Multimodal localization: Stereo over LiDAR map

In this paper, we present a real‐time high‐precision visual localization system for an autonomous vehicle which employs only low‐cost stereo cameras to localize the vehicle with a priori map built using a more expensive 3D LiDAR sensor. To this end, we construct two different visual maps: a sparse feature visual map for visual odometry (VO) based motion tracking, and a semidense visual map for registration with the prior LiDAR map. To register two point clouds sourced from different modalities (i.e., cameras and LiDAR), we leverage probabilistic weighted normal distributions transformation (ProW‐NDT), by particularly taking into account the uncertainty of source point clouds. The registration results are then fused via pose graph optimization to correct the VO drift. Moreover, surfels extracted from the prior LiDAR map are used to refine the sparse 3D visual features that will further improve VO‐based motion estimation. The proposed system has been tested extensively in both simulated and real‐world experiments, showing that robust, high‐precision, real‐time localization can be achieved.     

Passive sensor evaluation for unmanned ground vehicle mud detection

Detecting mud hazards is a significant challenge to unmanned ground vehicle (UGV) autonomous off‐road navigation. A military UGV stuck in a body of mud during a mission may need to be sacrificed or rescued, both unattractive options. The Jet Propulsion Laboratory is currently developing a daytime mud detection capability under the U.S. Army Research Laboratory Robotics Collaborative Technology Alliances program using UGV‐mounted sensors. To perform robust mud detection under all conditions, we expect that multiple sensors will be necessary. A passive mud detection solution is desirable to meet future combat system requirements. To characterize the advantages and disadvantages of candidate passive sensors, outdoor data collections have been performed on wet and dry soil using visible, multispectral (including near‐infrared), shortwave infrared, midwave infrared, long‐wave infrared, polarization, and stereo sensors. In this paper, we examine the cues for mud detection that each of these sensors provide, along with their deficiencies, and we illustrate localizing detected mud in a world model that can used by a UGV to plan safe paths. We mostly limit our examination to mud detection during the daytime under ideal conditions: isolated wet soil surrounded by dry soil during nominal weather, i.e., no precipitation, calm wind, and near‐average temperatures. © 2010 Wiley Periodicals, Inc.     

Recursive Filter with Partial Knowledge on Inputs and Outputs

 This paper investigates the problem of state estimation for discrete-time stochastic linear systems, where additional knowledge on the unknown inputs is available at an aggregate level and the knowledge on the missing measurements can be described by a known stochastic distribution. Firstly, the available knowledge on the unknown inputs and the state equation is used to form the prior distribution of the state vector at each time step. Secondly, to obtain an analytically tractable likelihood function, the effect of missing measurements is broken down into a systematic part and a random part, and the latter is modeled as part of the observation noise. Then, a recursive filter is obtained based on Bayesian inference. Finally, a numerical example is provided to evaluate the performance of the proposed methods.     

一种能量有效的WSN目标跟踪动态协同自组织算法

针对无线传感器网络目标跟踪应用中跟踪精度与网络能耗的权衡问题,提出一种能量有效的动态协同自组织算法(E-DCS)。根据目标预测位置和节点的位置、能量信息,建立了信息效用、通信开销和节点剩余能量的综合性能指标,并利用层次分析法确定了性能指标中各要素的权值系数。通过自适应动态成簇策略,分别设定簇首切换精度阈值和节点选择精度阈值判断是否切换簇首和选择任务节点。簇首节点根据簇内节点提供的测量信息采用序贯EKF进行状态估计。仿真结果表明,与信息驱动传感器查询(IDSQ)和自适应动态协同自组织算法(A-DCS)相比,该算法在保证跟踪精度的基础上,降低了网络能耗,有效延长了网络的生命周期。     

