Motion Planning for Autonomous Driving with Real Traffic Data Validation

Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.In this paper,a safe motion planning approach is proposed based on the deep learning-based trajectory prediction method.To begin with,a trajectory prediction model is established based on the graph neural network(GNN)that is trained utilizing the INTERACTION dataset.Then,the validated trajectory prediction model is used to predict the future trajectories of surrounding road users,including pedestrians and vehicles.In addition,a GNN prediction model-enabled motion planner is developed based on the model predictive control technique.Furthermore,two driving scenarios are extracted from the INTERACTION dataset to validate and evaluate the effectiveness of the proposed motion planning approach,i.e.,merging and roundabout scenarios.The results demonstrate that the proposed method can lower the risk and improve driving safety compared with the baseline method.

The New Method for CNC Trajectory Machining Motion Planning Based on Reference Time

In order to make motion planning fitting practice,many characteristic of CNC trajectory motion are discussed, such as the geometric function,the motion and the time.It is found that the relation between orbit function and motional parame- ter,so the differential equation about the trajectory motion be set-up by the goal of trajectory motion.The actual motion process is defined as reference time to link planning and practice.Present a new movement planning method based on self-defining time.At rest state,the differential simultaneous equation can be calculated according geometric characteristic analysis,it can be get that simple function consisted of coordinate and reference time variants.At motive state,dynamic parameter can be worked out accord- ing practical value of reference time,It is proved by experiment and simulation that it is a good way to control geometry and motion comprehensively,to reduce computation times and to increase the ability of environmental adaptation for path

A Unified Trajectory Optimization Approach for Long-Term and Reactive Motion Planning of Legged Locomotion

This paper proposes a unified trajectory optimization approach that simultaneously optimizes the trajectory of the center of mass and footholds for legged locomotion.Based on a generic point-mass model,the approach is formulated as a nonlinear optimization problem,incorporating constraints such as robot kinematics,dynamics,ground reaction forces,obstacles,and target location.The unified optimization approach can be applied to both long-term motion planning and the reactive online planning through the use of model predictive control,and it incorporates vector field guidance to converge to the long-term planned motion.The effectiveness of the approach is demonstrated through simulations and physical experiments,showing its ability to generate a variety of walking and jumping gaits,as well as transitions between them,and to perform reactive walking in obstructed environments.

Trajectory planning and motion control of full-row seedling pick-up arm

Frequent start-stops of automatic seedling transplanters would lengthen the seedling picking time due to alternating movement of the motor,and cause positioning errors and frequent motor vibrations when starting the machine.To solve these problems and ensure the pick-up continuity of automatic transplanters,in this study the smooth circular arc interpolation algorithm and the least square method for multinomial curve fitting were used to conduct the trajectory planning of automatic transplanter based on the movement of the pick-up arm of the transplanter.Velocity and time curves were fitted in segments to acquire motion control parameters and further tracking control was conducted.The mathematical model of the control system was established using Simulink,and simulation analysis and system debugging test were performed.Experiments show that the trajectory curves obtained by MATLAB’s data processing can realize the continual and smooth motion trajectory of the pick-up arm;stepper motor velocity control can effectively track the planning curve and improve the seedling pick-up efficiency.The pick-up and pushing time of each motion of the planned plug seedling transplanter reduced by 1.0678 s and the start-stop times reduced from 6 to 1,which solved the frequent motor vibrations when starting the machine and improved the stability of the system.In addition,overstep and out-of-step of the motor at the start-stop moment were avoided and displacement error was reduced.

Third-order trajectory planning for high accuracy point-topoint motion

This article studies a third-order trajectory planning method for point-to-point motion.All available instances for third-order trajectory planning are first analyzed.To distinguish those,three criteria are presented relying on trajectory characteristics.Following that,a fast preprocessing approach considering the trajectory as a whole is given based on the criteria constructed and system constraints.Also,the time-optimality of the trajectory is obtained.The relevant formulas are derived with the combination of geometrical symmetry of trajectory and area method.As a result,an accurate algorithm and its implementation procedure are proposed.The experimental results show the effectiveness and precision of the proposed method.The presented algorithm has been applied in semiconductor manufacturing equipment successfully.

