the increasing number of vehicles and dynamic changes in traffic situations make real-time route planning strongly necessary. the route-guiding method is supposed to cope with dynamic traffic situations. In addition, ...
详细信息
ISBN:
(纸本)9781665476881
the increasing number of vehicles and dynamic changes in traffic situations make real-time route planning strongly necessary. the route-guiding method is supposed to cope with dynamic traffic situations. In addition, the ability to adapt to the second fastest route is very important when traffic congestion suddenly occurs on the fastest path. this paper proposes a method of using reinforcement learning to solve dynamic route planning problems, and the adaptation from a static learning rate to a dynamic learning rate enhances the capability to deal with emergent congestion. Meanwhile, the waiting time before each traffic light also is considered as a reward factor in the proposed algorithm. Contrast experiments have been conducted on the simulation network by SUMO, which has demonstrated well that our proposed method has better performance than other methods.
this paper addresses the global waste management crisis by proposing an innovative strategy that combines visual recognition technology withrobotics, grounded in the ACP methodology, aiming to create an intelligent g...
详细信息
ISBN:
(数字)9798350349252
ISBN:
(纸本)9798350349269
this paper addresses the global waste management crisis by proposing an innovative strategy that combines visual recognition technology withrobotics, grounded in the ACP methodology, aiming to create an intelligent garbage classification system. the primary goal of the system is to handle the growing volume of waste by employing the YOLOv7 object detection model in conjunction with a Sawyer/Baxter collaborative robot to achieve effective garbage categorization. the study simulates the application process of ACP in a laboratory setting. Robots can select different 3D-printed soft grippers based on needs. Collaborative robots generate new data through actual operations, which is then used to update and improve the model, forming a continuous iterative closed-loop system. Despite environmental challenges, the system’s achievements indicate potential for large-scale applications. Future research will focus on refining detection models, enhancing human-robot collaboration, and ensuring scalability for broader integration into waste management systems.
Semi-supervised semantic segmentation aims to maximize the training performance for a limited annotation cost. Existing methods such as cross pseudo supervision have shown excellent performance, yet ignore potential i...
详细信息
ISBN:
(纸本)9781665476881
Semi-supervised semantic segmentation aims to maximize the training performance for a limited annotation cost. Existing methods such as cross pseudo supervision have shown excellent performance, yet ignore potential information interactions between labeled and unlabeled data, and suffer from misleading incorrect pseudo labels. this paper takes two ways to improve each of these shortcomings. Firstly, we perform feature-level mixing and cross-decoupling using labeled and unlabeled data to establish potential interactions between the two types of data. Secondly, an uncertainty-aware loss re-weighting method based on information entropy is used to mitigate the negative effects of incorrect pseudo labels. Experimentally, our method further improves the previous cross pseudo supervision method with competitive performance on PASCAL VOC 2012 dataset under various data partition protocols.
In this paper, we present KeyMatchNet, a novel network for zero-shot pose estimation in 3D point clouds. Our method uses only depth information, making it more applicable for many industrial use cases, as color inform...
详细信息
ISBN:
(数字)9798350358513
ISBN:
(纸本)9798350358520
In this paper, we present KeyMatchNet, a novel network for zero-shot pose estimation in 3D point clouds. Our method uses only depth information, making it more applicable for many industrial use cases, as color information is seldom available. the network is composed of two parallel components for computing object and scene features. the features are then combined to create matches used for pose estimation. the parallel structure allows for pre-processing of the individual parts, which decreases the *** a zero-shot network allows for a very short set-up time, as it is not necessary to train models for new objects. However, as the network is not trained for the specific object, zero-shot pose estimation methods generally have lower accuracy compared with conventional methods. To address this, we reduce the complexity of the task by including the scenario information during training. this is typically not feasible as collecting real data for new tasks drastically increases the cost. However, for zero-shot pose estimation, training for new objects is not necessary and the expensive data collection can thus be performed only *** method is trained on 1,500 objects and is only tested on unseen objects. We demonstrate that the trained network can not only accurately estimate poses for novel objects, but also demonstrate the ability of the network on objects outside of the trained class. Test results are also shown on real data. We believe that the presented method is valuable for many real-world scenarios. Project page available at ***
Deep learning methods on remote sensing data are an attractive approach in place of human observation for automating recognition of hundreds of thousands of tree species in nature. However, this approach requires a la...
详细信息
ISBN:
(纸本)9781665476881
Deep learning methods on remote sensing data are an attractive approach in place of human observation for automating recognition of hundreds of thousands of tree species in nature. However, this approach requires a large amount of training data for each species, while actual data are scarce - only a small subset of tree species data can be acquired, notwithstanding the unknown, new species. To overcome the data scarcity challenge and to enable versatile recognition of known and unknown species, we propose a knowledge-driven transfer learning framework for tree species profiling, where a base model of multitasking graph neural network is trained on synthetic species data, which are generated from the universal botany domain knowledge and limited field measurement data. this base model is then transferred to a new multitasking graph neural network model to train on real tree data of limited availability. Our proposed species recognition framework was tested for profiling tree species by classifying a few species profile parameters and showed a significant improvement in the prediction accuracy in comparison to deep learning models trained on just real tree data.
Traditional equipment failures are often identified only when they manifest during production, leading to costly downtime, increased defect rates, and safety hazards. this study focuses on the progressive stages and s...
