检索结果-南通市图书馆

A policy iteration method for improving robot assembly trajectory efficiency

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2023年第3期36卷 436-448页

作者： Qi ZHANG zongwu xie Baoshi CAO Yang LIU State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Bolt assembly by robots is a vital and difficult task for replacing astronauts in extravehicular activities(EVA),but the trajectory efficiency still needs to be improved during the wrench insertion into hex hole of *** this paper,a policy iteration method based on reinforcement learning(RL)is proposed,by which the problem of trajectory efficiency improvement is constructed as an issue of RL-based objective ***,the projection relation between raw data and state-action space is established,and then a policy iteration initialization method is designed based on the projection to provide the initialization policy for *** iteration based on the protective policy is applied to continuously evaluating and optimizing the action-value function of all state-action pairs till the convergence is *** verify the feasibility and effectiveness of the proposed method,a noncontact demonstration experiment with human supervision is *** results show that the initialization policy and the generated policy can be obtained by the policy iteration method in a limited number of demonstrations.A comparison between the experiments with two different assembly tolerances shows that the convergent generated policy possesses higher trajectory efficiency than the conservative *** addition,this method can ensure safety during the training process and improve utilization efficiency of demonstration data.

关键词： Bolt assembly Policy initialization Policy iteration Reinforcement learning(RL) Robotic assembly Trajectory efficiency

基于元启发式优化的机器人智能体无碰撞轨迹规划

在线全文

学校读者我要写书评

暂无评论

载人航天 2024年第4期30卷 510-515页

作者：谢宗武马博宇孙万东杨晓航姬一明谢光虎哈尔滨工业大学机器人技术与系统全国重点实验室哈尔滨150001

针对机器人智能体在复杂三维环境中的安全运动,提出一种基于元启发式优化的无碰撞轨迹规划方案。轨迹点采用五次样条插值,以确保运动轨迹足够平滑,且起始点和目标点的速度与加速度均为零。以轨迹长度最短为优化目标,将轨迹与障碍物的最... 详细信息

针对机器人智能体在复杂三维环境中的安全运动,提出一种基于元启发式优化的无碰撞轨迹规划方案。轨迹点采用五次样条插值,以确保运动轨迹足够平滑,且起始点和目标点的速度与加速度均为零。以轨迹长度最短为优化目标,将轨迹与障碍物的最近距离限制在约束条件中,从而表述为一个优化问题,并采用基于元启发式的灰狼算法进行求解。随后,在复杂的三维地形中对该方案开展2个模拟仿真。结果表明:该方案能够有效地在规划空间内求解出预定数目的最优轨迹插值点,通过五次样条插值形成的轨迹长度达到最短,且不与障碍物发生任何碰撞。

关键词：机器人智能体轨迹规划无碰撞五次样条插值灰狼算法元启发式

维普期刊数据库博看期刊

Mechanical design,modeling,and identification for a novel antagonistic variable stiffness dexterous finger

在线全文

学校读者我要写书评

暂无评论

Frontiers of Mechanical Engineering 2022年第3期17卷 59-74页

作者： Handong HU Yiwei LIU zongwu xie Jianfeng YAO Hong LIU State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

This study traces the development of dexterous hand research and proposes a novel antagonistic variable stiffness dexterous finger mechanism to improve the safety of dexterous hand in unpredictable environments,such as unstructured or man-made operational errors through comprehensive consideration of cost,accuracy,manufacturing,and *** on the concept of mechanical passive compliance,which is widely implemented in robots for interactions,a finger is dedicated to improving mechanical *** finger mechanism not only achieves passive compliance against physical impacts,but also implements the variable stiffness actuator principle in a compact finger without adding supererogatory *** achieves finger stiffness adjustability according to the biologically inspired stiffness variation principle of discarding some mobilities to adjust *** mechanical design of the finger and its stiffness adjusting methods are *** stiffness characteristics of the finger joint and the actuation unit are *** results of the finger joint stiffness identification and finger impact tests under different finger stiffness presets are provided to verify the validity of the *** have been experimentally proven to be robust against physical ***,the experimental part verifies that fingers have good power,grasping,and manipulation performance.

关键词： multifingered hand mechanism design robot safety variable stiffness actuator

Trajectory planning and base attitude restoration of dual-arm free-floating space robot by enhanced bidirectional approach

在线全文

学校读者我要写书评

暂无评论

Frontiers of Mechanical Engineering 2022年第1期17卷 2-17页

作者： zongwu xie Xiaoyu ZHAO Zainan JIANG Haitao YANG Chongyang LI State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China Robotic System Department Jiangsu Jitri-Hust Intelligent Equipment TechnologyWuxi 214000China

When free-floating space robots perform space tasks,the satellite base attitude is disturbed by the dynamic *** disturbance of the base orientation may affect the communication between the space robot and the control center on *** this paper,the enhanced bidirectional approach is proposed to plan the manipulator trajectory and eliminate the final base attitude variation.A novel acceleration level state equation for the nonholonomic problem is proposed,and a new intermediate variable-based Lyapunov function is derived and solved for smooth joint trajectory and restorable base *** the method,the state equation is first proposed for dual-arm robots with and without end constraints,and the system stability is analyzed to obtain the system *** input modification further increases the system stability and simplifies the calculation *** are carried out in the end,and the proposed method is validated in minimizing final base attitude change and trajectory ***,the minute internal force during the coordinated operation and the considerable computing efficiency increases the feasibility of the method during space tasks.