Synergic Motion Trajectory Planning for Airplane Docking Based on6PURU Parallel Mechanism

Motion planning issues encountered in assembling airplanes by employing the 6PURU parallel mechanism are analyzed in this paper. A sine curve of the change rate of acceleration, which is called as jerk in the following text, is proposed for uniaxial flexible acceleration and deceleration planning based on the optimal time and velocity and acceleration constraints. Compared with other curves, the proposed curve can realize a continuous n-order derivative and the smooth change of the speed and acceleration. The method is computational^y simple and suitable for programming. In addition, a multiaxial coordinated movement scheme is proposed. The motion trajectory is no longer simply split into many single-direction trajectories nor are all single-direction planning trajectories combined directly. The multiaxial coordinated movement scheme aims to achieve synergic movement in multiple directions to ensure smoothness of the movement in the event of a kinematic error when maintaining a stable value. If the movement fails to achieve this goal, driving force mutations will deteriorate the effect of synergic movement. A physical model of the parallel mechanism is developed in simMechanics, and a holistic system model is completed in SIMULINK. The feasibility of the new planning algorithm is simulated and tested, and then, the multiaxial synergic movement planning method is proposed and verified.

A control structure for the autonomous locomotion on rough terrain with a hexapod robot

A motion control structure used for autonomous walking on uneven terrain with a hexapod biomimetic robot is proposed based on function-behavior-integration. In the gait planning level, a set of local rules operating between adjacent legs were put forward and the theory of finite state machine was employed to model them; further, a distributed network of local rules was constructed to adaptively adjust the fluctuation of inter-leg phase sequence. While in the leg-end trajectory planning level, combined polynomial curve was adopted to generate foot trajectory, which could realize real-time control of robot posture and accommodation to terrain conditions. In the simulation experiments, adaptive regulation of inter-leg phase sequence, omnidirectional locomotion and ground accommodation were realized, moreover, statically stable free gait was obtained simultaneously, which provided hexapod robot with the capability of walking on slightly irregular terrain reliably and expeditiously.

障碍物无规则运动下启发式Gauss配点参数化连续避障规划

针对障碍物无规则运动下自动驾驶车辆(SDV)的避障轨迹规划,本文提出一种结合模型约束简化和启发式非均匀Gauss配点参数化的轨迹规划算法.首先,结合SDV运动学方程和约束条件建立了SDV连续避障轨迹规划的问题;然后,在高斯伪谱法离散化算法框架下,采用Gauss配点对状态变量进行离散化;进一步,提出了启发式Gauss配点初始化策略,以此提升SDV求解速度进而实现避障实时规划;同时,对经过约束处理后的轨迹进行验证,以此保证规划轨迹的安全性;最后,在车辆模型上针对不同障碍物运动场景进行仿真测试,验证提出方法的有效性和实时性.结果显示,本文方法可以有效进行避障轨迹规划,并确保轨迹的安全性,轨迹规划平均求解耗时维持在25ms左右,显示出本文方法在实时避障规划的效能和实际应用价值.

4+2自由度叶片抛磨专用机器人轨迹规划方法研究

砂带抛磨作为复杂曲面叶片精密加工的最后一道工序,其加工质量直接影响叶片的服役性能和寿命。传统6自由度机器人多关节串联具有明显的弱刚性,在末端夹持大型叶片时抗变形能力欠佳。为此,文章自主设计研发了4+2自由度叶片抛磨专用机器人系统,并开展复杂曲面叶片抛磨轨迹规划方法研究。首先基于D-H法建立该机器人运动学模型,进行机器人运动学的正、逆解的求解;其次给出了综合考虑抛磨工具与工件曲率的干涉、刀路轨迹行距和轨迹点密度对残留高度的影响规律的轨迹规划方法,建立了2个单元的协同运动模型保证叶片的加工实现;最后通过叶片抛磨轨迹数控程序验证了所获得的抛磨轨迹的正确性。

自动泊车发展现状及运动规划研究进展

汽车保有量持续上升与城市停车场建设不足间的矛盾引发了严重的停车问题,同时泊车位数量不足、泊车空间狭小等问题严重阻碍了车辆出行任务的完成。自动泊车因其较低的车速以及在特定场景下的高度自动驾驶,成为最先落地的自动驾驶产品。分析了国内外自动泊车市场的发展现状及趋势,重点讨论了泊车系统的规划决策模块。强调了运动规划的重要性,它直接影响车辆行驶质量,综述了国内外的研究成果,包括曲线插值、随机采样、图搜索、智能算法和数值优化方法,并分析了不同路径规划的优势和局限性。最后,展望了未来自动泊车技术的融合和发展方向。

