Environmental map building for a mobile robot using infrared range-finder sensors

This paper presents a methodology for building a high-accuracy environmental map using a mobile robot. The design approach uses low-cost infrared range-finder sensors incorporating with neural networks. To enhance the map quality, the errors occurring from the sensors are corrected. The non-linearity error of the sensors is compensated using a backpropagation neural network and the random error of readings including the uncertainty of the environment is taken into a sensor model as a probabilistic approach. The map is represented by an occupancy grid framework and updated by the Bayesian estimation mechanism. The effectiveness of the proposed method is verified through a series of experiments.     

Uncertainty-aware soft sensor using Bayesian recurrent neural networks

Data-driven soft sensors have been widely used to measure key variables for industrial processes. Soft sensors using deep learning models have attracted considerable attention and shown superior predictive performance. However, if a soft sensor encounters an unexpected situation in inferring data or if noisy input data is used, the estimated value derived by a standard soft sensor using deep learning may at best be untrustworthy. This problem can be mitigated by expressing a degree of uncertainty about the trustworthiness of the estimated value produced by the soft sensor. To address this issue of uncertainty, we propose using an uncertainty-aware soft sensor that uses Bayesian recurrent neural networks (RNNs). The proposed soft sensor uses a RNN model as a backbone and is then trained using Bayesian techniques. The experimental results demonstrated that such an uncertainty-aware soft sensor increases the reliability of predictive uncertainty. In comparisons with a standard soft sensor, it shows a capability to use uncertainties for interval prediction without compromising predictive performance.     

Incremental supervised learning for mobile robot reactive control

Reactive control for a mobile robot can be defined as a mapping from a perceptual space to a command space. This mapping can be hard-coded by the user (potential fields, fuzzy logic), and can also be learnt. This paper is concerned with supervised learning for perception to action mapping for a mobile robot. Among the existing neural approaches for supervised learning of a function, we have selected the grow and learn network for its properties adapted to robotic problems: incrementality and flexible structure. We will present the results we have obtained with this network using first raw sensor data and then pre-processed measures with the automatic construction of virtual sensors.     

Information-theoretic Approaches Based on Sequential Monte Carlo to Collaborative Distributed Sensors for Mobile Robot Localization

We consider the Sequential Monte Carlo (SMC) method for Bayesian inference applied to the problem of information-theoretic distributed sensor collaboration in complex environments. The robot kinematics and sensor observation under consideration are described by nonlinear models. The exact solution to this problem is prohibitively complex due to the nonlinear nature of the system. The SMC method is, therefore, employed to track the probabilistic kinematics of the robot and to make the corresponding Bayesian estimates and predictions. To meet the specific requirements inherent in distributed sensors, such as low-communication consumption and collaborative information processing, we propose a novel SMC solution that makes use of the particle filter technique for data fusion, and the density tree representation of the a posterior distribution for information exchange between sensor nodes. Meanwhile, an efficient numerical method is proposed for approximating the information utility in sensor selection. A further experiment, obtained with a real robot in an indoor environment, illustrates that under the SMC framework, the optimal sensor selection and collaboration can be implemented naturally, and significant improvement in localization accuracy is achieved when compared to conventional methods using all sensors.     

A modular design of Bayesian networks using expert knowledge: Context-aware home service robot

Recently, demand for service robots increases, and, particularly, one for personal service robots, which requires robot intelligence, will be expected to increase more. Accordingly, studies on intelligent robots are spreading all over the world. In this situation, we attempt to realize context-awareness for home robot while previous robot research focused on image processing, control and low-level context recognition. This paper uses probabilistic modeling for service robots to provide users with high-level context-aware services required in home environment, and proposes a systematic modeling approach for modeling a number of Bayesian networks. The proposed approach supplements uncertain sensor input using Bayesian network modeling and enhances the efficiency in modeling and reasoning processes using modular design based on domain knowledge. We verify the proposed method is useful as measuring the performance of context-aware module and conducting subjective test.     

