An Adaptive Obstacle Avoidance Algorithm for Unmanned Surface Vehicle in Complicated Marine Environments

Unmanned surface vehicles (USVs) are important autonomous marine robots that have been studied and gradually applied into practice. However, the autonomous navigation of USVs, especially the issue of obstacle avoidance in complicated marine environment, is still a fundamental problem. After studying the characteristics of the complicated marine environment, we propose a novel adaptive obstacle avoidance algorithm for USVs, based on the Sarsa on-policy reinforcement learning algorithm. The proposed algorithm is composed of local avoidance module and adaptive learning module, which are organized by the "divide and conquer" strategy-based architecture. The course angle compensation strategy is proposed to offset the disturbances from sea wind and currents. In the design of payoff value function of the learning strategy, the course deviation angle and its tendency are introduced into action rewards and penalty policies. The validity of the proposed algorithm is verified by comparative experiments of simulations and sea trials in three sea-state marine environments. The results show that the algorithm can enhance the autonomous navigation capacity of USVs in complicated marine environments.      

基于双旋Lyapunov矢量场的无人机避障算法

提出一种基于双旋Lyapunov矢量场的无人机避障算法.首先,建立无人机和障碍物的模型,并根据无人机有限时间是否会侵犯障碍物安全圆设计避障判定规则;然后,基于最小侧向偏移量原则选定避障机动中无人机速度旋转方向为最优避障方向,选定其反方向为矢量场旋转方向,定义成功避障的标准并进行证明;最后,通过建立的障碍物合并规则提升避障效率,使得上述方法适用于未知环境下的无人机在线避障.仿真结果表明,在无人机性能约束下,所提出的算法对动态和静态障碍都能有效避障,算法性能优于Dubins路径和人工势场法.     

Robust underwater obstacle detection and collision avoidance

A robust obstacle detection and avoidance system is essential for long term autonomy of autonomous underwater vehicles (AUVs). Forward looking sonars are usually used to detect and localize obstacles. However, high amounts of background noise and clutter present in underwater environments makes it difficult to detect obstacles reliably. Moreover, lack of GPS signals in underwater environments leads to poor localization of the AUV. This translates to uncertainty in the position of the obstacle relative to a global frame of reference. We propose an obstacle detection and avoidance algorithm for AUVs which differs from existing techniques in two aspects. First, we use a local occupancy grid that is attached to the body frame of the AUV, and not to the global frame in order to localize the obstacle accurately with respect to the AUV alone. Second, our technique adopts a probabilistic framework which makes use of probabilities of detection and false alarm to deal with the high amounts of noise and clutter present in the sonar data. This local probabilistic occupancy grid is used to extract potential obstacles which are then sent to the command and control (C2) system of the AUV. The C2 system checks for possible collision and carries out an evasive maneuver accordingly. Experiments are carried out to show the viability of the proposed algorithm.     

A 3D reactive collision avoidance algorithm for underactuated underwater vehicles

Avoiding collisions is an essential goal of the control system of autonomous vehicles. This paper presents a reactive algorithm for avoiding obstacles in a three‐dimensional space, and shows how the algorithm can be applied to an underactuated underwater vehicle. The algorithm is based on maintaining a constant avoidance angle to the obstacle, which ensures that a guaranteed minimum separation distance is achieved. The algorithm can thus be implemented without knowledge of the obstacle shape. The avoidance angle is designed to compensate for obstacle movement, and the flexibility of operating in 3D can be utilized to implement traffic rules or operational constraints. We exemplify this by incorporating safety constraints on the vehicle pitch and by making the vehicle seek to move behind the obstacle, while also minimizing the required control effort. The underactuation of the vehicle induces a sway and heave movement while turning. To avoid uncontrolled gliding into the obstacle, we account for this movement using a Flow frame controller, which controls the direction of the vehicle's velocity rather than just the pitch and yaw. We derive conditions under which it is ensured that the resulting maneuver is safe, and these results are verified trough simulations and through full‐scale experiments on the Hugin HUS autonomous underwater vehicle. The latter demonstrates the performance of the proposed algorithm when applied to a case with unmodeled disturbances and sensor noise, and shows how the modular nature of the collision avoidance algorithm allows it to be applied on top of a commercial control system.     

