检索结果-内蒙古大学图书馆

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

来源：评论

学校读者我要写书评

暂无评论

NNPP: A Learning-Based Heuristic Model for Accelerating Optimal Path Planning on Uneven Terrain

arXiv

引用

arXiv 2023年

作者： Ji, Yiming Liu, Yang Xie, Guanghu Ma, Boyu Xie, Zongwu Cao, Baoshi State Key Laboratory of Robotics and System Harbin Institute of Technology Heilongjiang Harbin150001 China

Intelligent autonomous path planning is essential for enhancing the exploration efficiency of mobile robots operating in uneven terrains like planetary surfaces and off-road environments. In this paper, we propose the NNPP model for computing the heuristic region, enabling foundation algorithms like A* to find the optimal path solely within this reduced search space, effectively decreasing the search time. The NNPP model learns semantic information about start and goal locations, as well as map representations, from numerous pre-annotated optimal path demonstrations, and produces a probabilistic distribution over each pixel representing the likelihood of it belonging to an optimal path on the map. More specifically, the paper computes the traversal cost for each grid cell from the slope, roughness and elevation difference obtained from the digital elevation model. Subsequently, the start and goal locations are encoded using a Gaussian distribution and different location encoding parameters are analyzed for their effect on model performance. After training, the NNPP model is able to accelerate path planning on novel maps. Experiments demonstrate that the heuristic region generated by the NNPP model achieves a 3×speedup for optimal path planning under identical hardware conditions. Moreover, the NNPP model’s advantage becomes more pronounced as the size of the map increases. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Novel Gait Pattern Recognition Method Based on LSTM-CNN for Lower Limb Exoskeleton

引用

Journal of Bionic Engineering 2021年第5期18卷 1059-1072页

作者： Chao-feng Chen Zhi-jiang Du Long He Yong-jun Shi Jia-qi Wang Wei Dong State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150001China China South Industries Group Corporation Weapon Equipment Research InstituteBeijing 102202China

This paper describes a novel gait pattern recognition method based on Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN)for lower limb *** Inertial Measurement Unit(IMU)installed on the exoskeleton to collect motion information,which is used for LSTM-CNN *** article considers five common gait patterns,including walking,going up stairs,going down stairs,sitting down,and standing *** the LSTM-CNN model,the LSTM layer is used to process temporal sequences and the CNN layer is used to extract *** optimize the deep neural network structure proposed in this paper,some hyperparameter selection experiments were carried *** addition,to verify the superiority of the proposed recognition method,the method is compared with several common methods such as LSTM,CNN and *** results show that the average recognition accuracy can reach 97.78%,which has a good recognition eff ***,according to the experimental results of gait pattern switching,the proposed method can identify the switching gait pattern in time,which shows that it has good real-time performance.

关键词： Lower limb exoskeleton Gait pattern recognition LSTM-CNN Recognition accuracy Real-time performance

来源：评论

学校读者我要写书评

暂无评论

Inverse Kinematics of a Reconfigurable Space Manipulator Based on the Closed-Loop Algorithm

Inverse Kinematics of a Reconfigurable Space Manipulator Bas...

引用

IEEE International Conference on Mechatronics and Automation

作者： Zhiyuan Zhao Xiaohang Yang Zichun Xu Yuntao Li Zhonglai Tian Jingdong Zhao State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin Heilongjiang Province China

This paper investigates a reconfigurable space manipulator’s inverse kinematics (IK) with two lockable passive telescopic links (LPTLs). Depending on these LPTLs’ locking state, the manipulator includes free-space and reconfiguration operation modes. Firstly, we introduce a new ball joint-based solution for the reconfigurable operation mode. Then, we propose an IK simplified method capable of significantly reducing the computational load of the complex inverse differential kinematic (IDK) equations corresponding to the two operation modes. Next, to solve the resulting simplified IDK equations efficiently, we present an IK solution method based on the closed-loop algorithm. This method is developed to resolve the redundancy at the velocity level and can generate highly accurate and smooth trajectory IK solutions that satisfy the joint limit constraints. Finally, we design two typical case studies corresponding to working scenarios of the manipulator during two operation modes. Their simulation results validate the proposed methods’ effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review:Wearable Sweat Sensors for Diseases Prevention and Monitoring

