一种基于改进RRT*的全局路径规划算法

针对传统RRT*全局路径规划算法在多障碍物复杂环境中搜索效率低、占用内存过大、搜索路径不平滑等问题,提出一种基于简化地图的区域采样RRT*算法(simplified map-based regional sampling RRT*,SMRS-RRT*).首先简化处理全局栅格地图,在此基础上寻找从起点到目标点的最优路径点...     

基于改进RRT*FN算法的机器人路径规划

针对固定节点数的渐近最优快速扩展随机数算法(RRT*FN)精度低、收敛到最优值速度慢等问题,提出一种改进的RRT*FN路径规划算法,并用于解决二维静态环境下的移动机器人全局路径规划问题.首先,改进算法使用与RRT*FN算法相同的均匀采样方法进行路径搜索,当搜索到一条初始路径时,在之后的路径规划中使用启发式采样方法.在之...     

动态环境下基于人工势场引导的RRT路径规划算法

现有的大多数动态RRT路径规划算法不能使规划的路径远离障碍物,这有可能导致机器人没有足够的避障时间。针对此问题,提出了一种利用人工势场引导快速扩展随机树向目标区域生长并远离障碍物的改进RRT算法APFG-RRT(artificial potential field guided RRT)。为了进一步加快算法的收敛速度、加速算法跳出局部极小值,引入了一种按自适应概率选择目标点作为采样点的策略;针对动态环境采用全局规划结合局部重新规划的方法以提高算法的实时性。仿真实验表明,相比于初始RRT和Goal-bias RRT,APFG-RRT的计算效率更高,内存需求更小,并且搜索到的路径能够有效地远离障碍物,提高了动态路径规划的成功率。     

针对包含狭窄通道复杂环境的高效RRT*△路径规划算法

针对RRT*算法在狭窄通道等复杂环境产生大量节点和收敛速度慢的问题,提出一种基于多种启发式策略和强化节点机制改进的高效RRT*路径规划算法(heuristic node enhancement informed RRT*,HNEI-RRT*).该算法首先采取组合启发式采样策略,快速找到初始路径之后在启发式子集内完成采样;同时提出启发式节点拒绝策略,拒绝不满足预设条件的节点参与后续扩展;其次,该算法提出强化节点机制,扩大节点蕴涵的信息,提高节点利用率.在各种障碍物分布和狭窄通道的复杂环境中的仿真结果表明,HNEI-RRT*算法的节点数量、收敛时间相比其他五类RRT*改进算法更少,验证了该算法能够节省内存花销的同时有效提高收敛速度.     

基于改进双树RRT*算法的冗余机械臂末端路径规划

针对冗余机械臂的冗余特性与相关RRT*算法在规划机械臂末端路径的应用中存在的搜索效率较低、收敛性不稳定以及没有充分考虑到机械臂末端几何构型与自身运动特性对路径规划影响的问题,提出一种改进策略。首先,引入一种基于根尾节点连线夹角的采样点选择方式,并设置目标逼近区域。根据连续采样成功次数动态选择改进采样与随机采样。接着,将双树扩展策略与上述方法相结合。最后,将初始可行路径进行二次重连得到最终的优化路径。通过验证,改进双树RRT*方法能够有效地提升搜索效率、收敛性以及路径的优越性。虚拟碰撞体与胶囊碰撞体的引入也能较好地应对机械臂末端结构与运动特性带来的影响。使用Mujoco物理仿真引擎进行机械臂运动验证,证明该策略可以为冗余机械臂末端规划出一条较优的可行路径。     

基于改进RRT算法的机械臂路径规划

针对快速探索随机树(RRT)路径规划算法缺乏导向性和规划空间增大时算法时间复杂度高的问题,提出一种目标概率偏置与步长控制的改进RRT算法(I-RRT)。I-RRT结合目标概率偏置,以一定概率使采样点偏置为目标点,提高路径规划的导向性,并引入步长控制优化算法,提高运算效率,优化路径。在MATLAB平台建立了算法的仿真实验,结果表明:I-RRT的导向性与算法时间复杂度均优于经典的RRT算法;并在ROS平台上搭建了六自由度机械臂的避障规划与控制实验,实验验证了该算法的有效性。     

Collision-free path planning of cable-driven parallel robots in cluttered environments

Intelligent Service Robotics - Path planning of cable-driven parallel robots (CDPRs) is a challenging task due to cables which may cause various collisions. In this paper, three steps are suggested...     

