基于学习机制的移动机器人动态场景自适应导航方法

针对在单一学习机制中,移动机器人自主导航一般只适用于静态场景,适应性差的问题,提出一种动态场景自适应导航方法．该方法通过激光测距仪（LRF）获取周围环境的距离信息,在基于增量判别回归（IHDR）算法的单一学习机制导航的基础上,提出了最远距离优先机制的局部避障环节．该导航方法克服了传统导航方法对环境模型的过度依赖,并且本文提出的基于最远距离优先机制的局部避障算法,解决了基于单一学习机制的导航方法对动态场景适应能力不足的问题．本文将动态场景自适应导航方法应用到了MT-R机器人中,与基于单一学习机制的导航方法进行了对比实验,并且运用提出的局部避障算法,对实验中的激光数据进行了算法性能分析．实验结果证实了该方法的可行性,并显示了该方法在动态场景下的良好表现．     

Distributed cooperative localization with lower communication path requirements

Free communication topology for cooperative localization cannot be guaranteed in real scenarios. A flexible distributed algorithm aiming at reducing communication path requirements is presented under EKF. In this algorithm, not all agents need to communicate with each other instantaneously for covariance update and it has no adverse effect on state update. We prove that the missed covariance update caused by communication absence can be exactly corrected when it is required. Additionally, we prove that this algorithm is adaptive to most available one-way communication topologies. The equivalent localization performance to free connection communication is achieved.     

Decremental algorithm for adaptive routing incorporating traveler information

Routing in a stochastic and dynamic (time-dependent) network is a crucial transportation problem. A new variant of adaptive routing, which assumes perfect online information of continuous real-time link travel time, is proposed. Driver's speed profile is taken into consideration to realistically estimate travel times, which also involves the stochasticity of links in a dynamic network. An adaptive approach is suggested to tackle the continuous dynamic shortest path problem. A decremental algorithm is consequently developed to reduce optimization time. The impact of the proposed adaptive routing and the performance of the decremental approach are evaluated in static and dynamic networks under different traffic conditions. The proposed approach can be incorporated into vehicle navigation systems.     

Real-time path planning in dynamic virtual environments using multiagent navigation graphs

We present a novel approach for efficient path planning and navigation of multiple virtual agents in complex dynamic scenes. We introduce a new data structure, Multi-agent Navigation Graph (MaNG), which is constructed using first- and second-order Voronoi diagrams. The MaNG is used to perform route planning and proximity computations for each agent in real time. Moreover, we use the path information and proximity relationships for local dynamics computation of each agent by extending a social force model [Helbing05]. We compute the MaNG using graphics hardware and present culling techniques to accelerate the computation. We also address undersampling issues and present techniques to improve the accuracy of our algorithm. Our algorithm is used for real-time multi-agent planning in pursuit-evasion, terrain exploration and crowd simulation scenarios consisting of hundreds of moving agents, each with a distinct goal.     

H∞鲁棒自适应CKF算法在组合导航中的应用

针对组合导航系统状态模型及噪声统计特性不确定的情况下,标准容积卡尔曼滤波（Cubature Kalman Filter,CKF）算法鲁棒性差,导致滤波精度下降甚至出现滤波发散的问题,提出一种H∞鲁棒自适应CKF算法。该算法基于标准的三阶CKF算法理论框架,在观测方程为线性的条件下,对其量测更新进行了简化,并引入数值稳定性较强的奇异值分解（Singular Value Decomposition,SVD）对系统状态协方差阵进行分解迭代,改善了计算的数值稳定性;在系统状态协方差阵更新过程中引入H∞ 滤波思想,并基于矩阵不等式的理论,对其约束条件[γ]进行了自适应选取,进一步改善了滤波的稳定性,提高了系统的鲁棒性。将该算法用于GNSS/INS组合导航的数值仿真实验,结果验证了该算法的有效性和优越性。     

