移动机器人路径规划强化学习的初始化

针对现有机器人路径规划强化学习算法收敛速度慢的问题,提出了一种基于人工势能场的移动机器人强化学习初始化方法.将机器人工作环境虚拟化为一个人工势能场,利用先验知识确定场中每点的势能值,它代表最优策略可获得的最大累积回报.例如障碍物区域势能值为零,目标点的势能值为全局最大.然后定义Q初始值为当前点的立即回报加上后继点的最大折算累积回报.改进算法通过Q值初始化,使得学习过程收敛速度更快,收敛过程更稳定.最后利用机器人在栅格地图中的路径对所提出的改进算法进行验证,结果表明该方法提高了初始阶段的学习效率,改善了算法性能.     

未知环境下移动机器人遍历路径规划

为提高未知环境下移动机器人遍历路径规划的效率,提出了一种可动态调节启发式规则的滚动路径规划算法.该算法以生物激励神经网络为环境模型,通过在线识别环境信息特征,动态调用静态搜索算法和环绕障碍搜索算法,有效减少了路径的转弯次数.引入虚拟障碍和直接填充算法,解决了u型障碍区域的连续遍历问题.最后通过仿真实验表明了该方法在未知复杂环境下的有效性.     

一种未知环境下的快速路径规划方法*

为提高机器人在未知环境中的快速路径规划能力,引入自由路径表征可以通过的自由空间,引入风险函数评价机器人切入自由路径过程中发生碰撞的风险。通过搜索最优自由路径、评价碰撞风险压缩表示环境信息,使得未知环境中利用模糊控制器进行局部路径规划的实时性大为提高。与虚拟势场法等传统方法相比,其无局部最小,且极大缓解了狭窄环境中的振荡现象。实验及仿真均表明该方法实时性好、规划所得路径优于已有方法。     

Case-based path planning for autonomous underwater vehicles

Case-based reasoning is reasoning based on specific instances of past experience. A new solution is generated by retrieving and adapting an old one which approximately matches the current situation. In this paper, we outline a case-based reasoning scheme for path planning in autonomous underwater vehicle (AUV) missions. An annotated map database is employed to model the navigational environment. Routes which are used in earlier missions are represented as objects in the map. When a new route is to be planned, the path planner retrieves a matching route from the database and modifies it to suit to the current situation. Whenever a matching route is not available, a new route is synthesized based on past cases that describe similar navigational environments. Case-based approach is thus used not only to adapt old routes but also to synthesize new ones. Since the proposed scheme is centered around reuse of old routes, it would be fast especially when long routes need to be generated. Moreover, better reliability of paths can be expected as they are adapted from earlier missions. The scheme is novel and appropriate for AUV mission scenarios. In this paper, we describe the representation of navigation environment including past routes and objects in the navigational space. Further, we discuss the retrieval and repair strategies and the scheme for synthesizing new routes. Sample results of both synthesis and reuse of routes and system performance analysis are also presented. One major advantage of this system is the facility to enrich the map database with new routes as they are generated.This work was supported in part by National Science Foundation Grant No. BCS-9017990.     

基于信息融合的移动机器人定位与路径规划

针对镜面反射引起的声呐测距不准的问题,设计一种加权融合的方法对声呐和摄像头的信息进行融合,使移动机器人能够精确地完成在拐角区域下的自身定位,并给出了机器人的路径规划。通过在先锋3机器人平台上进行的实验结果证明,该方法能够使移动机器人安全、平滑地通过拐角区域。     

Real-time path planning of autonomous robots in a two-dimensional unknown dynamic navigation environment

This paper deals with the real-time path planning of an autonomous mobile robot in two-dimensional, unknown, dynamic multiple robot navigation space. In particular, a collision-free navigation path planning strategy is presented in real time by using a heuristichuman like approach. The heuristic scheme used here is based on thetrial and error methodology with the attempt to minimize the cost of the navigation efforts, when time plays a significant role. Past built-up navigation experience and current extracted information from the surrounding environment are used for the detection of other moving objects (robots) in the same navigation environment. Moreover, the determination of asecure navigation path is supported by a set of generic traffic priority rules followed by the autonomous robots moving in the same environment. Simulated results for two moving objects in the same navigation space are also presented.     

