实验中,采用高斯混合模型（GMM）对演示数据进行统计编码,利用高斯混合回归（GMR）方法实现机器人轨迹动作再现,消除噪声点.最后,基于Primesense Carmine摄像机采用帧差法与多特征图核相关滤波算法（MKCF）的融合跟踪算法分别获取X轴与Y轴方向的环境变化,采用2个相同的网络结构并行进行连续过程的深度强化学习.在轴孔相对位置变化的情况下,机械臂能根据强化学习得到的泛化策略模型自动对机械臂末端位置进行调整,实现轴孔装配的演示学习.     

A nonparametric Bayesian approach toward robot learning by demonstration

In the past years, many authors have considered application of machine learning methodologies to effect robot learning by demonstration. Gaussian mixture regression (GMR) is one of the most successful methodologies used for this purpose. A major limitation of GMR models concerns automatic selection of the proper number of model states, i.e., the number of model component densities. Existing methods, including likelihood- or entropy-based criteria, usually tend to yield noisy model size estimates while imposing heavy computational requirements. Recently, Dirichlet process (infinite) mixture models have emerged in the cornerstone of nonparametric Bayesian statistics as promising candidates for clustering applications where the number of clusters is unknown a priori. Under this motivation, to resolve the aforementioned issues of GMR-based methods for robot learning by demonstration, in this paper we introduce a nonparametric Bayesian formulation for the GMR model, the Dirichlet process GMR model. We derive an efficient variational Bayesian inference algorithm for the proposed model, and we experimentally investigate its efficacy as a robot learning by demonstration methodology, considering a number of demanding robot learning by demonstration scenarios.     

基于深度强化学习的双足机器人斜坡步态控制方法

为提高准被动双足机器人斜坡步行稳定性, 本文提出了一种基于深度强化学习的准被动双足机器人步态控制方法. 通过分析准被动双足机器人的混合动力学模型与稳定行走过程, 建立了状态空间、动作空间、episode过程与奖励函数. 在利用基于DDPG改进的Ape-X DPG算法持续学习后, 准被动双足机器人能在较大斜坡范围内实现稳定行走. 仿真实验表明, Ape-X DPG无论是学习能力还是收敛速度均优于基于PER的DDPG. 同时, 相较于能量成型控制, 使用Ape-X DPG的准被动双足机器人步态收敛更迅速、步态收敛域更大, 证明Ape-X DPG可有效提高准被动双足机器人的步行稳定性.