检索结果-内蒙古大学图书馆

HIT-Hawk and HIT-Phoenix: Two kinds of flapping-wing flying robotic birds with wingspans beyond 2 meters

Biomimetic Intelligence & robotics 2021年第1期1卷 13-25页

作者： Erzhen Pan Hui Xu Han Yuan Jianqing Peng Wenfu Xu The School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhen 518055China The State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Inspired by large and medium-sized birds,two kinds of flapping-wing flying robots with wingspans beyond 2 meters were *** have the appearance of a hawk and a phoenix respectively,so they are called HIT-Hawk and *** this paper,the bionic concept,theoretical analysis,design and manufacturing are introduced in ***,the flight principle and characteristics of large and medium-sized birds were ***,the aerodynamics was modeled based on the thin airfoil theory,and the main design basis was ***,the mechanical structures of HIT-Hawk and HIT-Phoenix were designed to ensure the lateral and longitudinal stability and have optimized flight ***,an autonomous flight control method was proposed and realized in highly integrated on-onboard controller;it satisfies the strict restrictions on mass,size,power and ***,the prototypes were fabricated and verified through practical flight *** wingspans of these two flapping wing aircrafts are 2.0 m and 2.3 m respectively,the take-off weights are 1.15 kg and 0.86 kg,and the maximum stable endurance is 65 min(with battery of 3S LiPo,4300 mAh)and 8 min(with battery of 3S LiPo,800 mAh).Their wind resistance can both reach level *** with the small and micro flapping-wing aerial vehicles that mimic insects or small birds,they both have strong load capacity,strong wind resistance and long endurance.

关键词： Bionic robots Flapping-wing flying Unmanned aerial vehicle Robotic bird

来源：评论

学校读者我要写书评

暂无评论

Continuous Path Tracking of Robots Based on Positioning Error Compensation With Iterative Learning Control

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Liu, Ying Li, Yuwen Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai201900 China East China Jiaotong University School of Mechatronics and Vehicle Engineering Nanchang330013 China

Due to the inaccuracy of absolute positioning, it is still challenging to apply industrial robots for precise and efficient tracking of the end-effector tool along a continuous path, especially for those frequently changing robotic operations within low-volume and high-mix scenarios. To overcome this problem, this work proposes a method of continuous path tracking of robots with iterative learning control (ILC) such that the pose errors of the tool along the path can be compensated by the robot. An optical tracking system is integrated to measure the tool pose. Developed from a comprehensive kinematic error model that incorporates errors in the Denavit-Hartenberg (D-H) parameters and errors induced by the installation of the robot base and the tool, the ILC algorithm can convert the tool pose error into the joint angle compensation for the robot. The robustness of the algorithm is analyzed to prove that the compensated path approaches the desired path as the number of iterations increases. An experimental test of continuous path tracking has been performed with a UR10 robot to validate the proposed method. It is demonstrated that the average and maximum position errors can be reduced from 14.57 and 20.31 to about 0.26 and 0.78 mm, respectively. The average and maximum orientation errors are reduced from 0.66° and 0.94° to about 0.08° and 0.20°, respectively. For a test of robotic laser cutting, the average dimensional accuracy of the rectangular workpiece can be reduced from 0.416 to about 0.154 mm, and the average shape accuracy is reduced from 0.101° to about 0.059°. Using the ILC algorithm and the measurement with the optical tracking system, our method can significantly enhance the tracking accuracy of the end-effector tool along continuous paths by autonomous adjustment of the joint angles without the need for human teaching. © 2025 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Fusing Dynamics and Reinforcement Learning for Control Strategy: Achieving Precise Gait and High Robustness in Humanoid Robot Locomotion*

Fusing Dynamics and Reinforcement Learning for Control Strat...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Zida Zhao Haodong Huang Shilong Sun Chiyao Li Wenfu Xu School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen and Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics China