未知环境下基于约束点的移动机器人路径规划

针对未知环境中障碍物种类多样性和位置不确定性的特点,提出了基于约束点的路径规划方法。首先对机器人在未知环境中检测到的局部障碍物信息进行分类和几何特征属性描述,得其约束点信息,然后引入改进后的A*算法,将其搜索范围局限于约束点上,计算约束点的评价函数值后得到子目标点,机器人到达子目标点后,若陷入死区,则采取回溯路径策略,重新选择子目标点,否则根据该点所属的障碍物种类采取跨越或绕行避障策略,最后移动机器人在未知环境中顺利到达目标点。仿真研究说明本文提出的路径规划方法具有可行性和有效性。     

Global path planning of mobile robots using a memetic algorithm

In this paper, a memetic algorithm for global path planning (MAGPP) of mobile robots is proposed. MAGPP is a synergy of genetic algorithm (GA) based global path planning and a local path refinement. Particularly, candidate path solutions are represented as GA individuals and evolved with evolutionary operators. In each GA generation, the local path refinement is applied to the GA individuals to rectify and improve the paths encoded. MAGPP is characterised by a flexible path encoding scheme, which is introduced to encode the obstacles bypassed by a path. Both path length and smoothness are considered as fitness evaluation criteria. MAGPP is tested on simulated maps and compared with other counterpart algorithms. The experimental results demonstrate the efficiency of MAGPP and it is shown to obtain better solutions than the other compared algorithms.     

改进的混合蛙跳移动机器人路径规划算法

为了实现移动机器人在障碍环境中的路径规划,提出一种改进的混合蛙跳算法(SFLA).改进算法在原算法基础上引入交叉操作,并在青蛙更新策略中充分利用学习机制;此外提出了一种带控制参数的产生新个体的方法代替原本的随机更新操作.把路径规划问题转换为最小化问题,基于环境中目标和障碍物的位置定义青蛙的适应度,机器人依次到达每次迭代中最好蛙的位置,从而实现最优路径规划.移动机器人仿真实验中,与基本蛙跳算法和其他智能算法相比,改进算法在规划时间和成功次数上均有很大的提高.实验结果表明了改进算法的有效性.     

Complete coverage path planning for wheeled agricultural robots

In the agricultural industry, an evolutionary effort has been made over the last two decades to achieve precise autonomous systems to perform typical in-field tasks, including harvesting, mowing, and spraying. One of the main objectives of an autonomous system in agriculture is to improve the efficiency while reducing the environmental impact and cost. Due to the nature of these operations, complete coverage path planning (CCPP) approaches play an essential role to find an optimal path which covers the entire field while taking into account land topography, operation requirements, and robot characteristics. The aim of this paper is to propose a CCPP approach defining the optimal movements of mobile robots over an agricultural field. First, a method based on tree exploration is proposed to find all potential solutions satisfying some predefined constraints. Second, a similarity check and selection of optimal solutions method is proposed to eliminate similar solutions and find the best solutions. The optimization goals are to maximize the coverage area and to minimize overlaps, nonworking path length, and overall travel time. To explore a wide range of possible solutions, our approach is able to consider multiple entrances for the robot. For fields with a complex shape, different dividing lines to split them into simple polygons are also considered. Our approach also computes the headland zones and covers them automatically which leads to a high coverage rate of the field.     

基于强化学习的自动驾驶汽车路径规划方法研究综述

路径规划作为自动驾驶的关键技术,具有广阔的应用前景和科研价值。探索解决自动驾驶车辆路径规划问题的方法,着重关注基于强化学习的路径规划方法。在阐述基于常规方法和强化学习方法的路径规划技术的基础上,重点总结了基于强化学习和深度强化学习来解决自动驾驶车辆路径规划问题的算法,并将算法按照基于值和基于策略的方式进行分类,分析各类算法的特点、优缺点及改进措施。最后对基于强化学习的路径规划技术的未来发展方向进行了展望。     

改进A*算法的移动机器人最短路径规划

针对复杂室内环境下移动机器人路径规划存在实时性差的问题,通过对Dijkstra算法、传统A^*算法以及一些改进的A^*算法的分析比较,提出了对A^*算法的进一步改进的思路。首先对当前节点及其父节点的估计路径代价进行指数衰减的方式加权,使得A^*算法在离目标点较远时能够很快地向目标点靠近,在距目标点较近时能够局部细致搜索保证目标点附近障碍物较多时目标可达;然后对生成的路径进行五次多项式平滑处理,使得路径进一步缩短且便于机器人控制。仿真结果表明,改进算法较传统A^*算法时间减少93.8%,路径长度缩短17.6%、无90°转折点,使得机器人可以连续不停顿地跟踪所规划路径到达目标。在不同的场景下,对所提算法进行验证,结果表明所提算法能够适应不同的环境且有很好的实时性。     

室外自主移动机器人AMOR的导航技术

在非结构化环境,移动机器人行驶运动规划和自主导航是非常挑战性的问题。基于实时的动态栅格地图,提出了一个快速的而又实效的轨迹规划算法,实现机器人在室外环境的无碰撞运动导航。AMOR是自主研发的室外运动移动机器人,它在2007年欧洲C-ELROB大赛中赢得了野外自主侦察比赛的冠军。它装备了SICK的激光雷达,用来获取机器人运动前方的障碍物体信息,建立实时动态的环境地图。以A*框架为基础的改造算法,能够在众多的路径中快速地找到最佳的安全行驶路径,实现可靠的自主导航。所有的测试和比赛结果表明所提方案是可行的、有效的。     