基于改进运动原语生成的陆空两栖机器人Kinodynamic A^(*)算法

针对Kinodynamic A^(*)算法采用统一的运动原语生成,在陆空两栖机器人上应用时存在机动性无法充分发挥等问题,提出了基于改进运动原语生成的陆空两栖机器人Kinodynamic A^(*)算法。该算法从考虑陆、空模态运动能力差异出发,通过以下三个方法改进陆空两栖机器人Kinodynamic A^(*)算法性能。首先是基于动力边界决定状态空间加速度输入,差异化生成陆、空模态运动原语;其次是基于动力学约束剪枝,确保运动原语不超过速度边界;最后是构造轨迹优化代价函数优化轨迹平顺性、安全性及机动性。在仿真场景下的结果表明,所改进的算法在将空中平均速度提高了54.1%,平均路径总时间降低6.7 s,路径总代价降低22.00%,且算法运行时间降低0.069 s,充分发挥陆空两栖机器人上的强机动能力与高续航能力。

高速公路无人驾驶的分层抽样多动态窗口轨迹规划算法

高速公路无人驾驶轨迹规划面临着实时性强、安全性高的挑战.为此,提出一种分层抽样多动态窗口的轨迹规划算法(Stratified sampling based multi-dynamic window trajectory planner,SMWTP).首先,用多动态窗口表征可行轨迹的搜索空间,并基于贝叶斯网络构建轨迹概率分布模型.其次,采用先速度后路径的分层抽样策略生成符合动态场景约束的候选轨迹集合.最后,利用引入障碍车辆速度估计不确定性的责任敏感安全模型(Responsibility sensitive safety,RSS)从中选择最优轨迹.大量仿真实验和实际交通场景测试验证了算法的有效性,对比实验结果表明,所提算法性能显著优于人工势场最优轨迹规划算法和多动态窗口模拟退火轨迹规划算法.

基于甲虫搜索算法的空间机械臂轨迹规划技术研究

针对中国空间站问天实验舱机械臂(EMM)的轨迹规划任务,提出了一种基于甲虫搜索(BAS)算法的轨迹规划技术,使机械臂关节轨迹满足多目标约束的同时,机械臂末端沿预定的任务轨迹运动。基于GJK算法将机械臂本体与周围障碍物的最小距离作为首要优化目标,保证机械臂与障碍物保持安全距离;根据笛卡尔空间中的目标轨迹,基于DH法建立的EMM运动学模型,将机械臂末端与目标轨迹的位置误差作为次级优化目标;为减少机械臂关节磨损,把第3、4、5关节运动行程作为第三个优化目标。采用加权系数法将3个优化目标组成轨迹规划算法的优化模型。实验结果表明:提出的轨迹规划算法具有较快的收敛速度,末端误差曲线变换平缓,精度明显高于粒子群算法的结果。验证了BAS规划出的轨迹能够使机械臂末端在跟踪目标轨迹的同时,机械本体可安全避开空间站舱外的障碍物。

自动泊车运动规划方法综述

自动泊车是自动驾驶车辆在低速行驶场景中的核心技术之一,已被广泛应用于各类车型中。运动规划确保所规划出的轨迹能指引车辆从起始位姿无碰撞、符合运动学规律地行驶至目标位姿,是体现自动泊车智能水准的关键技术模块。随着当前自动驾驶技术从初步的技术原型研究逐渐向产业化应用转型,低速自动驾驶领域中的自动泊车技术成为了这一转型过程中的关键突破点。文章回顾了现有的应用于自动泊车领域的运动规划方法,将其归纳为几何方法、采样方法、搜索方法、数值优化方法以及机器学习方法等类别,并对各类方法的发展历程与技术特点进行了回顾;探讨了自动泊车运动规划方法的未来研究方向,具体包括构建泛化性更强的模型、提升规划方法的稳定性、关注在线实时高质量重规划的能力与防御性驾驶的能力,以及考虑与其他交通参与者的交互等。

基于D-H参数的六轴机器人运动学分析与仿真

将六轴协作机器人作为研究目标,对其进行了运动学分析,并通过D-H参数法实现了机器人的运动学研究与模拟,同时利用机器人的尺寸图与结构图建立连杆坐标系并形成了相关的参数表,在相同关节角度上分别通过正、逆运动理论与MATLAB模型中的方法实现了机器人末端的姿态计算与模型的正确性检验。通过蒙特卡洛算法可以计算出机器人的空间点云图,通过MATLAB工具包可以计算出机器人末端节点的位置、速度和加速度的拟合曲线。