Group online adaptive learning

Sharing information among multiple learning agents can accelerate learning. It could be particularly useful if learners operate in continuously changing environments, because a learner could benefit from previous experience of another learner to adapt to their new environment. Such group-adaptive learning has numerous applications, from predicting financial time-series, through content recommendation systems, to visual understanding for adaptive autonomous agents. Here we address the problem in the context of online adaptive learning. We formally define the learning settings of Group Online Adaptive Learning and derive an algorithm named Shared Online Adaptive Learning (SOAL) to address it. SOAL avoids explicitly modeling changes or their dynamics, and instead shares information continuously. The key idea is that learners share a common small pool of experts, which they can use in a weighted adaptive way. We define group adaptive regret and prove that SOAL maintains known bounds on the adaptive regret obtained for single adaptive learners. Furthermore, it quickly adapts when learning tasks are related to each other. We demonstrate the benefits of the approach for two domains: vision and text. First, in the visual domain, we study a visual navigation task where a robot learns to navigate based on outdoor video scenes. We show how navigation can improve when knowledge from other robots in related scenes is available. Second, in the text domain, we create a new dataset for the task of assigning submitted papers to relevant editors. This is, inherently, an adaptive learning task due to the dynamic nature of research fields evolving in time. We show how learning to assign editors improves when knowledge from other editors is available. Together, these results demonstrate the benefits for sharing information across learners in concurrently changing environments.

     

基于多Agent结构的自适应蚁群优化聚类算法

该文在分析蚁群优化算法多Agent结构的基础上,提出了一种新的自适应蚁群优化聚类算法。算法的多Agent分层结构为L0层agent构造解,L1层agent改进可行解,L2层agent更新信息素,更新后的信息素矩阵为下一轮解的构造提供反馈信息。算法选取变异概率p及信息素残留度ρ作为自适应参数,在演化过程中进行自动调节,较好地解决了加速收敛和停滞早熟的矛盾。实验结果验证了算法的有效性,该算法的聚类效果和运行效率优于GA和SA两种演化聚类算法。     

Live path: adaptive agent navigation in the interactive virtual world

We present a novel approach to adaptive navigation in the interactive virtual world by using data from the user. Our method constructs automatically a navigation mesh that provides new paths for agents by referencing the user movements. To acquire accurate data samples from all the user data in the interactive world, we use the following techniques: an agent of interest (AOI), a region of interest (ROI) map, and a discretized path graph (DPG). Our method enables adaptive changes to the virtual world over time and provides user-preferred path weights for smart-agent path planning. We have tested the usefulness of our algorithm with several example scenarios from interactive worlds such as video games. In practice, our framework can be applied easily to any type of navigation in an interactive world. In addition, it may prove useful for solving previous pathfinding problems in static navigation planning.     

Spatial learning for navigation in dynamic environments

This article describes techniques that have been developed for spatial learning in dynamic environments and a mobile robot system, ELDEN, that integrates these techniques for exploration and navigation. In this research, we introduce the concept of adaptive place networks, incrementally-constructed spatial representations that incorporate variable-confidence links to model uncertainty about topological adjacency. These networks guide the robot's navigation while constantly adapting to any topological changes that are encountered. ELDEN integrates these networks with a reactive controller that is robust to transient changes in the environment and a relocalization system that uses evidence grids to recalibrate dead reckoning.     

基于Hash_tree的多维IP包分类算法

随着各种网络应用的发展,路由器必须能够快速完成对IP数据包的分类,以支持如防火墙、QoS等服务。文章分析了多维IP包分类中Hash算法的应用,在此基础上提出了一种基于Hash_tree的多维IP包分类算法。该算法充分发挥了Hash函数查找快速的特点,对IP数据包的分类能够以T位的线速进行处理,同时算法还具有支持较大的匹配规则集、支持增量更新等特点。     

