A framework for robotic clothing assistance by imitation learning

ABSTRACT

The recent demographic trend across developed nations shows a dramatic increase in the aging population, fallen fertility rates and a shortage of caregivers. Hence, the demand for service robots to assist with dressing which is an essential Activity of Daily Living (ADL) is increasing rapidly. Robotic Clothing Assistance is a challenging task since the robot has to deal with two demanding tasks simultaneously, (a) non-rigid and highly flexible cloth manipulation and (b) safe human–robot interaction while assisting humans whose posture may vary during the task. On the other hand, humans can deal with these tasks rather easily. In this paper, we propose a framework for robotic clothing assistance by imitation learning from a human demonstration to a compliant dual-arm robot. In this framework, we divide the dressing task into three phases, i.e. reaching phase, arm dressing phase, and body dressing phase. We model the arm dressing phase as a global trajectory modification using Dynamic Movement Primitives (DMP), while we model the body dressing phase toward a local trajectory modification applying Bayesian Gaussian Process Latent Variable Model (BGPLVM). We show that the proposed framework developed towards assisting the elderly is generalizable to various people and successfully performs a sleeveless shirt dressing task. We also present participants feedback on public demonstration at the International Robot Exhibition (iREX) 2017. To our knowledge, this is the first work performing a full dressing of a sleeveless shirt on a human subject with a humanoid robot.     

Dynamic motion learning for multi-DOF flexible-joint robots using active–passive motor babbling through deep learning

This paper proposes a learning strategy for robots with flexible joints having multi-degrees of freedom in order to achieve dynamic motion tasks. In spite of there being several potential benefits of flexible-joint robots such as exploitation of intrinsic dynamics and passive adaptation to environmental changes with mechanical compliance, controlling such robots is challenging because of increased complexity of their dynamics. To achieve dynamic movements, we introduce a two-phase learning framework of the body dynamics of the robot using a recurrent neural network motivated by a deep learning strategy. The proposed methodology comprises a pre-training phase with motor babbling and a fine-tuning phase with additional learning of the target tasks. In the pre-training phase, we consider active and passive exploratory motions for efficient acquisition of body dynamics. In the fine-tuning phase, the learned body dynamics are adjusted for specific tasks. We demonstrate the effectiveness of the proposed methodology in achieving dynamic tasks involving constrained movement requiring interactions with the environment on a simulated robot model and an actual PR2 robot both of which have a compliantly actuated seven degree-of-freedom arm. The results illustrate a reduction in the required number of training iterations for task learning and generalization capabilities for untrained situations.     

结合层次分割和跨域字典学习的服装检索

目的 针对现有的跨场景服装检索框架在服装躯干部分检索问题上,因服装款式识别优化存在服装信息丢失和跨场景款式识别的问题,提出一种新的服装分割方法和基于跨域字典学习的服装款式识别。方法 首先,提出基于超像素融合和姿态估计相结合的方法分割出完整的服装,用完整的服装进行检索可以最大限度地保留服装信息。然后,在服装款式识别时,通过学习服装商品数据集与日常服装图像数据的中间数据集字典,使其逐渐适应日常服装图像数据的方式,调节字典的适应性,进而提高不同场景下的服装款式识别的准确性。另外,由于目前国际缺少细粒度标注的大型服装数据库,本文构建了2个细粒度标注的服装数据库。结果 在公认的Fashionista服装数据集及本文构建的数据库上验证本文方法并与目前国际上流行的方法进行对比,本文方法在上下装检索中精度达到62.1%和63.4%,本文方法在服装分割、款式识别,检索方面的准确度要优于当前前沿的方法。结论 针对现有的跨场景服装检索框架分割服装不准确的问题,提出一种新的层次服装过分割融合方法及域自适应跨域服装款式识别方法,保证了服装的完整性,提高了跨场景服装检索及款式识别的精度,适用于日常服装检索。     

