According to the analysis of the research level of "smart pharmacy" at home and abroad, the research level of "smart pharmacy" in China is relatively backward, and the construction method of "...
详细信息
ISBN:
(数字)9798350386776
ISBN:
(纸本)9798350386783
According to the analysis of the research level of "smart pharmacy" at home and abroad, the research level of "smart pharmacy" in China is relatively backward, and the construction method of "smart pharmacy" is single and the popularity rate is low. At present, most of the primary medical institutions in our country still adopt the traditional pharmacy or HIS system pharmacy management mode, and a small number of large hospitals use automatic drug dispensing machine with rail transportation to improve efficiency. However, due to the disadvantages of high cost, large space and low flexibility, this method is not suitable for the vast majority of primary medical institutions in China. In the face of the current social form, the team analyzes and designs according to the needs of users, and uses artificial intelligence, Internet of Things and other technologies to create a smart pharmacy management system that combines intelligent prescription management, intelligent prescription management, and intelligent drug management to meet the market demand and promote the development of the industry.
The paper discusses the problem of creating an autonomous SCARA robot that can precisely carry out pick-and-place operations in unstructured settings. The suggested method combines computervision and deep learning al...
详细信息
ISBN:
(数字)9798331527549
ISBN:
(纸本)9798331527556
The paper discusses the problem of creating an autonomous SCARA robot that can precisely carry out pick-and-place operations in unstructured settings. The suggested method combines computervision and deep learning algorithms to provide accurate 6D pose estimation and reliable object detection. Combining YOLOv8 for object detection, hand-eye calibration for precise transformation to robot coordinates, and Principal Component Analysis (PCA) for orientation estimation within the generated point cloud, a novel method for estimating object pose is presented. Monocular depth estimation techniques are used to extract depth information from RGB images to create point clouds. The results demonstrate the potential of combining advanced algorithms with user-friendly design for robotics automation, showing notable gains in pose estimation accuracy and task execution efficiency.
The rise of intelligent question-answering systems has increased the demand for comprehensive, multimodal knowledge graphs that integrate information from diverse data sources such as text, images, and audio. However,...
详细信息
Advancement in vision-based techniques has enabled the autonomous vehicle system (AVS) to understand the driving scene in depth. The capability of autonomous vehicle system to understand the scene, and detecting the s...
详细信息
Advancement in vision-based techniques has enabled the autonomous vehicle system (AVS) to understand the driving scene in depth. The capability of autonomous vehicle system to understand the scene, and detecting the specific object depends on the strong feature representation of such objects. However, pothole objects are difficult to identify due to their non-uniform structure in challenging, and dynamic road environments. Existing approaches have shown limited performance for the precise detection of potholes. The study on the detection of potholes, and intelligent driving behaviour of autonomous vehicle system is little explored in existing articles. Hence, here, an improved prototype model, which is not only truly capable of detecting the potholes but also shows its intelligent driving behaviour when any pothole is detected, is proposed. The prototype is developed using a convolutional neural network with a vision camera to explore, and validates the potential, and autonomy of its driving behaviour in the prepared road environment. The experimental analysis of the proposed model on various performance measures have obtained accuracy, sensitivity, and F-measure of 99.02%, 99.03%, and 98.33%, respectively, which are comparable with the available state-of-art techniques.
Current existing stereo visual odometry algorithms are computationally too expensive for robots with restricted resources. Executing these algorithms on such robots leads to a low frame rate and unacceptable decay in ...
详细信息
ISBN:
(纸本)9781665417143
Current existing stereo visual odometry algorithms are computationally too expensive for robots with restricted resources. Executing these algorithms on such robots leads to a low frame rate and unacceptable decay in accuracy. We modify S-MSCKF, one of the most computationally efficient stereo Visual Inertial Odometry (VIO) algorithm, to improve its speed and accuracy when tracking low numbers of features. Specifically, we implement the Inverse Lucas-Kanade (ILK) algorithm for feature tracking and stereo matching. An outlier detector based on the average sum square difference of the template and matching warp in the ILK ensures higher robustness, e.g., in the presence of brightness changes. We restrict stereo matching to slide the window only in the x-direction to further decrease the computational costs. Moreover, we limit detection of new features to the regions of interest that have too few features. The modified S-MSCKF uses half of the processing time while obtaining competitive accuracy. This allows the algorithm to run in real-time on the extremely limited Raspberry Pi Zero single-board computer.
Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error acc...
