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。     

基于人机交互的移动服务机器人导航系统

针对目前全自主移动机器人尚难实现的问题,基于人机结合的思想研制了由操作者、人机交互平台和移动机器人组成的“人—机—环境”一体化移动机器人导航系统．介绍了该系统的结构组成,阐述了系统导航策略,详细分析了人机交互、人机协作、移动机器人位姿预测及基于扩展卡尔曼滤波的位姿校正方法．设计了导航系统界面,通过在室内真实环境下的导航实验,验证了该“人—机—环境”一体化移动机器人导航系统的有效性．     

面向室内移动机器人的无迹滤波实时导航方法

根据轮式移动机器人室内自主漫游的目标要求和约束条件,提出了一种新的实时导航策略,利用UKF（unscented Kalman filter）算法对置顶相机和里程计获取的移动机器人位姿信息进行在线滤波,为实现移动机器人的室内自主漫游控制进行实时导航定位．实验结果表明,提出的导航策略和实现算法满足实时性要求,具有较高的精度,可为进一步的实际应用提供参考．     

基于增强转移网络（ATN）的室外移动机器人道路图像理解

道路图像理解是室外移动机器人视觉导航自主驾驶研究中的一个关键技术 ,由于基于视觉导航的室外移动机器人自主驾驶时 ,对实时性和鲁棒性要求很高 ,因此 ,为了满足室外移动机器人自主驾驶的实时性和鲁棒性要求 ,将人工智能研究句法分析中的一个形式体系——增强转移网络 (ATN )成功地应用于室外移动机器人的道路理解中 ,进而提出了基于 ATN的室外移动机器人道路图像理解算法 ,该算法在统一的 ATN构建思想指导下 ,针对不同的道路情况 ,不仅可以灵活地构建出不同的道理理解 ATN网络 ,还可达到本质上的统一及应用上的灵活。经实验检验 ,该算法在满足系统要求的鲁棒性条件下 ,具有非常高的实时性 ,即能充分地满足自主移动机器人高速自主导航的需要     

激光测距在移动机器人自主导航中的应用

移动机器人在运动范围内需要有足够的传感器信息可供利用来进行自主导航,在完全未知的环境中,由机器人依靠其自身携带的传感器所提供的信息建立环境模型是机器人进行自主定位和导航的前提之一。介绍了激光测距在移动机器人自主导航中的应用研究;通过二维测距传感器对其周围环境进行扫描,提出了自主导航中地图创建、定位如何用二维扫描获得三维数据流的算法描述,并实验验证该算法的运用使机器人获得一个很好的三维视觉结构图。     

机器人动态神经网络导航算法的研究和实现

针对Pioneer3-DX 移动机器人, 提出了基于强化学习的自主导航策略, 完成了基于动态神经网络的移动机器人导航算法设计. 动态神经网络可以根据机器人环境状态的复杂程度自动地调整其结构, 实时地实现机器人的状态与其导航动作之间的映射关系, 有效地解决了强化学习中状态变量表的维数爆炸问题. 通过对Pioneer3-DX移动机器人导航进行仿真和实物实验, 证明该方法的有效性, 且导航效果明显优于人工势场法.     

基于3D-NDT的移动机器人定位算法研究北大核心CSCD

移动机器人定位是移动机器人自主导航的基本问题,在室外环境,GPS作为成熟方案被广泛使用,但在存在遮挡、有强电磁干扰等环境下,GPS定位的精度、稳定性及可靠性受到很大影响。本文详细阐述了三维激光点云3D-NDT匹配方法,在此基础上提出了融合里程计与3D-NDT点云匹配方法的移动机器人实时定位方法,解决了移动机器人在室外弱GPS环境下定位精度无法保证的问题。利用自主研发的移动机器人平台,在大范围室外环境中进行了测试,实验结果验证了本文所提算法的有效性。     

自主移动机器人导航定位技术研究初探

介绍了当前自主移动机器人常采用的导航定位技术,以及所采用的各种传感器的工作原理、适应场摘要:介绍了当前自主移动机器人常采用的导航定位技术,以及所采用的各种传感器的工作原理、适应场合和优缺点,并提出了浆液下搅拌机器人导航定位的初步方案.这对自主移动机器人导航定位技术的进一步研究具有一定的参考价值.     

基于行为优先与模糊控制的移动机器人导航

由于动态未知环境下自主移动机器人的导航具有较大困难,为实现自主机器人在动态未知环境下的无碰撞运行,文中将行为优先级控制与模糊逻辑控制相结合,提出4种基本行为控制策略:目标寻找、避障、跟踪和解锁.针对'U'型和'V'型障碍物运行解锁问题,提出了行走路径记忆方法,并通过构建虚拟墙来避免机器人再次走入此类区域.仿真实验表明,所提出的控制策略可有效地运用于复杂和未知环境下自主移动机器人的导航,且具有较好的鲁棒性和适应性.     