结合深度多标签解析的哈希服装检索

目的 服装检索对于在线服装的推广和销售有着重要的作用。而目前的服装检索算法无法准确地检索出非文本描述的服装。特别是对于跨场景的多标签服装图片,服装检索算法的准确率还有待提升。本文针对跨场景多标签服装图片的差异性较大以及卷积神经网络输出特征维度过高的问题,提出了深度多标签解析和哈希的服装检索算法。方法 该方法首先在FCN（fully convolutional network）的基础上加入条件随机场,对FCN的结果进行后处理,搭建了FCN粗分割加CRFs（conditional random fields）精分割的端到端的网络结构,实现了像素级别的语义识别。其次,针对跨场景服装检索的特点,我们调整了CCP（Clothing Co-Parsing）数据集,并构建了Consumer-to-Shop数据集。针对检索过程中容易出现的语义漂移现象,使用多任务学习网络分别训练了衣物分类模型和衣物相似度模型。结果 我们首先在Consumer-to-Shop数据集上进行了服装解析的对比实验,实验结果表明在添加了CRFs作为后处理之后,服装解析的效果有了明显提升。然后与3种主流检索算法进行了对比,结果显示,本文方法在使用哈希特征的条件下,也可以取得较好的检索效果。在top-5正确率上比WTBI（where to buy it）高出1.31%,比DARN（dual attribute-aware ranking network）高出0.21%。结论 针对服装检索的跨场景效果差、检索效率低的问题,本文提出了一种基于像素级别语义分割和哈希编码的快速多目标服装检索方法。与其他检索方法相比,本文在多目标、多标签服装检索场景有一定的优势,并且在保持了一定检索效果的前提下,有效地降低了存储空间,提高了检索效率。     

Towards physical interaction-based sequential mobility assistance using latent generative model of movement state

ABSTRACT

In this paper, we address sequential mobility assistance for daily elderly care through physical human–robot interaction. The goal of this work is to develop a robotic assistive system to provide physical support in daily life such as movement transition, e.g. sit-to-stand and walking. Using a mobile human support robotic platform, we propose an unsupervised learning-based approach to providing desirable physical support through an adaptive impedance parameter selection strategy according to the recognized user's movement state in an online manner. Using a latent generative model with a long short-term memory-based variational autoencoder, we first estimate the probability of the user's current movement state based on the sensory information in a low dimensional latent space. Then, the desired impedance parameters are selected adaptively according to the estimated movement state. One of the benefits of such an unsupervised learning approach is that no labeling is necessary in the training phase. Furthermore, our proposed framework is capable of detecting possible novel states such as falling over based on the obtained latent space. In order to demonstrate the proof of concept of our proposed approach, we present the experimental results of performance evaluations of online movement state recognition as well as novel movement detection.     

Human–robot skills transfer interfaces for a flexible surgical robot

In minimally invasive surgery, tools go through narrow openings and manipulate soft organs to perform surgical tasks. There are limitations in current robot-assisted surgical systems due to the rigidity of robot tools. The aim of the STIFF-FLOP European project is to develop a soft robotic arm to perform surgical tasks. The flexibility of the robot allows the surgeon to move within organs to reach remote areas inside the body and perform challenging procedures in laparoscopy. This article addresses the problem of designing learning interfaces enabling the transfer of skills from human demonstration. Robot programming by demonstration encompasses a wide range of learning strategies, from simple mimicking of the demonstrator's actions to the higher level imitation of the underlying intent extracted from the demonstrations. By focusing on this last form, we study the problem of extracting an objective function explaining the demonstrations from an over-specified set of candidate reward functions, and using this information for self-refinement of the skill. In contrast to inverse reinforcement learning strategies that attempt to explain the observations with reward functions defined for the entire task (or a set of pre-defined reward profiles active for different parts of the task), the proposed approach is based on context-dependent reward-weighted learning, where the robot can learn the relevance of candidate objective functions with respect to the current phase of the task or encountered situation. The robot then exploits this information for skills refinement in the policy parameters space. The proposed approach is tested in simulation with a cutting task performed by the STIFF-FLOP flexible robot, using kinesthetic demonstrations from a Barrett WAM manipulator.     

