Learning to transfer optimal navigation policies

Autonomous agents that act in the real world utilizing sensory input greatly rely on the ability to plan their actions and to transfer these skills across tasks. The majority of path-planning approaches for mobile robots, however, solve the current navigation problem from scratch, given the current and goal configuration of the robot. Consequently, these approaches yield highly efficient plans for the specific situation, but the computed policies typically do not transfer to other, similar tasks. In this paper, we propose to apply techniques from statistical relational learning to the path-planning problem. More precisely, we propose to learn relational decision trees as abstract navigation strategies from example paths. Relational abstraction has several interesting and important properties. First, it allows a mobile robot to imitate navigation behavior shown by users or by optimal policies. Second, it yields comprehensible models of behavior. Finally, a navigation policy learned in one environment naturally transfers to unknown environments. In several experiments with real robots and in simulated runs, we demonstrate that our approach yields efficient navigation plans. We show that our system is robust against observation noise and can outperform hand-crafted policies.     

Kinematics-Based Navigation Functions

In this paper, we introduce a new family of navigation laws which are based on analytic navigation functions derived using the kinematics equations. These navigation laws combine local and global aspects, and can be used for both indoor and outdoor navigation. The robot's kinematics model is represented in polar coordinates. The analytic navigation functions suggested here are functions of the line-of-sight angle between the robot and the goal, and depend on one or more navigation parameters. The navigation parameters allow us to control the navigation law and, thus, the path of the robot. The choice of the navigation function and its parameters is important, and must satisfy some conditions. Different paths are obtained for different navigation functions and different parameters. This property is used to avoid collision with obstacles. Under this formulation, the number of navigation functions allowing the robot to reach a given goal is infinite. An extensive simulation study shows the effectiveness of the method.     

Neural Navigation Approach for Intelligent Autonomous Vehicles (IAV) in Partially Structured Environments

The use of Neural Networks (NN) is necessary to bring the behavior of Intelligent Autonomous Vehicles (IAV) near the human one in recognition, learning, decision-making, and action. First, current navigation approaches based on NN are discussed. Indeed, these current approaches remedy insufficiencies of classical approaches related to real-time,autonomy , and intelligence. Second, a neural navigation approach essentially based on pattern classification to acquire target localization and obstacle avoidance behaviors is suggested. This approach must provide vehicles with capability, after supervised Gradient Backpropagation learning, to recognize both six (06) target location and thirty (30) obstacle avoidance situations using NN1 and NN2 classifiers, respectively. Afterwards, the decision-making and action consist of two association stages, carried out by reinforcement Trial and Error learning, and their coordination using a NN3. Then, NN3 allows to decide among five (05) actions (move towards 30°, move towards 60°, move towards 90°, move towards 120°, and move towards 150°). Third, simulation results which display the ability of theneural approach to provide IAV with capability to intelligently navigate in partially structured environments are presented. Finally, a discussion dealing with the suggested approach and how it relates to some other works is given.     

Coordination of Multiple Control Schemes for Mobile Robot Navigation on the Basis of the Generalized Stochastic Petri-Nets

There have been two major streams of research for the motion control of mobile robots: model-based deliberate control and sensor-based reactive control. Since the two schemes have complementary advantages and disadvantages, each cannot completely replace the other. There are a variety of environmental conditions that affect the performance of navigation. The motivation of this study is that multiple motion control schemes are required to survive in dynamic real environments. In this paper, we exploit two discrete motion controllers for mobile robots. One is the deliberate trajectory tracking controller and the other is the reactive dynamic window approach. We propose the selective coordination of two controllers on the basis of the generalized stochastic Petri net (GSPN) framework. The major scope of this paper is to clarify the advantage of the proposed controller based on the coordination of multiple controllers from the results of quantitative performance comparison among motion controllers. For quantitative comparison, both simulations and experiments in dynamic environments were carried out. In addition, it is shown that navigation experiences are accumulated in the GSPN formalism. The performance of navigation service can be significantly improved owing to the automatically stored experiences.     

