检索结果-内蒙古大学图书馆

Reinforcement Learning Navigation for Robots Based on Hippocampus Episode Cognition

Journal of Bionic Engineering 2024年第1期21卷 288-302页

作者： Jinsheng Yuan Wei Guo Zhiyuan Hou Fusheng Zha Mantian Li Pengfei Wang Lining Sun State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150001China Shenzhen Academy of Aerospace Technology Shenzhen 518057China School of Mechanical and Electrical Engineering Lanzhou University of TechnologyLanzhou 730050China

Artificial intelligence is currently achieving impressive success in all ***,autonomous navigation remains a major challenge for *** learning is used for target navigation to simulate the interaction between the brain and the environment at the behavioral level,but the Artificial Neural Network trained by reinforcement learning cannot match the autonomous mobility of humans and *** hippocampus–striatum circuits are considered as key circuits for target navigation planning and *** paper aims to construct a bionic navigation model of reinforcement learning corresponding to the nervous system to improve the autonomous navigation performance of the *** ventral striatum is considered to be the behavioral evaluation region,and the hippocampal–striatum circuit constitutes the position–reward *** this paper,a set of episode cognition and reinforcement learning system simulating the mechanism of hippocampus and ventral striatum is constructed,which is used to provide target guidance for the robot to perform autonomous *** with traditional methods,this system reflects the high efficiency of learning and better Environmental *** research is an exploration of the intersection and fusion of artificial intelligence and neuroscience,which is conducive to the development of artificial intelligence and the understanding of the nervous system.

关键词： Episode cognition Reinforcement learning Hippocampus Robot navigation

来源：评论

学校读者我要写书评

暂无评论

Structural Design and Experiment of a Small Wheel-legged Mobile Robot with Variable Configuration 20

Structural Design and Experiment of a Small Wheel-legged Mob...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Cui, Xiulong Fan, Jizhuang Dong, Zhihui Ou, Yue Zhao, Jie Harbin Institute of Technology The State Key Laboratory of Robotics and System Harbin150001 China

ISBN: (纸本)9798350320831

In this paper, we made an improved design on the traditional quadruped robot structure and developed a new small wheel-legged mobile robot structure. It has four legged configurations, which can be selected according to different situations, improving the mobility and operability of the robot. In wheeled mode, the robot can adjust its center of gravity according to actual needs. Including the rotational degree of freedom of the wheel, each leg has four degrees of freedom. Each leg adopts a series structure and moves the knee drive motor to the fuselage position using a parallel four-link mechanism and is symmetrically arranged with the hip drive motor. A wheel is installed at the end of the shank, and a DC brushless motor is built inside it, enabling the robot to have the function of wheeled motion. This article introduces the details of the wheel-legged robot, emphasizing the innovative design of the physical structure and the diversity of deformation. The forward kinematics was analyzed. Based on the full-elbow configuration (a type of legged configuration), a cycloidal motion optimization simulation was completed for the single leg structure. Simulation experiment has proven that the optimized robot's single leg motion is smoother. Finally, we conducted a typical experiment using an embedded controller to control single leg motion. The experimental results verify that the optimized cycloidal motion of the robot meets the desired motion effect. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

RGB-D Camera Based Map Building and Path Planning of Snake Robot 16th

RGB-D Camera Based Map Building and Path Planning of Snake R...

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Sun, Yongjun Wang, Qiang Xue, Zhao Liu, Rongqiang Liu, Hong State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9789819964826

Snake robot is a robot that can move freely in a small and complex space with super-redundant DOF and motion flexibility, and it has been proven to have a wide range of application prospects. RGB-D camera is a new type of visual sensor that can directly obtain color images and depth information. To enable the snake robot to work in some special task environments, we developed an orthogonal modular snake robot using RGB-D cameras, and conducted research on snake robot map building and path planning. An improved Batch Informed Tree (BIT*) algorithm is proposed. Finally, to verify the effectiveness of the proposed method, a corresponding experimental program is designed and related experimental analysis is carried out. The results show that our designed snake robot can complete the task of map building and path planning. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Quasi-Direct-Drive Legs for a Frog-Like Jumping Robot 3

Design and Implementation of Quasi-Direct-Drive Legs for a F...