Efficient Exploration for Multi-Agent Reinforcement Learning via Transferable Successor Features

In multi-agent reinforcement learning (MARL), the behaviors of each agent can influence the learning of others, and the agents have to search in an exponentially enlarged joint-action space. Hence, it is challenging for the multi-agent teams to explore in the environment. Agents may achieve suboptimal policies and fail to solve some complex tasks. To improve the exploring efficiency as well as the performance of MARL tasks, in this paper, we propose a new approach by transferring the knowledge across tasks. Differently from the traditional MARL algorithms, we first assume that the reward functions can be computed by linear combinations of a shared feature function and a set of task-specific weights. Then, we define a set of basic MARL tasks in the source domain and pre-train them as the basic knowledge for further use. Finally, once the weights for target tasks are available, it will be easier to get a well-performed policy to explore in the target domain. Hence, the learning process of agents for target tasks is speeded up by taking full use of the basic knowledge that was learned previously. We evaluate the proposed algorithm on two challenging MARL tasks: cooperative box-pushing and non-monotonic predator-prey. The experiment results have demonstrated the improved performance compared with state-of-the-art MARL algorithms.      

Unified framework for representing and ranking

In the database retrieval and nearest neighbor classification tasks, the two basic problems are to represent the query and database objects, and to learn the ranking scores of the database objects to the query. Many studies have been conducted for the representation learning and the ranking score learning problems, however, they are always learned independently from each other. In this paper, we argue that there are some inner relationships between the representation and ranking of database objects, and try to investigate their relationships by learning them in a unified way. To this end, we proposed the Unified framework for Representation and Ranking (UR²) of objects for the database retrieval and nearest neighbor classification tasks. The learning of representation parameter and the ranking scores are modeled within one single unified objective function. The objective function is optimized alternately with regard to representation parameter and the ranking scores. Based on the optimization results, iterative algorithms are developed to learn the representation parameter and the ranking scores on a unified way. Moreover, with two different formulas of representation (feature selection and subspace learning), we give two versions of UR². The proposed algorithms are tested on two challenging tasks – MRI image based brain tumor retrieval and nearest neighbor classification based protein identification. The experiments show the advantage of the proposed unified framework over the state-of-the-art independent representation and ranking methods.     

多模态引导的局部特征选择小样本学习方法

深度学习模型取得了令人瞩目的成绩,但其训练依赖于大量的标注样本,在标注样本匮乏的场景下模型表现不尽人意.针对这一问题,近年来以研究如何从少量样本快速学习的小样本学习被提了出来,方法主要采用元学习方式对模型进行训练,取得了不错的学习效果.但现有方法:1)通常仅基于样本的视觉特征来识别新类别,信息源较为单一; 2)元学习的使用使得模型从大量相似的小样本任务中学习通用的、可迁移的知识,不可避免地导致模型特征空间趋于一般化,存在样本特征表达不充分、不准确的问题.为解决上述问题,将预训练技术和多模态学习技术引入小样本学习过程,提出基于多模态引导的局部特征选择小样本学习方法.所提方法首先在包含大量样本的已知类别上进行模型预训练,旨在提升模型的特征表达能力;而后在元学习阶段,方法利用元学习对模型进行进一步优化,旨在提升模型的迁移能力或对小样本环境的适应能力,所提方法同时基于样本的视觉特征和文本特征进行局部特征选择来提升样本特征的表达能力,以避免元学习过程中模型特征表达能力的大幅下降;最后所提方法利用选择后的样本特征进行小样本学习.在MiniImageNet、CIFAR-FS和FC-100这3个基准数...     

Obstacle Modelling Oriented to Safe Motion Planning and Control for Planar Rigid Robot Manipulators

Trajectory planning and tracking are crucial tasks in any application using robot manipulators. These tasks become particularly challenging when obstacles are present in the manipulator workspace. In this paper a n-joint planar robot manipulator is considered and it is assumed that obstacles located in its workspace can be approximated in a conservative way with circles. The goal is to represent the obstacles in the robot configuration space. The representation allows to obtain an efficient and accurate trajectory planning and tracking. A simple but effective path planning strategy is proposed in the paper. Since path planning depends on tracking accuracy, in this paper an adequate tracking accuracy is guaranteed by means of a suitably designed Second Order Sliding Mode Controller (SOSMC). The proposed approach guarantees a collision-free motion of the manipulator in its workspace in spite of the presence of obstacles, as confirmed by experimental results.     