Natural path planning using wavelet noise in static environment

In a constrained virtual environment, motion of a character has to be controlled with precision to avoid collisions. For modeling motion of a character representing some real‐life object, it is important to generate paths that look natural. A number of path planning algorithms have been introduced to solve real‐time path queries in an environment. However, in all such algorithms, a fixed path is returned always for the same start and goal positions in the environment. Recently, Perlin noise has been used to add variations to a path so that it appears more natural. However, because of pure random nature of Perlin noise function, often unnatural path occurs. In this paper, we present a new approach to natural path planning by adding wavelet noise to a path generated using subdivision‐based Corridor Map Method. Because wavelet noise is almost perfectly band limited and provides good details with minimal aliasing effects, the resulting path becomes smoother and more natural. Moreover, by appropriately choosing the levels of down/up sampling in the wavelet noise generation algorithm, frequency of wavelet noise can be adjusted. This serves as an effective tool in bringing variations in path as per the requirement. Copyright © 2012 John Wiley & Sons, Ltd.     

改进RRT算法陷阱空间下的无人机航迹规划

针对大部分航迹规划算法在陷阱空间下,存在规划时间长、成功率低的问题,提出了一种改进RRT算法。通过将人与RRT算法相结合,由人设置虚拟目标点,引导航迹搜索走出陷阱空间;同时对节点扩展进行优化,保证航迹搜索在可行域内;并设置快速收敛策略,删除冗余节点,使航迹搜索速度加快。最后,通过仿真验证表明,该方法在陷阱空间规划中具有良好的效果,可快速规划可行航迹。     

A real-time path planning algorithm for cable-driven parallel robots in dynamic environment based on artificial potential guided RRT

Microsystem Technologies - This paper deals with the collision-free path planning of cable-driven parallel robots (CDPRs) in a dynamic three-dimensional environment. The proposed algorithm is based...     

基于对比优化的RRT路径规划改进算法

针对动态环境下机器人RRT路径规划算法缺乏稳定性和偏离最优解的问题,提出一种基于对比优化的RRT路径规划改进算法。算法在新一周期的环境下,通过对上一周期路径树进行剪枝和重新规划得到一条稳定的路径,同时利用基本RRT算法规划出一条新路径,通过对比两条路径得到较优解。仿真和真实机器人实验结果均表明,改进的算法提高了动态复杂环境下RRT路径规划的稳定性,并保证了规划的路径逼近最优解。     

基于子目标搜索的机器人目标导向RRT路径规划算法

为解决移动机器人未知环境下的路径规划问题,提出基于子目标搜索的机器人目标导向RRT (rapidly-exploring random trees)路径规划算法.一方面,针对传统RRT算法固有的盲目搜索问题,引入目标导向函数,形成目标导向RRT路径规划算法,这一改进可减少冗余搜索,提高路径规划效率;另一方面,为了使机器人在首次探索未知环境时也能顺利抵达目标点,提出3种不同情况下的子目标搜索策略,包括无障碍环境下的直达策略、扫到边界点时的最短距离策略和扫不到边界点时的后退策略,这3种策略使机器人能够完成对未知环境的探索,而且可以克服易出现的局部极小点问题,使机器人具有逃离局部极小环境的能力.仿真实验结果验证了所提出算法的可行性和有效性.     

赛场环境实时变化的帆船比赛最优路径规划

最优行驶路径规划是帆船比赛取胜的关键环节。文章提出了赛场环境参数实时变化时,基于模糊综合评价的帆船直航比赛最优路径规划方法。该方法利用模糊综合评价思想,综合考虑行驶速度和接近目标两个因素建立综合评价函数进行航行方向决策,赛场环境参数变化时,从当前航行位置相对目标点重新进行路径规划,保证局部状态始终最优,利用宽度优先搜索算法实现全局最优路径搜索。仿真结果证明,该路径规划方法能够取得较好的规划结果,对指导帆船运动员进行科学训练有很好的理论意义和应用价值。     