空间站舱内悬浮实验台制导控制方法

针对中国空间站舱内悬浮实验台微重力水平最优的控制问题,考虑舱内运动行程空间约束及各类不确定性因素的影响,以不同时长下的最优微重力水平为目标,提出基于凸优化的空间站舱内悬浮实验台自主轨迹规划方法和基于误差反馈控制的轨迹跟踪方案。介绍悬浮实验台的结构,建立空间相对运动动力学模型,并将其线性化;通过凸优化的方法求解微重力水平最优的运动轨迹及相应的控制力序列;设计基于误差反馈的PID跟踪控制律,兼顾微重力水平的同时实现对优化轨迹的快速跟踪控制。数值仿真结果表明:当微重力科学实验时长需求为1 h时,最优微重力水平可达9.121×10^(−6)m/s^(2)。基于凸优化的空间站舱内悬浮实验台自主轨迹规划方法和基于误差反馈控制的轨迹跟踪方案,能够实现指定时长需求的最优微重力水平,给当前中等时长(1 h)最优微重力水平问题提供了解决思路,提升了中国空间站舱内悬浮实验台的应用价值。

基于345-修正梯形运动规律的4-RR(SS)_(2)并联机器人运动轨迹规划

研究了一种新型四自由度高速并联机器人运动轨迹规划方法。该机器人采用单动平台结构以减轻末端平台质量,提升机器人加减速性能。建立机器人机构运动学逆解模型,通过融合345多项式和梯形运动规律的优点,构造一种可兼顾运动时长和运动平稳性的345-修正梯形运动规律。在此基础上,通过插补叠加轨迹过渡传统门形轨迹的直角部分,并统筹考虑总运动时长最短以及角加速度峰值最小为目标完成插补叠加时机的优选,最后在样机上开展运动频次试验。试验结果显示,采用优化后的运动规律和轨迹样机运动频次可提升至218次/min,工作效率较传统Adept门形轨迹提高55.7%。

Kinematics and trajectory planning of a cucumber harvesting robot manipulator

In order to reduce cucumber harvesting cost and improve economic benefits,a cucumber harvesting robot was developed.The cucumber harvesting robot consists of a vehicle,a 4-DOF articulated manipulator,an end-effector,an upper monitor,a vision system and four DC servo drive systems.The Kinematics of the cucumber harvesting robot manipulator was constructed using D-H coordinate frame model.And the inverse kinematics which provides a foundation for trajectory planning has been solved with inverse transform technique.The cycloidal motion,which has properties of continuity and zero velocity and acceleration at the ports of the bounded interval,was adopted as a feasible approach to plan trajectory in joint space of the cucumber harvesting robot manipulator.Moreover,hardware and software based on CAN-bus communication between the upper monitor and the joint controllers have been designed.Experimental results show that the upper monitor communicates with the four joint controllers efficiently by CAN-bus,and the integrated errors of four joint angles do not exceed four degrees.Probable factors resulting in the errors were analyzed and the corresponding solutions for improving precision are proposed.

Real-time trajectory planning for UCAV air-to-surface attack using inverse dynamics optimization method and receding horizon control

This paper presents a computationally efficient real-time trajectory planning framework for typical unmanned combat aerial vehicle （UCAV） performing autonomous air-to-surface （A/S） attack. It combines the benefits of inverse dynamics optimization method and receding horizon optimal control technique. Firstly, the ground attack trajectory planning problem is mathematically formulated as a receding horizon optimal control problem （RHC-OCP）. In particular, an approximate elliptic launch acceptable region （LAR） model is proposed to model the critical weapon delivery constraints. Secondly, a planning algorithm based on inverse dynamics optimization, which has high computational efficiency and good convergence properties, is developed to solve the RHCOCP in real-time. Thirdly, in order to improve robustness and adaptivity in a dynamic and uncer- tain environment, a two-degree-of-freedom （2-DOF） receding horizon control architecture is introduced and a regular real-time update strategy is proposed as well, and the real-time feedback can be achieved and the not-converged situations can be handled. Finally, numerical simulations demon- strate the efficiency of this framework, and the results also show that the presented technique is well suited for real-time implementation in dynamic and uncertain environment.

激光切割高频动态复合运动轨迹规划与控制方法

为提升激光切割的加工质量评价,提出一种激光切割高频动态复合运动轨迹规划与控制方法。首先,设计激光切割光学系统,实现激光焦点光斑在三维空间内的高频动态运动;然后,探讨激光焦点光斑不同维度的运动轨迹规划方法;接着,提出激光焦点光斑高频动态运动轨迹规划方法,并设计相应的激光切割驱动控制系统;最后,将该文方法与静态表面质量优先切割方法、静态最快切割方法进行钢板激光切割试验测试。试验测试结果表明,该文方法的切割速度为1 m/min、挂渣尺寸为0.9 mm、表面粗糙度为0.09 mm,其切割加工质量评价参数优于以上两种方法。