引用

3rd International Conference on Computer, Control and robotics, ICCCR 2023

作者： Zhihui, Dong Jizhuang, Fan Qilong, Du Jie, Zhao Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin150001 China

ISBN: (纸本)9781665492126

This study aims to design and optimize a motor-driven frog-like jumping robot leg for efficient vertical jumps and multiple consecutive horizontal jumps. We have conducted bionic research on frog legs' structure and motion characteristics and further explored their motion mechanism, providing new ideas and methods for designing and manufacturing robots with high mobility and adaptability. First, our research team designed a robot leg prototype based on the frog's body structure, optimized the robot using computer-Aided design software, and selected a suitable motor-driven actuator. Secondly, the weight reduction optimization of the robot body is carried out regarding material selection and topology optimization to improve the robot's maneuverability and jump height. Finally, after manufacturing the prototype of the robot legs, the robot is experimentally verified. The results show that the robot legs can achieve efficient vertical jumps (the maximum height is 1.40 meters, about 7.8 times the length of the leg link). It can also jump multiple times consecutively, which is significant for applying robots in dangerous environments, search and rescue, and other fields. © 2023 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Aerodynamic Analysis and Deployment Mechanism of A Foldable Mars Quadrotor 20

Aerodynamic Analysis and Deployment Mechanism of A Foldable ...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Zhu, Kaijie Tang, Dewei Quan, Qiquan Wang, Kaiyi Dong, Yachao Deng, Zongquan Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin150001 China

ISBN: (纸本)9798350320831

The Mars quadrotor is a vertical take-off and landing aerial platform developed to enhance the efficiency of Mars exploration. The four-blade rotor has a high thrust coefficient due to its high solidity, which enables the quadrotor to navigate the Martian atmospheric environment efficiently. This paper proposes a payload-carrying Mars quadrotor featuring four four-bladed rotors that can fold along the rotor arms. The computational fluid dynamics (CFD) method is employed to perform numerical hovering simulations, exploring the propulsion capability and aerodynamic efficiency of rotors with different diameters. The mass distribution and hovering time are estimated when the quadrotor consists of the rotors with the highest figure of merit. The results demonstrate that a larger rotor diameter of the quadrotor yields greater payload capacity and shorter hovering time. During the launch, the quadrotor is folded and constrained within an envelope to protect it from vibrations and shocks. A lifting mechanism with shape-constraint slides is utilized for quadrotor deployment. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Torque Ripple Suppression Under Open-Circuit Fault for DTPPMSM Considering Back EMF Harmonics

Torque Ripple Suppression Under Open-Circuit Fault for DTPPM...

引用

2023 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2023

作者： Liu, Chengsi Zou, Jibin Harbin Institute of Technology Hit State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350301571

This paper analyzed the impact of phase back electromotive force (back EMF) harmonics on torque of dual three phase permanent magnet synchronous motor (DTPPMSM) from the view of electromagnetic power, and proposed a torque ripple suppression fault-tolerant method for open-circuit fault of DTPPMSM. The proposed method can consider the phase back EMF harmonics, thus achieveing both minimum torque ripple and maximum average torque. The proposed method is verified by both finite element analysis (FEA) and prototype experiment. © 2023 IEEE.

关键词： Dual three phase permanent magnet synchronous motor (DTPPMSM) fault-tolerant finite element analysis (FEA) open circuit

来源：评论

学校读者我要写书评

暂无评论

Watt Linkage–Based Legged Deployable Landing Mechanism for Reusable Launch Vehicle: Principle, Prototype Design, and Experimental Validation

引用

Engineering 2023年第1期20卷 120-133页

作者： Haitao Yu Baolin Tian Zhen Yan Haibo Gao Hongjian Zhang Huiqiang Wu Yingchao Wang Yuhong Shi Zongquan Deng State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150080China Beijing Institute of Aerospace Systems Engineering Beijing 100076China

The reusable launch vehicle (RLV) presents a new avenue for reducing cost of space transportation. The landing mechanism, which provides landing support and impact absorption, is a vital component of the RLV at final stage of recovery. This study proposes a novel legged deployable landing mechanism (LDLM) for RLV. The Watt-II six-bar mechanism is adopted to obtain the preferred configuration via the application of the linkage variation approach. To endow the proposed LDLM with advantages of large landing support region, lightweight, and reasonable linkage internal forces, a multi-objective optimization paradigm is developed. Furthermore, the optimal scale parameters for guiding the LDLM prototype design is obtained numerically using the non-dominated sorting genetic algorithm-II (NSGA-II) evolutionary algorithm. A fully-functional scaled RLV prototype is developed by integrating the gravity-governed deploying scheme to facilitate unfolding action to avoid full-range actuation, a dual-backup locking mechanism to enhance reliability of structure stiffening as fully deployed, and a shock absorber (SA) with multistage honeycomb to offer reliable shock absorbing performance. The experimental results demonstrate that the proposed LDLM is capable of providing rapid and smooth deployment (duration less than 1.5 s) with mild posture disturbance to the cabin (yaw and pitch fluctuations less than 6°). In addition, it provides satisfactory impact attenuation (acceleration peak less than 10g (g is the gravitational acceleration)) in the 0.2 m freefall test, which makes the proposed LDLM a potential alternative for developing future RLV archetype.