基于采样点优化RRT算法的机械臂路径规划

针对基于随机采样的RRT机械臂路径规划算法在全局工作空间下采样效率低、随机性强等问题,提出一种基于采样点优化RRT算法的机械臂路径规划算法.相对于全局工作空间采样,优化算法首先基于非障碍物空间生成随机采样点,以降低算法碰撞检测概率与冗余节点的生成,再结合一定概率的人工势场法产生启发式采样点,使得机械臂臂体于路径规划采样过程中既能保证随机采样的概率完备,又能使采样点更具目标导向性.其次,为使得路径更加简洁平滑,使用冗余节点删除策略剔除路径中的冗余节点来优化最终路径.最后在二维、三维的仿真环境中对优化算法进行对比实验分析,以验证算法在随机采样路径规划算法中的良好性能,并在IRB 1200-7/0.7机械臂上进行避障规划算法实验.仿真和实验结果都表明,所提出的算法在机械臂路径规划中可以获得更高的规划效率和更优的路径.     

A robust online path planning approach in cluttered environments for micro rotorcraft drones

We present in this paper a robust online path planning method, which allows a micro rotorcraft drone to fly safely in GPS-denied and obstacle-strewn environments with limited onboard computational power. The approach is based on an efficiently managed grid map and a closed-form solution to the two point boundary value problem (TPBVP). The grid map assists trajectory evaluation whereas the solution to the TPBVP generates smooth trajectories. Finally, a top-level trajectory switching algorithm is utilized to minimize the computational cost. Advantages of the proposed approach include its conservation of computational resource, robustness of trajectory generation and agility of reaction to unknown environment. The result has been realized on actual drones platforms and successfully demonstrated in real flight tests. The video of flight tests can be found at: http://uav.ece.nus.edu.sg/robust-online-path-planning-Lai2015.html.     

A Gaussian process-based RRT planner for the exploration of an unknown and cluttered environment with a UAV

A new framework which adopts a rapidly-exploring random tree (RRT) path planner with a Gaussian process (GP) occupancy map is developed for the navigation and exploration of an unknown but cluttered environment. The GP map outputs the probability of occupancy given any selected query point in the continuous space and thus makes it possible to explore the full space when used in conjunction with a continuous path planner. Furthermore, the GP map-generated path is embedded with the probability of collision along the path which lends itself to obstacle avoidance. Finally, the GP map-building algorithm is extended to include an exploration mission considering the differential constraints of a rotary unmanned aerial vehicle and the limitation arising from the environment. Using mutual information as an information-theoretic measure, an informative path which reduces the uncertainty of the environment is generated. Simulation results show that GP map combined with RRT planner can achieve the 3D navigation and exploration task successfully in unknown and complex environments.     

Lifting path planning of mobile cranes based on an improved RRT algorithm

Lifting operations of mobile cranes are one of the commonly-seen and most important activities for prefabrication housing production (PHP) on sites. However, relevant operations are normally based on the experience of operators or project managers, this often leads to low efficiency as well as high accident rate due to dynamic and complex construction sites. Thus, it is important and necessary to develop an appropriate approach to the lifting planning of mobile cranes so as to guide on-site operations. This paper proposes an improved Rapidly-exploring Random Tree (RRT) algorithm for lifting path planning of mobile cranes. Considering the critical role of Nearest Neighbor Search (NNS) in the implementation of RRT algorithm, a novel strategy for searching the nearest neighbor is developed, i.e., Generalized Distance Method and Cell Method. Both methods are tested in simulation-based experiments. The results show that 1) the Generalized distance method not only reduces the search time, but also unifies the unit of distance measurement and clarifies the physical meaning of distance; 2) the Cell method dramatically reduces the traversal range as well as the search time; and 3) both methods improve the quality of lifting path planning of mobile cranes. This improved RRT algorithm enables rapid path planning of mobile cranes in a dynamic and complex construction environment. The outcomes of this research not only contribute to the body of knowledge in spatial path planning of crane lifting operations, but also have the potential of significantly improving efficiency and safety in crane lifting practices.     

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。     

越野环境建模与动态路径规划

针对越野环境下移动机器人的导航与控制问题，提出了一种越野环境下环境建模与动态路径规划方法。该方法能够针对地形的数字高程模型，在综合考虑机器人的性能约束和地形特征等因素的基础上有效地实现越野环境的建模；在此基础上的路径规划采用全局信息与局部信息、前期规划结果与当前规划相结合的方法，满足了越野环境下动态路径规划的要求。实验结果表明，该方法能够很好地适应各种复杂的越野环境。