The proceedings contain 85 papers. The topics discussed include: a hybrid method for INS/GPS integrated navigation system based on the improved Karman filter and back propagation neural network;development of Simulink...
ISBN:
(纸本)9798350344721
The proceedings contain 85 papers. The topics discussed include: a hybrid method for INS/GPS integrated navigation system based on the improved Karman filter and back propagation neural network;development of Simulink-based physical experiment platform for EtherCAT bipedal robots;a biogeography-based optimization algorithm with heuristics for distributed multiproduct scheduling problem;research on low energy consumption AC system control strategy of battery electric vehicles;flyback converter modeling and overload control characteristics for power supply based on state space averaging;a simple confidence-supervised model for high resolution defect recognition;research and development of intelligent warehouse management system based on RFID technology;research on methods of vehicle image retrieval in expressway scenarios based on deep learning neural network;and motion simulation control system of detecting robot based on digital twin.
This paper designs a wind turbine cabin inspection robot system, which comprises three components: the robot body, the communication system, and the monitoring software. The robot body features an elliptical track and...
详细信息
In this paper, an automatic cigarette appearance defect detection system based on deep learning algorithm is proposed, aiming to improve the defect detection efficiency and accuracy in the cigarette production process...
详细信息
ISBN:
(纸本)9798350377040;9798350377033
In this paper, an automatic cigarette appearance defect detection system based on deep learning algorithm is proposed, aiming to improve the defect detection efficiency and accuracy in the cigarette production process. By using a pre-trained ResNet18 network model, the system automatically identifies defective products in the cigarette production line. We trained and validated the model on the dataset, and showed the trends of the loss function and accuracy during the training process. The experimental results show that the model can effectively recognize multiple cigarette defects, especially in handling broken and deformed defects, and exhibits high accuracy and robustness. The study shows that the application of deep learning-based defect detection technology in cigarette production has significant potential and can provide intelligent solutions for quality control.
Grasp detection is an essential task in robotics with various industrial applications. However, traditional methods often struggle with occlusions and do not utilize language for grasping. Incorporating natural langua...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Grasp detection is an essential task in robotics with various industrial applications. However, traditional methods often struggle with occlusions and do not utilize language for grasping. Incorporating natural language into grasp detection remains a challenging task and largely unexplored. To address this gap, we propose a new method for language-driven grasp detection with mask-guided attention by utilizing the transformer attention mechanism with semantic segmentation features. Our approach integrates visual data, segmentation mask features, and natural language instructions, significantly improving grasp detection accuracy. Our work introduces a new framework for language-driven grasp detection, paving the way for language-driven robotic applications. Intensive experiments show that our method outperforms other recent baselines by a clear margin, with a 10.0% success score improvement. We further validate our method in real-world robotic experiments, confirming the effectiveness of our approach.
With the widespread use of distributed systems, multi-subspace whole-flow industrial monitoring methods are evolving. However, due to the lack of distinctive features, incipient faults in plant-wide processes are more...
详细信息
ISBN:
(纸本)9798350364200;9798350364194
With the widespread use of distributed systems, multi-subspace whole-flow industrial monitoring methods are evolving. However, due to the lack of distinctive features, incipient faults in plant-wide processes are more difficult to detect. To improve the detection rate of incipient faults in plant-wide processes while maintaining the generality of the algorithm, a novel double-layer subspace weighted moving window reconstruction independent component analysis (DS-WRICA) method is proposed. In DS-WRICA, process variables are first divided into different subspaces based on process knowledge and data-driven partitioning methods. Secondly, a weighted moving window is used to increase the offset of incipient faults, and monitoring statistics are constructed by combining optimized reconstructed independent component analysis (RICA) and local outlier factor (LOF) in each subspace. Then, the monitoring statistics in each subspace are fused with information by Bayesian inference fusion method to obtain distributed monitoring results. Finally, the effectiveness and superiority of the DS-WRICA method are verified by industrial examples.
Path planning processes in 3D environments with obstacles are essential for ensuring the successful navigation of Unmanned Aerial Vehicles (UAVs). Recently, the artificial intelligence theory presents increasingly eff...
