Novel robot arm design and implementation for hot forging press automation

Manual handling of hot and heavy workpiece in forging press industry increases the process time and causes safety risks to workers. To increase the productivity and optimise the use of manpower, manipulators are needed to be designed for supporting the workers handling the workpiece. Designing robots for such applications is challenging since the robot suffers from a heavy payload at the arm tip, and it operates at a high speed in a large workspace. This research addresses the design and implementation of a novel robot for handling workpiece for a given forging press cell. A novel robotic mechanism is designed with two key features: (i) the addition of parallel links in between serial links and (ii) the use of hydraulic actuators for driving robot’s joints. The addition of parallel links and the use of hydraulic cylinders are to increase the structural rigidity. It is also to reduce the number of joint variables and restrict the end-effector moving parallel to the ground surface so that the robot grips and releases the workpiece in a more efficient and simplified manner. The effectiveness of the designed robot mechanism is demonstrated through functional tests, and experimental results are carried out on the implemented robot.     

人机交互式机器人弧焊再制造系统设计

在分析失效零件再制造的特点的基础上,提出了基于人机交互技术的机器人熔化极气体保护焊(gas metal arc welding,GMAW)再制造思想.将操作者作为系统的一个因素,构成人机交互式的机器人GMAW再制造系统,人机协作共同完成失效零件的再制造任务.其中操作者主要负责解决再制造过程中的非线性、难建模的复杂问题;机器人主要负责数据计算和运动控制等线性问题.根据上述思想,文中建立了人机交互式机器人GMAW再制造试验系统平台,研究了基于开放式图形库(open graphics library,OpenGL)的再制造系统软件结构和人机交互实现方式,采用模块化方法设计实现了可视化的人机交互界面.     

基于强化学习神经网络的车速跟踪控制

提出一种用于汽车排放试验中驾驶机器人对车速跟踪控制的新方法.该控制方法基于神经网络并结合强化学习的自适应能力,通过神经网络的在线学习对车速进行跟踪控制.利用试验汽车所获得的数据,首先开发出用于车速控制的神经网络模型.然后基于强化学习神经网络结构设计神经网络控制器以取得车速跟踪的自适应控制.在仿真研究中,使用神经网络车速控制模型替代实际汽车来训练初始控制器,并用开发与训练好的自学习神经网络控制器用于汽车车速跟踪控制.结果表明,所开发的神经网络控制器具有良好的车速跟踪性能,控制效果明显.     

盾形洄游算法

为解决机器鱼因高速带球失误造成的绕球和逆向顶球行为,对盾形洄游算法进行研究。该算法通过栅格建模,在球周围一定范围内进行布线确定栅格,使得机器鱼在超出目标点后快速寻找最短洄游路径,并找到折返初始位置的最佳方式。实验结果证明：盾形洄游算法能有效地改善带球失误,极大地提高了机器鱼在比赛中的稳定性。     

基于URWPGSim2D 仿真新平台的花样游泳策略

针对2016国际水中机器人大赛花样游泳项目的URWPGSim2D仿真新平台,提出仿真机器鱼的位姿变化、路径规划、规定动作和自由动作的实现策略.为完成在规定时间内实现规定动作和自由动作的大赛要求,采用分时准备的思想,提出动态判断调整函数和跟随距离函数算法,设计多个主题鲜明、具有创意的动作,并通过多次实验验证.实验结果表明:该策略能解决多条仿真机器鱼协作配合困难的问题,具有较高的观赏性.     

3D augmented reality teleoperated robot system based on dual vision

A 3D augmented reality navigation system using stereoscopic images is developed for teleoperated robot systems.The accurate matching between the simulated model and the video image of the actual robot can be realized,which helps the operator to accomplish the remote control task correctly and reliably.The system introduces the disparity map translation transformation method to take parallax images for stereoscopic displays,providing the operator an immersive 3D experience.Meanwhile,a fast and accurate registration method of dynamic stereo video is proposed,and effective integration of a virtual robot and the real stereo scene can be achieved.Preliminary experiments show that operation error of the system is maintained at less than 2.2 mm and the average error is 0.854 7,0.909 3 and 0.697 2 mm at x,y,z direction respectively.Lots of experiments such as pressing the button,pulling the drawer and so on are also conducted to evaluate the performance of the system.The feasibility studies show that the depth information of structure can be rapidly and recognized in remote environment site.The augmented reality of the image overlay system could increase the operating accuracy and reduce the procedure time as a result of intuitive 3D viewing.     

ICD/ITKE Research Pavilion 2014–15: Fibre Placement on a Pneumatic Body Based on a Water Spider Web

Process-based biomimetics focuses on the transfer of biological principles to architectural construction. To realise the ICD/ITKE Research Pavilion 2014 -15, presented here by Moritz Doerstelmann, Jan Knippers, Valentin Koslowski, Achim Menges, Marshall Prado, Gundula Schieber and Lauren Vasey of the Institute for Computational Design (ICD) and Institute of Building Structures and Structural Design (ITKE) research team at the University of Stuttgart, sensor-driven robotic fabrication was combined with advanced design computation and simulation. This enabled the construction of an architectural fibre structure on a pneumatic mould, drawing on the complex design of the web of a water spider.     

Impossible Objects

Jonathan Proto and Brandon Kruysman of Kruysman-Proto, both design technologists at San Francisco-based Bot & Dolly, a design and engineering studio that specialises in automation, robotics and filmmaking, describe their radical approach to architectural representation. They explain how by combining cinematic techniques and advanced robotic manufacturing they have been able to explore a new model for making that shifts the role of robotics in fabrication away from a process largely focused on geometric rationalisation into the sphere of visualisation and ideas creation.     

2D 仿真机器鱼协作过孔策略

在机器鱼2D仿真协作过孔比赛项目中,针对无球游动过程中固定路线的行进方法所存在的问题,提出一种优化策略。根据比赛规则,将比赛分为无球游动和带球运输2部分。在无球游动过程中,使用一种根据当前所处位置动态选择最优路线的路径优化思路。在带球运输部分,利用场地的特殊性使用机器鱼身体的所有部位运输。结果表明:优化后的策略能充分考虑该项目的得分要求和场地特点,在速度和稳定性上都有很大程度的提高。     

基于ANSYS的工业机器人腰关节结构分析

腰关节是机器人的基础,它支撑着大臂和小臂上的各运动部件,机器人末端执行器与腰转部件间的距离最大,腰转部件的惯性负载也最大。针对腰关节的结构特点和性能要求,采用基于Pro/E的三维建模和基于ANSYS的结构性能分析相结合的方法,对自主研发的工业机器人腰关节进行了结构静力分析和模态分析,对解决产品结构性能设计中存在的问题、缩短产品设计周期具有指导意义,改变了传统工业机器人设计方面的局限性,一定程度上丰富了工业机器人的设计方法。