A review of mobile robot motion planning methods:from classical motion planning workflows to reinforcement learning-based architectures

Motion planning is critical to realize the autonomous operation of mobile robots.As the complexity and randomness of robot application scenarios increase,the planning capability of the classical hierarchical motion planners is challenged.With the development of machine learning,the deep reinforcement learning(DRL)-based motion planner has gradually become a research hotspot due to its several advantageous feature.The DRL-based motion planner is model-free and does not rely on the prior structured map.Most importantly,the DRL-based motion planner achieves the unification of the global planner and the local planner.In this paper,we provide a systematic review of various motion planning methods.Firstly,we summarize the representative and state-of-the-art works for each submodule of the classical motion planning architecture and analyze their performance features.Then,we concentrate on summarizing reinforcement learning(RL)-based motion planning approaches,including motion planners combined with RL improvements,map-free RL-based motion planners,and multi-robot cooperative planning methods.Finally,we analyze the urgent challenges faced by these mainstream RLbased motion planners in detail,review some state-of-the-art works for these issues,and propose suggestions for future research.

Inverted Modelling:An Effective Way to Support Motion Planning of Legged Mobile Robots

This paper presents an effective way to support motion planning of legged mobile robots—Inverted Modelling,based on the equivalent metamorphic mechanism concept.The difference from the previous research is that we herein invert the equivalent parallel mechanism.Assuming the leg mechanisms are hybrid links,the body of robot being considered as fixed platform,and ground as moving platform.The motion performance is transformed and measured in the body frame.Terrain and joint limits are used as input parameters to the model,resulting in the representation which is independent of terrains and particular poses in Inverted Modelling.Hence,it can universally be applied to any kind of legged robots as global motion performance framework.Several performance measurements using Inverted Modelling are presented and used in motion performance evaluation.According to the requirements of actual work like motion continuity and stability,motion planning of legged robot can be achieved using different measurements on different terrains.Two cases studies present the simulations of quadruped and hexapod robots walking on rugged roads.The results verify the correctness and effectiveness of the proposed method.

Genetic algorithm-fuzzy based dynamic motion planning approach for a mobile robot

Presents the mobile robots dynamic motion planning problem with a task to find an obstacle free route that requires minimum travel time from the start point to the destination point in a changing environment, due to the obstacle’s moving. An Genetic Algorithm fuzzy (GA Fuzzy) based optimal approach proposed to find any obstacle free path and the GA used to select the optimal one, points out that using this learned knowledge off line, a mobile robot can navigate to its goal point when it faces new scenario on line. Concludes with the optimal rule base given and the simulation results showing its effectiveness.

MOTION PLANNING OF MULTIPLE MOBILE ROBOTS COOPERATIVELY TRANSPORTING A COMMON OBJECT

Many applications above the capability of a single robot need the cooperation of multiple mobile robots, but effective cooperation is hard to achieve. In this paper, a master slave method is proposed to control the motions of multiple mobile robots that cooperatively transport a common object from a start point to a goal point. A noholonomic kinematic model to constrain the motions of multiple mobile robots is built in order to achieve cooperative motions of them, and a “Dynamic Coordinator” strategy is used to deal with the collision avoidance of the master robot and slave robot individually. Simulation results show the robustness and effectiveness of the method.

Kinematics Modeling and Motion Planning of Tendon Driven Continuum Manipulators

Continuum manipulators have important applications in the human–machine interaction fields.The kinematics,dynamics,and control issues of the continuum manipulators are rather different from a conventional rigid-link manipulator.By the aid of Lie groups theory and exponential coordinate representations,the kinematics of the continuum manipulators with piecewise constant curvatures and actuated by tendons is investigated in this paper.On the basis of differential kinematics analysis,the complete Jacobian of the continuum manipulators is derived analytically,and then a new motion planning approach,named as“dynamic coordination method”is presented for the multisegments continuum manipulators,which is a class of superredundant manipulators.The novel motion planning approach is featured by some appealing properties,and the feasibility of the modeling and the motion planning method is demonstrated by some numerical simulations.

