检索结果-内蒙古大学图书馆

7th Asia-Pacific Conference on Intelligent Robot systems, ACIRS 2022

作者： Zou, Shourui Xi, Wei Guo, Xian Fang, Yongchun Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin China

ISBN: (数字)9781665485197

ISBN: (纸本)9781665485197

The snake robot is a biologically inspired robot with hyper-redundant joints. Though the locomotion control of the robot has been widely studied for decades, there are few works about the manipulation, which is more and more important. In this paper, a two-stage manipulation method is proposed by planning head raising locomotion and controlling the head pose of the snake robot. Specifically, the whole robot is divided into the ground part and the manipulation part, where the ground part is considered as the support polygon to maintain the stability during the head raising motion, and the manipulation part is considered as the manipulator to achieve tasks. The head raising motion planning is solved by nonlinear optimization and the head pose controller is designed by inverse kinematics. Finally the proposed method is verified through simulation. Results show that the head of the snake robot can reach any desired valid pose accurately. © 2022 IEEE.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Self-Aligning Knee Exoskeleton for Knee Extension Assistance during Walking 37

Design and Evaluation of a Self-Aligning Knee Exoskeleton fo...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Liu, Zhaoyuan Yin, Weihao Han, Jianda Zhang, Juanjuan Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300350 China

ISBN: (纸本)9781665465366

Exoskeletons can help people with impaired knee extensor function by providing assistance. Previous studies have shown that adding passive degrees of freedom to the knee exoskeleton can help reduce unwanted load on the knee joint. However, the problem of achieving passive degrees of freedom with low-weight structures has not been resolved. We designed and built a self-aligning knee exoskeleton which weighs 1.76kg and uses a slider-rail structure to add a passive degrees of freedom in the kinematic chain. The device was actuated by an off board motor to apply knee extension assist torque during walking. A magnetic connection device was designed to quickly connect the thigh and calf segments of the exoskeleton. The exoskeleton was evaluated on a healthy subject walking uphill at 0°, 2°, 4° and 6° slope with a setup assistance profile. The results indicated a decrease in rectus femoris, vastus medialis and vastus lateralis activity under assistance. The root mean squared (RMS) of the vastus medialis muscle activity decreased 21%, 25%, 24%, and 33% in each of the four conditions. These preliminary results show that the device has the capability to explore more assistance strategies to improve gait rehabilitation. © 2022 IEEE.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a Bionic Cable-driven Ankle Exoskeleton system for Human Walking Assistance 37

Evaluation of a Bionic Cable-driven Ankle Exoskeleton System...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Yin, Weihao Wang, Wei Ding, Jianquan Liu, Jingtai Zhang, Juanjuan Tianjin Key Laboratory of Intelligent Robotics Institute of Robotics and Automatic Information System Nankai University Tianjin300350 China

ISBN: (纸本)9781665465366

In order to further explore the performance of assistive exoskeleton, we tested and evaluated a bionic cable-driven ankle exoskeleton system for human walking assistance in this paper. A bionic ankle exoskeleton was used as an end-effector to provide many different patterns of assistance. Assistive forces were transmitted by a flexible Bowden cable which attached fewer moments of inertia to the wearer and minimized the impact of wearable devices on the wearer's natural movements. We preset the assistive torque trajectory according to biological ankle moment during walking and used a torque control method of proportional control with damping injection compensated by adaptive iterative learning to achieve high-performance torque control. We evaluated the kinematics and biological efforts of one subject with predefined assistance patterns. Assistance during walking on a treadmill reduced the metabolic cost by 10.34% compared with normal shoes. The root mean square (RMS) of the soleus muscle activity decreased by 52.2%, and ankle joint moment reduced by 40.4% with the same pattern. The experimental results show that the device is capable of improving walking economy. © 2022 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Estimation of Vehicle Sideslip Angle based on Modified Sliding Mode Observer and Recurrent Neural Network 7

Estimation of Vehicle Sideslip Angle based on Modified Slidi...