基于轨迹引导的移动机器人导航策略优化算法

针对在杂乱、障碍物密集的复杂环境下移动机器人使用深度强化学习进行自主导航所面临的探索困难,进而导致学习效率低下的问题,提出了一种基于轨迹引导的导航策略优化（TGNPO）算法。首先,使用模仿学习的方法为移动机器人训练一个能够同时提供专家示范行为与导航轨迹预测功能的专家策略,旨在全面指导深度强化学习训练;其次,将专家策略预测的导航轨迹与当前时刻移动机器人所感知的实时图像进行融合,并结合坐标注意力机制提取对移动机器人未来导航起引导作用的特征区域,提高导航模型的学习性能;最后,使用专家策略预测的导航轨迹对移动机器人的策略轨迹进行约束,降低导航过程中的无效探索和错误决策。通过在仿真和物理平台上部署所提算法,实验结果表明,相较于现有的先进方法,所提算法在导航的学习效率和轨迹平滑方面取得了显著的优势。这充分证明了该算法能够高效、安全地执行机器人导航任务。     

多移动机器人的领航-跟随编队避障控制

针对多移动机器人的编队控制问题,提出了一种结合Polar Histogram避障法的领航-跟随协调编队控制算法。该算法在领航-跟随l-φ编队控制结构的基础上引入虚拟跟随机器人,将编队控制转化为跟随机器人对虚拟跟随机器人的轨迹跟踪控制。结合移动机器人自身传感器技术,在简单甚至复杂的环境下为机器人提供相应的路径运动策略,实现实时导航的目的。以两轮差动Qbot移动机器人为研究对象,搭建半实物仿真平台,进行仿真实验。仿真结果表明:该方法可以有效地实现多移动机器人协调编队和避障控制。     

A Neural Network Approach to Dynamic Task Assignment of Multirobots

In this paper, a neural network approach to task assignment, based on a self-organizing map (SOM), is proposed for a multirobot system in dynamic environments subject to uncertainties. It is capable of dynamically controlling a group of mobile robots to achieve multiple tasks at different locations, so that the desired number of robots will arrive at every target location from arbitrary initial locations. In the proposed approach, the robot motion planning is integrated with the task assignment, thus the robots start to move once the overall task is given. The robot navigation can be dynamically adjusted to guarantee that each target location has the desired number of robots, even under uncertainties such as when some robots break down. The proposed approach is capable of dealing with changing environments. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.     

Robot Navigation Based on Discrimination of Artificial Fields: Application to Single Robots

The paper introduces a method for local navigation of mobile robots based on the discrimination of multiple artificial fields, which correspond to targets, obstacles, robots and, if this is the case, robot collectives. Instead of just adding up all potentials, the robot discerns the pertinent potentials at its location and applies a set of motion decisions at each moment. Satisfactory results are obtained. This is the first paper of a more extensive work dealing with individual robots, unorganized groups of robot and robot formations. Here, the method is introduced, with examples for a single robot and for several independent robots.     

Robot Navigation Based on Discrimination of Artificial Fields: Application to Robot Formations

In the preceding paper, a method for mobile robot navigation control based on discrimination of multiple artificial fields was introduced. In this second paper, the method is extended to robot formations. Experimental demonstrations are presented taking examples of four types of formations. The experiments cover formation initialization, maneuvering, obstacle avoidance and formation switching.     

Leveraging Graph Cut’s Energy Function for Context Aware Facial Recognition in Indoor Environments

Context-aware facial recognition regards the recognition of faces in association with their respective environments. This concept is useful for the domestic robot which interacts with humans when performing specific functions in indoor environments. Deep learning models have been relevant in solving facial and place recognition challenges; however, they require the procurement of training images for optimal performance. Pre-trained models have also been offered to reduce training time significantly. Regardless, for classification tasks, custom data must be acquired to ensure that learning models are developed from other pre-trained models. This paper proposes a place recognition model that is inspired by the graph cut energy function, which is specifically designed for image segmentation. Common objects in the considered environment are identified and thereafter they are passed over to a graph cut inspired model for indoor environment classification. Additionally, faces in the considered environment are extracted and recognised. Finally, the developed model can recognise a face together with its environment. The strength of the proposed model lies in its ability to classify indoor environments without the usual training process(es). This approach differs from what is obtained in traditional deep learning models. The classification capability of the developed model was compared to state-of-the-art models and exhibited promising outcomes.     