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

Achieving precise gait planning and high robustness in locomotion control is crucial for the development and application of humanoid robots. In this paper, a novel control strategy is proposed, which combines dynamics control and reinforcement learning (RL), leveraging the precision of dynamics control and the robustness of RL. Specifically, foot placements for each step of the humanoid robot are designed, and the trajectories of the center of mass (CoM) and feet are obtained using a 3D linear inverted pendulum model (3D LIPM). Subsequently, joint angles during motion are calculated based on the trajectories of the CoM and feet using inverse kinematics equations. Finally, the obtained joint angles are trained as baseline actions using RL algorithms. To enhance control robustness, parameter domain randomization is introduced during the training process. By employing this control strategy, simulations of various single-step gaits, such as walking forward, walking to the right, and making right turns, are achieved. Additionally, trajectory tracking, locomotion tests on different terrains, and disturbance resistance are conducted. The simulation results demonstrate that the proposed control strategy enables precise gait control and exhibits strong robustness in humanoid robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sim-MEES: Modular End-Effector System Grasping Dataset for Mobile Manipulators in Cluttered Environments

arXiv

引用

arXiv 2023年

作者： Li, Juncheng Cappelleri, David J. The Multi-Scale Robotics & Automation Lab School of Mechanical Engineering Purdue University West LafayetteIN United States

In this paper, we present Sim-MEES: a large-scale synthetic dataset that contains 1,550 objects with varying difficulty levels and physics properties, as well as 11 million grasp labels for mobile manipulators to plan grasps using different gripper modalities in cluttered environments. Our dataset generation process combines analytic models and dynamic simulations of the entire cluttered environment to provide accurate grasp labels. We provide a detailed study of our proposed labeling process for both parallel jaw grippers and suction cup grippers, comparing them with state-of-the-art methods to demonstrate how Sim-MEES can provide precise grasp labels in cluttered environments. Copyright © 2023, The Authors. All rights reserved.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Driver Intention Prediction Using Text Prompts with In-Cabin and Out-Cabin Cameras

Driver Intention Prediction Using Text Prompts with In-Cabin...

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Bin He Ningmei Yu Hongcheng Han School of Automation and Information Engineering Xi'an University of Technology Xi’an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an China

ISBN: (数字)9798331506896

ISBN: (纸本)9798331506902

Human-machine collaborative driving is poised to become a cornerstone of intelligent transportation systems, where accurate recognition of driver behavior and intent is crucial for vehicle decision-making and real-time traffic management. Existing methods for driver maneuver recognition, primarily based on 3D convolutional neural networks (3D-CNNs) and Transformers, encounter challenges such as spatiotemporal redundancy, limited spatial perception, and inadequate capture of detailed object motion. To overcome these limitations, we propose a novel text-driven approach utilizing Large Language Models (LLMs) for driver maneuver recognition. By integrating textual semantics from both in-car and external environments, the Contrastive Language–Image Pre-training (CLIP) text encoder enhances the model's comprehension of complex video scenarios, improving both training and inference efficiency while enabling more precise identification of motion dynamics. Experimental results demonstrate that our approach outperforms state-of-the-art methods in driver intention prediction.

关键词： Training Accuracy Three-dimensional displays Target recognition Large language models Redundancy Transformers Spatiotemporal phenomena Vehicle dynamics Vehicles

来源：评论

学校读者我要写书评

暂无评论

MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion

arXiv

引用

arXiv 2024年

作者： Liu, Qi Guo, Jingxiang Lin, Sixu Ma, Shuaikang Zhu, Jinxuan Li, Yanjie The Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics The School of Mechanical Engineering and Automation The Harbin Institute of Technology Shenzhen518055 China

This paper proposes a novel method to improve locomotion for a single quadruped robot using multi-agent deep reinforcement learning (MARL). Many existing methods use single-agent reinforcement learning for an individual robot or MARL for the cooperative task in multi-robot systems. Unlike existing methods, this paper proposes using MARL for the locomotion of a single quadruped robot. We propose a learning structure called Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion (MASQ), considering each leg as an agent to explore the action space of the quadruped robot, sharing a global critic, and learning cooperatively. Experimental results show that MASQ not only speeds up learning convergence but also enhances robustness in real-world settings, suggesting that applying MASQ to single robots such as quadrupeds could surpass traditional single-robot reinforcement learning approaches. Our study provides insightful guidance on integrating MARL with single-robot locomotion. © 2024, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Balance Control for Lower Limb Exoskeleton based on the Center of Mass 12

Balance Control for Lower Limb Exoskeleton based on the Cent...