引用

7th Asia-Pacific Conference on Intelligent Robot systems, ACIRS 2022

作者： Song, Rui Fang, Yongchun Institute of Robotics and Automatic Information System Nankai University College of Artificial Intelligence Tianjin China

ISBN: (数字)9781665485197

ISBN: (纸本)9781665485197

It is well known that the knowledge of dynamic states is crucial for electronic stability control (ESC) and active safety system of automotive vehicles. In this paper, a novel method is established for the estimation of side slip angle in the presence of measurement noises and different road frictions. To begin with, a vehicle dynamic model and a tire model are exploited to reveal the relationship between tire road friction coefficient (TRFC) and sideslip angle. Furthermore, in order to eliminate the sensors error in the inertial measurement unit, a recurrent neural network is deployed by modeling the lateral motion and sensors measurement. Unlike conventional methods, a modified Sliding Mode Observer (MSMO) is proposed to manage the uncertainty brought by road conditions. Finally, the presented method is validated by co-simulations of Carsim and Matlab. The results show that the developed approach is robust to the abnormal measurement noise and different road friction coefficients. © 2022 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Fall Recognition based on Deep Learning Methods and Single Depth Image with Privacy Requirements 37

Real-Time Human Fall Recognition based on Deep Learning Meth...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Wang, Youwei Song, Rui Zhang, Xuebo College of Artificial Intelligence Institute of Robotics and Automatic Information System Nankai University Tianjin China

ISBN: (纸本)9781665465366

With the decline in physical function of the elderly, the risk of falling down increases and threatening their health. In the traditional fall recognition methods, multi-frame RGB image sequences are obtained to recognize falls, which may lead to problems of a high computational cost, real-time recognition, privacy leakages. In this paper, a novel fall recognition algorithm based on a single frame human binary image is proposed. Especially, the method is suitable for scenes with a basically unchanged background and privacy protection requirements, such as bathroom and toilet. The experimental results show that the precision and recall of the model achieves 97.3% and 99.4% on the public URFD dataset, which meets the practical application requirements. Furthermore, a posture recognition algorithm based on yolov5s and depth images is designed to distinguish between falling and lying down, which can be applied to bedrooms, living rooms and other places. On the basis of these algorithms, a depth image fall recognition software based on the flask framework is developed and deployed to the Alibaba cloud platform. Finally, the proposed fall recognition approach is validated by experiments and realized in real time. © 2022 IEEE.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Modeling and MPC-based balance control for a wheeled bipedal robot 41

Modeling and MPC-based balance control for a wheeled bipedal...

引用

第41届中国控制会议

作者： Haixin Cao Biao Lu Huawang Liu Rui Liu Xian Guo Institute of Robotics and Automatic Information System Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In recent years,wheeled bipedal robots have been widely researched as its flexible structures and superior *** the utilization of wheels,wheeled bipedal robots have the ability to move quickly on flat *** addition to this,they can cope with some complicated terrains by motors mounted on *** tasks have been achieved by wheeled bipedal robots such as trajectory tracking,carrying objects and leaping over *** whether the task is,the balance control is the basis of the subsequent *** this article,we established the dynamic equations of a wheeled bipedal robot on an inclined surface *** linearization and discretization around the equilibrium point,a model predictive controller(MPC) with input constraints is constructed to keep the balance of the *** order to deal with unmodeled dynamics and external disturbances,an extended state observer(ESO) is designed to enhance the robustness of the *** simulation results prove that the proposed control method can ensure the balance of the robot and has a satisfactory adaptability to external interference.

关键词： Wheeled Bipedal Robot Balance Control Model Predictive Control Extended State Observer

来源：评论

学校读者我要写书评

暂无评论

FT-TF: A 4D Long-Term Flight Trajectory Prediction Method Based on Transformer 42

FT-TF: A 4D Long-Term Flight Trajectory Prediction Method Ba...

引用

42nd Chinese Control Conference, CCC 2023

作者： Luo, Shijin Zhao, Minghui Zhao, Zhenjie Li, Lun Zhang, Shiyong 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

ISBN: (纸本)9789887581543

The accurate prediction of target aircraft trajectory in the process of air combat can significantly improve the ability of aircraft to gain air superiority. Most of the trajectory prediction methods currently applied in air combat are based on traditional time-series prediction algorithms such as LSTM with short prediction steps, which can not realize the demand for long-term prediction in air combat. To address the issue, a novel prediction method FT-TF is proposed in this paper. FT-TF is a multi-step 4D flight trajectory prediction method based on Transformer applied to further improve the accuracy and practicality of trajectory prediction problems. FT-TF uses the first 30 steps of aircraft historical trajectory data as input and the last 30 steps as output. Flight trajectory data sets of aircraft in air combat are used in the experiment to make the trained model closer to the real air combat scene. The experimental results show that the proposed FT-TF can achieve higher prediction accuracy than LSTM and BP neural network. Related Transformer variants of the algorithm are also added to the experiment for comparison, the results demonstrate that the proposed method achieves the smallest prediction error. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