Confidence estimation methods for neural networks: a practicalcomparison

Feedforward neural networks, particularly multilayer perceptrons, are widely used in regression and classification tasks. A reliable and practical measure of prediction confidence is essential. In this work three alternative approaches to prediction confidence estimation are presented and compared. The three methods are the maximum likelihood, approximate Bayesian, and the bootstrap technique. We consider prediction uncertainty owing to both data noise and model parameter misspecification. The methods are tested on a number of controlled artificial problems and a real, industrial regression application, the prediction of paper "curl". Confidence estimation performance is assessed by calculating the mean and standard deviation of the prediction interval coverage probability. We show that treating data noise variance as a function of the inputs is appropriate for the curl prediction task. Moreover, we show that the mean coverage probability can only gauge confidence estimation performance as an average over the input space, i.e., global performance and that the standard deviation of the coverage is unreliable as a measure of local performance. The approximate Bayesian approach is found to perform better in terms of global performance.     

Negotiating Uneven Terrain with a Compliant Designed Unmanned Ground Vehicle Equipped with Locomotive Master‐Slave Operation

In recent years, a number operational unmanned ground vehicles (UGVs) have been developed that can negotiate irregular terrain. They have a number of degrees‐of‐freedom (DOF) giving them enhanced mobility, e.g., the ability to climb stairs and over obstacles. However, operating them remotely is complicated because their controllers are similar to conventional control pads or joysticks used in computer games or toys. It is hard for the operator to achieve an intuitive and natural feel, thus mistakes are common. To intuitively control the locomotion of a UGV with many DOFs, a master‐slave operation was implemented. A novel UGV called Kurogane, which consists of a typical crawler combined with a human‐like torso section, was developed. The torso section is controlled via a wearable controller interface. In addition, the UGV is equipped with models of muscle viscoelasticity and stretch reflex, called the involuntary autonomous adaptation system, inspired by the adaptive compliance of animals. The proposed system can autonomously and flexibly react and adapt to irregular terrain in real time. Therefore, the operation of Kurogane is simple and does not require great skill or precision. Experimental results show that it performs well over a fixed step, stairs, and rough outdoor terrain. © 2013 Wiley Periodicals, Inc.     

Tracking and Following a Tagged Leopard Shark with an Autonomous Underwater Vehicle

This paper presents a prototype system that enables an autonomous underwater vehicle (AUV) to autonomously track and follow a shark that has been tagged with an acoustic transmitter. The AUV's onboard processor handles both real‐time estimation of the shark's two‐dimensional planar position, velocity, and orientation states, as well as a straightforward control scheme to drive the AUV toward the shark. The AUV is equipped with a stereo‐hydrophone and receiver system that detects acoustic signals transmitted by the acoustic tag. The particular hydrophone system used here provides a measurement of relative bearing angle to the tag, but it does not provide the sign (+ or ?) of the bearing angle. Estimation is accomplished using a particle filter that fuses bearing measurements over time to produce a state estimate of the tag location. The particle filter combined with a heuristic‐based controller allows the system to overcome the ambiguity in the sign of the bearing angle. The state estimator and control scheme were validated by tracking both a stationary tag and a moving tag with known positions. Offline analysis of these data showed that state estimation can be improved by optimizing diffusion parameters in the prediction step of the filter, and considering signal strength of the acoustic signals in the resampling stage of the filter. These experiments revealed that state estimate errors were on the order of those obtained by current long‐distance shark‐tracking methods, i.e., manually driven boat‐based tracking systems. Final experiments took place in SeaPlane Lagoon, Los Angeles, where a 1‐m leopard shark (Triakis semifasciata) was caught, tagged, and released before being autonomously tracked and followed by the proposed AUV system for several hours. © 2013 Wiley Periodicals, Inc.     