Interval Type-2 Fuzzy Logic Control of Mobile Robots

Navigation of autonomous mobile robots in dynamic and unknown environments needs to take into account different kinds of uncertainties. Type-1 fuzzy logic research has been largely used in the control of mobile robots. However, type-1 fuzzy control presents limitations in handling those uncertainties as it uses precise fuzzy sets. Indeed type-1 fuzzy sets cannot deal with linguistic and numerical uncertainties associated with either the mechanical aspect of robots, or with dynamic changing environment or with knowledge used in the phase of conception of a fuzzy system. Recently many researchers have applied type-2 fuzzy logic to improve performance. As control using type-2 fuzzy sets represents a new generation of fuzzy controllers in mobile robotic issue, it is interesting to present the performances that can offer type-2 fuzzy sets by regards to type-1 fuzzy sets. The paper presented deep and new comparisons between the two sides of fuzzy logic and demonstrated the great interest in controlling mobile robot using type-2 fuzzy logic. We deal with the design of new controllers for mobile robots using type-2 fuzzy logic in the navigation process in unknown and dynamic environments. The dynamicity of the environment is depicted by the presence of other dynamic robots. The performances of the proposed controllers are represented by both simulations and experimental results, and discussed over graphical paths and numerical analysis.

Motion planning and tracking control of a four-wheel independently driven steered mobile robot with multiple maneuvering modes

Safe and effective autonomous navigation in dynamic environments is challenging for four-wheel independently driven steered mobile robots(FWIDSMRs)due to the flexible allocation of multiple maneuver modes.To address this problem,this study proposes a novel multiple mode-based navigation system,which can achieve efficient motion planning and accurate tracking control.To reduce the calculation burden and obtain a comprehensive optimized global path,a kinodynamic interior-exterior cell exploration planning method,which leverages the hybrid space of available modes with an incorporated exploration guiding algorithm,is designed.By utilizing the sampled subgoals and the constructed global path,local planning is then performed to avoid unexpected obstacles and potential collisions.With the desired profile curvature and preselected mode,a fuzzy adaptive receding horizon control is proposed such that the online updating of the predictive horizon is realized to enhance the trajectory-following precision.The tracking controller design is achieved using the quadratic programming(QP)technique,and the primal-dual neural network optimization technique is used to solve the QP problem.Experimental results on a real-time FWIDSMR validate that the proposed method shows superior features over some existing methods in terms of efficiency and accuracy.

Artificial coordinating field and its application to motion planning of robots in uncertain dynamic environments

Artificial coordinating fields (ACF) are proposed to deal with the motion planning problems of mobile robots in uncertain dynamic environments. An ACF around an obstacle can generate two orthogonal force vectors to a robot: one is called the coordinating force vector which is purposively designed in this paper, and the other is the repulsive force vector which is the same as that in a conventional artificial potential field. The ACF is designed according to the updated motion purpose and the relative states of the robot with respect to its local environment, and it also satisfies the robot’s dynamic constraints. The direction of the coordinating force can be determiend on line according to an optimal evaluation function. The ACF can effectively remove the local minima, and reduce the oscillation of the planned trajectory between multiple obstacles. Only local knowledge of the environments is needed in the ACF-based motion planning. The properties of the ACF such as controllability, adaptability, safety and reachability are studied and discussed in detail in this paper. Theoretical analysis and simulations are given to illustrate our main results.

移动机器人避障运动研究

随着人工智能技术的飞速进展,移动机器人在工业、航天及农业等领域的作用逐渐凸显,其自主避障能力直接关系到在不同环境中作业的安全性与效率,而路径规划作为避障的核心技术之一,在决定避障性能方面起着至关重要的作用。对移动机器人路径规划技术进行了综述。基于作业需求将算法分为全局规划和局部避障两类。详述了以采样、图搜索和仿生学为基础的全局规划方法,分析了其收敛速度、内存需求及计算效率,并探讨了其改进策略。对局部避障算法进行了探讨,概述了其原理与特点,并明确其最佳应用场景。对当前的自主避障技术进行了总结,强调了传统算法的智能化程度仍需提升,以及集成不同的算法以提高规划性能将是未来的发展大势。

改进D^(*)算法的未知场景机器人运动规划

随着机器人技术不断发展,自主移动机器人的应用已拓展到复杂未知环境中。针对传统运动规划算法在复杂未知环境中存在搜索盲目、计算效率低、难获得安全轨迹等问题,本文提出了一种基于改进D^(*)算法的运动规划方法。其中,前端路径规划使用融合跳跃点搜索(JPS)思想的D^(*)算法,后端轨迹优化基于B样条构建二次规划问题。利用矩阵实验室(Matlab)与机器人操作系统(ROS)的仿真平台进行实验,结果表明,改进D^(*)算法在30×30的栅格地图中,相比传统D^(*)算法、FocussedD^(*)、有向D^(*)算法搜索耗时减少0.297、0.269、0.191s;动态障碍物存在时,可使移动机器人快速、安全运动至目标点。