G²VD Planner: Efficient Motion Planning With Grid-Based Generalized Voronoi Diagrams

引用

IEEE Transactions on Automation Science and Engineering 2024年 22卷 3743-3755页

作者： Jian Wen Xuebo Zhang Qingchen Bi Hui Liu Jing Yuan Yongchun Fang Institute of Robotics and Automatic Information System College of Artificial Intelligence and Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin China

In this paper, an efficient motion planning approach with grid-based generalized Voronoi diagrams (G2VD) is newly proposed for mobile robots. Different from existing approaches, the novelty of this work is twofold: 1) a new state lattice-based path searching approach is proposed, in which the search space is reduced to a novel Voronoi corridor to further improve the search efficiency; 2) an efficient quadratic programming-based path smoothing approach is presented, wherein the clearance to obstacles is considered to improve the path clearance of hard-constrained path smoothing approaches. We validate the efficiency and smoothness of our approach in various challenging simulation scenarios and outdoor environments. It is shown that the computational efficiency is improved by 17.1% in the path searching stage, and path smoothing with the proposed approach is 6.6 times faster than an advanced sparse-banded structure-based path smoothing approach and 53.3 times faster than the popular timed-elastic-band planner. A video showing outdoor navigation on our campus is available at https://***/iMXGthgvp58 . Note to Practitioners—This paper is motivated by the challenges of motion planning problems of mobile robots. An efficient motion planning approach called G2VD planner is proposed by combining path searching, path smoothing, and time-optimal velocity planning. Extensive simulation and experimental results show the effectiveness of the proposed motion planning approach. However, the prediction information of dynamic obstacles is not incorporated in the proposed motion planner, thus the motion planner may be a bit sluggish in response to dynamic obstacles. Furthermore, we plan to integrate the intention/trajectory prediction of pedestrians/vehicles into the proposed framework to enhance the foreseeability of the motion planner.

关键词： Smoothing methods Planning Robots Search problems Mobile robots Safety Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Reliable observer-based control against sensor failures for fractional order systems 41

Reliable observer-based control against sensor failures for ...

引用

第41届中国控制会议

作者： Bingxin Li Xiangfei Zhao Yaowei Liu Xin Zhao Institute of Robotics and Automatic Information System and the Tianjin Key Laboratory of Intelligent Robotics Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In the paper,the state and sensor failure observer for fractional order systems with order 0 <α <1 and 1 <α<2 is proposed to estimate the system state and sensor failures at the same *** general,unbounded sensor faults will inevitably lead to system ***,it is very necessary to study the reliable controller for fractional order systems against sensor *** the linear matrix inequality concept and the augmented system method,the sensor faults can be in any form,even unbounded.A reliable observer-based controller based on the state and sensor failures estimation is proposed,which can make the system work well regardless of whether the sensor *** α=1,methods proposed in the paper are equivalent to these of the integer order systems,scilicet,our methods can be extended to integer order ***,a simulation example is used to demonstrate the efficiency of the present methods.

关键词： Fractional order systems state and sensor failures linear matrix inequality reliable observer-based controller

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Methods for Fixed-Wing Aircraft Control 9

Reinforcement Learning Methods for Fixed-Wing Aircraft Contr...

引用

9th International Conference on systems and Informatics, ICSAI 2023

作者： Li, Lun Zhang, Xuebo Wang, Yang Qian, Chenxu Zhao, Minghui Nankai University Institute of Robotics and Automatic Information System Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin China Tianjin Municipal Data Management Center Tianjin China

ISBN: (纸本)9798350383706

In recent years, reinforcement learning (RL) has been widely researched for fixed-wing aircraft control, offering transformative potential for more adaptive, efficient, and autonomous flight operations. This paper presents a comprehensive analysis of the current state, advantages, challenges, and future prospects of employing RL in fixed-wing aircraft control. The advantages of RL include model-free, adaptive decision-making, and effectively solving complex nonlinear constraints, leading to increased efficiency and maneuverability in high-dynamic environments. However, significant challenges, such as the guarantee of stability and optimization, interpretability, and sim-to-real transferring, highlight areas necessitating further attention and development. Overcoming these challenges requires collaborative efforts among aviation experts, control theory experts, and machine learning researchers to ensure safe, reliable integration of RL in flight systems. As research and advancements continue, the RL holds promise for providing a more efficient, maneuverable, and autonomous strategy for controlling fixed-wing aircraft in the future. © 2023 IEEE.

关键词： Reinforcement learning

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：