To realize the autonomous navigation of mobile robots, this study built a new robot autonomous navigation system by improving the Gmapping algorithm. The new system uses the Gmapping algorithm to realize the robot'...
详细信息
The burgeoning field of automated assembly is undergoing rapid evolution, thanks to the recent strides in deep learning and computervision technologies. However, the journey is marred by significant challenges, parti...
详细信息
The burgeoning field of automated assembly is undergoing rapid evolution, thanks to the recent strides in deep learning and computervision technologies. However, the journey is marred by significant challenges, particularly inaccurate classification precision and suboptimal positioning accuracy, which stifles technological progression. To address these challenges, this study proposes a new Swin Transformer and ORB (STO) algorithm, aimed at improving the classification, positioning, and rotation accuracy of key components, especially rectangular objects, in automated assembly lines. The STO algorithm consists of three main components: a Swin Transformer-based object classification system, a positioning model for rectangular objects, and a model for calculating rotation angles. The positioning model uses the techniques of threshold processing and contour detection to locate rectangular objects effectively. Meanwhile, the rotation angle calculation model employs the oriented FAST and rotated BRIEF(ORB) algorithm for feature extraction and matching, ensuring precise determination of the required rotation angles. This study sets up an experimental apparatus including a camera, a robotic arm, and randomly placed rectangular workpieces. The randomly placed rectangular workpieces are regarded as rectangular workpieces that need to be assembled. Results demonstrate that the STO algorithm excels in object recognition and angle determination, particularly showing high precision in angle calculation, with a mean absolute error (MAE) of 0.10 degrees. In summary, the proposed method improves the accuracies of rotation angle estimation and pattern recognition of the workpieces, thereby showing potential applications in the industrial assembly process. The STO method principle also shows potentials in recognizing irregular workpieces in various industrial scenarios.
Embodied artificial intelligence (AI) agents, which navigate and interact with their environment using sensors and actuators, are being applied for mobile robotic platforms with limited computing power, such as autono...
详细信息
Embodied artificial intelligence (AI) agents, which navigate and interact with their environment using sensors and actuators, are being applied for mobile robotic platforms with limited computing power, such as autonomous vehicles, drones, and humanoid robots. These systems make decisions through environmental perception from deep neural network (DNN)-based visual encoders. However, the constrained computational resources and the large amounts of visual data to be processed can create bottlenecks, such as taking almost 300 milliseconds per decision on an embedded GPU board (Jetson xavier). Existing DNN acceleration methods need model retraining and can still reduce accuracy. To address these challenges, our paper introduces a bionic visual encoder framework, }Robye\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathsf \small {Robye}$$\end{document}, to support real-time requirements of embodied AI agents. The proposed framework complements existing DNN acceleration techniques. Specifically, we integrate motion data to identify overlapping areas between consecutive frames, which reduces DNN workload by propagating encoding results. We bifurcate processing into high-resolution for task-critical areas and low-resolution for less-significant regions. This dual-resolution approach allows us to maintain task performance while lowering the overall computational demands. We evaluate }Robye\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathsf \small {Robye}$$\end{document} across three robotic scenarios: autonomous driving, vision-and-language navigation, and drone navigation, using various DNN models and mobile pl
The prominence of embodied Artificial Intelligence (AI), which empowers robots to navigate, perceive, and engage within virtual environments, has attracted significant attention, owing to the remarkable advances in co...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
The prominence of embodied Artificial Intelligence (AI), which empowers robots to navigate, perceive, and engage within virtual environments, has attracted significant attention, owing to the remarkable advances in computervision and large language models. Privacy emerges as a pivotal concern within the realm of embodied AI, as the robot accesses substantial personal information. However, the issue of privacy leakage in embodied AI tasks, particularly concerning reinforcement learning algorithms, has not received adequate consideration in research. This paper aims to address this gap by proposing an attack on the training process of the value-based algorithm and the gradient-based algorithm, utilizing gradient inversion to reconstruct states, actions, and supervisory signals. The choice of using gradients for the attack is motivated by the fact that commonly employed federated learning techniques solely utilize gradients computed based on private user data to optimize models, without storing or transmitting the data to public servers. Nevertheless, these gradients contain sufficient information to potentially expose private data. To validate our approach, we conducted experiments on the AI2THOR simulator and evaluated our algorithm on active perception, a prevalent task in embodied AI. The experimental results demonstrate the effectiveness of our method in successfully reconstructing all information from the data in 120 room layouts. Check our website for videos.
The problem of detecting dangerous or prohibited objects in luggage is a very important step during the implementation of Security setup at Airports, Banks, Government buildings, etc. At present, the most common techn...