Realization of a Pheromone Potential Field for Autonomous Navigation by Radio Frequency Identification

This paper presents the results of our research that aims to implement autonomous navigation with an artificial pheromone system. As social insects, a group of ants show advanced performance in their activity by using a chemical substance called a pheromone. By introducing an artificial pheromone system composed of data carriers and autonomous robots, the robotic system creates a potential field to navigate their group. Using this approach we have developed a pheromone density model to realize the function of pheromones with the help of data carriers. We intend to show the effectiveness of the proposed system by performing computer simulations and real experiments for one and two dimensions. The proposed system can be used for an autonomous navigation system. Results are discussed and future works are proposed.     

动态环境下分布式异构多机器人避障方法研究

多机器人系统在联合搜救、智慧车间、智能交通等领域得到了日益广泛的应用。目前,多个机器人之间、机器人与动态环境之间的路径规划和导航避障仍需依赖精确的环境地图,给多机器人系统在非结构环境下的协调与协作带来了挑战。针对上述问题,本文提出了不依赖精确地图的分布式异构多机器人导航避障方法,建立了基于深度强化学习的多特征策略梯度优化算法,并考虑了人机协同环境下的社会范式,使分布式机器人能够通过与环境的试错交互,学习最优的导航避障策略;并在Gazebo仿真环境下进行了最优策略的训练学习,同时将模型移植到多个异构实体机器人上,将机器人控制信号解码,进行真实环境测试。实验结果表明:本文提出的多特征策略梯度优化算法能够通过自学习获得最优的导航避障策略,为分布式异构多机器人在动态环境下的应用提供了一种技术参考。     

An optimized modular neural network controller based on environment classification and selective sensor usage for mobile robot reactive navigation

A new approach to the design of a neural network (NN) based navigator is proposed in which the mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment. This navigator can be optimized for any user-defined objective function through the use of an evolutionary algorithm. The motivation of this research is to develop an efficient methodology for general goal-directed navigation in generic indoor environments as opposed to learning specialized primitive behaviors in a limited environment. To this end, a modular NN has been employed to achieve the necessary generalization capability across a variety of indoor environments. Herein, each NN module takes charge of navigating in a specialized local environment, which is the result of decomposing the whole path into a sequence of local paths through clustering of all the possible environments. We verify the efficacy of the proposed algorithm over a variety of both simulated and real unstructured indoor environments using our autonomous mobile robot platform.     

一种基于改进Elman神经网络的机器人行为控制器

为了增强移动机器人在动态环境中的学习和适应能力,提出了一种新的基于改进Elman神经网络的具有学习和记忆功能的机器人行为控制器,并且利用遗传算法来优化神经网络的连接权值,提高了机器人行为的准确性和快速型。仿真实验结果显示,本文提出的方法对机器人的学习和适应能力有很大的提高。     

基于情感与环境认知的移动机器人自主导航控制

将基于情感和认知的学习与决策模型引入到基于行为的移动机器人控制体系中, 设计了一种新的自主导航控制系统. 将动力学系统方法用于基本行为设计, 并利用ART2神经网络实现对连续的环境感知状态的分类, 将分类结果作为学习与决策算法中的环境认知状态. 通过在线情感和环境认知学习, 形成合理的行为协调机制. 仿真表明, 情感和环境认知能明显地改善学习和决策过程效率, 提高基于行为的移动机器人在未知环境中的自主导航能力     

Autonomic microcell assignment in massively distributed online virtual environments