基于块稀疏贝叶斯学习的体域网心电压缩采样

为有效提高体域网的实时性和降低体域网的功耗,提出一种基于块稀疏贝叶斯学习的体域网心电压缩采样方法。该方法在体域网框架下,利用压缩采样理论,在体域网的传感节点利用二进制随机观测矩阵对心电信号进行压缩采样,远程监护中心获得采样值之后,利用块稀疏贝叶斯学习重构算法和离散余弦稀疏变换矩阵对心电信号进行重构。实验结果表明,当心电信号压缩率在70%~90%时,基于块稀疏贝叶斯学习的重构算法要比其他重构算法的重构信噪比高出3 dB~21 dB。该方法能有效减少数据采样,减轻后续的数据存储、数据传输压力,提高体域网的实时性。同时该方法具有功耗低,易于硬件实现的优点。     

Classifying sensor data with Calchas

Learning how to classify sensor data is one of the basic learning tasks in engineering. Data from sensors are usually made available over time, and are classified according to the behavior they exhibit in specific time intervals. This paper addresses the problem of classifying finite, univariate time series that are governed by unknown deterministic processes contaminated by noise. Time series in the same class are allowed to follow different processes. In this context, the appropriateness of using induction algorithms not specifically designed for temporal data is investigated. The paper presents Calchas, a simple supervised induction algorithm that uses serial correlation as its inductive bias in a Bayesian framework, and compares it empirically to a popular general-purpose classifier, in a NASA telemetry monitoring application. Two comparisons were performed: one in which the general purpose classifier was applied directly to the data, and another in which features that captured serial correlations were extracted before the induction. Serial correlation appeared to be an important form of inductive bias, most effectively utilized as an integral part of the learning algorithm. Feature extraction occurs too early in the training process to utilize correlation knowledge effectively.     

基于惯性传感器的集群移动机器人定位系统设计

为了对集群机器人的定位技术做进一步研究,本文对群体移动机器人的整体框架进行了设计,主要包括控制单元、通信模块和传感器单元等,重点对基于MPU9250惯性传感器的定位技术进行了研究,定位系统以ZigBee模块组成无线传感网络,用Arduino对MPU9250进行姿态数据获取并进行处理,利用ZigBee网络将位置信息传输到上位机.本文提出的机器人惯导定位技术对于解决机器人的定位问题具有一定的指导意义.     

Sensor planning for mobile robot localization using Bayesian network inference

We propose a new method of sensor planning for mobile robot localization using Bayesian network inference. Since we can model causal relations between situations of the robot's behavior and sensing events as nodes of a Bayesian network, we can use the inference of the network for dealing with uncertainty in sensor planning and thus derive appropriate sensing actions. In this system we employ a multi-layered-behavior architecture for navigation and localization. This architecture effectively combines mapping of local sensor information and the inference via a Bayesian network for sensor planning. The mobile robot recognizes the local sensor patterns for localization and navigation using a learned regression function. Since the environment may change during the navigation and the sensor capability has limitations in the real world, the mobile robot actively gathers sensor information to construct and reconstruct a Bayesian network, and then derives an appropriate sensing action which maximizes a utility function based on inference of the reconstructed network. The utility function takes into account belief of the localization and the sensing cost. We have conducted some simulation and real robot experiments to validate the sensor planning system.     

Gaussian Process Models for Indoor and Outdoor Sensor-Centric Robot Localization

This paper presents an approach to building a map from a sparse set of noisy observations, taken from known locations by a sensor with no obvious geometric model. The basic approach is to fit an interpolant to the training data, representing the expected observation, and to assume additive sensor noise. This paper takes a Bayesian view of the problem, maintaining a posterior over interpolants rather than simply the maximum-likelihood interpolant, giving a measure of uncertainty in the map at any point. This is done using a Gaussian process (GP) framework. The approach is validated experimentally both in an indoor office environment and an outdoor urban environment, using observations from an omnidirectional camera mounted on a mobile robot. A set of training data is collected from each environment and processed offline to produce a GP model. The robot then uses that model to localize while traversing each environment.      

