In this paper, the consideration of the stability problem for the vehicular platoon system (VPS) with communication delays under proportional differential (PD) control is studied by the Lyapunov-Krasovskii functional ...
详细信息
ISBN:
(纸本)9798350350319;9798350350302
In this paper, the consideration of the stability problem for the vehicular platoon system (VPS) with communication delays under proportional differential (PD) control is studied by the Lyapunov-Krasovskii functional (LKF). Firstly, a VPS considering delay is modeled to analyze the influence of delays for the VPS in operation. Then, an error state-space system of the VPS is constructed and transformed into a singular system. As a result, the stability criterion is proposed based on the state decomposition method via the LKF. Finally, the tolerance for delay is calculated for a case of four vehicles with different controller gains. The result shows that the proportional gain is inversely proportional to the time delay and the differential gain is in direct proportion to the time delay meanwhile. Besides, the high-speed vehicular platoon is more affected by the time delay.
The proceedings contain 144 papers. The topics discussed include: a robust approach to e-banking phishing detection using ensemble methods and LSTM;improving QR code security using multiple encryption layers;RollBot: ...
ISBN:
(纸本)9798350372748
The proceedings contain 144 papers. The topics discussed include: a robust approach to e-banking phishing detection using ensemble methods and LSTM;improving QR code security using multiple encryption layers;RollBot: an automatic curtain opener robot;developing an ML model for detecting the cyber-attacks in electric vehicles;early accurate identification of grape leaf disease detection using CNN based VGG-19 model;dynamic load balancing and resource optimization algorithm for reverse proxy servers;smart aquarium and water quality monitoring using IoT;design and development of fin-ray finger using topology optimization with multiple load cases;deep learning-based skin cancer diagnosis using dermoscopy images;and optimization of neural networks using swarm intelligence techniques for achieving energy efficiency in smart building architecture.
With the popularity of industrial collaborative robots, people have put forward higher requirements for the dynamic control performance of cooperative robots. Due to the collaborative robot with serial joint modules, ...
详细信息
ISBN:
(纸本)9798350385731;9798350385724
With the popularity of industrial collaborative robots, people have put forward higher requirements for the dynamic control performance of cooperative robots. Due to the collaborative robot with serial joint modules, the model will increase in order with the increase of the number of joints. Therefore, we design a practical high-order robust control method accordingly. This control method uses nominal control and inherits the traditional PID control algorithm to eliminate errors, and then designs high-order robust terms to eliminate errors caused by modeling and external disturbances. Furthermore, simulations are carried out on a planar 2-DOF manipulator to verify the actual performance of the controller, and its static performance and transient performance are excellent.
This paper proposes an online path planning method for multi-robot collision avoidance that accounts for uncertainties in robot positioning. Firstly, the online path planning problem for multiple robots is transformed...
详细信息
ISBN:
(纸本)9798331518509;9798331518493
This paper proposes an online path planning method for multi-robot collision avoidance that accounts for uncertainties in robot positioning. Firstly, the online path planning problem for multiple robots is transformed into a multi-objective optimization problem by considering some necessary factors that affect task efficiency and safety. Notably, the paper considers the uncertainty in robot positions, in which the position follows a Gaussian distribution. Then, by converting probabilistic collision conditions into deterministic constraints, the fitness function ensuring probabilistic collision avoidance is constructed. Next, an improved sine-cosine algorithm is proposed to solve the ideal position. Finally, simulation experiments demonstrate that the proposed method effectively resolves collision issues under probabilistic uncertainty conditions.
Classifying intentions of other traffic agents is an essential task for intelligent transportation systems. To simplify this task, vehicles are equipped with various illumination systems, including turn indicators, em...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Classifying intentions of other traffic agents is an essential task for intelligent transportation systems. To simplify this task, vehicles are equipped with various illumination systems, including turn indicators, emergency lights, rear lights, and brake lights. We extend theWaymo open perception dataset with ground truth annotations for different visual intentions to develop methods designed to classify the state of such systems. Furthermore, we propose the VISUAL INTENTION FORMER, a two-step transformer-based architecture to classify visual intentions in image sequences of tracked traffic participants. We use a vision transformer to extract image features, which are passed into a transformer encoder that reasons about temporal dependencies among them. We evaluate against different baseline architectures where our proposed method achieves state-of-the-art results. Additionally, we conduct an in-depth performance analysis of our method regarding different input sequence lengths, vehicle headings, and daytime conditions.