引用

Journal of Harbin Institute of Technology(New Series) 2023年第3期30卷 1-21页

作者： Yanan Ding Haiying Xiao Ping’an Hu School of Chemistry and Chemical Engineering Harbin Institute of TechnologyHarbin 150080China MOE Key Lab of Micro-System and Micro-Structures Manufacturing Harbin Institute of TechnologyHarbin 150080China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150080China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150080China

Advanced in wireless technologies and flexible materials with great biocompatibility,wearable devices have been utilized in the field of healthcare,sports management,and diseases prevention,which have been widely applied in current electronic ***,as a common metabolite on the skin surface,contains a wealth of biomarkers for disease detection and ***,developing wearable sweat sensors can provide a non⁃invasive method for health data collecting,sports monitoring,and clinical diagnosis in a convenient *** research in sweat metabolomics has offered a lot of information for sweat analysis and the wearable sweat sensors with small size,various sensing,and transmission units,and good skin contact has exhibited dynamic multi⁃signal *** article introduces the biomarkers in sweat related to different diseases and the current development of sweat sensors for user􀆳s activation monitoring and diseases *** barriers and difficulties in the future are also discussed and perspectives in the next generation sweat sensors are proposed.

关键词： sweat sensor sweat metabolites disease monitoring wearable device

来源：评论

学校读者我要写书评

暂无评论

TRUSTS: A novel treadmill-based multifunctional testing system for performance evaluation of wheeled planetary exploration rover

引用

robotics and Autonomous systems 2023年 164卷

作者： Yu, Haitao Chen, Jian Pan, Dong Gao, Haibo State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China Beijing Institute of Spacecraft System Engineering Beijing100094 China

This paper presents a novel treadmill-based multifunctional testing system (TRUSTS) to execute ground testing for wheeled planetary exploration rover (WPER) in both regular and extreme physical conditions before launching. The TRUSTS with specially-made components featuring compact structure and multifunctional testing items comprises a traction loading subsystem (TLS) and a treadmill-based resistance torque loading subsystem (TRTLS). The former offers the working modes including traction loading, position holding, and range limiting. The latter offers working modes including resistance torque loading and leader–follower tracking. By appropriately allocating the working modes of two subsystems, the TRUSTS is capable of conducting diverse testing items. The customized controllers for the TLS and the TRTLS are proposed to guarantee the operation performance of the TRUSTS in all testing items. Extensive experimental results on a Mars rover prototype in both regular and extreme physical conditions demonstrate that the devised TRUSTS could effectively executing trafficability and maneuverability as well as adaptability tests with reliable scenarios and satisfactory precisions of motion tracking and traction/torque loading, which makes the TRUSTS a favorable choice for comprehensive performance assessment of rover in simulant extraterrestrial environment. © 2023 Elsevier B.V.

关键词： Sporting goods

来源：评论

学校读者我要写书评

暂无评论

Energy-Consumption Optimization Control for Lunar Rover's Travel with Torque-Distribution-strategy in Rear Wheels

Energy-Consumption Optimization Control for Lunar Rover's Tr...

引用

IEEE International Conference on Control Science and systems Engineering (CCSSE)

作者： Delun Li Jianfei Cao Yiliang Chen Zongwu Xie State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing China

ISBN: (数字)9798331517199

ISBN: (纸本)9798331517205

In anticipation of future extensive lunar surface operations, lunar rovers are required to advance towards higher speeds and improved energy conservation. When traveling at high speeds on the lunar surface, the vehicle's energy expenditure is greatly amplified by the influence of the terrain, particularly in conditions where driving and steering are coupled. This paper proposes an energy-saving control strategy for lunar rovers that employs dynamic rear-axle torque distribution, with the goal of optimizing transient energy consumption during travel. To tackle the challenge of non-differentiable functions within the optimization objectives, we suggest using a zeroth-order gradient optimization method for resolution, dynamically constraining the range of control parameters to fulfill the dynamic torque distribution objectives as needed for the task. The energy-saving control effectiveness of the algorithm has been confirmed through simulation, demonstrating a minimum energy-saving ratio of at least 4%, which increases to over 11% as the speed level rises, offering a valuable technical solution for the energy optimization of lunar rovers.

