检索结果-内蒙古大学图书馆

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Gao, Jianqi Li, Yanjie Ye, Zhaohui Wu, Xinyu Department of Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Multi-agent path finding (MAPF) is an essential issue for warehouse automation, where multiple agents plan collision-free paths from the start to goal positions. Reinforcement learning (RL) has been employed to develop partially observable distributed MAPF methods that can be scaled to any number of agents. However, existing RL-based MAPF methods still have some limitations in handling redundant information and avoiding deadlock, resulting in a low success rate or longer makespan. This paper proposes a Priority-aware Communication & Experience learning method (PCE), which combines RL with a novel priority-aware multi-agent communication and a new priority-aware deadlock experience replay to tackle this challenge. To be specific, our innovation encompasses two-fold. Our proposed communication mechanism aims to handle redundant information, which establishes a dynamic communication topology based on agents' priorities and proposes a two-head priority-aware graph attention network to aggregate information. In order to help the agent avoid deadlock, we prioritize the expert experience that solves the deadlock when performing experience replay. We conduct multiple simulation experiments on warehouse-like structured grid maps. Compared with the state-of-the-art RL-based MAPF methods, PCE performs significantly better with a higher success rate and lower makespan in small and large MAPF and higher average throughput in the lifelong MAPF, which can further improve the efficiency of warehouse automation. Finally, we validate PCE using three Turtlebot3-Burger robots, which shows that PCE can be applied in real warehouse automation scenarios. IEEE

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Learning Agile Quadrotor Flight in Restricted Environments with Safety Guarantees

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 1-8页

作者： Chen, Shiyu Li, Yanjie Lou, Yunjiang Lin, Ke Wu, Xinyu Department of Control Science and Engineering Harbin Institute of Technology Shenzhen and Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

With the increasing requirement for agile and efficient controllers in safety-critical scenarios, controllers that exhibit both agility and safety are attracting attention, especially in the aerial robotics domain. This paper focuses on the safety issue of Reinforcement Learning (RL)-based control for agile quadrotor flight in restricted environments. To this end, we propose a unified Adaptive Safety Predictive Corrector (ASPC) to certify each output action of the RL-based controller in real-time, ensuring its safety while maintaining agility. Specifically, we develop the ASPC as a finite-horizon optimal control problem, formulated by a variant of Model Predictive Control (MPC). Given the safety constraints determined by the restricted environment, the objective of minimizing loss of agility can be optimized by reducing the difference between the actions of RL and ASPC. As the safety constraints are decoupled from the RL-based control policy, the ASPC is plug-and-play and can be incorporated into any potentially unsafe controllers. Furthermore, an online adaptive regulator is presented to adjust the safety bounds of the state constraints with respect to the environment changes, extending the proposed ASPC to different restricted environments. Finally, simulations and real-world experiments are demonstrated in various restricted environments to validate the effectiveness of the proposed ASPC. IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Robustness and Push Recovery of Humanoid Robots Using Predictive and Whole-Body Control

Robustness and Push Recovery of Humanoid Robots Using Predic...

引用

2024 IEEE International Conference on Unmanned systems, ICUS 2024

作者： Zhang, Shaojie Ni, Fenglei Li, Xueai Li, Xu Ji, Yi Shao, Xiangyu State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China Key Laboratory of Autonomous Intelligent Unmanned Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350384185

Robustness walking and recovery ability in uneven terrains and unexpected collisions are crucial for the practical application of humanoid ***, existing methods struggle to effectively balance stability, motion safety and walking *** paper proposes a hybrid control strategy combing Nonlinear Model Predictive Control (NMPC) and Whole-Body Control (WBC) to improve the robot's walking stability and reaction safety in collisions *** NMPC generates long-term and macroscopic movements, with capture point theory being utilized for foot placements determination under external *** this foundation, the WBC regulates the robot refinedly in real-time based on task priorities and *** verify the effectiveness of the proposed method, involving uneven terrain walking and external impacts rejection. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Versatile Jumping of Humanoid Robots via Curriculum-Assisted Reinforcement Learning

Versatile Jumping of Humanoid Robots via Curriculum-Assisted...