详细信息
Visual simultaneous localization and mapping (vSLAM), one of the most important applications in autonomous vehicles and robots to estimate the position and pose using inexpensive visual sensors, suffers from error accumulation for long-term navigation without loop closure detection. Recently, deep neural networks (DNNs) are leveraged to achieve high accuracy for loop closure detection, however the execution time is much slower than those employing handcrafted visual features. In this paper, a parallel loop searching and verifying method for loop closure detection with both high accuracy and high speed, which combines two parallel tasks using handcrafted and DNN features, respectively, is proposed. A fast loop searching is proposed to link the bag-of-words features and histogram for higher accuracy, and it splits the images into multiple grids for high parallelism;meanwhile, a DNN feature extractor is utilized for further verification. A loop state control method based on a finite state machine to control these tasks is designed, wherein the loop closure detection is described as a context-related procedure. The framework is implemented on a real machine, and the top-2 best accuracy and fastest execution time of 80-543 frames per second (min: 1.84ms, and max: 12.45ms) are achieved on several public benchmarks compared with some existing algorithms.
Human-Robot Collaboration (HRC) enabling mechanisms require real-time detection of potential collisions among human and robots. Taking under consideration the already existing standards and the literature, most of col...
详细信息
An excellent representation is crucial for reinforcement learning (RL) performance, especially in vision-based reinforcement learning tasks. The quality of the environment representation directly influences the achiev...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
An excellent representation is crucial for reinforcement learning (RL) performance, especially in vision-based reinforcement learning tasks. The quality of the environment representation directly influences the achievement of the learning task. Previous vision-based RL typically uses explicit or implicit ways to represent environments, such as images, points, voxels, and neural radiance fields. However, these representations contain several drawbacks. They cannot either describe complex local geometries or generalize well to unseen scenes, or require precise foreground masks. Moreover, these implicit neural representations are akin to a "black box", significantly hindering interpretability. 3D Gaussian Splatting (3DGS), with its explicit scene representation and differentiable rendering nature, is considered a revolutionary change for reconstruction and representation methods. In this paper, we propose a novel Generalizable Gaussian Splatting framework to be the representation of RL tasks, called GSRL. Through validation in the RoboMimic environment, our method achieves better results than other baselines in multiple tasks, improving the performance by 10%, 44%, and 15% compared with baselines on the hardest task. This work is the first attempt to leverage generalizable 3DGS as a representation for RL.
The field of traditional mobile robot navigation has undergone a gradual transformation, evolving into a standardized and procedural research domain. Through a fresh cognitive perspective on this navigation process, a...
The field of traditional mobile robot navigation has undergone a gradual transformation, evolving into a standardized and procedural research domain. Through a fresh cognitive perspective on this navigation process, a bridge emerges between robotic researchers and cognitive neuroscientists, thereby fostering the growth of interdisciplinary exploration. This article meticulously examines three pivotal phases of robot navigation: information acquisition, simultaneous localization and mapping (SLAM), and path planning. These phases are intricately linked to pertinent cognitive research. Furthermore, a comprehensive survey of existing biomimetic and neuromorphic algorithms is presented, highlighting their applications in augmenting robot navigation capabilities. Ultimately, this article charts a visionary course for the future of robot navigation, envisioning its potential in facilitating more intelligent and efficient navigation techniques.
Multiple object tracking (MOT) is a valuable perception function for robots and intelligent systems. Despite rapid improvements in metrics such as Average Multiple Object Tracking Accuracy (AMOTA) on MOT benchmarks, m...
详细信息
ISBN:
(数字)9798350375022
ISBN:
(纸本)9798350375039
Multiple object tracking (MOT) is a valuable perception function for robots and intelligent systems. Despite rapid improvements in metrics such as Average Multiple Object Tracking Accuracy (AMOTA) on MOT benchmarks, many trackers are application-specific or run at speeds <1 frames per second (FPS) making them impractical for dynamic tracking applications such as human-robot interaction. To this end, we introduce Modular and Reconfigurable Multiple Object Tracking (MaRMOT), a general-purpose tracking framework for robots implemented in ROS2. Using the nuScenes MOT development kit, we provide accuracy and speed metrics (AMOTA, average FPS, and worst-case FPS) for various tracking methods. We achieve AMOTA of 50.5% with an average of 62.0 FPS on the nuScenes test split, making MaRMOT suitable for online tracking in complex scenes. We demonstrate MaRMOT’s modularity on two human tracking applications with different hardware configurations: a 2x object detection camera "smart space" configuration, and a mobile robot configuration with 3D LiDAR detector and an object detection camera. We show that an alternate sensor configuration using human position measurements from a headset improves multiple object tracking accuracy (MOTA) over vision and LiDAR detection alone. Finally, we provide software and hardware design recommendations for tracking applications with tracker speed requirements >10 FPS. MaRMOT is open source and can be extended with new detectors, process models, matching algorithms, and track management techniques.
暂无评论