未知环境下多AUV协同避障方法研究

针对多AUV（autonomous underwater vehicle）系统在未知环境中进行路径规划时难以兼顾避障与编队的问题,提出了一种基于领航—跟随者与行为的多AUV协同避障方法。首先,通过构造碰撞危险度及偏离目标评价函数,设计了AUV局部路径规划方法;在此基础上,结合编队控制方法,分别为领航者和跟随者设计不同的行为以及行为选择模式。半物理仿真实验结果表明,该算法能够实现多AUV系统在未知环境中的协同避障,且队形偏离度与恢复队形时间优于传统多机器人避障算法。实验结果证明了该算法的可行性与有效性。     

飞行器分层势场路径规划算法

传统势场法是飞行器路径规划的一种常用方法,但是存在目标不可达、易收敛到局部极小值和无评价机制等问题.本文针对这些问题提出了一种飞行器路径规划的分层势场算法.利用分段思想对势场函数进行修正,解决了目标不可达问题.引入回环力和飞行器间作用力,解决了易收敛到局部极小值问题和飞行器间的碰撞问题.采用分层方法,建立了多层次多方位路径点阵,并以此计算最优路径点,从而引入了势场法的评价机制.通过数值仿真,对在复杂障碍环境中的飞行器路径规划进行了传统势场法、改进势场法和分层势场法的对比研究.仿真结果验证了所提出的分层势场算法的有效性和可行性.     

基于APF的AGV局部路径规划改进算法研究

针对原有人工势场法（artificial potential field,APF）在局部路径规划时的避障效果不良问题,提出一种APF-PSO的改进算法改善原算法优化路径规划的效果。将速度势场引入位置势场中使AGV（automated guided vehicle）动态避开不同速度的移动障碍物;当算法陷入局部最小值时,采取PSO（particle swarm optimization）算法,并对其惯性权重因子和学习因子做出调整,通过三次样条曲线插值来平滑路径,使得AGV找到最短路径。结果表明APF-PSO改进算法可根据障碍物速度不同动态避障,解决了APF算法运算中避障效果不良问题。     

融合改进A*算法和Morphin算法的移动机器人动态路径规划

在动态未知环境下对机器人进行路径规划,传统A*算法可能出现碰撞或者路径规划失败问题。为了满足移动机器人全局路径规划最优和实时避障的需求,提出一种改进A*算法与Morphin搜索树算法相结合的动态路径规划方法。首先通过改进A*算法减少路径规划过程中关键节点的选取,在规划出一条全局较优路径的同时对路径平滑处理。然后基于移动机器人传感器采集的局部信息,利用Morphin搜索树算法对全局路径进行动态的局部规划,确保更好的全局路径的基础上,实时避开障碍物行驶到目标点。MATLAB仿真实验结果表明,提出的动态路径规划方法在时间和路径上得到提升,在优化全局路径规划的基础上修正局部路径,实现动态避障提高机器人达到目标点的效率。     

一种动态环境下移动机器人的路径规划方法

本文提出了在动态环境中，移动机器人的一种路径规划方法，适用于环境中存 在已知和未知、静止和运动障碍物的复杂情况．采用链接图法建立了机器人工作空间模型， 整个系统由全局路径规划器和局部路径规划器两部分组成．在全局路径规划器中，应用遗传 算法规划出初步全局优化路径．在局部路径规划器中，设计了三种基本行为：跟踪全局路径 的行为、避碰的行为和目标制导的行为，采用基于行为的方法进一步优化路径．其中，避碰 的行为是通过强化学习得到的．仿真和实验结果表明所提方法简便可行，能够满足移动 机器人导航的高实时性要求．     