未知动态环境下非完整移动群机器人围捕

针对未知动态障碍物环境下非完整移动群机器人围捕,提出了一种基于简化虚拟受力模型的自组织方法.首先给出了个体机器人的运动方程,然后给出了未知动态环境下目标和动态障碍物的运动模型.通过对复杂环境下围捕行为的分解,抽象出简化虚拟受力模型,基于此受力模型,设计了个体运动控制方法,接着证明了系统的稳定性并给出了参数设置范围.不同情况下的仿真结果表明,本文给出的围捕方法可以使群机器人在未知动态障碍物环境下保持较好的围捕队形,并具有良好的避障性能和灵活性.最后分析了本文与基于松散偏好规则的围捕方法相比的优势.     

基于观测器的轮式移动机器人路径跟踪控制

研究基于状态观测器的轮式移动机器人的路径跟踪控制问题.首先简要回顾了基于状态反馈的移动机器人的路径跟踪控制问题;进而通过适当的状态变换将移动机器人模型转换为合适的形式,并在移动机器人的位置可以测量的情况下设计了一种可保证状态观测误差指数收敛的状态观测器;最后结合状态反馈路径跟踪控制器和所设计的观测器得到了一种基于观测器的路径跟踪控制器,该控制器可以保证移动机器人的运动轨迹指数收敛到期望路径上.仿真结果证实了所提出的基于观测器的路径跟踪控制器的有效性.     

一种水下群机器人路径规划算法的形式化研究

为了增强基于遗传算法的水下群机器人路径规划算法正确性的说服力,使用定理证明对其进行形式化研究,给出算法在定理证明器HOL4中的形式化模型。基于算法形式化的一般步骤,首先对算法的设计进行了详细的分析,指出算法设计的核心步骤与建模难点。在此基础上建立了总体形式化建模框架,然后对其进行化简,得到种群初始化、选择、交叉三个核心模块。接着给出模型中要用到的基本数据类型的形式化描述,并分别对三个模块进行形式化描述,最终得到算法的形式化模型。通过证明与模型相关的97条性质,说明了模型的合理性及有效性,在此模型的基础上,可以完成对算法的形式化验证,同时还能拓展HOL4的应用范围。     

基于无线传感器网络的未知环境下移动机器人实时路径规划

利用无线传感器网络技术、多传感器信息融合技术、基于占用网格的概率地图构建和基于群集智能的微粒群仿生学算法,采用三层控制结构的规划策略,提出了一种新的在未知环境下移动机器人在线实时路径规划方法。最后设计并构造出了实际的无线传感器网络,验证了算法的有效性、准确性和实时性。     

提高移动机器人路径规划效率的方法

针对传统遗传算法存在的初始种群数目庞大,寻优效率和收敛速度慢的缺点,提出了一种基于粗糙集约简决策规则和删除冗余属性的方法。首先建立基于特定栅格法的环境模型,获得机器人路径规划的初始决策表,然后根据粗糙集约简推导最小化决策规则,并用于训练初始种群。最后利用遗传算法优化初始种群,获得最优规划路径。分别在简单和复杂的环境模型下进行了实验,仿真结果表明该方法能够大大减小遗传算法初始种群的规模,缩小算法搜索范围,提高遗传算法的收敛速度和寻优效率,验证了该方法的可行性和优越性。     

面向地图构建的移动机器人局部路径自主规划

移动机器人在未知场景中规划路径以自主完成定位与地图构建是机器人领域的一个重要研究课题.本文阐述了一种利用实时构建的信息熵地图动态生成机器人的局部探索路径,并综合转向约束和避障约束设计了一种基于模糊评价方法的方向选择策略跟踪生成的局部路径并进行环境构图.与现有方法相比,本文方法能够根据环境动态地生成平滑连续的局部探索路径,并能引导机器人进行障碍物躲避和完成自主构图.实验结果表明相较对比方法,本文方法的探索路程最短,观测覆盖度最高,同时整个自主构图过程所需的时间也更短.     

A dynamic priority based path planning for cooperation of multiple mobile robots in formation forming

Robots that work in a proper formation show several advantages compared to a single complex robot, such as a reduced cost, robustness, efficiency and improved performance. Existing researches focused on the method of keeping the formation shape during the motion, but usually neglect collision constraints or assume a simplified model of obstacles. This paper investigates the path planning of forming a target robot formation in a clutter environment containing unknown obstacles. The contribution lies in proposing an efficient path planner for the multiple mobile robots to achieve their goals through the clutter environment and developing a dynamic priority strategy for cooperation of robots in forming the target formation. A multirobot system is set up to verify the proposed method of robot path planning. Simulations and experiments results demonstrate that the proposed method can successfully address the collision avoidance problem as well as the formation forming problem.