Position estimation of a mobile robot using images of a moving target in intelligent space with distributed sensors

Latest advances in hardware technology and state-of-the-art of mobile robots and artificial intelligence research can be employed to develop autonomous and distributed monitoring systems. A mobile service robot requires the perception of its present position to co-exist with humans and support humans effectively in populated environments. To realize this, a robot needs to keep track of relevant changes in the environment. This paper proposes localization of a mobile robot using images recognized by distributed intelligent networked devices in intelligent space (ISpace) in order to achieve these goals. This scheme combines data from the observed position, using dead-reckoning sensors, and the estimated position, using images of moving objects, such as a walking human captured by a camera system, to determine the location of a mobile robot. The moving object is assumed to be a point-object and projected onto an image plane to form a geometrical constraint equation that provides position data of the object based on the kinematics of the ISpace. Using the a priori known path of a moving object and a perspective camera model, the geometric constraint equations that represent the relation between image frame coordinates for a moving object and the estimated robot's position are derived. The proposed method utilizes the error between the observed and estimated image coordinates to localize the mobile robot, and the Kalman filtering scheme is used for the estimation of the mobile robot location. The proposed approach is applied for a mobile robot in ISpace to show the reduction of uncertainty in determining the location of a mobile robot, and its performance is verified by computer simulation and experiment.     

Learning to recognize three-dimensional objects

A learning account for the problem of object recognition is developed within the probably approximately correct (PAC) model of learnability. The key assumption underlying this work is that objects can be recognized (or discriminated) using simple representations in terms of syntactically simple relations over the raw image. Although the potential number of these simple relations could be huge, only a few of them are actually present in each observed image, and a fairly small number of those observed are relevant to discriminating an object. We show that these properties can be exploited to yield an efficient learning approach in terms of sample and computational complexity within the PAC model. No assumptions are needed on the distribution of the observed objects, and the learning performance is quantified relative to its experience. Most important, the success of learning an object representation is naturally tied to the ability to represent it as a function of some intermediate representations extracted from the image. We evaluate this approach in a large-scale experimental study in which the SNoW learning architecture is used to learn representations for the 100 objects in the Columbia Object Image Library. Experimental results exhibit good generalization and robustness properties of the SNoW-based method relative to other approaches. SNoW's recognition rate degrades more gracefully when the training data contains fewer views, and it shows similar behavior in some preliminary experiments with partially occluded objects.     

Efficient pose estimation using view-based object representations

We present an efficient method for estimating the pose of a three-dimensional object. Its implementation is embedded in a computer vision system which is motivated by and based on cognitive principles concerning the visual perception of three-dimensional objects. Viewpoint-invariant object recognition has been subject to controversial discussions for a long time. An important point of discussion is the nature of internal object representations. Behavioral studies with primates, which are summarized in this article, support the model of view-based object representations. We designed our computer vision system according to these findings and demonstrate that very precise estimations of the poses of real-world objects are possible even if only a small number of sample views of an object is available. The system can be used for a variety of applications.     

Weighted attentional blocks for probabilistic object tracking

In this paper we represent the object with multiple attentional blocks which reflect some findings of selective visual attention in human perception. The attentional blocks are extracted using a branch-and-bound search method on the saliency map, and meanwhile the weight of each block is determined. Independent particle filter tracking is applied to each attentional block and the tracking results of all the blocks are then combined in a linear weighting scheme to get the location of the entire target object. The attentional blocks are propagated to the object location found in each new frame and the state of the most likely particle in each block is also updated with the new propagated position. In addition, to avoid error accumulation caused by the appearance variations, the object template and the positions of the attentional blocks are adaptively updated while tracking. Experimental results show that the proposed algorithm is able to efficiently track salient objects and is better accounted for partial occlusions and large variations in appearance.     

Discovering and restoring changes in object positions using an autonomous robot with laser rangefinders

This paper describes an object rearrangement system for an autonomous mobile robot. The objective of the robot is to autonomously explore and learn about an environment, to detect changes in the environment on a later visit after object disturbances and finally, to move objects back to their original positions. In the implementation, it is assumed that the robot does not have any prior knowledge of the environment and the positions of the objects. The system exploits Simultaneous Localisation and Mapping (SLAM) and autonomous exploration techniques to achieve the task. These techniques allow the robot to perform localisation and mapping which is required to perform the object rearrangement task autonomously. The system includes an arrangement change detector, object tracking and map update that work with a Polar Scan Match (PSM) Extended Kalman Filter (EKF) SLAM system. In addition, a path planning technique for dragging and pushing an object is also presented in this paper. Experimental results of the integrated approach are shown to demonstrate that the proposed approach provides real-time autonomous object rearrangements by a mobile robot in an initially unknown real environment. Experiments also show the limits of the system by investigating failure modes.     

