This paper focuses on the fault-tolerant control (FTC) problem for unmanned aerial vehicles (UAVs) subject to possible multiple actuator failures, which is a tough problem to solve with traditional FTC methods since t...
详细信息
ISBN:
(数字)9798350379228
ISBN:
(纸本)9798350390780
This paper focuses on the fault-tolerant control (FTC) problem for unmanned aerial vehicles (UAVs) subject to possible multiple actuator failures, which is a tough problem to solve with traditional FTC methods since they usually require accurate mathematical models. To address the limitation of traditional FTC methods, a model-free FTC approach is proposed based on reinforcement learning (RL). Subsequently, the proposed approach is applied to construct fault-tolerant controller for UAVs without any knowledge of the quadrotor dynamic information. Then, an end-to-end control policy that can tolerant actuator failures is obtained, which can map the state of the UAVs directly to the control commands of the four rotors after learning. Finally, the effectiveness of the proposed fault-tolerant approach is demonstrated by using the flexible modular quadrotor simulator.
Fault information of rotating machinery is often drowned in strong noise signals, so it is crucial to accurately identify faults from high-intensity noise signals. In this article, an end-to-end fault diagnosis model ...
Fault information of rotating machinery is often drowned in strong noise signals, so it is crucial to accurately identify faults from high-intensity noise signals. In this article, an end-to-end fault diagnosis model is developed, which consists of a multi-stage selection filter based on wavelet packet and 2D-CNN. First, the original measured mechanical signals were processed by the three-level wavelet packet decomposition to obtain eight sub-bands with coefficient matrices. Second, the signal is reconstructed using different numbers of sub-bands, where the number is increased by one at a time to obtain eight different multi-stage reconstructed signals. Third, the reconstructed signals are reorganized into 2D signal maps; and a parallel training network is constructed using signal maps and 2D-CNN to achieve fault classification. Then, guided by the training results, eight parallel classification results are compared, so as to train the best fault diagnosis model. Finally, the simulation experiment based on a bearing data set illustrates the proposed multi-stage selection filter is effective and feasible in application.
In this paper, we summarize the methods and experimental results we proposed for Task 2 in the learn2reg 2024 Challenge. This task focuses on unsupervised registration of anatomical structures in brain MRI images betw...
详细信息
Integration of diverse visual prompts like clicks, scribbles, and boxes in interactive image segmentation significantly facilitates users’ interaction as well as improves interaction efficiency. However, existing stu...
详细信息
In the post-COVID-19 pandemic era, hospitals and other places have an urgent need for mobile robots with autonomous disinfection ability, and robots need to complete SLAM tasks to realize autonomous navigation. Lidar ...
In the post-COVID-19 pandemic era, hospitals and other places have an urgent need for mobile robots with autonomous disinfection ability, and robots need to complete SLAM tasks to realize autonomous navigation. Lidar is widely used for indoor SLAM. However, due to the lack of geometric structure in the indoor environment, two-dimensional lidar information degrades, rendering the robot unable to obtain effective positioning. Therefore, we leverage the easy identification and high robustness of ARTag to fuse vision and range sensor information. We introduce ARTag as visual marker to assist positioning, establish observation window to screen the acquired ARTag pose. We employ the pose graph optimization method to optimize the visual markers and laser scanning results in the back end. This reduces the positioning errors caused by the degradation of lidar information and reduces the frequency of optimization by improving the back end optimization strategy. This method is applied in a UltraViolet C (UVC) Disinfection robot experiment. Experimental results show that our method effectively improves the positioning accuracy and robustness of the robot in the environments with degraded laser information.
Traffic Salient Object Detection (TSOD) aims to segment the objects critical to driving safety by combining semantic (e.g., collision risks) and visual saliency. Unlike SOD in natural scene images (NSI-SOD), which pri...
详细信息
This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in aut...
详细信息
— visual place recognition has gained significant attention in recent years as a crucial technology in autonomous driving and robotics. Currently, the two main approaches are the perspective view retrieval (P2P) para...
详细信息
controller Area Network (CAN) protocol is an efficient standard enabling communication among Electronic control Units (ECUs). However, the CAN bus is vulnerable to malicious attacks because of a lack of defense featur...
详细信息
The widely deployed power transmission line expedites developing the age of electricity. Thus, it is necessary to maintain a power system with a great quantity of manpower and material resources, especially for crucia...
详细信息
暂无评论