Anytime search in dynamic graphs

Agents operating in the real world often have limited time available for planning their next actions. Producing optimal plans is infeasible in these scenarios. Instead, agents must be satisfied with the best plans they can generate within the time available. One class of planners well-suited to this task are anytime planners, which quickly find an initial, highly suboptimal plan, and then improve this plan until time runs out.A second challenge associated with planning in the real world is that models are usually imperfect and environments are often dynamic. Thus, agents need to update their models and consequently plans over time. Incremental planners, which make use of the results of previous planning efforts to generate a new plan, can substantially speed up each planning episode in such cases.In this paper, we present an A^∗-based anytime search algorithm that produces significantly better solutions than current approaches, while also providing suboptimality bounds on the quality of the solution at any point in time. We also present an extension of this algorithm that is both anytime and incremental. This extension improves its current solution while deliberation time allows and is able to incrementally repair its solution when changes to the world model occur. We provide a number of theoretical and experimental results and demonstrate the effectiveness of the approaches in a robot navigation domain involving two physical systems. We believe that the simplicity, theoretical properties, and generality of the presented methods make them well suited to a range of search problems involving dynamic graphs.     

Character navigation in dynamic environments based on optical flow

Steering and navigation are important components of character animation systems to enable them to autonomously move in their environment. In this work, we propose a synthetic vision model that uses visual features to steer agents through dynamic environments. Our agents perceive optical flow resulting from their relative motion with the objects of the environment. The optical flow is then segmented and processed to extract visual features such as the focus of expansion and time‐to‐collision. Then, we establish the relations between these visual features and the agent motion, and use them to design a set of control functions which allow characters to perform object‐dependent tasks, such as following, avoiding and reaching. Control functions are then combined to let characters perform more complex navigation tasks in dynamic environments, such as reaching a goal while avoiding multiple obstacles. Agent's motion is achieved by local minimization of these functions. We demonstrate the efficiency of our approach through a number of scenarios. Our work sets the basis for building a character animation system which imitates human sensorimotor actions. It opens new perspectives to achieve realistic simulation of human characters taking into account perceptual factors, such as the lighting conditions of the environment.     

An algorithm for safe navigation of mobile robots by a sensor network in dynamic cluttered industrial environments

Mobile robots have been widely implemented in industrial automation and smart factories. Different types of mobile robots work cooperatively in the workspace to complete some complicated tasks. Therefore, the main requirement for multi-robot systems is collision-free navigation in dynamic environments. In this paper, we propose a sensor network based navigation system for ground mobile robots in dynamic industrial cluttered environments. A range finder sensor network is deployed on factory floor to detect any obstacles in the field of view and perform a global navigation for any robots simultaneously travelling in the factory. The obstacle detection and robot navigation are integrated into the sensor network and the robot is only required for a low-level path tracker. The novelty of this paper is to propose a sensor network based navigation system with a novel artificial potential field (APF) based navigation algorithm. Computer simulations and experiments confirm the performance of the proposed method.     

An Integral Framework of Task Assignment and Path Planning for Multiple Unmanned Aerial Vehicles in Dynamic Environments

In this paper, a hierarchical framework for task assignment and path planning of multiple unmanned aerial vehicles (UAVs) in a dynamic environment is presented. For multi-agent scenarios in dynamic environments, a candidate algorithm should be able to replan for a new path to perform the updated tasks without any collision with obstacles or other agents during the mission. In this paper, we propose an intersection-based algorithm for path generation and a negotiation-based algorithm for task assignment since these algorithms are able to generate admissible paths at a smaller computing cost. The path planning algorithm is also augmented with a potential field-based trajectory replanner, which solves for a detouring trajectory around other agents or pop-up obstacles. For validation, test scenarios for multiple UAVs to perform cooperative missions in dynamic environments are considered. The proposed algorithms are implemented on a fixed-wing UAVs testbed in outdoor environment and showed satisfactory performance to accomplish the mission in the presence of static and pop-up obstacles and other agents.     

