基于神经网络的移动机器人路径规划

针对移动机器人未知环境下的安全路径规划,本文采用了一种局部连接Hopfield神经网络（ANN）规划器。对任意形状环境,ANN中兼顾处理了“过近”和“过远”来形成安全 路径,而无需学习过程。为在单处理器上进行有效的在线路径规划,提出用基于距离变换的串行模拟,加速数值势场的传播。仿真表明,该方法具有较高的实时性和环境适应性。     

未知环境下移动机器人安全路径规划的一种神经网络方法

针对未知环境下移动机器人的安全路径规划,采用了一种局部连接Hopfield神经网 络(Hopfield Neural Networks,HNN)规划器;分析了HNN稳定性,并给出了存在可行路 径的条件.如果存在可行路径,该方法不存在非期望的局部吸引点,并在连接权设计中兼顾 "过近"和"过远"来形成安全路径.为在单处理器上有效地在线路径规划,采用多顺序的 Gauss-Seidel迭代方法来加速HNN势场的传播.结果表明该方法具有较高的实时性和环境 适应性.     

一种动态环境中的移动机器人路径规划安全策略

文章针对有运动障碍的环境,基于局部信息,从安全性的角度为机器人规划动态避障路径——安全路径。算法考虑了对机器人速度和加速度的限制,将“安全性,,概念引入到设计规划策略中来。选择一条使“静安全函数、目标引力、动安全函数,,的乘积最大的路径。“静安全函数”依赖于加速度的约束;“目标引力”依赖于距目标的远近;“动安全函数”依赖于机器人与移动障碍的距离。     

基于接近觉的机械臂避障路径规划

提出了一种基于接近觉的机械臂避障路径规划方法。首先,针对排列稀疏的接近觉传感器阵列的障碍物感知问题,定义连杆“运动方向”的概念,优先读取连杆运动方向上的传感器以缩短读取周期的长度,并将距离传感器最近的障碍物表面建模为“假想圆锥”,过其顶点作“安全平面”,连杆在运动过程中不能与其发生碰撞。其次,针对避障路径规划问题,采用...     

五次多项式优化的平行泊车路径规划

针对目前自动泊车路径规划普遍存在的曲率突变问题,提出了一种五次多项式优化的平行泊车路径规划方法。五次多项式曲线由约束条件建立的方程组求解得出,并对路径的曲率突变处进行过渡优化。为简化计算,引入“虚圆半径”的概念,以“虚圆半径”作为最小转弯半径,并按照“圆弧-直线-圆弧”平行泊车路径规划的方法进行求解,由此得出优化的平行泊车路径。仿真结果表明,五次多项式优化的平行泊车路径规划方法能够规划出曲率连续、满足避障约束和车辆运动学约束的优化路径,提高了路径跟踪的效果,保证车辆安全完成泊车。     

基于海图和改进粒子群优化算法的AUV全局路径规划

针对AUV（自主水下机器人）在复杂条件海域做全局路径规划时面临的环境信息缺少,环境建模困难和常规算法复杂、求解能力弱等问题,提出一种基于海图和改进粒子群优化算法的全局路径规划方法．首先利用电子海图的先验知识建立3维静态环境模型,并构造路径航程、危险度和平滑函数;在粒子群优化算法中引入搜索因子和同性因子自适应地调整参数,并结合鱼群算法的“跳跃”过程提升算法的求解能力．同时建立安全违背度和选优规则以提高所规划路径的安全性．仿真实验结果表明,本文方法与传统粒子群算法和蚁群算法相比,规划出短航程、安全性高的全局路径的能力更强,可满足AUV在复杂海域航行时的全局路径规划需求．     

基于生物启发模型的AUV三维自主路径规划与安全避障算法

针对自治水下机器人(AUV)的路径规划问题,在三维栅格地图的基础上,给出一种基于生物启发模型的三维路径规划和安全避障算法. 首先建立三维生物启发神经网络模型,利用此模型表示AUV的三维工作环境,神经网络中的每一个神经元与栅格地图中的位置单元一一对应;然后,根据神经网络中神经元的活性输出值分布情况自主规划AUV的运动路径.静态环境与动态环境下仿真实验结果表明了生物启发模型在AUV三维水下环境中路径规划和安全避障上的有效性.     

实现机器人动态路径规划的仿真系统

针对机器人动态路径规划问题,提出了在动态环境中移动机器人的一种路径规划方法,适用于环境中同时存在已知和未知,静止和运动障碍物的复杂情况。采用栅格法建立机器人空间模型,整个系统由全局路径规划和局部避碰规划两部分组成。在全局路径规划中,用快速搜索随机树算法规划出初步全局优化路径,局部避碰规划是在全局优化路径的同时,通过基于滚动窗口的环境探测和碰撞规则,对动态障碍物实施有效的局部避碰策略,从而使机器人安全顺利地到达目的地。仿真实验结果说明该方法具有可行性。     

智能空间中的服务机器人路径规划

为了加深服务机器人对环境的理解,实现安全高效的智能空间导航,建立了一种信息更为丰富的环境模型——危险度地图;并针对智能空间环境部分未知的特点,设计了分层的路径规划方法.静态规划层根据已知环境信息,采用改进的粒子群优化算法规划初始最优路径,动态规划层利用基于动态危险度地图的改进A＊算法进行避障.该方法克服了常规算法只追求路径最短的缺点,增加了对路径危险度的评价,规划出的路径既安全又较短;且该方法实现简单,实时性好.仿真结果验证了该方案的可行性.     

