Monocular Visual Mapping for Obstacle Avoidance on UAVs

An unmanned aerial vehicle requires adequate knowledge of its surroundings in order to operate in close proximity to obstacles. UAVs also have strict payload and power constraints which limit the number and variety of sensors available to gather this information. It is desirable, therefore, to enable a UAV to gather information about potential obstacles or interesting landmarks using common and lightweight sensor systems. This paper presents a method of fast terrain mapping with a monocular camera. Features are extracted from camera images and used to update a sequential extended Kalman filter. The features locations are parameterized in inverse depth to enable fast depth convergence. Converged features are added to a persistent terrain map which can be used for obstacle avoidance and additional vehicle guidance. Simulation results, results from recorded flight test data, and flight test results are presented to validate the algorithm.     

New Visual Invariants for Terrain Navigation Without 3D Reconstruction

For autonomous vehicles to achieve terrain navigation, obstacles must be discriminated from terrain before any path planning and obstacle avoidance activity is undertaken. In this paper, a novel approach to obstacle detection has been developed. The method finds obstacles in the 2D image space, as opposed to 3D reconstructed space, using optical flow. Our method assumes that both nonobstacle terrain regions, as well as regions with obstacles, will be visible in the imagery. Therefore, our goal is to discriminate between terrain regions with obstacles and terrain regions without obstacles. Our method uses new visual linear invariants based on optical flow. Employing the linear invariance property, obstacles can be directly detected by using reference flow lines obtained from measured optical flow. The main features of this approach are: (1) 2D visual information (i.e., optical flow) is directly used to detect obstacles; no range, 3D motion, or 3D scene geometry is recovered; (2) knowledge about the camera-to-ground coordinate transformation is not required; (3) knowledge about vehicle (or camera) motion is not required; (4) the method is valid for the vehicle (or camera) undergoing general six-degree-of-freedom motion; (5) the error sources involved are reduced to a minimum, because the only information required is one component of optical flow. Numerous experiments using both synthetic and real image data are presented. Our methods are demonstrated in both ground and air vehicle scenarios.     

LiDAR Based Negative Obstacle Detection for Field Autonomous Land Vehicles

Negative obstacles for field autonomous land vehicles (ALVs) refer to ditches, pits, or terrain with a negative slope, which will bring risks to vehicles in travel. This paper presents a feature fusion based algorithm (FFA) for negative obstacle detection with LiDAR sensors. The main contributions of this paper are fourfold: (1) A novel three‐dimensional (3‐D) LiDAR setup is presented. With this setup, the blind area around the vehicle is greatly reduced, and the density of LiDAR data is greatly improved, which are critical for ALVs. (2) On the basis of the proposed setup, a mathematical model of the point distribution of a single scan line is deduced, which is used to generate ideal scan lines. (3) With the mathematical model, an adaptive matching filter based algorithm (AMFA) is presented to implement negative obstacle detection. Features of simulated obstacles in each scan line are employed to detect the real negative obstacles. They are supposed to match with features of the potential real obstacles. (4) Grounded on AMFA algorithm, a feature fusion based algorithm is proposed. FFA algorithm fuses all the features generated by different LiDARs or captured at different frames. Bayesian rule is adopted to estimate the weight of each feature. Experimental results show that the performance of the proposed algorithm is robust and stable. Compared with the state‐of‐the‐art techniques, the detection range is improved by 20%, and the computing time is reduced by an order of two magnitudes. The proposed algorithm had been successfully applied on two ALVs, which won the champion and the runner‐up in the “Overcome Danger 2014” ground unmanned vehicle challenge of China .     