A vision-based collision avoidance technique for micro air vehicles using local-level frame mapping and path planning

This paper presents a vision-based collision avoidance technique for small and miniature air vehicles (MAVs) using local-level frame mapping and path planning. Using computer vision algorithms, a depth map that represents the range and bearing to obstacles is obtained. Based on the depth map, we estimate the range, azimuth to, and height of obstacles using an extended Kalman filter that takes into account the correlations between obstacles. We then construct maps in the local-level frame using cylindrical coordinates for three dimensional path planning and plan Dubins paths using the rapidly-exploring random tree algorithm. The behavior of our approach is analyzed and the characteristics of the environments where the local path planning technique guarantees collision-free paths and maneuvers the MAV to a specific goal region are described. Numerical results show the proposed technique is successful in solving path planning and multiple obstacle avoidance problems for fixed wing MAVs.     

A novel obstacle avoidance algorithm: “Follow the Gap Method”

In this paper, a novel obstacle avoidance method is designed and applied to an experimental autonomous ground vehicle system. The proposed method brings a new solution to the problem and has several advantages compared to previous methods. This novel algorithm is easy to tune and it takes into consideration the field of view and the nonholonomic constraints of the robot. Moreover the method does not have a local minimum problem and results in safer trajectories because of its inherent properties in the definition of the algorithm. The proposed algorithm is tested in simulations and after the observation of successful results, experimental tests are performed using static and dynamic obstacle scenarios. The experimental test platform is an autonomous ground vehicle with Ackermann steering geometry which brings nonholonomic constraints to the vehicle. Experimental results show that the task of obstacle avoidance can be achieved using the algorithm on the autonomous vehicle platform. The algorithm is very promising for application in mobile and industrial robotics where obstacle avoidance is a feature of the robotic system.     

动态环境下机器人多目标路径规划蚂蚁算法

研究了一种新颖的动态复杂不确定环境下的机器人多目标路径规划蚂蚁算法。该方法首先根据蚂蚁觅食行为对多个目标点的组合进行优化,规划出一条最优的全局导航路径。在此基础上,机器人按照规划好的目标点访问顺序根据多蚂蚁协作局部路径算法完成局部路径的搜索。机器人每前进一步都实时地进行动态障碍物运动轨迹预测以及碰撞预测,并重新进行避碰局部路径规划。仿真结果表明,即使在障碍物非常复杂的地理环境,用该算法也能使机器人沿一条全局优化的路径安全避碰的遍历各个目标点,效果十分令人满意。     

An online collision-free trajectory generation algorithm for human–robot collaboration

The premise of human–robot collaboration is that robots have adaptive trajectory planning strategies in hybrid work cell. The aim of this paper is to propose a new online collision avoidance trajectory planning algorithm for moderate dynamic environments to insure human safety when sharing collaborative tasks. The algorithm contains two parts: trajectory generation and local optimization. Firstly, based on empirical Dirichlet Process Gaussian Mixture Model (DPGMM) distribution learning, a neural network trajectory planner called Collaborative Waypoint Planning network (CWP-net) is proposed to generate all key waypoints required for dynamic obstacle avoidance in joint space according to environmental inputs. These points are used to generate quintic spline smooth motion trajectories with velocity and acceleration constraints. Secondly, we present an improved Stochastic Trajectory Optimization for Motion Planning (STOMP) algorithm which locally optimizes the generated trajectories of CWP-net by constraining the trajectory optimization range and direction through the DPGMM model. Simulations and real experiments from an industrial use case of human–robot collaboration in the field of aircraft assembly testing show that the proposed algorithm can smoothly adjust the nominal path online and effectively avoid collisions during the collaboration.     