关键词： Reusable launch vehicle(RLV) Deployable mechanism Optimization desi gn

来源：评论

学校读者我要写书评

暂无评论

Fast-convergent model predictive control of omni-directional mobile robots

引用

International Journal of systems, Control and Communications 2023年第2期14卷 148-167页

作者： Hu, Yin Zhao, Minghui Zhang, Xuebo Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin300350 China Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin300350 China

Omni-directional wheeled mobile robots (OWMRs) present high manoeuvrability and can move in all directions of the plane. However, for active-caster-type OWMRs (ACT-OWMRs), satisfying physical constraints of multiple motors is challenging. To guarantee motor constraints and improve the tracking control performance, a new model predictive control (MPC)-based controller termed as ‘MPC-FCR’ is designed, which embeds a real-time fast-convergent trajectory planner to generate high efficient gentle reference trajectory. Such a framework has two main advantages. First, the gentle trajectory generation module is formulated as a constrained optimisation problem, which can achieve fast convergence performance while satisfying the robot constraints. Second, both motor and robot constraints are considered in MPC-FCR control law. The proposed MPC-FCR is implemented to achieve real-time performance within a control period of 20 milliseconds. Experimental results show the superior performance of MPC-FCR in terms of convergence speed and the capability to handle physical constraints, compared with the classical controller. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Collaborative Teaching with Attention Distillation for Multiple Cross-Domain Few-Shot Learning 14

Collaborative Teaching with Attention Distillation for Multi...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent systems, CYBER 2024

作者： Shang, Zhenduo Liu, Xiyao Xie, Xing Han, Zhi State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences The Institutes for Robotics and Intelligent Manufacturing The University of Chinese Academy of Sciences China Shenyang Institute of Automation Chinese Academy of Sciences The Institutes for Robotics and Intelligent Manufacturing State Key Laboratory of Robotics China

ISBN: (纸本)9798331506056

Multiple Cross-Domain Few-Shot Learning (MCD-FSL) aims to improve the generalization ability of the model across unseen domains by utilizing the diverse knowledge of different teacher networks. Knowledge transferring among multiple domains is complex and difficult due to significantly different data distributions. In current tasks, effectively utilizing knowledge from multiple domains to improve model generalization in an unseen domain remains challenging. Therefore, we propose Collaborative Teaching with Attention Distillation (CTAD-Net), exploring a collaborative strategy among multiple teacher networks of teachers to address this issue. Specifically, we introduce a weight allocation (WA) module and a deep fusion (DF) module for distilling knowledge from the teacher networks to a single student network. Additionally, our CTAD-Net combines attention mechanisms and employs both response-based and relation-based knowledge distillation to transfer more comprehensive and effective knowledge. The experimental results on four fine-grained datasets have demonstrated the effectiveness of our proposed CTAD-Net approach. © 2024 IEEE.

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

Construction and manipulation of origami-inspired tubular structures with controlled mechanical buckling for collection and transportation of microspheres based on optically induced electrokinetics

引用

Science China(Technological Sciences) 2024年第9期67卷 2954-2964页

作者： YANG WenGuang WANG WenHao TENG XiangYu QIAO ZeZheng YU HaiBo School of Electromechanical and Automotive Engineering Yantai UniversityYantai 264005China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China

The development of microengineered hydrogels has opened up unlimited possibilities for designing complex structures at the microscale. In this study, we constructed an origami-inspired tubular structure with controlled mechanical buckling based on optically induced electrokinetics(OEK). By inducing a stress gradient in the thickness, a tubular structure can be formed from a poly(ethylene glycol) diacrylate(PEGDA) hydrogel film of various shapes that have been custom fabricated. To achieve an ideal three-dimensional(3D) structure, the amplitude of the tubular structure can be controlled by adjusting the aspect ratios or polymerization time. Furthermore, the tubular structure can be manipulated for the collection and transportation of *** summary, we provide an effective method for designing 3D structures at the micro-nano scale. This forming method holds great potential for achieving various functions in tissue engineering, drug packaging, and transportation in the future.

关键词： origami-inspired tubular structures optically induced electrokinetics microfabrication mechanical buckling

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：