The Application of Connectionist Structures to Learning Impedance Control in Robotic Contact Tasks

The goal of this paper is to consider the synthesis of learning impedance control using recurrent connectionist structures for on-line learning of robot dynamic uncertainties in the case of robot contact tasks. The connectionist structures are integrated in non-learning impedance control laws that are intended to improve the transient dynamic response immediately after the contact. The recurrent neural network as a part of hybrid learning control algorithms uses fast learning rules and available sensor information in order to improve the robotic performance progressively for a minimum possible number of learning epochs. Some simulation results of deburring process with the MANUTEC r3 robot are presented here in order to verify the effectiveness of the proposed control learning algorithms.     

Sensor Planning for Mobile Robot Localization---A Hierarchical Approach Using a Bayesian Network and a Particle Filter

In this paper, we propose a hierarchical approach to solving sensor planning for the global localization of a mobile robot. Our system consists of two subsystems: a lower layer and a higher layer. The lower layer uses a particle filter to evaluate the posterior probability of the localization. When the particles converge into clusters, the higher layer starts particle clustering and sensor planning to generate an optimal sensing action sequence for the localization. The higher layer uses a Bayesian network for probabilistic inference. The sensor planning takes into account both localization belief and sensing cost. We conducted simulations and actual robot experiments to validate our proposed approach.     

基于神经网络技术的机器人并发故障自动诊断方法

为了提高柔性负载抓握机器人的故障检测能力,提出基于神经网络技术的机器人并发故障自动诊断方法.运用高分辨的智能传感器信息识别技术,结合刚度和强度等机械结构特征分析,构建柔性负载抓握机器人的故障信息采集模型,采用变刚度原理,提取柔性负载抓握机器人的振荡信息特征,通过谱特征检测和动态信息融合进行柔性负载抓握机器人的故障信息的...     

A novel data fusion scheme using grey model and extreme learning machine in wireless sensor networks

With the increasing presence and adoption of wireless sensor networks (WSNs), the demand of data acquisition and data fusion are becoming stronger and stronger. In WSN, sensor nodes periodically sense data and send them to the sink node. Since the network consists of plenty of low-cost sensor nodes with limited battery power and the sensed data usually are of high temporal redundancy, prediction- based data fusion has been put forward as an important issue to reduce the number of transmissions and save the energy of the sensor nodes. Considering the fact that the sensor node usually has limited capabilities of data processing and storage, a novel prediction-based data fusion scheme using grey model (GM) and optimally pruned extreme learning machine (OP-ELM) is proposed. The proposed data fusion scheme called GM-OP-ELM uses a dual prediction mechanism to keep the prediction data series at the sink node and sensor node synchronous. During the data fusion process, GM is introduced to initially predict the data of next period with a small number of data items, and an OPELM- based single-hidden layer feedforward network (SLFN) is used to make the initial predicted value approximate its true value with extremely fast speed. As a robust and fast neural network learning algorithm, OP-ELM can adaptively adjust the structure of the SLFN. Then, GM-OP-ELM can provide high prediction accuracy, low communication overhead, and good scalability. We evaluate the performance of GM-OP-ELM on three actual data sets that collected from 54 sensors deployed in the Intel Berkeley Research lab. Simulation results have shown that the proposed data fusion scheme can significantly reduce redundant transmissions and extend the lifetime of the whole network with low computational cost.     

Bayesian Fault Probability Estimation: Application in Wind Turbine Drivetrain Sensor Fault Detection