自然地形环境下移动机器人的一种路径规划方法

本文给出了一种规划移动机器人在自然地形中运动的新方法，该方法利用ＮＵＲＢＳ曲面模拟自然地形地貌，以ＴｒｉｍｍｅｄＮＵＲＢＳ曲面描述带有障碍物或不可逾越区域的地形，在综合考虑机器人动力学、地形及障碍描述和曲面特性等各方面因素的情形下，运用测地线的概念和计算方法以及Ａ＊搜索算法，获得了在自然地形环境下任意两点间的距离最短路径和时间最优路径，所有的路径均由ＮＵＲＢＳ曲线表示，实验结果表明，该方法在性能与效率上均十分令人满意．     

用于室外移动机器人实时自主导航的2.5维角度势场法

本文提出了一种针对装备有激光测距仪的地面移动机器人系统的实时自主导航算法.与现有的专为解决2维导航问题所设计的算法不同,新算法在导航过程中引入了障碍物的高度信息,并且使用2.5维角度势场法来满足在复杂的户外地形条件下的自主导航要求.首先,一幅激光测距仪扫描地图被划分为两种不同的功能扇区:导航扇区和监测扇区.然后,在充分利用障碍物高度信息的条件下,对导航扇区和监测扇区进行重构,从而获得一幅虚拟的2维激光扫描地图.最后,传统的角度势场法被进行了适当的改进,以便能够顺利的作用到虚拟的2维激光扫描地图上,产生恰当的导航指令.新算法在履带型地面移动机器人上进行了测试,实验结果充分的证明了其有效性和可实现性.     

基于选择交叉烟花算法的无人车路径规划

在三维地形环境下,基本烟花算法进行路径规划时易陷入局部最优解且存在收敛速度慢的问题,为此,提出选择交叉烟花算法。利用栅格法构建三维地形环境并设置威胁区域,使无人车选择合适的节点进行路径探索,结合燃耗代价、平滑代价和威胁代价构建适应度函数,以约束路径节点的生成位置,确保规划出的路径平滑且远离威胁区域。通过基本烟花算法的爆炸、变异、映射和选择操作进行路径搜索,同时加入针对路径节点的轮盘选择操作,使偏离原始路径较远的节点具有更高的爆炸概率,以约束路径的搜索方向,从而加快算法的搜索速度。在此基础上,引入选择交叉火花,通过对轮盘选择后节点间的路径片段进行交叉,以增强种群中烟花之间信息的交互性,提高搜索全局最优解的性能。仿真结果表明,相比基本烟花算法,该算法在简单和复杂地形环境下的适应度值平均提高6%,且运行时间平均缩短13.5%。在各类地形环境下,无人车通过该算法能有效规避威胁区域,并在较短时间内寻找到更加平滑且燃耗更低的路径。     

Near Optimal Robust Path Planning for Mobile Robots: the Viscous Fluid Method with Friction

A new approach is proposed to robot path planning that consists of using the viscous fluid equations including external forces. Unlike the majority of potential field techniques, the method is able to cope not only with 2-dimensional binary environments made of obstacles and free space, but also with so-called weighted regions, as well as uneven natural terrain where slope and ground characteristics influence the robot performance. It shows how the viscosity coefficient can be used to control the corridors of navigation, and how the external forces acting on the fluid particles can model the forces due to gravity and to friction between the ground and the vehicle. The planner automatically constructs several routes of equivalent costs, that makes the solutions more robust than those obtained by the search of optimal paths, by allowing reactivity in case of an unexpected local disturbance. Comparisons with the scent diffusion method for a binary universe and with a genetic algorithm for a real natural terrain are presented.     

Wheeled vehicles’ velocity updating by navigating on outdoor terrains

This paper addresses the velocity control of wheeled vehicles regarding the terrain features, beyond detection and avoidance of the obstacles as most current works do. Terrain appearance average is used to enable the wheeled vehicle to adapt velocity such that, as speedy as possible, it safely navigates. The vehicle velocity adaptation imitates the human beings’ driving behavior regarding the terrain features: humans use a quick and imprecise estimation of the terrain features but enough to drive–navigate without sliding or falling. A fuzzy neural network sets the vehicle velocity according to average estimations of terrain roughness. The terrain textures are modeled by the principal components that are enough to use pattern recognition for navigation purpose. One set of tests is executed using a small, wheeled robot, which adjusts velocity while navigating on surfaces such as ground, ground with grass, and stones paving. The other tests are done using images of roads of ground, concrete, asphalt, and loose stones, which are video filmed from a real car driven at less than 60 km/h of velocity; by applying the present approach, the required time/distance ratio to smoothly velocity change is granted.     