基于残差BP神经网络的Baxter机器人逆运动学分析方法

提出1种基于残差BP(back propagation)神经网络的自适应逆运动学分析方法,围绕数据采集至实时控制的整个运动规划流程,采集140组位置和欧拉角数据,利用残差BP神经网络对Baxter机械臂进行逆运动学分析,拟合得到机械臂7个关节角度;将训练好的关节角度以话题的形式发布,通过在抓取物体的脚本中订阅该话题实现通讯;结合Rviz进行可视化展示和实物双臂协同实验,对4种物体模型分别用残差BP神经网络和普通BP神经网络进行抓取实验,验证所提方法的有效性。结果表明:所提方法的计算单点时间约8.1 ms,远小于机械臂的控制周期,可实现实时性的要求;在进行1500次训练的情况下,残差BP神经网络模型的均方误差为0.006,相比普通BP神经网络模型,误差降低0.077,提高了模型的准确性;所提方法的抓取成功率为87.5%,比普通BP神经网络提高了22.5%,验证了本文所提方法的有效性和实用性。

基于改进RRT算法的移动机器人路径规划

针对快速扩展随机树(rapidly exploring random tree,RRT)算法在移动机器人路径规划过程中存在盲目搜索、内存计算量大和冗余点较多等问题,提出了改进的RRT算法。首先,随机点进行扩展时引入动态目标采样率,引导随机点向目标点方向扩展;其次,融合A*算法中代价函数策略,在加入不同权重因子之后,选取代价值合适的节点作为待扩展节点;然后,针对初始路径过长并存在过多冗余点的问题,提出反向搜索剪枝方法,对裁剪后的路径进行三次样条插值平滑处理来改善路径质量;最后,利用Pycharm对改进的RRT算法进行仿真验证。仿真结果表明,改进的RRT算法相较于传统RRT算法、RRT*算法和基于概率P的RRT算法(P-RRT),在路径的规划长度、规划时间和扩展节点数上都具有明显优势,提高了机器人的路径规划效率。

机器鳄鱼运动的仿生步态规划方法

模仿真实动物的运动步态是仿生机器人步态规划研究的一个重点。针对一种新型仿生机器鳄鱼的步态规划问题,采用动作捕捉技术获取了真实鳄鱼的运动步态。在此基础上,利用高斯牛顿法求解出机器鳄鱼的腿部关节角度,拟合得到与真实步态轨迹相似性较好的仿生步态,并分析了机器鳄鱼在该步态下的运动稳定性。虚拟样机的运动仿真实验结果表明:机器鳄鱼能用与真实鳄鱼相似的步态,以0.3 m/s的速度向前爬行,且具备较高的稳定性。

移动焊接机器人结构设计与路径规划

针对大型焊接件生产中存在的大范围复杂焊缝以及狭窄空间内部焊接条件恶劣的情况,设计一种新型移动焊接机器人。采用3个独立驱动的OMNI全向轮作为机器人的移动机构,同时在移动机构底盘安装支撑轮及可调节磁吸附装置,并设计五自由度机械臂作为焊接执行机构;对机器人移动平台与机械臂分别进行运动学分析以及整体运动学分析,推导出机器人末端执行器与驱动轮、机械臂关节角位移之间的函数关系;针对曲率变化较大的焊缝难以焊接的问题,提出基于改进粒子群优化算法的多段直线逼近曲线的移动平台路径规划算法,并用MATLAB仿真验证了该路径规划算法可以完成任意曲率曲线的焊缝离散化,在满足焊接精度的前提下,能够减少焊缝离散点数目,提高了移动平台路径规划的效率。

基于MATLAB Robotics Toolbox的Dobot机械臂运动规划

为实现Dobot机械臂的运动控制,验证运动学分析准确性和运动规划的可行性,首先理论求解机械臂正逆运动学,然后基于蒙特卡洛法对机械臂进行了工作空间分析,利用Robotics Toolbox工具箱对Dobot机械臂进行运动规划仿真验证。仿真结果证明Dobot机械臂正、逆向运动学分析计算正确,运动规划合理可行。