详细信息
ISBN:
(纸本)9798350367607;9798350367591
Path planning processes in 3D environments with obstacles are essential for ensuring the successful navigation of Unmanned Aerial Vehicles (UAVs). Recently, the artificial intelligence theory presents increasingly effective algorithms and tools to address such a robotics challenge. This paper presents a comparative study of two most commonly used Reinforcement Learning (RL) algorithms, namely Q-learning and SARSA learning. Through numerical experimentations under different navigation scenarios with varying levels of complexity and increasing numbers of static obstacles, key performance metrics like path's length, total actions number, average reward, execution time and collision avoidance are considered and evaluated. The demonstrative results indicate that the Q-learning algorithm well addressed the challenges of UAVs' path planning in static environments. The performance of such an algorithm has proven to be satisfactory and more promising for UAVs' navigation in complex configuration spaces when compared to the SARSA algorithm.
automatic license plate recognition (ALPR) is a powerful tool for analyzing the growing number of vehicles in major cities worldwide. However, building datasets that accurately represent vehicles and license plates (L...
详细信息
ISBN:
(纸本)9798350373981;9798350373974
automatic license plate recognition (ALPR) is a powerful tool for analyzing the growing number of vehicles in major cities worldwide. However, building datasets that accurately represent vehicles and license plates (LPs) is challenging, as most current datasets are specific to certain countries and do not provide a comprehensive representation. This remains particularly true for French LPs, where there is currently no publicly available dataset that covers a wide range of scenarios such as plate inclinations, varying lighting conditions, and changing weather. To address this issue, we present a benchmark suite called PGFLP 1.0, which includes more than 14k fully annotated LPs from several vehicle categories (e.g. cars, trucks, motorcycles). PGFLP 1.0 includes three annotation levels: rectangular boxes for the LP, four vertices of the LP region, and labels for the full LP sequence. Using PGFLP 1.0, we provide an experimental evaluation of the most recent ALPR approaches, assessing their ability to detect and recognize LPs. This work provides a useful benchmark in terms of accuracy and speed for current and future research efforts in ALPR.
Continuum robots with soft, deformable and multi-degree-of-freedom features can adapt to complex environments and perform tasks flexibly, therefore, gradually reflecting important application values in minimally invas...
详细信息
ISBN:
(纸本)9789819607792;9789819607808
Continuum robots with soft, deformable and multi-degree-of-freedom features can adapt to complex environments and perform tasks flexibly, therefore, gradually reflecting important application values in minimally invasive surgery, deep cavity exploration and other fields. To enable continuum robots to perform tasks dexterously and adaptively in complex environments, their motion control is crucial. Traditional model-based control methods require accurate system modelling, have high environmental and structural requirements, and face real-time and computational complexity challenges. With the continuous development of robotics, model-free control and hybrid-model control have become two important approaches to solve the motion control problems of continuum robots. This review systematically summarizes the current status of research on model-free and hybrid-model control for continuum robots in recent years, and discusses in depth the advantages and disadvantages as well as the challenges of the various methods, so as to provide guidance for the coming followers, and to promote the further development and application of continuum robots.
One of the challenging research issues in building construction is using robot for reducing people's labor intensity. This paper develops a cement mortar scraping robot which can scrape a whole wall in one time wi...
详细信息
ISBN:
(纸本)9798350388084;9798350388077
One of the challenging research issues in building construction is using robot for reducing people's labor intensity. This paper develops a cement mortar scraping robot which can scrape a whole wall in one time without operator invention. In this paper, the mechanical and electrical structure of the robot is described, and the algorithm of the omnidirectional movement algorithm is given. The robot is tested in construction site, and the result shows that it can reduce people's labor intensity and improve work efficiency significantly.
The proceedings contain 70 papers. The topics discussed include: Frustum PointVoxel-RCNN: a high-performance framework for accurate 3D object detection in point clouds and images;design of intelligent pet drying syste...
ISBN:
(纸本)9798350373141
The proceedings contain 70 papers. The topics discussed include: Frustum PointVoxel-RCNN: a high-performance framework for accurate 3D object detection in point clouds and images;design of intelligent pet drying system based on OpenMv;a multimodal knowledge representation method for fake news detection;computer and vision aided mapping in farmer's market and visually aided shopping strategy for visually impaired individuals;knowledge exploring on the medication regularity of the infectious fever treatment in Wai Tai Mi Yao based on cluster analysis and association rules;comparative analysis of deep learning-based defect monitoring in metal additive manufacturing;simulation analysis of two-phase flow field in robotic sand blasting with aluminum alloy car body;and a reinforcement learning driven iterated greedy algorithm for energy-efficiency flexible job-shop scheduling problem.
暂无评论