Efficient, adaptive estimation of two-dimensional firing rate surfaces via Gaussian process methods

Estimating two-dimensional firing rate maps is a common problem, arising in a number of contexts: the estimation of place fields in hippocampus, the analysis of temporally nonstationary tuning curves in sensory and motor areas, the estimation of firing rates following spike-triggered covariance analyses, etc. Here we introduce methods based on Gaussian process nonparametric Bayesian techniques for estimating these two-dimensional rate maps. These techniques offer a number of advantages: the estimates may be computed efficiently, come equipped with natural errorbars, adapt their smoothness automatically to the local density and informativeness of the observed data, and permit direct fitting of the model hyperparameters (e.g., the prior smoothness of the rate map) via maximum marginal likelihood. We illustrate the method's flexibility and performance on a variety of simulated and real data.     

A Bayesian Multiple Models Combination Method for Time Series Prediction

In this paper we present the Bayesian Combined Predictor (BCP), a probabilistically motivated predictor for time series prediction. BCP utilizes local predictors of several types (e.g., linear predictors, artificial neural network predictors, polynomial predictors etc.) and produces a final prediction which is a weighted combination of the local predictions; the weights can be interpreted as Bayesian posterior probabilities and are computed online. Two examples of the method are given, based on real world data: (a) short term load forecasting for the Greek Public Power Corporation dispatching center of the island of Crete, and (b) prediction of sugar beet yield based on data collected from the Greek Sugar Industry. In both cases, the BCP outperforms conventional predictors.     

Improving the coordination efficiency of limited‐communication multi–autonomus underwater vehicle operations using a multiagent architecture

This research addresses the problem of coordinating multiple autonomous underwater vehicle (AUV) operations. An intelligent mission executive has been created that uses multiagent technology to control and coordinate multiple AUVs in communication‐deficient environments. By incorporating real‐time vehicle prediction, blackboard‐based hierarchical mission plans, mission optimization, and a distributed multiagent–based paradigm in conjunction with a simple broadcast communication system, this research aims to handle the limitations inherent in underwater operations, namely poor communication, and intelligently control multiple vehicles. In this research, efficiency is evaluated and then compared to the current state of the art in multiple AUV control. The research is then validated in real AUV coordination trials. Results will show that compared to the state of the art, the control system developed and implemented in this research coordinates multiple vehicles more efficiently and is able to function in a range of poor communication environments. These findings are supported by in‐water validation trials with heterogeneous AUVs. © 2010 Wiley Periodicals, Inc.     

Adaptive Gaussian filters for nonlinear state estimation with one-step randomly delayed measurements

This paper proposes new algorithms of adaptive Gaussian filters for nonlinear state estimation with maximum one-step randomly delayed measurements. The unknown random delay is modeled as a Bernoulli random variable with the latency probability known a priori. However, a contingent situation has been considered in this work when the measurement noise statistics remain partially unknown. Due to unavailability of the complete knowledge of measurement noise statistics, the unknown measurement noise covariance matrix is estimated along with states following: (i) variational Bayesian approach, (ii) maximum likelihood estimation. The adaptation algorithms are mathematically derived following both of the above approaches. Subsequently, a general framework for adaptive Gaussian filter is presented with which variants of adaptive nonlinear filters can be formulated using different rules of numerical approximation for Gaussian integrals. This paper presents a few of such filters, viz., adaptive cubature Kalman filter, adaptive cubature quadrature Kalman filter with their higher degree variants, adaptive unscented Kalman filter, and adaptive Gauss–Hermite filter, and demonstrates the comparative performance analysis with the help of a nontrivial Bearing only tracking problem in simulation. Additionally, the paper carries out relative performance comparison between maximum likelihood estimation and variational Bayesian approaches for adaptation using Monte Carlo simulation. The proposed algorithms are also validated with the help of an off-line harmonics estimation problem with real data.     

Bayesian smoothing spline analysis of variance

Smoothing spline ANOVA (SSANOVA) provides an approach to semiparametric function estimation based on an ANOVA type of decomposition. Wahba et al. (1995) decomposed the regression function based on a tensor sum decomposition of inner product spaces into orthogonal subspaces, so the effects of the estimated functions from each subspace can be viewed independently. Recent research related to smoothing spline ANOVA focuses on either frequentist approaches or a Bayesian framework for variable selection and prediction. In our approach, we seek “objective” priors especially suited to estimation. The prior for linear terms including level effects is a variant of the Zellner–Siow prior (Zellner and Siow, 1980), and the prior for a smooth effect is specified in terms of effective degrees of freedom. We study this fully Bayesian SSANOVA model for Gaussian response variables, and the method is illustrated with a real data set.     