基于KQML语言的多自主移动机器人仿真系统

用JAVA语言开发了栅格环境下的多自主移动机器人仿真系统,通过KQML语言通信模拟了多个自主的移动机器人,机器人的自主性主要体现在自主感知环境和自主进行路径规划、任务执行和安全导航等工作．该仿真系统具有平台无关性、地图无关性、算法无关性以及机器人配置的无关性,为多自主机器人系统的研究提供了一个可借鉴的平台．     

Neural networks based reinforcement learning for mobile robots obstacle avoidance

This study proposes a new approach for solving the problem of autonomous movement of robots in environments that contain both static and dynamic obstacles. The purpose of this research is to provide mobile robots a collision-free trajectory within an uncertain workspace which contains both stationary and moving entities. The developed solution uses Q-learning and a neural network planner to solve path planning problems. The algorithm presented proves to be effective in navigation scenarios where global information is available. The speed of the robot can be set prior to the computation of the trajectory, which provides a great advantage in time-constrained applications. The solution is deployed in both Virtual Reality (VR) for easier visualization and safer testing activities, and on a real mobile robot for experimental validation. The algorithm is compared with Powerbot's ARNL proprietary navigation algorithm. Results show that the proposed solution has a good conversion rate computed at a satisfying speed.     

Autonomous mobile robot navigation and learning

Research focused on the development and experimental validation of intelligent control techniques for autonomous mobile robots able to plan and perform a variety of assigned tasks in unstructured environments is presented. In particular, an autonomous mobile robot, HERMIES-IIB intelligence experiment series, is described. It is a self-powered, wheel-driven platform containing an onboard 16-node Ncube hypercube parallel processor interfaced to effectors and sensors through a VME-based system containing a Motorola 68020 processor, a phased sonar array, dual manipulator arms, and multiple cameras. Research on navigation and learning is examined     

Path planning of fire-escaping system for intelligent building

We present the path-planning techniques of the fire-escaping system for intelligent building, and use multiple mobile robots to present the experimental scenario. The fire-escaping system contains a supervised computer, an experimental platform, some fire-detection robots and some navigation robots. The mobile robot has the shape of a cylinder, and its diameter, height and weight are 10?cm, 15?cm and 1.5?kg, respectively. The mobile robot contains a controller module, two DC servomotors (including drivers), three IR sensor modules, a voice module and a wireless RF module. The controller of the mobile robot acquires the detection signals from reflective IR sensors through I/O pins and receives the command from the supervised computer via wireless RF interface. The fire-detection robot carries the flame sensor to detect fire sources moving on the grid-based experiment platform, and calculates the more safety escaping path using piecewise cubic Bezier curve on all probability escaping motion paths. Then the user interface uses A* searching algorithm to program escaping motion path to approach the Bezier curve on the grid-based platform. The navigation robot guides people moving to the safety area or exit door using the programmed escaping motion path. In the experimental results, the supervised computer programs the escaping paths using the proposed algorithms and presents movement scenario using the multiple smart mobile robots on the experimental platform. In the experimental scenario, the user interface transmits the motion command to the mobile robots moving on the grid-based platform, and locates the positions of fire sources by the fire-detection robots. The navigation robot guides people leaving the fire sources using the low-risk escaping motion path and moves to the exit door.     

Probabilistic Road Map sampling strategies for multi-robot motion planning

This paper presents a Probabilistic Road Map (PRM) motion planning algorithm to be queried within Dynamic Robot Networks—a multi-robot coordination platform for robots operating with limited sensing and inter-robot communication.

First, the Dynamic Robot Networks (DRN) coordination platform is introduced that facilitates centralized robot coordination across ad hoc networks, allowing safe navigation in dynamic, unknown environments. As robots move about their environment, they dynamically form communication networks. Within these networks, robots can share local sensing information and coordinate the actions of all robots in the network.

Second, a fast single-query Probabilistic Road Map (PRM) to be called within the DRN platform is presented that has been augmented with new sampling strategies. Traditional PRM strategies have shown success in searching large configuration spaces. Considered here is their application to on-line, centralized, multiple mobile robot planning problems. New sampling strategies that exploit the kinematics of non-holonomic mobile robots have been developed and implemented. First, an appropriate method of selecting milestones in a PRM is identified to enable fast coverage of the configuration space. Second, a new method of generating PRM milestones is described that decreases the planning time over traditional methods. Finally, a new endgame region for multi-robot PRMs is presented that increases the likelihood of finding solutions given difficult goal configurations.

Combining the DRN platform with these new sampling strategies, on-line centralized multi-robot planning is enabled. This allows robots to navigate safely in environments that are both dynamic and unknown. Simulations and real robot experiments are presented that demonstrate: (1) speed improvements accomplished by the sampling strategies, (2) centralized robot coordination across Dynamic Robot Networks, (3) on-the-fly motion planning to avoid moving and previously unknown obstacles and (4) autonomous robot navigation towards individual goal locations.     