动态规划最优控制在非线性系统中的应用

应用一种新的自适应动态最优化方法(ADP),在线实现对非线性连续系统的最优控制。首先应用汉密尔顿函数（Hamilton-Jacobi-Bellman, HJB）求解系统的最优控制,并应用神经网络BP算法对汉密尔顿函数中的性能指标进行估计,进而得到非线性连续系统的最优控制。同时引进一种新的自适应算法,基于参数误差,在线实现对系统进行动态最优求解,而且通过李亚普诺夫方法对参数收敛情况也进行详细的分析。最后,用仿真结果来验证所提出的方法的可行性。     

抗干扰兼容型卫星导航接收机设计与仿真

抗干扰兼容型卫星导航接收机既可以使用组合卫星定位系统进行高精度定位,又具有优良的抗干扰性能。其抗干扰性能通过自适应调零天线实现,介绍了系统硬件电路实现,并在相应硬件平台上,采用功率反演算法进行干扰抑制。仿真测试结果表明,自适应调零天线有效地提高了接收信号的信噪比,提高了兼容型卫星导航接收机的应用范围。     

Multi-agent based path planning for first responders among moving obstacles

Natural or man-made disasters can cause different kinds of moving obstacles (e.g., fires, plumes, floods), which make some parts of the road network temporarily unavailable. After such incidents occur, responders have to go to different destinations to perform their tasks in the environment affected by the disaster. Therefore they need a path planner that is capable of dealing with such moving obstacles, as well as generating and coordinating their routes quickly and efficiently. In this paper, we present a novel approach for using a multi-agent system for navigating one or multiple responders to one or multiple destinations in the presence of moving obstacles. Our navigation system supports information collection from hazard simulations, spatio-temporal data processing and analysis, connection with a geo-database, and route generation in dynamic environments affected by disasters. We design and develop a set of software geospatial agents that assist emergency actors in dealing with the spatio-temporal data required for emergency navigation, based on their roles in the disaster response. One of the key components of the system is the path planning module, which combines the modified A* algorithm, insertion heuristics, and auction algorithm to calculate obstacle-avoiding routes for multiple responders with multiple destinations. A spatial data model is designed to support the storage of information about the tasks and routes produced during the disaster response. Our system has been validated using four navigation cases. Some preliminary results are presented in this paper and show the potential of the system for solving more navigation cases.     

一种自适应运动目标检测算法及其应用

针对ViBe算法在动态背景下存在鬼影消除时间长、算法适应性差、前景检测噪声多的问题,本文提出一种基于ViBe算法框架的改进算法.该算法采用鬼影检测法标记第1帧中的鬼影区域,并向位于鬼影区域的背景模型中强制引入背景样本,从而快速抑制鬼影;在像素分类过程中,引入自适应分类阈值,解决全局阈值易受动态噪声干扰的问题;在背景模型更新中,根据像素分类的匹配值来动态决定更新因子,提高算法适应场景变化的能力.定性与定量的对比实验结果表明,本文算法相较于ViBe算法能够有效地检测动态背景下的运动目标,应用于河流漂浮物检测场景中也有较好的效果.     

基于序贯概率映射的组合导航自适应容错算法

基于联邦滤波的容错组合导航系统通常在判定故障时刻对故障子系统进行整体隔离,未充分考虑缓变故障影响的渐近变化与状态分量间的差异。为此,提出一种基于序贯概率映射的组合导航自适应容错算法。该算法通过子滤波器新息动态映射建立局部估计状态统计模型,通过序贯概率比检测在线估计缓变故障影响下的局部状态质量,并据此对融合过程进行自适应调节。仿真结果表明,所提出的方法能有效提高组合导航系统对缓变故障的自适应容错调节能力。     

Automated Web navigation using multiagent adaptive dynamic programming

Today a massive amount of information available on the WWW often makes searching for information of interest a long and tedious task. Chasing hyperlinks to find relevant information may be daunting. To overcome such a problem, a learning system, cognizant of a user's interests, can be employed to automatically search for and retrieve relevant information by following appropriate hyperlinks. In this paper, we describe the design of such a learning system for automated Web navigation using adaptive dynamic programming methods. To improve the performance of the learning system, we introduce the notion of multiple model-based learning agents operating in parallel, and describe methods for combining their models. Experimental results on the WWW navigation problem are presented to indicate that combining multiple learning agents, relying on user feedback, is a promising direction to improve learning speed in automated WWW navigation.