Decentralized planning and control for UAV–UGV cooperative teams

In this paper we study a symbiotic aerial vehicle-ground vehicle robotic team where unmanned aerial vehicles (UAVs) are used for aerial manipulation tasks, while unmanned ground vehicles (UGVs) aid and assist them. UGV can provide a UAV with a safe landing area and transport it across large distances, while UAV can provide an additional degree of freedom for the UGV, enabling it to negotiate obstacles. We propose an overall system control framework that includes high-accuracy motion planning for each individual robot and ad-hoc decentralized mission planning for complex missions. Experimental results obtained in a mockup arena for parcel transportation scenario show that the system is able to plan and execute missions in various environments and that the obtained plans result in lower energy consumption.     

基于多重指标拍卖机制的车联网任务卸载策略

在5G移动边缘计算(MEC)的车联网场景中, 针对车辆任务卸载目标的选择问题, 设计了一种基于任务优先级的服务器选择方案. 综合考虑时间、能耗、成本等因素对卸载位置选择的影响, 提出了基于多重指标拍卖博弈的解决方法. 通过多重指标拍卖机制, 选择最优的MEC服务器为车辆提供任务卸载服务, 实现车辆与RSU协作的贝叶斯纳什均衡. 仿真结果表明, 该方案能在保障车辆任务卸载时间和能耗的约束条件下, 降低任务卸载的总费用, 满足多个性能指标.     

基于小波域隐马尔可夫树模型的图像复原

从图像复原的Bayesian方法出发,提出一种基于小波域隐马尔可夫树(HMT)模型的线性图像复原算法,小波域HMT模型采用混合高斯模型刻画各子带系数的概率分布,并通过小波系数隐状态在多个尺度之间的Markov依赖性来刻画自然图像小波系数随尺度减小而指数衰减的特性,由于小波域HMT模型准确刻画了自然图像小波变换的统计特性,该文算法以此作为自然图像的先验模型,将图像复原问题转化为一个约束优化问题并用最速下降法对其进行求解,同时,提出了一种规整化参数和HMT模型参数的自适应选择方法,实验结果表明,基于小波域HMT模型的图像复原算法较好地再现了各种边缘信息,复原出的图像在信噪比和视觉效果方面都有明显的提高。     

Multistage bayesian autonomy for high‐precision operation in a large field

This paper presents a generalized multistage bayesian framework to enable an autonomous robot to complete high‐precision operations on a static target in a large field. The proposed framework consists of two multistage approaches, capable of dealing with the complexity of high‐precision operation in a large field to detect and localize the target. In the multistage localization, locations of the robot and the target are estimated sequentially when the target is far away from the robot, whereas these locations are estimated simultaneously when the target is close. A level of confidence (LOC) for each detection criterion of a sensor and the associated probability of detection (POD) of the sensor are defined to make the target detectable with different LOCs at varying distances. Differential entropies of the robot and target are used as a precision metric for evaluating the performance of the proposed approach. The proposed multistage observation and localization approaches were applied to scenarios using an unmanned ground vehicle (UGV) and an unmanned aerial vehicle (UAV). Results with the UGV in simulated environments and then real environments show the effectiveness of the proposed approaches to real‐world problems. A successful demonstration using the UAV is also presented.     