High‐precision control of tracked field robots in the presence of unknown traction coefficients

Accurate steering through crop rows that avoids crop damage is one of the most important tasks for agricultural robots utilized in various field operations, such as monitoring, mechanical weeding, or spraying. In practice, varying soil conditions can result in off‐track navigation due to unknown traction coefficients so that it can cause crop damage. To address this problem, this paper presents the development, application, and experimental results of a real‐time receding horizon estimation and control (RHEC) framework applied to a fully autonomous mobile robotic platform to increase its steering accuracy. Recent advances in cheap and fast microprocessors, as well as advances in solution methods for nonlinear optimization problems, have made nonlinear receding horizon control (RHC) and receding horizon estimation (RHE) methods suitable for field robots that require high‐frequency (milliseconds) updates. A real‐time RHEC framework is developed and applied to a fully autonomous mobile robotic platform designed by the authors for in‐field phenotyping applications in sorghum fields. Nonlinear RHE is used to estimate constrained states and parameters, and nonlinear RHC is designed based on an adaptive system model that contains time‐varying parameters. The capabilities of the real‐time RHEC framework are verified experimentally, and the results show an accurate tracking performance on a bumpy and wet soil field. The mean values of the Euclidean error and required computation time of the RHEC framework are equal to 0.0423 m and 0.88 ms, respectively.     

An indoor localization system in a multiblock workspace

As service robots and other ubiquitous technology have evolved, an increasing need for the autonomous navigation of mobile objects has arisen. In a large number of localization schemes, the absolute-position estimation method, which relies on navigation beacons or landmarks, has been widely used as it has the advantages of being economical and accurate. However, only a few of these schemes have expanded their application to complicated workspaces, or those that have many rooms or blocks. As the navigation of mobile objects in complicated workspaces is vital for ubiquitous technology, multiblock navigation is necessary. This article presents methodologies and techniques for the multiblock navigation of the indoor localization system with active beacon sensors. This new indoor localization system design includes ultrasonic attenuation compensation, dilution-of-precision analysis, and a fault detection and isolation algorithm using redundant measurements. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

动态环境下改进人工势场法的仓储机器人自主导航系统研究

为了解决仓储机器人在全动态环境中的自主导航问题,在分析自主导航技术基础上建立了机器人和动态障碍物的数学模型,搭建了以二维激光雷达为主的环境感知平台,提出了一种改进的人工势场法。在传统人工势场法中同时引入相对速度和相对加速度因素得到改进的人工势场模型,实现机器人在全动态环境中的自主移动。设计了无障碍物和多动态障碍物两种移动环境。经仿真验证,应用改进的人工势场法进行路径规划能高效地避开动态障碍物、跟踪动态目标,且运动路径光滑。     

Hybrid autonomous control for multi mobile robots

Reinforcement learning can be an adaptive and flexible control method for autonomous system. It does not need a priori knowledge; behaviors to accomplish given tasks are obtained automatically by repeating trial and error. However, with increasing complexity of the system, the learning costs are increased exponentially. Thus, application to complex systems, like a many redundant d.o.f. robot and multi-agent system, is very difficult. In the previous works in this field, applications were restricted to simple robots and small multi-agent systems, and because of restricted functions of the simple systems that have less redundancy, effectiveness of reinforcement learning is restricted. In our previous works, we had taken these problems into consideration and had proposed new reinforcement learning algorithm, 'Q-learning with dynamic structuring of exploration space based on GA (QDSEGA)'. Effectiveness of QDSEGA for redundant robots has been demonstrated using a 12-legged robot and a 50-link manipulator. However, previous works on QDSEGA were restricted to redundant robots and it was impossible to apply it to multi mobile robots. In this paper, we extend our previous work on QDSEGA by combining a rule-based distributed control and propose a hybrid autonomous control method for multi mobile robots. To demonstrate the effectiveness of the proposed method, simulations of a transportation task by 10 mobile robots are carried out. As a result, effective behaviors have been obtained.     

Behavior analysis and training-a methodology for behaviorengineering

We propose Behavior Engineering as a new technological area whose aim is to provide methodologies and tools for developing autonomous robots. Building robots is a very complex engineering enterprise that requires the exact definition and scheduling of the activities which a designer, or a team of designers, should follow. Behavior Engineering is, within the autonomous robotics realm, the equivalent of more established disciplines like Software Engineering and Knowledge Engineering. In this article we first give a detailed presentation of a Behavior Engineering methodology, which we call Behavior Analysis and Training (BAT), where we stress the role of learning and training. Then we illustrate the application of the BAT methodology to three cases involving different robots: two mobile robots and a manipulator. Results show the feasibility of the proposed approach.