Task Transfer by a Developmental Robot

Scaffolding is a process of transferring learned skills to new and more complex tasks through arranged experience in open-ended development. In this paper, we propose a developmental learning architecture that enables a robot to transfer skills acquired in early learning settings to later more complex task settings. We show that a basic mechanism that enables this transfer is sequential priming combined with attention, which is also the driving mechanism for classical conditioning, secondary conditioning, and instrumental conditioning in animal learning. A major challenge of this work is that training and testing must be conducted in the same program operational mode through online, real-time interactions between the agent and the trainers. In contrast with former modeling studies, the proposed architecture does not require the programmer to know the tasks to be learned and the environment is uncontrolled. All possible perceptions and actions, including the actual number of classes, are not available until the programming is finished and the robot starts to learn in the real world. Thus, a predesigned task-specific symbolic representation is not suited for such an open-ended developmental process. Experimental results on a robot are reported in which the trainer shaped the behaviors of the agent interactively, continuously, and incrementally through verbal commands and other sensory signals so that the robot learns new and more complex sensorimotor tasks by transferring sensorimotor skills learned in earlier periods of open-ended development     

结合面料属性和触觉感测的织物识别

目的 织物识别是提高纺织业竞争力的重要计算机辅助技术。与通用图像相比,织物图像通常只在纹理和形状特征方面呈现细微差异。目前常见的织物识别算法仅考虑图像特征,未结合织物面料的视觉和触觉特征,不能反映出织物本身面料属性,导致识别准确率较低。本文以常见服用织物为例,针对目前常见织物面料识别准确率不高的问题,提出一种结合面料属性和触觉感测的织物图像识别算法。方法 针对输入的织物样本,建立织物图像的几何测量方法,量化分析影响织物面料属性的3个关键因素,即恢复性、拉伸性和弯曲性,并进行面料属性的参数化建模,得到面料属性的几何度量。通过传感器设置对织物进行触感测量,采用卷积神经网络（convolutional neural network,CNN）提取测量后的织物触感图像的底层特征。将面料属性几何度量与提取的底层特征进行匹配,通过CNN训练得到织物面料识别模型,学习织物面料属性的不同参数,实现织物面料的识别并输出识别结果。结果 在构建的常见服用织物样本上验证了本文方法,与同任务的方法比较,本文方法识别率更高,平均识别率达到89.5%。结论 提出了一种基于面料属性和触觉感测的织物图像识别方法,能准确识别常用的服装织物面料,有效提高了织物识别的准确率,能较好地满足实际应用需求。     

杂乱场景下小物体抓取检测研究

目的 杂乱场景下的物体抓取姿态检测是智能机器人的一项基本技能。尽管六自由度抓取学习取得了进展,但先前的方法在采样和学习中忽略了物体尺寸差异,导致在小物体上抓取表现较差。方法 提出了一种物体掩码辅助采样方法,在所有物体上采样相同的点以平衡抓取分布,解决了采样点分布不均匀问题。此外,学习时采用多尺度学习策略,在物体部分点云上使用多尺度圆柱分组以提升局部几何表示能力,解决了由物体尺度差异导致的学习抓取操作参数困难问题。通过设计一个端到端的抓取网络,嵌入了提出的采样和学习方法,能够有效提升物体抓取检测性能。结果 在大型基准数据集GraspNet-1Billion上进行评估,本文方法取得对比方法中的最优性能,其中在小物体上的抓取指标平均提升了7%,大量的真实机器人实验也表明该方法具有抓取未知物体的良好泛化性能。结论 本文聚焦于小物体上的抓取,提出了一种掩码辅助采样方法嵌入到提出的端到端学习网络中,并引入了多尺度分组学习策略提高物体的局部几何表示,能够有效提升在小尺寸物体上的抓取质量,并在所有物体上的抓取评估结果都超过了对比方法。     