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．     

基于模糊避障算法的履带式搬运机器人的设计

以HC-SR04超声波传感器模块获取机器人周围环境信息,以链式叉车作为搬运货物的执行机构,以STM32F103单片机作为机器人控制器,设计了一种自动搬运并且避障的小型履带式搬运机器人。针对局部静态环境下多障碍物对系统避障的复杂性,引入了模糊控制算法,通过对机器人与障碍物之间的距离进行模糊化,建立模糊规则,实现搬运机器人的避障控制。为了提高机器人的稳定性及避障的可靠性,对直流电机建立了数学模型,并利用积分分离PID算法进行仿真,最后实验结果表明该算法提高了直流电机的控制性能。     

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。     

The obstacle avoidance motion planning problem for autonomous vehicles: A low-demanding receding horizon control scheme

The paper addresses the obstacle avoidance motion planning problem for ground vehicles operating in uncertain environments. By resorting to set-theoretic ideas, a receding horizon control algorithm is proposed for robots modelled by linear time-invariant (LTI) systems subject to input and state constraints and disturbance effects. Sequences of inner ellipsoidal approximations of the exact one-step controllable sets are pre-computed for all the possible obstacle scenarios and then on-line exploited to determine the more adequate control action to be applied to the robot in a receding horizon fashion. The resulting framework guarantees Uniformly Ultimate Boundedness and constraints fulfilment regardless of any obstacle scenario occurrence.     

Optimization-Based Safety Analysis of Obstacle Avoidance Systems for Unmanned Aerial Vehicles

The integration of Unmanned Aerial Vehicles (UAVs) in airspace requires new methods to certify collision avoidance systems. This paper presents a safety clearance process for obstacle avoidance systems, where worst case analysis is performed using simulation based optimization in the presence of all possible parameter variations. The clearance criterion for the UAV obstacle avoidance system is defined as the minimum distance from the aircraft to the obstacle during the collision avoidance maneuver. Local and global optimization based verification processes are developed to automatically search the worst combinations of the parameters and the worst-case distance between the UAV and an obstacle under all possible variations and uncertainties. Based on a 6 Degree of Freedom (6DoF) kinematic and dynamic model of a UAV, the path planning and collision avoidance algorithms are developed in 3D space. The artificial potential field method is chosen as a path planning and obstacle avoidance candidate technique for verification study as it is a simple and widely used method. Different optimization algorithms are applied and compared in terms of the reliability and efficiency.     

动态复杂环境下的机器人路径规划蚂蚁预测算法

研究了一种新颖的动态复杂不确定环境下的机器人路径规划方法和动态避障码蚁预测算法.该方法模拟蚂蚁的觅食行为,由多组蚂蚁采用最近邻居搜索策略和趋近导向函数相互协作完成全局最优路径的搜索.在此基础上用虚拟蚂蚁完成与动态障碍物碰撞的预测,并用蚁群算法进行避障局部规划.理论和仿真实验结果均表明,即使在障碍物非常复杂的地理环境,用文中算法也能迅速规划出优化路径,且能安全避碰.     

A new min-max methodology for computing optimised obstacle avoidance steering manoeuvres of ground vehicles

In this paper, a new methodology for computing optimised obstacle avoidance steering manoeuvres for ground vehicles is presented and discussed. Most of the existing methods formulate the obstacle avoidance problem as an optimal control problem which is hard to solve or as a numerical optimisation problem with a large number of unknowns. This method is based on a reformulation of Pontryagin's Maximum Principle and leads to the solution of an adjustable time optimal controller. The control input is significantly simplified and permits its application in a sample and hold sense. Furthermore, with the proposed approach the maximum tyre forces exerted during the manoeuvre are minimised. In this study, it is shown how to ‘warm start’ the proposed algorithm and which constraints to ‘relax’. Numerical examples and benchmark tests illustrate the performance of the proposed controller and compare it with other standard controllers. A sensitivity analysis for different vehicle parameters is performed and finally conclusions are drawn. A significant advantage of the method is the small computational complexity. The overall simplicity of the controller makes it attractive for application on autonomous vehicles.