Obstacle recognition in front of vehicle based on geometry information and corrected laser intensity

Accurate identification and classification of obstacles in front of vehicle is an important part of intelligent vehicle safety driving. To solve the difficulties in distinguishing geometry similar obstacles and blocked obstacles, a real-time algorithm to accurately identify vehicles and pedestrians in a single frame was presented using laser intensity correction model and obstacle characteristic information. To complete the identification of obstacles, there are two classifications; the first classification according to the diagonal lengths of obstacles’ minimum enclosing rectangle, and then the second classification according to the mean and variance of intensity. As for different overlap criterion, result shows that the classification performance of our methods is better than other methods available.     

基于量子粒子群优化的在线航迹规划

现代战场中,环境信息是变化的,飞行器很难预先获得精确的全局环境信息,因此要求无人飞行器具有实时的航迹规划能力,采用量子粒子群优化算法,将约束条件和搜索算法相结合,有效解决了简单粒子群算法在高维空间中易陷入局部最优点的问题;同时,根据地形障碍、敌方防御雷达、防空火力等威胁以及禁飞区的分布情况,引入最小威胁面的概念,利用B-Spline插值逼近最小威胁面中的三维航迹在二维水平面内的投影,从而将三维曲线的规划问题简化为二维平面中控制点的寻优问题,简化了问题复杂度,提高了计算效率.仿真结果表明该方法可以满足在线航迹规划的要求.     

虚拟视景中的装甲车辆运动仿真算法研究

通过分析履带式装甲车的行动装置与运动特点,研究了装甲车在任意地形上的运动情况,以满足分布交互式虚拟仿真实时性和逼真度要求对实体行为进行了建模与简化,选取适合于履带式车辆的支撑点来研究车辆的姿态问题,提出了在任意地形中的运动仿真算法来确定运动后的位置和姿态.在基于VTP平台开发的装甲对抗仿真系统中,该算法实现了装甲车的运动仿真,并能很好的满足系统实时性和高逼真度的需求.     

新型树启发式搜索算法的机器人路径规划

面对三维空间移动机器人从起始点到终止点的最短路径问题,提出一种新型的边缘点树启发式搜索(TreeEP)算法,该方法将地图空间进行密度可调的三维离散化处理,根据障碍安全距离筛选出障碍物的可靠边缘点信息,再利用树扩散架构选出最能引导搜索方向的潜力点进行扩散搜索,最终得出最短路径。提出局部调整策略,得到改进的Tree-EP算法。实验结果表明,在带障碍复杂地形最短路径搜索应用中,提出的Tree-EP算法与已有方法相比,能找到更短的移动路径。     

Visual navigation of an autonomous vehicle using white linerecognition

A method is presented for the autonomous visual navigation of a vehicle by using a white guide for path recognition. The vehicle moves over a white guide line on the flat ground or floor, which is contrasted with its background. The vehicle uses a forward-looking TV camera for sensing. The white-line recognition algorithm presented uses a state transition algorithm. A field pattern monitoring method is also presented for vehicle guidance using a state transition scheme. When the vehicle comes to branches, it selects a suitable direction according to a path planner output. The vehicle can also avoid collisions with obstacles in front of it by monitoring the field patterns and their changes. An experimental moving vehicle system was constructed. Tests conforming the effectiveness of these approaches are described     

基于SLIC区域分割的三维地形重建算法

为利用无人机在高空连续拍摄的两幅航拍图像准确实现三维地形重建,提出了通过将图像进行区域分割来达到不同地形区域分别生成数字高程模型DEM数据的方法。首先利用简单线性迭代聚类SLIC超像素算法将图像分割为多个包含单一地形的超像素区域,再利用各区域的颜色信息进行相邻同类地形区域的融合,最后在所得的各区域内通过SIFT特征点提取与匹配、计算三维坐标来生成DEM数据。通过将重建地形结果与卫星地图对比表明,利用该方法能够有效实现地形重建;通过对比本文算法与传统地形重建算法的重建结果表明,利用该方法能准确呈现各地形间的边界信息。     

基于三维相机的未知环境地形通行性识别方法

三维相机用于移动机器人环境感知,可以实时、可靠、较高精度地获取未知环境三维信息,提出了灰度信息和三维信息相结合提取突起障碍物的方法,通过提取障碍物的特征,识别未知地形的可通行区域.实验表明:该方法即使在障碍物与周围环境灰度值几乎一致的情况下,也有较好的识别效果.     