Combat data shift in few-shot learning with knowledge graph

Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from various data distributions. Most existing few-shot learning approaches are not designed with the consideration of data shift, and thus show downgraded performance when data distribution shifts. However, it is non-trivial to address the data shift problem in few-shot learning, due to the limited number of labeled samples in each task. Targeting at addressing this problem, we propose a novel metric-based meta-learning framework to extract task-specific representations and task-shared representations with the help of knowledge graph. The data shift within/between tasks can thus be combated by the combination of task-shared and task-specific representations. The proposed model is evaluated on popular benchmarks and two constructed new challenging datasets. The evaluation results demonstrate its remarkable performance.     

Latent semantic factorization for multimedia representation learning

Due to the rapid development of multimedia applications, cross-media semantics learning is becoming increasingly important nowadays. One of the most challenging issues for cross-media semantics understanding is how to mine semantic correlation between different modalities. Most traditional multimedia semantics analysis approaches are based on unimodal data cases and neglect the semantic consistency between different modalities. In this paper, we propose a novel multimedia representation learning framework via latent semantic factorization (LSF). First, the posterior probability under the learned classifiers is served as the latent semantic representation for different modalities. Moreover, we explore the semantic representation for a multimedia document, which consists of image and text, by latent semantic factorization. Besides, two projection matrices are learned to project images and text into a same semantic space which is more similar with the multimedia document. Experiments conducted on three real-world datasets for cross-media retrieval, demonstrate the effectiveness of our proposed approach, compared with state-of-the-art methods.

     

整合全局—局部度量学习的人体目标再识别

目的 人体目标再识别的任务是匹配不同摄像机在不同时间、地点拍摄的人体目标。受光照条件、背景、遮挡、视角和姿态等因素影响,不同摄相机下的同一目标表观差异较大。目前研究主要集中在特征表示和度量学习两方面。很多度量学习方法在人体目标再识别问题上了取得了较好的效果,但对于多样化的数据集,单一的全局度量很难适应差异化的特征。对此,有研究者提出了局部度量学习,但这些方法通常需要求解复杂的凸优化问题,计算繁琐。方法 利用局部度量学习思想,结合近几年提出的XQDA（cross-view quadratic discriminant analysis）和MLAPG（metric learning by accelerated proximal gradient）等全局度量学习方法,提出了一种整合全局和局部度量学习框架。利用高斯混合模型对训练样本进行聚类,在每个聚类内分别进行局部度量学习;同时在全部训练样本集上进行全局度量学习。对于测试样本,根据样本在高斯混合模型各个成分下的后验概率将局部和全局度量矩阵加权结合,作为衡量相似性的依据。特别地,对于MLAPG算法,利用样本在各个高斯成分下的后验概率,改进目标损失函数中不同样本的损失权重,进一步提高该方法的性能。结果 在VIPeR、PRID 450S和QMUL GRID数据集上的实验结果验证了提出的整合全局—局部度量学习方法的有效性。相比于XQDA和MLAPG等全局方法,在VIPeR数据集上的匹配准确率提高2.0%左右,在其他数据集上的性能也有不同程度的提高。另外,利用不同的特征表示对提出的方法进行实验验证,相比于全局方法,匹配准确率提高1.3%~3.4%左右。结论 有效地整合了全局和局部度量学习方法,既能对多种全局度量学习算法的性能做出改进,又能避免局部度量学习算法复杂的计算过程。实验结果表明,对于使用不同的特征表示,提出的整合全局—局部度量学习框架均可对全局度量学习方法做出改进。     

Robot Position/Force Control in Unknown Environment Using Hybrid Reinforcement Learning

Abstract

Robot position/force control provides an interaction scheme between the robot and the environment. When the environment is unknown, learning algorithms are needed. But, the learning space and learning time are big. To balance the learning accuracy and the learning time, we propose a hybrid reinforcement learning method, which can be in both discrete and continuous domains. The discrete-time learning has poor learning accuracy and less learning time. The continuous-time learning is slow but has better learning precision. This hybrid reinforcement learning learns the optimal contact force, meanwhile it minimizes the position error in the unknown environment. Convergence of the proposed learning algorithm is proven. Real-time experiments are carried out using the pan and tilt robot and the force/torque sensor.     