Invariant object recognition with trace learning and multiple stimuli present during training

Over successive stages, the ventral visual system develops neurons that respond with view, size and position invariance to objects including faces. A major challenge is to explain how invariant representations of individual objects could develop given visual input from environments containing multiple objects. Here we show that the neurons in a 1-layer competitive network learn to represent combinations of three objects simultaneously present during training if the number of objects in the training set is low (e.g. 4), to represent combinations of two objects as the number of objects is increased to for e.g. 10, and to represent individual objects as the number of objects in the training set is increased further to for e.g. 20. We next show that translation invariant representations can be formed even when multiple stimuli are always present during training, by including a temporal trace in the learning rule. Finally, we show that these concepts can be extended to a multi-layer hierarchical network model (VisNet) of the ventral visual system. This approach provides a way to understand how a visual system can, by self-organizing competitive learning, form separate invariant representations of each object even when each object is presented in a scene with multiple other objects present, as in natural visual scenes.     

A CAD Model Based System for Object Recognition

3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major components, namely: an object modeller and a system that performs the matching of stored representations to those derived from the sensed image. The performance of systems wherein the construction of object models is done by training from one or more images of the objects, has not been very satisfactory. Although objects used in a robotic workcell or in assembly processes have been designed using a CAD system, the vision systems used for recognition of these objects are independent of the CAD database. This paper proposes a scheme for interfacing the CAD database of objects and the computer vision processes used for recognising these objects. CAD models of objects are processed to generate vision oriented features that appear in the different views of the object and the same features are extracted from images of the object to identify the object and its pose.     

基于局部自适应核回归的仪表定位方法

计算机视觉技术不断发展,利用巡检机器人对钻井平台、水电工程等复 杂工业环境下的各种仪表设备进行定期检查成为可能,然而这些功能的实现依赖仪表的精准 定位。本文提出一种基于局部自适应核回归（Locally adaptive regression kernels,LARK）的方法进行仪表的快速定位。LARK算 法无需训练,可以快速搜索感兴趣的视觉对象,并且不需要进行过多的预处理,提高了 定位的效率。通过提取查询图像的显著特征,在目标图像中寻找所有可能相似的 对象,然后用非极大值抑制法保留最强相似点,实现目标对象的定位。实验选用从不同角度 拍摄的具有不同放缩比例的仪表图像作为实验所需数据。实验结果表明,该算法定位准确度 高,可以很好地满足工业环境下仪表的定位要求。     

基于模糊逻辑的图像检索研究

提出一个基于模糊逻辑的图像检索系统.该系统使用模糊语言变量描述图像特征之间的相似性程度,而非图像特征本身,使得图像相似性推理能以非线性方式进行;模糊规则建立在用户对对象的认知基础之上,能够反映用户主观感知.由于具有相似特征变化范围的不同对象可以适用于相同的规则,使得算法对检索图像的不同类别具有良好的鲁棒性.另外,提出一种改进的直方图--平均面积直方图,以提取色彩特征.实验结果表明了模糊检索系统的有效性与可行性.     

Active learning of visual descriptors for grasping using non-parametric smoothed beta distributions

One of the basic skills for a robot autonomous grasping is to select the appropriate grasping point for an object. Several recent works have shown that it is possible to learn grasping points from different types of features extracted from a single image or from more complex 3D reconstructions. In the context of learning through experience, this is very convenient, since it does not require a full reconstruction of the object and implicitly incorporates kinematic constraints as the hand morphology. These learning strategies usually require a large set of labeled examples which can be expensive to obtain. In this paper, we address the problem of actively learning good grasping points to reduce the number of examples needed by the robot. The proposed algorithm computes the probability of successfully grasping an object at a given location represented by a feature vector. By autonomously exploring different feature values on different objects, the systems learn where to grasp each of the objects. The algorithm combines beta–binomial distributions and a non-parametric kernel approach to provide the full distribution for the probability of grasping. This information allows to perform an active exploration that efficiently learns good grasping points even among different objects. We tested our algorithm using a real humanoid robot that acquired the examples by experimenting directly on the objects and, therefore, it deals better with complex (anthropomorphic) hand–object interactions whose results are difficult to model, or predict. The results show a smooth generalization even in the presence of very few data as is often the case in learning through experience.     

EL-E: an assistive mobile manipulator that autonomously fetches objects from flat surfaces

Assistive mobile robots that autonomously manipulate objects within everyday settings have the potential to improve the lives of the elderly, injured, and disabled. Within this paper, we present the most recent version of the assistive mobile manipulator EL-E with a focus on the subsystem that enables the robot to retrieve objects from and deliver objects to flat surfaces. Once provided with a 3D location via brief illumination with a laser pointer, the robot autonomously approaches the location and then either grasps the nearest object or places an object. We describe our implementation in detail, while highlighting design principles and themes, including the use of specialized behaviors, task-relevant features, and low-dimensional representations. We also present evaluations of EL-E’s performance relative to common forms of variation. We tested EL-E’s ability to approach and grasp objects from the 25 object categories that were ranked most important for robotic retrieval by motor-impaired patients from the Emory ALS Center. Although reliability varied, EL-E succeeded at least once with objects from 21 out of 25 of these categories. EL-E also approached and grasped a cordless telephone on 12 different surfaces including floors, tables, and counter tops with 100% success. The same test using a vitamin pill (ca. 15 mm × 5 mm × 5 mm) resulted in 58% success.     