Accurate and efficient external calibration, available in real-time within a targetless environment, remains a significant challenge due to the inherent inhomogeneous reflectance, density distribution, and small FOV o...
详细信息
ISBN:
(纸本)9798350352481;9798350352474
Accurate and efficient external calibration, available in real-time within a targetless environment, remains a significant challenge due to the inherent inhomogeneous reflectance, density distribution, and small FOV of Non-Repeat Scanning (NRS) LiDAR system data, these issues bring difficulties for subsequent applications in areas such as simultaneously localization and mapping (SLAM) and autonomous driving. To address these issues, this paper proposes a targetless method for the automatic calibration of LiDAR and camera systems. Initially, we analyzed the complexity and variability of LiDAR point cloud information and developed a feature extraction method that integrates geometric and intensity data. Subsequently, we optimized the intensity data within the point cloud to extract reliable intensity information. Finally, we matched and iteratively optimized the sensor system data to obtain the final extrinsic parameters. Through extensive experimental analysis, we verified the effectiveness and accuracy of our algorithm.
At present, swarm robotics represents a very interesting option for solving complex problems in dynamic and changing environments. To do so, the agents that form a robot swarm must be able to deploy one or more collec...
详细信息
ISBN:
(纸本)9798400717291
At present, swarm robotics represents a very interesting option for solving complex problems in dynamic and changing environments. To do so, the agents that form a robot swarm must be able to deploy one or more collective behaviors. In order to learn the latter, in the last few years, different automatic design methods have become very popular. In this paper, we propose a hybrid method to automatically design an autonomous navigation behavior for swarm robotics. The idea is to combine multi-agent reinforcement learning and neuro-evolution. Furthermore, we present and compare two evolutionary algorithms whose aim is to implement the learning process of the aforementioned behavior. In particular, they are the well-known cross-entropy method and covariance matrix adaptation evolution strategy. Finally, we include some experiments in which we demonstrate that the covariance matrix adaptation evolution strategy is more appropriate than the cross-entropy method, when performing a vision-based collision-free exploration task in a simulated indoor corridor.
This paper presents a robust image information hiding method integrating Convolutional Neural Networks (CNN) and image encryption based on the Lorenz three-dimensional chaotic system. We introduce chaotic image encryp...
详细信息
ISBN:
(纸本)9798350352481;9798350352474
This paper presents a robust image information hiding method integrating Convolutional Neural Networks (CNN) and image encryption based on the Lorenz three-dimensional chaotic system. We introduce chaotic image encryption technology based on the Lorenz three-dimensional system into the CNN-based image steganography framework. Leveraging the high sensitivity and unpredictability of the Lorenz system, the original secret image is first encrypted to render it visually imperceptible. During the image hiding phase, the encrypted secret image is embedded into the carrier image using an improved CNN-based image information hiding model. This model capitalizes on CNN's powerful automatic learning and feature extraction capabilities to achieve information hiding, resulting in a steganographic image. In the information extraction phase, the steganographic image serves as the input for the decoder network within the model, where the decoder decrypts it to retrieve both the carrier image and the encrypted secret image. Finally, the secret image is decrypted using the Lorenz chaotic encryption algorithm. Analyses of PSNR/SSIM and visual quality demonstrate that the proposed hybrid image steganography scheme offers high security and robustness, effectively preventing distortion of the secret image.
This article involves the field of warehouse control technology and introduces an automatic loading and unloading warehouse control system and its loading and unloading equipment. The system is equipped with a parking...
详细信息
Localization using a monocular camera in the pre-built LiDAR point cloud map has drawn increasing attention in the field of autonomous driving and mobile robotics. However, there are still many challenges (e.g. diffic...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Localization using a monocular camera in the pre-built LiDAR point cloud map has drawn increasing attention in the field of autonomous driving and mobile robotics. However, there are still many challenges (e.g. difficulties of map storage, poor localization robustness in large scenes) in accurately and efficiently implementing cross-modal localization. To solve these problems, a novel pipeline termed LHMap-loc is proposed, which achieves accurate and efficient monocular localization in LiDAR maps. Firstly, feature encoding is carried out on the original LiDAR point cloud map by generating offline heat point clouds, by which the size of the original LiDAR map is compressed. Then, an end-to-end online pose regression network is designed based on optical flow estimation and spatial attention to achieve real-time monocular visual localization in a pre-built map. In addition, a series of experiments have been conducted to prove the effectiveness of the proposed method. Our code is available at: https://***/IRMVLab/LHMap-loc.
暂无评论