关键词： free-floating space robot dual arm coordinated operation base attitude restoration bidirectional approach

Fabrication of a biomimetic controllable adhesive surface by ultraprecision multistep and layered scribing and casting molding

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2021年第8期64卷 1814-1826页

作者： WANG Wei xie zongwu State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin150001China

Wedge-shaped microstructures have the ability to reproduce the excellent adhesive properties of geckos’feet because of their unique anisotropic *** particular,the controllability of the wedge-shaped microstructures on adhesion is beneficial to the undisturbed grasp or the capture of space ***,the problem currently remains of how to process it efficiently and with high *** a strategy called ultraprecision multistep and layered scribing is proposed for the manufacture of the biomimetic controllable adhesive *** results show that the metal master mold prepared based on the manufacturing strategy has not only good surface topography but also high reliability and ***,the controllable adhesive surface of 1.96 cm2,fabricated by the proposed manufacturing strategy,has a normal adhesion of 1.012 N,and the corresponding shear friction and adhesion coefficient are 3.105 N and 4.82,***,the controllable adhesive surface has been shown to be approximately superhydrophobic and also to possess the properties of controllable adhesion and dynamic ***,after 250 adhesion-detachment cycles,the normal adhesion and shear friction only decrease by 5%and 3%,*** research realizes an environmentally friendly and efficient method by which to manufacture a durable metal mold for fabricating a biomimetic controllable adhesive surface,laying a foundation for its effective application in the adherence of space-floating targets.

关键词： continuous and tilted wedge-shaped microstructures biomimetic controllable adhesive surface ultraprecision multistep and layered scribing controllable adhesion dynamic adhesion

Three-line structured light vision system for non-cooperative satellites in proximity operations

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2020年第5期33卷 1494-1504页

作者： Yang LIU zongwu xie Hong LIU State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150000China

Adapter ring is a commonly used component in non-cooperative satellites,which has high strength and is suitable to be recognized and grasped by the space *** proximity operations,this circle feature may be occluded by the robot arm or limited field of ***,the captured images may be underexposed when there is not enough *** address these problems,this paper presents a structured light vision system with three line lasers and a monocular *** lasers project lines onto the surface of the satellite,and six break points are formed along both sides of the adapter ring.A closed-form solution for real-time pose estimation is given using these break ***,a virtual structured light platform is constructed to simulate synthetic images of the target *** with the predefined camera parameters and relative positions,the proposed method is demonstrated to be more effective,especially at a close ***,a physical space verification system is set up to prove the effectiveness and robustness of our method under different light *** results indicate that it is a practical and effective method for the pose measurement of on-orbit tasks.

关键词： Adapter ring Line detection Non-cooperative target Pose measurement Space robot Structured light

A noncontact robot demonstration method with human supervision

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2021年第11期64卷 2360-2372页

作者： ZHANG Qi xie zongwu LIU Yang State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

The widely used kinesthetic demonstration method of dragging robotic manipulators cannot obtain reliable information for autonomous robot manipulation because an additional external force rather than pure contact force will be reflected on the force sensor in end-constrained manipulation tasks. Therefore, a noncontact robot demonstration method with human supervision is proposed to avoid external influence. A human demonstrator sends motion commands by mouse and observes force data reflected in a monitor to protect the robotic manipulator. Simultaneously, the human demonstrator supervises the positionorientation relationship between the end-effector and the manipulated object. The wrench insertion task is adopted to illustrate the advantage of the proposed method. A contact model is established according to demonstration data acquired from the proposed demonstration method, and an orientation adjustment strategy is verified. The strategy verification experiment illustrates not only the effectiveness of the simplified contact model and corresponding strategy but also the advantage of the proposed demonstration method.

关键词： Robot demonstration contact model orientation adjustment

Gecko-Like Dry Adhesive Surfaces and Their Applications: A Review

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2021年第5期18卷 1011-1044页

作者： Wei Wang Yang Liu zongwu xie State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Gecko has the ability to climb flexibly on various natural surfaces because of its fine layered adhesion system of foot,which has motivated researchers to carry out a lot of researches on *** progresses have been made in the gecko-like dry adhesive surfaces in the past 2 decades,such as the mechanical measurement of adhesive characteristics,the theoretical modeling of adhesive mechanism and the production of synthetic dry adhesive *** application researches have been carried out as *** paper focuses on the investigations made in recent years on the gecko-like dry adhesive surfaces,so as to lay the foundation for further research ***,the adhesion system of gecko’s foot and its excellent adhesive characteristics are reviewed,and the adhesive models describing the gecko adhesion are summarily reviewed according to the diff erent contact ***,some gecko-like dry adhesive surfaces with outstanding adhesive characteristics are ***,some application researches based on the gecko-like dry adhesive surfaces are ***,the full text is summarized and the problems to be solved on the gecko-like dry adhesive surfaces are prospected.

关键词： Gecko adhesion Gecko-like dry adhesive surfaces Climbing robot Robot gripper Medical adhesive tape

Robot learning from demonstration for path planning: A review

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2020年第8期63卷 1325-1334页

作者： xie zongwu ZHANG Qi JIANG ZaiNan LIU Hong State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Learning from demonstration(LfD)is an appealing method of helping robots learn new *** papers have presented methods of LfD with good performance in ***,complicated robot tasks that need to carefully regulate path planning strategies remain *** or non-contact constraints in specific robot tasks make the path planning problem more difficult,as the interaction between the robot and the environment is *** this paper,we focus on the path planning of complex robot tasks in the domain of LfD and give a novel perspective for classifying imitation learning and inverse reinforcement *** classification is based on constraints and obstacle ***,we summarize these methods and present promising directions for robot application and LfD theory.

关键词： learning from demonstration path planning imitation learning inverse reinforcement learning obstacle avoidance