元迁移学习在少样本跨域图像分类中的研究

目的 现有基于元学习的主流少样本学习方法假设训练任务和测试任务服从相同或相似的分布,然而在分布差异较大的跨域任务上,这些方法面临泛化能力弱、分类精度差等挑战。同时,基于迁移学习的少样本学习方法没有考虑到训练和测试阶段样本类别不一致的情况,在训练阶段未能留下足够的特征嵌入空间。为了提升模型在有限标注样本困境下的跨域图像分类能力,提出简洁的元迁移学习（compressed meta transfer learning,CMTL）方法。方法 基于元学习,对目标域中的支持集使用数据增强策略,构建新的辅助任务微调元训练参数,促使分类模型更加适用于域差异较大的目标任务。基于迁移学习,使用自压缩损失函数训练分类模型,以压缩源域中基类数据所占据的特征嵌入空间,微调阶段引导与源域分布差异较大的新类数据有更合适的特征表示。最后,将以上两种策略的分类预测融合视为最终的分类结果。结果 使用mini-ImageNet作为源域数据集进行训练,分别在EuroSAT(EuropeanSatellite)、ISIC(InternationalSkinImagingCollaboration)、CropDiseas(Cr...     

结合人体检测和多任务学习的少数民族服装识别

目的 少数民族服装色彩及样式种类繁多等因素导致少数民族服装图像识别率较低。以云南少数民族服装为例,提出一种结合人体检测和多任务学习的少数民族服装识别方法。方法 首先通过k-poselets对输入的待识别图像和少数民族服装图像集中的训练图像进行人体整体和局部检测以及关键点的预测;其次,根据检测结果,从待识别图像和训练图像中分别提取颜色直方图、HOG （histogram of oriented gradient）、LBP（local binary pattern）、SIFT（scale invariant feature transform）以及边缘算子5种底层特征;然后,将自定义的少数民族服装语义属性与提取的底层特征进行匹配,采用多任务学习训练分类器模型,以学习少数民族服装的不同风格;最后实现少数民族服装图像的识别并输出识别结果。另外,由于目前缺少大型的少数民族服装数据集,本文构建了一个云南少数民族服装图像集。结果 在构建的云南少数民族服装图像集上验证了本文方法,识别精度达到82.5%88.4%,并与单任务学习方法进行比较,本文方法识别率更高。结论 针对现有的少数民族服装识别率较低的问题,提出一种结合人体检测和多任务学习的少数民族服装识别方法,提高了少数民族服装图像识别的准确率和效率,同时能较好地满足实际应用需求。     

Canonical locality preserving Latent Variable Model for discriminative pose inference

Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D poses. Learning such multi-modal models in high dimensional spaces, however, is challenging with limited training data; often resulting in over-fitting and poor generalization. To address these issues Latent Variable Models (LVMs) have been introduced. Shared LVMs learn a low dimensional representation of common causes that give rise to both the image features and the 3D pose. Discovering the shared manifold structure can, in itself, however, be challenging. In addition, shared LVM models are often non-parametric, requiring the model representation to be a function of the training set size. We present a parametric framework that addresses these shortcomings. In particular, we jointly learn latent spaces for both image features and 3D poses by maximizing the non-linear dependencies in the projected latent space, while preserving local structure in the original space; we then learn a multi-modal conditional density between these two low-dimensional spaces in the form of Gaussian Mixture Regression. With this model we can address the issue of over-fitting and generalization, since the data is denser in the learned latent space, as well as avoid the need for learning a shared manifold for the data. We quantitatively compare the performance of the proposed method to several state-of-the-art alternatives, and show that our method gives a competitive performance.