A 3D shape segmentation approach for robot grasping by parts

Neuro-psychological findings have shown that human perception of objects is based on part decomposition. Most objects are made of multiple parts which are likely to be the entities actually involved in grasp affordances. Therefore, automatic object recognition and robot grasping should take advantage from 3D shape segmentation. This paper presents an approach toward planning robot grasps across similar objects by part correspondence. The novelty of the method lies in the topological decomposition of objects that enables high-level semantic grasp planning.In particular, given a 3D model of an object, the representation is initially segmented by computing its Reeb graph. Then, automatic object recognition and part annotation are performed by applying a shape retrieval algorithm. After the recognition phase, queries are accepted for planning grasps on individual parts of the object. Finally, a robot grasp planner is invoked for finding stable grasps on the selected part of the object. Grasps are evaluated according to a widely used quality measure. Experiments performed in a simulated environment on a reasonably large dataset show the potential of topological segmentation to highlight candidate parts suitable for grasping.     

A machine learning based intelligent vision system for autonomous object detection and recognition

Existing object recognition techniques often rely on human labeled data conducting to severe limitations to design a fully autonomous machine vision system. In this work, we present an intelligent machine vision system able to learn autonomously individual objects present in real environment. This system relies on salient object detection. In its design, we were inspired by early processing stages of human visual system. In this context we suggest a novel fast algorithm for visually salient object detection, robust to real-world illumination conditions. Then we use it to extract salient objects which can be efficiently used for training the machine learning-based object detection and recognition unit of the proposed system. We provide results of our salient object detection algorithm on MSRA Salient Object Database benchmark comparing its quality with other state-of-the-art approaches. The proposed system has been implemented on a humanoid robot, increasing its autonomy in learning and interaction with humans. We report and discuss the obtained results, validating the proposed concepts.     

一种基于图像区域系综分类的室外场景理解方法

多层感知机分类器是一种有效的数据分类方法，但其分类性能受训练样本空间的限制。通过多层感知机分类器系综提高室外场景理解中图像区域的分类性能，提出了一种自动识别室外场景图像中多种景物所属概念类别的方法。该方法首先提取图像分割区域的低层视觉特征，然后基于系综分类方法建立区域视觉特征和语义类别的对应关系，通过合并相同标注区域，确定图像中景物的高层语义。对包含5种景物的150幅图像进行测试，识别率达到了87％。与基于多层感知机方法的实验结果相比，本文提出的方法取得了更好的性能，这表明该方法适合于图像区域分类。此外，系综方法还可以推广到其他的分类问题。     

Online Object Categorization Using Multimodal Information Autonomously Acquired by a Mobile Robot

Abstract

In this paper, we propose a robot that acquires multimodal information, i.e. visual, auditory, and haptic information, fully autonomously using its embodiment. We also propose batch and online algorithms for multimodal categorization based on the acquired multimodal information and partial words given by human users. To obtain multimodal information, the robot detects an object on a flat surface. Then, the robot grasps and shakes it to obtain haptic and auditory information. For obtaining visual information, the robot uses a small hand-held observation table with an XBee wireless controller to control the viewpoints for observing the object. In this paper, for multimodal concept formation, multimodal latent Dirichlet allocation using Gibbs sampling is extended to an online version. This framework makes it possible for the robot to learn object concepts naturally in everyday operation in conjunction with a small amount of linguistic information from human users. The proposed algorithms are implemented on a real robot and tested using real everyday objects to show the validity of the proposed system.     

Autonomous Salient Feature Detection through Salient Cues in an HSV Color Space for Visual Indoor Simultaneous Localization and Mapping

For successful simultaneous localization and mapping (SLAM), perception of the environment is important. This paper proposes a scheme to autonomously detect visual features that can be used as natural landmarks for indoor SLAM. First, features are roughly selected from the camera image through entropy maps that measure the level of randomness of pixel information. Then, the saliency of each pixel is computed by measuring the level of similarity between the selected features and the given image. In the saliency map, it is possible to distinguish the salient features from the background. The robot estimates its pose by using the detected features and builds a grid map of the unknown environment by using a range sensor. The feature positions are stored in the grid map. Experimental results show that the feature detection method proposed in this paper can autonomously detect features in unknown environments reasonably well.     

Invariant object recognition in the visual system with novel views of 3D objects

To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view.