Distributed virtual environments and massively multiplayer online games in particular have been on the rise for several years now. They offer huge digital environments characterized by tens of thousands of users interacting with each other. Efficiently managing these online worlds requires scalable architectures to distribute the load over multiple servers and maintain a high Quality of Experience (QoE). This need will only increase as online virtual worlds become more and more popular. A traditional approach to improve the scalability of this type of system is to statically partition the virtual world in smaller segments called cells, each assigned to a dedicated server.In this paper a novel approach of dividing the virtual world into even smaller parts called microcells is introduced. Critical in this approach are the algorithms that manage the microcell allocation over the available servers. These algorithms must face a number of challenges and have as a central goal to keep the load experienced by the servers below a given threshold. On one hand, clustering interacting microcells on one server allows to limit the overall load by minimizing the communication overhead. On the other hand, locating too many microcells on one server may cause the load to violate the threshold value, resulting in an overload situation. In this paper we present a number of algorithms that determine the microcell allocation and runtime adaptations of the microcell allocation to optimize the deployment. We evaluate the microcell approach by studying the impact of the microcell size and the number of servers. The efficiency of the algorithms in terms of their ability to decrease the maximum server load and their capability to maintain an ideal deployment in dynamic environments is also studied.     

基于无线通信的高精度室内人员定位系统在博物馆信息化建设中的应用

基于无线电通信的高精度室内人员定位系统能够提升博物馆观众参观体验及增强博物馆管理效率。采用分布式终端-集中数据管理的构架设计, 由一个服务器机柜（包含导航服务器、导览服务器、数据库服务器、信息发布服务器、票务服务器、监控服务器）、一台管理计算机、多个监控终端、多台人工票务终端、多个现场交换机、若干无线AP以及若干智能导览终端组成。运用高精度人员定位系统和无线通讯技术实现人员定位, 利用智能导览终端设备和实时数据库信息,进行展品信息推送、馆内游览路线导航、馆内设施使用及区域人流密度情况查询等.设立多台自动化票务终端,实现自助退换票、票务信息统计、网络票务预约、票卡运营及维护等功能。     

基于知识点关系的学习导航系统建模方法研究

学习导航系统的目的在于避免学习者在学习过程中“迷失”方向和提高学习效率,并能在一定程度上消除“孤独”感,其关键是系统能够提供高效的导航机制,指导学习者完成学习任务。本文基于Petri网建模工具,利用知识结构理论和知识点关系对导航系统建模方法进行了探讨,并着重强调学习者的个性化学习,结合利用相关鱼眼图和感知处理技术建立了一套个性化学习导航系统。     

Robot Motion Planning in Dynamic Uncertain Environments

In the real world, mobile robots often operate in dynamic and uncertain environments. Therefore, it is necessary to develop a motion planner capable of real-time planning that also addresses uncertainty concerns. In this paper, a new algorithm, Dynamic AO* (DAO*), is developed for navigation tasks of mobile robots. DAO* not only performs a good anytime behavior and offers a fast replanning framework, but also considers the motion uncertainty. Moreover, by incorporating DAO* with D* Lite, a new planning architecture, DDAO*, is represented to efficiently search in large state spaces. Finally, simulations and experiments are shown to verify the efficiency of the proposed algorithms.     

A practical and useful autonomous towed vehicle for port area inspection

This paper presents a novel underwater vehicle for port area inspection, which has various navigation modes (towed mode, autonomous mode and kite mode) to stand against fast and changeable sea currents. The property assures safe and reliable observation performance irrespective of current speed. Since in a port area sea currents are fast and complex, such a vehicle must be practical and useful for port area application. The unique point of the vehicle is the employment of an autonomous underwater vehicle (AUV) as a towed vehicle. In general, AUVs and towed vehicles are mutually contradictory. This paper describes the process of development to achieve the three different navigation modes. The system components and the results of computer simulations and towing tank tests to investigate the stability of the vehicle are presented. In addition, results of the first sea trial are also presented. These results show that the vehicle can navigate stably in the three different navigation modes.