引用

2024 China Automation Congress, CAC 2024

作者： Tan, Ruiyu Li, Xueai Ni, Fenglei Zhou, Dong Ji, Yi Shao, Xiangyu Key Laboratory of Autonomous Intelligent Unmanned Systems Harbin Institute of Technology Harbin China State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350368604

Versatile jumping is crucial for agile and adaptive behavior of humanoid robots in complex environments. However, humanoid robots have to manage impact forces while maintaining balance and stability throughout the take-off, flight, and landing phases, which imposes significant challenges for motion planning and controller design. This paper proposes a curriculum-assisted reinforcement learning framework for the humanoid robot to achieve various jumping tasks. The curriculum learning divides the jump training process into multi-stages and design different episodes in each stage to guarantee the training feasibility and generalize learned skills. Simulations on a 28 DOFs humanoid robot verify the excellent diverse jumping capability of the proposed policy. This exploration of different tasks also proves the policy’s robustness, allowing the robot quickly recover from perturbations using a variety of learned maneuvers. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Obstacle Identification Based on Deep Learning for Inspection Robot of FAST Wire Rope 2

Obstacle Identification Based on Deep Learning for Inspectio...

引用

2nd International Conference on Automation, robotics and Computer Engineering, ICARCE 2023

作者： Yang, Chengxu Sun, Xiangyu Liu, Gangfeng School of Mechatronics Engineering Harbin Institute of Technology Harbin China Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350308341

In this paper, for the requirements of image recognition and localization of the obstacles existing on the moving path in the inspection task of FAST cable inspection robot, the deep learning method is used to realize the recognition of multi-kind and multi-scale obstacles. The obstacles on FAST wire rope have not been identified before. By enhancing the data set and improving the network model, the recognition accuracy and speed are both improved, which meets the efficiency and accuracy requirements of obstacle detection on the wire rope, and provides help for the subsequent robot pace planning and overhaul tasks. © 2023 IEEE.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

Magnetic Actuated Shape-memory Helical Microswimmers with Programmable Recovery Behaviors

引用

Journal of Bionic Engineering 2021年第4期18卷 799-811页

作者： Fu Zhao Weibin Rong Lefeng Wang Lining Sun State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin150080China

Inspired by bacterial flagella in nature,magnetic helical microswimmer is an ideal model to perform complex task in a low Reynolds number *** Memory Polymers(SMPs)with desirable properties are considered as one of the most preferred options for the development of small-scale ***,fabricating and programming strategies are still ***,we report an approach to fabricate helical microswimmers based on thermoplastic SMP(polylactic acid).Melt-spun polylactic acid fibers containing magnetic particles were enwound to form helical *** shape recovery behaviors were programmed by annealing and *** forms of helical microswimmers(constant-helix-angle conical helix,constant-pitch conical helix,and straight helix)with controlled morphological parameters were *** obtained microswimmers showed 3D locomotion capability under rotating magnetic *** maximum swimming velocity of microswimmers was nearly six body lengths per second,and the near-wall swimming of conical helixes along their sharp end exhibited a smaller ***,we demonstrated programmed shape-switching processes(spring-like contraction and elongation,coiling and uncoiling)and self-repairing of the *** demonstrations of potential applications,tasks of mobile microstent,cargo delivery,and minimally invasive injection were carried *** multifunctional shape-memory microswimmers have immense potential in a variety of applications.

关键词： helical microrobot magnetic actuation Shape Memory Polymer(SMP) polylactic acid magnetic particles

来源：评论

学校读者我要写书评

暂无评论

A noncontact robot demonstration method with human supervision

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

Autonomous planning and control strategy for space manipulators with dynamics uncertainty based on learning from demonstrations

引用

Science China(Technological Sciences) 2021年第12期64卷 2662-2675页

作者： LI ChongYang LI ZhiQi JIANG ZaiNan CUI ShiPeng LIU Hong CAI HeGao State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Autonomous planning is a significant development direction of the space manipulator,and learning from demonstrations(LfD)is a potential strategy for complex tasks in the ***,separating control from planning may cause large torque fluctuations and energy consumptions,even instability or danger in control of space manipulators,especially for the planning based on the human ***,we present an autonomous planning and control strategy for space manipulators based on LfD and focus on the dynamics uncertainty problem,a common problem of actual *** process can be divided into three stages:firstly,we reproduced the stochastic directed trajectory based on the Gaussian process-based LfD;secondly,we built the model of the stochastic dynamics of the actual manipulator with Gaussian process;thirdly,we designed an optimal controller based on the dynamics model to obtain the improved commanded torques and trajectory,and used the separation theorem to deal with stochastic characteristics during *** evaluated the strategy with locating pre-screwed bolts experiment by Tiangong-2 manipulator system on the *** result showed that,compared with other strategies,the strategy proposed in this paper could significantly reduce torque fluctuations and energy consumptions,and its precision can meet the task requirements.

关键词： space manipulator optimal control dynamics uncertainty learning from demonstrations

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：