In this paper, the extension of the Bayesian framework for sensor fault detection of nonlinear systems proposed in [25] is studied utilizing particle filtering and the expectation maximization (EM) algorithm, in which the fault probability is calculated. The proposed algorithm is implemented on a wind turbine benchmark model to detect drivetrain sensor faults, which are one of the most addressed and likely faults in offshore wind turbines. The fault probability estimation effectively eliminates the need for installing identical redundant sensors. Indeed, because of the use of the unknown wind speed estimator, the residual signal, constructed based on the drivetrain estimated states, is not able to clearly signify the fault periods, a situation in which the fault probability accurately does this task. Also, using the proposed algorithm, the fault size for each sensor is estimated via a one‐step calculation, which decreases the complexity of this algorithm. The fault identification is performed using the recursive least square method and two other modifications, including exponentially weighted and windowed estimates. Additionally, in the fault accommodation step, the concept of a virtual sensor is used to remove the need for reconfiguring the current controller, which reduces complexity and expense. In the simulation section, using a real measured wind speed for two different fault scenarios, the proposed algorithm is evaluated and finally, conclusions are stated.     

基于强化学习和模糊逻辑的移动机器人导航

自主导航是移动机器人的一项关键技术。该文采用强化学习结合模糊逻辑的方法实现了未知环境下自主式移动机机器人的导航控制。文中首先介绍了强化学习原理,然后设计了一种未知环境下机器人导航框架。该框架由避碰模块、寻找目标模块和行为选择模块组成。针对该框架,提出了一种基于强化学习和模糊逻辑的学习、规划算法：在对避碰和寻找目标行为进行独立学习后,利用超声波传感器得到的环境信息进行行为选择,使机器人在成功避碰的同时到达目标点。最后通过大量的仿真实验,证明了算法的有效性。     

Path planning in GPS-denied environments via collective intelligence of distributed sensor networks

This paper proposes a framework for reactive goal-directed navigation without global positioning facilities in unknown dynamic environments. A mobile sensor network is used for localising regions of interest for path planning of an autonomous mobile robot. The underlying theory is an extension of a generalised gossip algorithm that has been recently developed in a language-measure-theoretic setting. The algorithm has been used to propagate local decisions of target detection over a mobile sensor network and thus, it generates a belief map for the detected target over the network. In this setting, an autonomous mobile robot may communicate only with a few mobile sensing nodes in its own neighbourhood and localise itself relative to the communicating nodes with bounded uncertainties. The robot makes use of the knowledge based on the belief of the mobile sensors to generate a sequence of way-points, leading to a possible goal. The estimated way-points are used by a sampling-based motion planning algorithm to generate feasible trajectories for the robot. The proposed concept has been validated by numerical simulation on a mobile sensor network test-bed and a Dubin’s car-like robot.     

基于智能解析余度的容错飞控系统设计

常规的解析余度容错方法容易受到不确定因素和随机干扰的影响,本文以飞行控制系统为研究对象,提出基于智能解析余度的容错飞行控制系统设计方案,使用径向基神经网络的在线学习和全局逼近的性能,建立飞行控制系统传感器之间的解析余度关系,利用不相同传感器之间的解析关系进行残差分析从而进行传感器的故障隔离与信号重构.这样有效地抑制了测量噪声和模型不确定性.应用某型飞机进行仿真,实现了传感器的在线故障隔离与重构,验证了该方法的有效性.     

Deep representation learning for road detection using Siamese network

Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network. The RGB images are fed into another branch of our proposed network. The feature maps that these two branches extract in multiple scales are fused before each pooling layer, via padding additional fusion layers. Extensive experimental results on public dataset KITTI ROAD demonstrate the effectiveness of our proposed approach.

     

Detection of anomalous behavior in a robot system based on deep learning elements

The preprocessing procedure for anomalous behavior of robot system elements is proposed in the paper. It uses a special kind of a neural network called an autoencoder to solve two problems. The first problem is to decrease the dimensionality of the training data using the autoencoder to calculate the Mahalanobis distance, which can be viewed as one of the best metrics to detect the anomalous behavior of robots or sensors in the robot systems. The second problem is to apply the autoencoder to transfer learning. The autoencoder is trained by means of the target data which corresponds to the extreme operational conditions of the robot system. The source data containing the normal and anomalous observations derived from the normal operation conditions is reconstructed to the target data using the trained autoencoder. The reconstructed source data is used to define a optimal threshold for making decision on the anomaly of the observation based on the Mahalanobis distance.