引用

12th International Conference on CYBER Technology in automation, Control, and Intelligent Systems, CYBER 2022

作者： Liu, Ligang Chen, Wanxin Li, Mengze Zhao, Jiawei Zhang, Bi Zhao, Xingang State Key Lab of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes of Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China College of Information Science and Engineering Northeastern University Shenyang China University of Chinese Academy of Sciences Beijing China School of Automation and Electrical Engineering Shenyang Ligong University Shenyang China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

This paper designs a compliance controller by imitating human walking characteristics, balance recovery strategy, and combining anomaly detection algorithm for lower limb exoskeleton. Our final goal is to run it on the lower limb exoskeleton. We first analyze the characteristics human balance control and introduce an anomaly detection algorithm based on One-Class Support Vector Machine (OCSVM). Then, according to the abnormal index, the controller is designed for each joint with the law of human joint activity. Finally, the results of human-exoskeleton experiment showed that the exoskeleton can balance recovery when the Center of Mass (CoM) of the human-exoskeleton system is over the range of balance. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Torque Optimization Strategy for Hip and Knee Joint of Passive Lower Limb Exoskeleton*

Torque Optimization Strategy for Hip and Knee Joint of Passi...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Yafei Ou Guangkui Song Rui Huang Chaobin Zou Zhinan Peng Xingzhong Xiong Jing Qiu Hong Cheng Artificial Intelligence Key Laboratory of Sichuan Province (AIKLSP) School of Automation and Information Engineering Sichuan University of Science and Engineering Yibin China Center for Robotics School of Automation Engineering University Electronic Science and Technology of China Chengdu China school of Mechanical Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Passive Lower Limb Exoskeleton (PLLE) have attracted extensive attention because it can help to participate in the application scenarios related to human functions. For the scenario of assisted stair climbing, the exoskeleton should have favorable and assisted torque to improve energy utilization efficiency. This paper studies a genetic algorithm-based auxiliary torque optimization strategy to find the optimal auxiliary torque of the exoskeleton hip joint and knee joint. And the simulation experiment based on the exoskeleton system verifies the effectiveness of the proposed strategy.

关键词： Legged locomotion Knee Torque Mechatronics Exoskeletons Stairs Springs Optimization Hip Robots

来源：评论

学校读者我要写书评

暂无评论

UAV Swarm Confrontation Based on Multi-agent Deep Reinforcement Learning 41

UAV Swarm Confrontation Based on Multi-agent Deep Reinforcem...

引用

第41届中国控制会议

作者： Zhi Wang Fan Liu Jing Guo Chen Hong Ming Chen Ershen Wang Yunbo Zhao Department of General Aviation Civil Aviation Management Institute of China School of Electronic and Information Engineering Shenyang Aerospace University College of Robotics Beijing Union University Department of Automation University of Science and Technology of China

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Multi-agent deep reinforcement learning(MADRL) has attracted a tremendous amount of interest in recent *** this paper,we introduce MADRL into the confrontation scene of Unmanned Aerial Vehicle(UAV) *** analysis the dynamic game process of UAV swarm confrontation,we build two non-cooperative game models based on MADRL *** using the multi-agent deep deterministic policy gradient(MADDPG) and the centralized training with decentralized execution method,we achieve the Nash equilibrium under 5 vs.5 UAV confrontation *** also introduce multi-agent soft actor critic(MASAC) method into the UAV swarm confrontation,simulation results indicate that the MASAC-based model outperforms the MADDPG-based model on exploring the UAV swarm combat environment,and more effectively converges to the Nash *** work will provide new insights into the confrontation of UAV swarm.

关键词： UAV Swarm Non-cooperative Game Multi-agent Deep Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Research on Visual Inspection Technology in Automatic Assembly for Manhole Cover of Rocket Fuel Tank 4

Research on Visual Inspection Technology in Automatic Assemb...

引用

4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022

作者： Zhang, Xiaolin Wang, Zanqin Yu, Hang Liu, Mei Xing, Baiqiang Harbin Institute of Technology School of Instrumentation Science and Engineering Harbin China Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing Robotics School of Mechatronic Engineering and Automation Shanghai China Capital Aerospace Machinery Corporation Limited Beijing China

ISBN: (数字)9781665458726

ISBN: (纸本)9781665458726

Manholes are openings on aerospace vehicles for people to enter the cabin for maintenance tasks. The covers of these openings are called manhole *** assembly quality of the manhole cover is related to the success or failure of refueling and flight in the rocket range. At present, the cover assembly is done manually, which is inefficient and error-prone. There is an urgent need for an automated assembly system, replacing manual assembly to complete the tasks. In this paper, an automatic assembly system for the manhole cover of rocket fuel tank is proposed and the visual inspection technology is mainly explained. The study uses machine vision and image processing with robots to meet actual assembly requirements, which is of great significance to assembly technology in the aerospace field. © 2022 IEEE.

关键词： Assembly

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：