面向未知环境探索的分层架构路径规划算法

为实现无人平台在未知环境下的高效路径探索,该文提出了一种以“感知-规划-控制”分层架构为基础的路径规划算法。在感知层通过 Cartographer 建图算法实时构建未知环境的二维栅格地图。在规划层,通过 Canny 边缘检测、基于密度的聚类算法、效能函数评估选择最佳探索目标点,并在规划的效能函数中引入探索方向延续性概念,克服了传统路径规划反复探索已知环境的难题。在控制层,通过概率路线图算法规划从当前位姿到目标点的最短路径,并通过纯跟踪算法和向量直方图算法实现了路径无碰撞跟踪。3 种典型环境下的仿真实验表明,所提出的算法在不同环境下均具有较高的探索效率和完成度。     

基于栅格法的虚拟人快速路径规划

在栅格中使用经典的Dijkstra算法进行路径规划有计算量大,规划时间长、进行扩展判断的节点个数多等缺点.栅格的组织结构决定了栅格中最短路径的特性--组成最短路径的各线段间的最小夹角为90°.根据栅格及最短路径的特性,提出了一种在栅格中使用Dijkstra算法规划路径时减少扩展节点的个数,进而缩短规划时间、降低计算代价的算法,并将其用于虚拟人的路径规划.实验验证了算法的可行性和有效性.     

An Artificial Neural Network Approach for Inverse Kinematics Computation and Singularities Prevention of Redundant Manipulators

In this article an Artificial Neural Network (ANN) approach for fast inverse kinematics computation and effective singularities prevention of redundant robot manipulators is presented. The approach is based on establishing some characterizing matrices, representing some geometrical concepts, in order to yield a simple performance index and a null space vector for singularities avoidance/prevention and safe path generation. Here, this null space vector is computed using a properly trained ANN and included in the computation of the inverse kinematics being performed also by another properly trained ANN.     

基于神经网络和遗传算法的足球机器人路径规划

针对足球机器人在动态环境下的安全路径规划,提出一种将神经网络和遗传算法相结合的路径规划方法.用hopfield神经网络描述存在障碍物的动态环境,然后用遗传算法对代表路径的控制点进行寻优,并把路径安全性和最短路径要求融合为一个适应度函数.通过仿真实验表明该方法具有较高的实时性和有效性.     

A Voronoi-diagram-based dynamic path-planning system for underactuated marine vessels

The main contribution of this paper is the development of a rapid, dynamic path-planning system for 3-DOF marine surface vessels navigating in environments where other marine vehicles might be operating too. The method is based on the Voronoi diagram and generates the initial path while ensuring that clearance constraints are satisfied with respect to both land and shallow waters. Fermat's Spiral (FS) segments are used to connect successive straight lines, hence, resulting in curvature-continuous paths that are rapidly computed. When a ship is detected, the range of its position during a given time frame is estimated, and the path-planning system produces in real time a new safe and smooth path. The International Regulations for Preventing Collisions at Sea (COLREG) are taken into account in the replanning procedure. An indirect adaptive Line-Of-Sight (LOS) guidance algorithm from the existing literature is implemented to ensure the underactuated vessel will counteract the effects of unknown environmental forces, such as ocean currents, while converging to the safe path. Simulations show the effectiveness of the proposed approach.     

基于神经网络租遗传算法的足球机器人路径规划

针对足球机器人在动态环境下的安全路径规划,提出一种将神经网络和遗传算法相结合的路径规划方法。用hopfield神经网络描述存在障碍物的动态环境,然后用遗传算法对代表路径的控制点进行寻优,并把路径安全性和最短路径要求融合为一个适应度函数。通过仿真实验表明该方法具有较高的实时性和有效性。     

Inverse kinematics and geometrically bounded singularities prevention of redundant manipulators: An Artificial Neural Network approach

This article presents an Artificial Neural Network (ANN) approach for fast inverse kinematics computation and effective geometrically bounded singularities prevention of redundant manipulators. Here, some bounded geometrical concepts are properly utilized to establish some characterizing matrices, to yield a simple performance index, and a null space vector for singularities avoidance/prevention and safe path generation. Then, a properly trained ANN is used in a novel scheme for the computation of inverse kinematics. This scheme includes the proposed null space vector being also computed by another properly trained ANN. The efficiency of the proposed ANN approach is demonstrated in the successful singularities prevention of a planar redundant manipulator performing a benchmark test.     

Grafting: A Path Replanning Technique for Rapidly-Exploring Random Trees in Dynamic Environments

The rapidly-exploring random trees (RRT) is a sampling-based path planner which utilizes simultaneously kinematics and dynamics of a robot. However, since the RRT has produced a robot path without taking the existence of dynamic obstacles into consideration, RRT-based navigation has the risk of a collision with dynamic obstacles. We proposed a path replanning technique for the RRT applied to robot navigation in dynamic environments, which is named grafting. The proposed technique replans a safe and efficient path in real time instead of the original path which may cause a collision with dynamic obstacles. Moreover, the replanned path can be easily merged into the original RRT path because the grafting technique preserves the property of the RRT. The grafting technique was tested by simulations in various dynamic environments, which revealed that the grafting technique was capable of replanning a safe and efficient path for RRT-based navigation in real time.     

A Vision and GPS-Based Real-Time Trajectory Planning for a MAV in Unknown and Low-Sunlight Environments

In this paper we address the problem of real-time optimal trajectory generation of a micro Air Vehicle (MAV) in unknown and low-sunlight environments. The MAV is required to navigate from an initial and outdoor position to a final position inside of a building. In order to achieve this goal, the MAV must estimate a window of the building. For this purpose, we develop a safe path planning method using the information provided by the GPS and a consumer depth camera. With the aim of developing a safe path planning with obstacle avoidance capabilities, a model predictive control approach is developed, which uses the environment information acquired by the navigation system. The results are tested on simulations and some preliminary experimental results are given. Our system’s ability to identify and estimate a window model and the relative position w.r.t. the window is demonstrated through video sequences collected from the experimental platform.