详细信息
ISBN:
(数字)9798331518158
ISBN:
(纸本)9798331518165
Traditional equipment failures are often identified only when they manifest during production, leading to costly downtime, increased defect rates, and safety hazards. this study focuses on the progressive stages and severity of AI pneumatic tube fault diagnosis, a critical component in industrial operations. By leveraging a sensor and a microphone to collect vibration and audio data, we developed a deep learning-based system to accurately classify and predict the progression of these failures. Temporal Convolutional Networks (TCN) and Long Short-Term Memory (LSTM) networks were trained to identify anomalies in the collected data, effectively distinguishing between different fault stages, from minor issues to major failures. TCN models, withtheir dilated convolutions, capture long-term dependencies in the data, allowing for early detection of subtle anomalies. LSTM models, using their gated architecture, retain and utilize critical historical information, enabling more precise fault classification. A comparative analysis of various equipment condition monitoring methods demonstrates the superiority of our proposed approach in terms of signal detection and classification accuracy. Additionally, system integration of a Robotic Arm Automatic Placement Workstation and a user-friendly Node-RED-based interface supports real-time monitoring and operator intervention. this integrated system allows seamless communication between hardware components and software, enhancing overall operational efficiency. this study highlights the potential of AI and deep learning to enhance predictive maintenance and operational efficiency in industrial settings, particularly for critical equipment like pneumatic tubes.
Autonomous systems, that need to operate in human environments and interact withthe users, rely on understanding and anticipating human activity and motion. Among the many factors which influence human motion, semant...
Autonomous systems, that need to operate in human environments and interact withthe users, rely on understanding and anticipating human activity and motion. Among the many factors which influence human motion, semantic attributes, such as the roles and ongoing activities of the detected people, provide a powerful cue on their future motion, actions, and intentions. In this work we adapt several popular deep learning models for trajectory prediction with labels corresponding to the roles of the people. To this end we use the novel thÖR-Magni dataset, which captures human activity in industrial settings and includes the relevant semantic labels for people who navigate complex environments, interact with objects and robots, work alone and in groups. In qualitative and quantitative experiments we show that the role-conditioned LSTM, Transformer, GAN and VAE methods can effectively incorporate the semantic categories, better capture the underlying input distribution and therefore produce more accurate motion predictions in terms of Top-K ADE/FDE and log-likelihood metrics.
the introduction of AI methods in production or production-related environments meets with resistance from operators due to their lack of relevant experience and their responsibility for plant safety. To overcome thes...
详细信息
ISBN:
(纸本)9781728189567
the introduction of AI methods in production or production-related environments meets with resistance from operators due to their lack of relevant experience and their responsibility for plant safety. To overcome these inhibitions one requires prototypical implementations, which offer considerable benefits, meet the highest requirements for reliability, are accepted by the operating personnel, and get support from those in charge. As a result, AI technologies must be embedded into the complex IT/OT infrastructure of the companies. Traceability, maintainability and longevity must also be guaranteed. As a first step towards this, we present a concept of the demonstrator and its first results, which should make AI comprehensible by visualizing challenges and exploring possibilities in the process industry.
Robots have limited perception capabilities when observing a new scene. When the objects on the scene are registered from a single perspective, only partial information about the shape of the objects is registered. In...
详细信息
ISBN:
(纸本)9781665476881
Robots have limited perception capabilities when observing a new scene. When the objects on the scene are registered from a single perspective, only partial information about the shape of the objects is registered. Incomplete models of objects influence the performance of grasping methods. In this case, the robot should scan the scene from other perspectives to collect information about the objects or use methodsthat fill in unknown regions of the scene. the CNN-based method for objects reconstruction from a single view utilize 3D structures like point clouds or 3D grids. In this research, we revisit the problem of scene reconstruction and show that scene reconstruction can be formulated in the 2D image space. We propose a new representation of the scene reconstruction problem for a robot equipped with an RGB-D camera. then, we present a method that generates a depth image of the object from the pose of the camera that is on the other side of the scene. We show how to train a neural network to obtain accurate depth images of the objects and reconstruct a 3D model of the scene observed from a single viewpoint. Moreover, we show that the obtained model can be applied to improve the success rate of the grasping method.
Open-vocabulary 3D object detection has recently attracted considerable attention due to its broad applications in autonomous driving and robotics, which aims to effectively recognize novel classes in previously unsee...
ISBN:
(纸本)9798331314385
Open-vocabulary 3D object detection has recently attracted considerable attention due to its broad applications in autonomous driving and robotics, which aims to effectively recognize novel classes in previously unseen domains. However, existing point cloud-based open-vocabulary 3D detection models are limited by their high deployment costs. In this work, we propose a novel open-vocabulary monocular 3D object detection framework, dubbed OVM3D-Det, which trains detectors using only RGB images, making it both cost-effective and scalable to publicly available data. Unlike traditional methods, OVM3D-Det does not require high-precision LiDAR or 3D sensor data for either input or generating 3D bounding boxes. Instead, it employs open-vocabulary 2D models and pseudo-LiDAR to automatically label 3D objects in RGB images, fostering the learning of open-vocabulary monocular 3D detectors. However, training 3D models with labels directly derived from pseudo-LiDAR is inadequate due to imprecise boxes estimated from noisy point clouds and severely occluded objects. To address these issues, we introduce two innovative designs: adaptive pseudo-LiDAR erosion and bounding box refinement with prior knowledge from large language models. these techniques effectively calibrate the 3D labels and enable RGB-only training for 3D detectors. Extensive experiments demonstrate the superiority of OVM3D-Det over baselines in both indoor and outdoor scenarios. the code will be released.
暂无评论