Estimation of Road Friction Coefficient and Vehicle States by 3‐DOF Dynamic Model and HSRI Model Based on Information Fusion

Vehicle states and the road friction coefficient in active safety control systems have become increasingly prominent. However, a low‐cost, high‐precision system in real‐time has yet to be achieved. The use of complex models has led to poor real‐time estimation, while variations in the road friction coefficient have often been neglected. This paper adopts information fusion technology by using DEKF theory for rapid simulation and estimation of these parameters. Using a vehicle dynamic model based on three degrees of freedom (3‐DOF) and the Highway Safety Research Institute tire model, DEKF recursive estimation models are established and verified. In the DEKF, two recursive state and parameter estimation models exist in parallel. The models are dependent upon each other and have real‐time interaction correction in order to forecast information, which quickly yields true value estimation in simulation. Experimental brake test results show that the DEKF estimator not only accurately estimates the vehicle state parameters, but also estimates the road friction coefficient in real‐time. This can reduce the cost of the vehicle sensor, and can estimate the status parameter, which is difficult to measure. The validity and feasibility of this algorithm have been verified by an HIL driving simulator, offering the possibility of future application in real cars.     

Experiments in unmanned aerial vehicle/unmanned ground vehicle radiation search

This paper discusses the results of a field experiment conducted at Savannah River National Laboratory to test the performance of several algorithms for the localization of radioactive materials. In this multirobot system, both an unmanned aerial vehicle, a custom hexacopter, and an unmanned ground vehicle (UGV), the ClearPath Jackal, equipped with γ‐ray spectrometers, were used to collect data from two radioactive source configurations. Both the Fourier scattering transform and the Laplacian eigenmap algorithms for source detection were tested on the collected data sets. These algorithms transform raw spectral measurements into alternate spaces to allow clustering to detect trends within the data which indicate the presence of radioactive sources. This study also presents a point source model and accompanying information‐theoretic active exploration algorithm. Field testing validated the ability of this model to fuse aerial and ground collected radiation measurements, and the exploration algorithm’s ability to select informative actions to reduce model uncertainty, allowing the UGV to locate radioactive material online.     

Optimal Multi-Criteria Waypoint Selection for Autonomous Vehicle Navigation in Structured Environment

This paper deals with autonomous navigation of unmanned ground vehicles (UGV). The UGV has to reach its assigned final configuration in a structured environments (e.g. a warehouse or an urban environment), and to avoid colliding neither with the route boundaries nor any obstructing obstacles. In this paper, vehicle planning/set-points definition is addressed. A new efficient and flexible methodology for vehicle navigation throughout optimal and discrete selected waypoints is proposed. Combining multi-criteria optimization and expanding tree allows safe, smooth and fast vehicle overall navigation. This navigation through way-points permits to avoid any path/trajectory planning which could be time consuming and complex, mainly in cluttered and dynamic environment. To evaluate the flexibility and the efficiency of the proposed methodology based on expanding tree (taking into account the vehicle model and uncertainties), an important part of this paper is dedicated to give an accurate comparison with another proposed optimization based on the commonly used grid map. A set of simulations, comparison with other methods and experiments, using an urban electric vehicle, are presented and demonstrate the reliability of our proposals.     

基于USARSim和ROS的无人平台编队仿真系统

针对越野非结构化环境下的地面无人平台(Unmanned ground vehicle, UGV)编队仿真系统存在功能模块不完善及算法集成测试困难等问题, 为便于有效测试地面无人平台编队协同控制方法性能及其适用的任务场景, 降低编队协同系统的开发成本, 本文提出了一种基于USARSim (Unified System for Automation and Robotics Simulator)和ROS (Robot Operating System)的地面无人平台编队协同仿真系统. 该仿真系统由人机交互界面、基于ROS架构的地面无人平台控制系统和基于USARSim的虚拟仿真场景三个部分组成, 其测试对象为地面无人平台编队协同控制算法. 通过充分利用ROS中集成的开源导航算法和USARSim中丰富的机器人及环境模型, 该系统为研究地面无人平台编队协同控制算法提供了新的思路和快速验证工具. 以领航者?跟随者编队控制方法为例进行该仿真系统的性能测试, 实验结果表明, 该仿真系统能够在外界条件一致的情况下完成对编队协同控制方法的性能测试, 系统稳定可靠.