动态环境下基于自适应步长Informed-RRT*和人工势场法的机器人混合路径规划

为解决移动机器人在动态环境下的路径规划问题,将Informed-RRT*和人工势场法相融合,提出全局与局部规划算法相融合的路径规划方法。首先,针对Informed-RRT*算法采样效率低,以及得到路径不满足机器人运动学约束的问题,采用目标偏置法与自适应步长法,减少冗余搜索与不必要树的生长;同时,引入走廊优化与时间重分配法,优化路径节点,使路径更加平滑。其次,针对人工势场法易陷入局部极小值和目标点附近不可达的问题,采用平滑窗格策略,增设全局路径子目标点,使机器人能够逃离局部极小值,完成规划任务。仿真结果表明,静态环境中自适应步长Informed-RRT*算法相比于Informed-RRT*算法求解时间缩短了71.98%;动态环境中,混合算法相比于人工势场法,搜索时间缩短了15.4%,路径长度缩短了11.1%。

曲线焊缝的机器人焊接轨迹规划与高频控制

机器人实时焊缝跟踪系统中,轨迹规划时间及控制延迟过高会影响跟踪精度和焊接质量。针对这一问题,结合B样条曲线插补算法和外部引导运动模块,提出一种用于曲线焊缝的分段式实时轨迹规划与控制方法。首先根据插补时间最优原则将轨迹分段,然后采用三次非均匀B样条插补每段轨迹并得到插补点,最后设计了机器人高频控制器,利用外部引导运动模块以4 ms为周期将插补点依次发送给机器人,引导机器人运动。试验结果表明,该方法在100 ms内即可完成正弦曲线焊缝的规划并引导机器人焊接,跟踪精度控制在±0.2 mm以内,实现了轨迹的快速规划和高频控制。

复杂场景下Baxter机器人的避碰运动规划

起始位形和目标状态不变的情况下,Baxter机器人运动规划器每次运行时的规划结果也可能不同。因此,文章将IKFAST分析方法和双向RRT运动规划算法相结合,旨在为Baxter机器人在复杂场景作业中快速规划一条无碰撞路径和轨迹。通过分析IKFAST分析方法的IK求解器与其他数值IK求解器(NR和MLA方法)在运动规划中的性能表现,证明了IKFAST分析方法可以有效提高运动规划性能。

钻锚机器人钻臂轨迹规划方法研究

为提高煤矿巷道支护效率,改善掘进工作面自动化智能化程度,设计了一种集成悬臂式掘进机和六自由度机械臂的钻锚机器人,研究了钻锚孔孔序规划策略及钻臂轨迹规划方法。首先,基于改进的DH方法建立机械臂结构的运动学模型,分析其运动学正解和逆解,解算钻机空间位姿及对应的关节变量值;其次,基于蒙特卡罗随机数方法分析机械臂运动空间,求解双机械臂运动范围;基于钻锚作业工艺要求提出一种钻锚孔孔序规划策略,在不同条件下两机械臂按照一定锚固顺序完成顶板锚固作业任务;最后,基于五次多项式插值方法完成机械臂轨迹规划,以实现钻臂快速平稳达到目标位置。仿真结果表明,钻锚机器人能满足宽×高为6000mm×4500mm范围内的巷道支护要求,基于该孔序规划策略和钻臂轨迹规划方法,两钻机在进行顶板锚固作业任务时能有效避免干涉,实现准确、平稳运动至锚固点,完成锚固任务。研究结果为发展自动支护和智能掘进提供了一种思路和方法。

基于高斯过程回归预测的舞台机器人避撞路径滚动时域规划

针对移动舞台机器人的避撞运动规划问题,提出基于高斯过程回归和模型预测控制(MPC)的方法。在获取舞台环境中运动体位置信息后,使用高斯过程回归方法对运动体位置进行预测,再利用运动体的未来位置信息,将控制时域内存在的碰撞风险作为硬性约束,在线优化求解移动机器人未来一段时刻的局部最优速度轨迹。进一步驱动移动舞台机器人跟踪规划速度,实现对移动舞台机器人运动轨迹的实时滚动规划与跟踪。最后在两类舞台场景下,仿真验证了本文方法的有效性。