基于稀疏A*搜索和改进人工势场的无人机动态航迹规划

针对不同属性的障碍物所构成的威胁分布模型, 本文提出了一种基于稀疏A*搜索算法预规划和改进人工势场相结合的无人机动态避障算法. 该算法首先对威胁分布建立栅格化模型; 然后根据静态威胁, 基于稀疏A*搜索算法进行全局航迹规划; 最后结合预规划路径和动态威胁分布, 利用改进人工势场法完成无人机的动态避障. 仿真结果表明, 该方法能够规划出给定威胁指标下的全局最优路径并达到良好的动态规避性能.     

一种基于A*算法的虚拟力场避障导航算法

针对传统A＊算法在实际应用中需要所有的节点信息,算法忽略车身实际宽度的问题,提出了基于A＊算法同时结合使用虚拟力场法的避障导航算法。该改进算法解决了 A＊算法在实际应用中存在的问题,也避免了单独使用虚拟力场法存在的容易陷入局部极小点、在目标点附近有障碍物时无法到达以及摆动剧烈的问题。仿真实验验证了新算法的有效性,实验结果表明该算法拓宽了原有算法的使用范围并且提高了无人车实时路径导航的能力。     

A New Navigation Method for an Automatic Guided Vehicle

This paper presents a new navigation method for an automatic guided vehicle (AGV). This method utilizes a new navigation and control scheme based on searching points on an arc. Safety measure indices are defined and are generated from the output of a fuzzy neural network which define the actions the AGV is to take when in the presence of obstacles. The proposed algorithm integrates several functions required for automatic guided vehicle navigation and tracking control and it exhibits satisfactory performance when maneuvering in complex environments. The automatic guided vehicle with this navigation control system not only can quickly process environmental information, but also can efficiently avoid dynamic or static obstacles, and reach targets safely and reliably. Extensive simulation and experimental results demonstrate the effectiveness and correct behavior of this scheme. © 2004 Wiley Periodicals, Inc.     

Seeking a path through the crowd: Robot navigation in unknown dynamic environments with moving obstacles based on an integrated environment representation

We present a novel algorithm for collision free navigation of a non-holonomic robot in unknown complex dynamic environments with moving obstacles. Our approach is based on an integrated representation of the information about the environment which does not require to separate obstacles and approximate their shapes by discs or polygons and is very easy to obtain in practice. Moreover, the proposed algorithm does not require any information on the obstacles’ velocities. Under our navigation algorithm, the robot efficiently seeks a short path through the crowd of moving or steady obstacles. A mathematically rigorous analysis of the proposed approach is provided. The performance of the algorithm is demonstrated via experiments with a real robot and extensive computer simulations.     

Real-time 2D height mapping method for an unmanned vehicle using a stereo camera and laser sensor fusion

This paper proposes a method for mapping the height information on an area around a vehicle and of identifying a drivable area by fusing a stereo camera and a laser sensor. A SOM (Self Organizing Map) clustering algorithm obtained from the depth information of the stereo camera is used to analyze the front part area of a vehicle in forms of several candidate planes. In addition, an IMU indicating the current pose of a vehicle is applied to detect a drivable plane. A laser sensor installed on a vehicle??s roof scans the front part with a single line and informs a distance value. A drivable plane detected is utilized to calculate height value in the normal direction detected by the laser scan data. Additionally, when the height already mapped has a value higher than that of the threshold, it is regarded as an obstacle and the vehicle is prevented from coming into contact with it. Regarding the vehicle position estimation, a Kalman filter method is used for real-time mapping during driving. The moving location of the vehicle is dead reckoned based on steering angle and velocity, and this value is compensated using the position value received from the GPS. The vehicle??s position and mapping coordinates are converted into latitude and longitude values. This study demonstrates that it is possible to generate a precise 2D height map by conducting a test in a real road environment with various slope angles and obstacles.