关键词： Space vehicles Energy consumption Torque Distribution strategy Moon Wheels Optimization methods systems engineering and theory Vehicle dynamics Transient analysis

来源：评论

学校读者我要写书评

暂无评论

MC-Tac: Modular Camera-Based Tactile Sensor for Robot Gripper 16th

MC-Tac: Modular Camera-Based Tactile Sensor for Robot Gripp...

引用

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

作者： Ren, Jieji Zou, Jiang Gu, Guoying Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China School of Mechanical Engineering State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9789819964949

Camera-based tactile sensors provide a convenient and low-cost approach for robot tactile perception. However, existing sensors are customized and only suit limited robots, which retards tactile applications. In this work, we proposed a modular design for camera-based tactile sensor to facilitate their integration on various robot grippers and fingers. Specifically, we disassemble tactile sensors into sense module for sensing surface interaction, receptor module for arranging camera, illumination, and structure elements, and adapter module for connection with robot gripper. Experiments show the proposed sensors can adopt various robot grippers and achieve high tactile perception performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

PI2-CMA Based Trajectory Planning Method for the Tractor-Trailer Vehicle 6

PI2-CMA Based Trajectory Planning Method for the Tractor-Tra...

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Wang, You Wang, Zehao Wang, Jingchuan Guo, Rui Xiao, Peng Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Institute of Medical Robotics and Department of Automation Shanghai200240 China State Grid Intelligence Technology CO. LTD China

ISBN: (纸本)9798350325485

The motion primitive-based state lattice trajectory planning method has been widely used in the field of trajectory planning. However, due to the limitations of the search space and resolution of motion primitives, and the lack of consideration of scenario information during offline generation of motion primitives, the tractor-Trailer vehicles can easily fall into "jackknife phenomenon"when making large pose adjustments in narrow scenarios, which brings dilemma for trajectory planning. In this paper, a trajectory planning algorithm is proposed based on a general model of tractor-Trailer vehicle, which combines global planning and local optimization. The method first generates a series of motion primitives, including forward and backward driving conditions, and then an A based global state lattice planner is used to obtain a planning result, which is imported as the initial solution into the local trajectory optimizer based on PI2-CMA (Path Integral Policy Improvement with Covariance Matrix Adaptation) algorithm and dynamic potential method. Experiments show that this method significantly improves the performance in the obstacle avoidance, "jackknife phenomenon"avoidance and curvature compared to traditional motion primitive-based state lattice planning methods. © 2023 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Realizing high-speed target tracking by using multi-rate feedforward predictive control for the acquisition, tracking, and pointing system

引用

Defence Technology 2025年

作者： Li, Hang Peng, Gaoliang Shan, Xiaobiao Zhao, Mingyuan Zhang, Wei Wang, Jinghan Cheng, Feng State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China College of Information Science and Technology Eastern Institute of Technology Ningbo315200 China

The acquisition, tracking, and pointing (ATP) system is widely used in target tracking, counter-UAV operations, and other related fields. As UAV technology develops, there is a growing demand to enhance the tracking capabilities of ATP systems. However, in practical applications, ATP systems face various design constraints and functional limitations, making it infeasible to indefinitely improve hardware performance to meet tracking requirements. As a result, tracking algorithms are required to execute increasingly complex tasks. This study introduces a multi-rate feedforward predictive controller to address issues such as low image feedback frequency and significant delays in ATP systems, which lead to tracking jitter, poor tracking performance, low precision, and target loss. At the same time, the proposed approach aims to improve the tracking capabilities of ATP systems for high-speed and highly maneuverable targets under conditions of low sampling feedback rates and high feedback delays. The method suggested is also characterized by its low order, fast response, and robustness to model parameter variations. In this study, an actual ATP system is built for target tracking test, and the proposed algorithm is fully validated in terms of simulation and actual system application verification. Results from both simulations and experiments demonstrate that the method effectively compensates for delays and low sampling rates. For targets with relative angular velocities ranging from 0 to 90°/s and angular accelerations between 0 and 470°/s2, the system improved tracking accuracy by 70.0%–89.9% at a sampling frequency of 50 Hz and a delay of 30 m s. Moreover, the compensation algorithm demonstrated consistent performance across actuators with varying characteristics, further confirming its robustness to model insensitivity. In summary, the proposed algorithm considerably enhances the tracking accuracy and capability of ATP systems for high-speed and highly maneuverable ta

关键词： Predictive control systems

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：