详细信息
The problem of detecting dangerous or prohibited objects in luggage is a very important step during the implementation of Security setup at Airports, Banks, Government buildings, etc. At present, the most common techniques for detecting such dangerous objects are by using intelligent data analysis algorithms such as deep learning techniques on x-ray imaging or employing a human workforce for inferring the presence of these threat objects in the obtained x-ray images. One of the major challenges while using deep-learning methods to detect such objects is the lack of high-quality threat image data containing the "dangerous " objects (objects of interest) versus the non-threat image data in practical scenarios. So, to tackle this data scarcity problem, anomaly detection techniques using normal data samples have shown great promise. Also, among the available Deep Learning Strategies for anomaly detection for computervision applications, generative adversarial networks have achieved state-of-the-art results. Considering these insights, we adopted a newly proposed architecture known as Skip-GANomaly and devised a modified version of it by using a UNet++ style generator which performed better than Skip-GANomaly, getting an AUC of 94.94% on Compass-xP, a public x-ray dataset. Finally, for targeting better latent space exploration, we combine these two architectures into an Ensemble, which gives another boost to the performance, getting an AUC of 96.8% on the same Compass-xP, a public x-ray dataset. To further validate the effectiveness of ensemble-based architecture, its performance was tested on patch-based training data on a subset of randomly chosen images of another huge public x-ray dataset named as SIxray, and obtained an AUC of 75.3% on this reduced dataset. To demonstrate the prowess of the discriminator and to bring some explainability to the working of our ensemble, we have used Uniform Manifold Approximation and Projection to plot the latent-space vectors for th
The rapid advancement of science and technology has underscored the significant potential of intelligent driving systems in the fields of robotics and automotive industries. We focus on the design and implementation o...
详细信息
Graph neural networks (GNNs) are ideally suited for mesh denoising. However, existing solutions such as those based on graph convolutional networks (GCNs) are built for a fixed graph thus making them not naturally gen...
详细信息
Graph neural networks (GNNs) are ideally suited for mesh denoising. However, existing solutions such as those based on graph convolutional networks (GCNs) are built for a fixed graph thus making them not naturally generalizable to unseen meshes. Furthermore, their graph Laplacian based global node embedding algorithms can cause excessive smoothing while achieving feature preserving mesh denoising requires a GNN to possess local processing capability. This paper presents a mesh denoising method via a new Dense lOcal Graph neural NETwork (DOGNET). DOGNET implements a local node embedding algorithm that generates node embeddings through aggregating information from a node's connected local neighbours which automatically make DOGNET inductive as well as effective for feature preserving mesh denoising. We present extensive experimental results to demonstrate quantitatively and qualitatively that DOGNET is superior to SOTA meshing denoising techniques.
Manual parsing of invoices is a tedious, arduous and error-prone task. Due to the academic and business importance of this problem, it has attracted the attention of machine learning enthusiasts. There are several com...
详细信息
Manual parsing of invoices is a tedious, arduous and error-prone task. Due to the academic and business importance of this problem, it has attracted the attention of machine learning enthusiasts. There are several complexities and challenges in the automated parsing of invoices. Some of them include a paucity of useful datasets, eclectic template formats, and poor performance of algorithms in real life scenarios. This problem can be solved by the automatic traversal of the invoices by object detection algorithms such as YOLO, SSD and R-CNN. These state-of-the-art algorithms will be trained to detect various fields or entities present in an invoice. In this paper, a dataset of 315 invoices has been generated using web testing tools. The dataset has been annotated for eight entities: billing address, shipping address, invoice date, invoice number, product name, price, quantity, and total amount. The text boxes detected by the models is converted to machine encoded text, using text extraction methods such as Optical Character Recognition (OCR). Hyperparameter tuning has been performed to improve model accuracy. The models have been evaluated on myriad metrics such as mean Average Precision (mAP), common objects in context (COCO) evaluation metrics and total loss during training and validation. The loss vs iteration graph has been visualized using Tensorboard. A front-end application encapsulates all the functions of the research paper and allows testing of various models.
In robotics, route planning is essential to ensure the safe and efficient movement of robots within the workplace. This process involves determining a trajectory, usually a series of points in the workspace, to achiev...
详细信息
ISBN:
(数字)9798331522742
ISBN:
(纸本)9798331522759
In robotics, route planning is essential to ensure the safe and efficient movement of robots within the workplace. This process involves determining a trajectory, usually a series of points in the workspace, to achieve a specific goal. It is essential to consider criteria such as reducing the length of the route, the number of manoeuvres and the avoidance of obstacles. Route planning techniques generally require modelling the environment, representing both the structure and the obstacles (fixed or mobile), and the implementation of algorithms that generate the trajectory through the free areas of the environment. This approach often includes constructing a graph of possible trajectories and using minimum path search algorithms, such as A*. This article presents a route planning algorithm that uses Voronoi diagrams and uses artificial visionalgorithms. In addition, a case study is described in which the proposed technique is applied to guide an automated system through a maze drawn on a whiteboard by a user.
This work provides a novel solution to the issues associated with effective supermarket inventory management: an autonomous wheeled robot equipped with excellent image identification and line-following capabilities. T...
详细信息
ISBN:
(数字)9798331505370
ISBN:
(纸本)9798331505387
This work provides a novel solution to the issues associated with effective supermarket inventory management: an autonomous wheeled robot equipped with excellent image identification and line-following capabilities. This system optimises product storage in supermarkets by employing state-of-the-art robotics, computervision, and artificial intelligence technology. The robot uses real-time shelf photos processed by sophisticated techniques along with image detection algorithms to precisely identify low-stock or empty shelves. The robot is capable of to identify things, classify them, and choose which shelves would be ideal for them according to deep learning algorithms. The robot simultaneously makes efficient use of line-following devices to transverse aisles. Using real-time demand data, the control system incorporates a dynamic decision-making algorithm which allows the robot to modify its trajectory and prioritise replenishment. With its substantial labour cost reductions, minimal error rate, and increased operational efficiency, this wheeled robot system has the potential to entirely transform the retail industry. The study opens the door for intelligent retail automation via demonstrating the practicality and efficacy of autonomous robots in automating supermarket restocking.
暂无评论