IET Cybersystems and Robotics最新文献

In crowded settings, mobile robots face challenges like target disappearance and occlusion, impacting tracking performance. Despite existing optimisations, tracking in complex environments remains insufficient. To address this issue, the authors propose a tailored visual navigation tracking system for crowded scenes. For target disappearance, an autonomous navigation strategy based on target coordinates, utilising a path memory bank for intelligent search and re-tracking is introduced. This significantly enhances tracking success. To handle target occlusion, the system relies on appearance features extracted by a target detection network and a feature memory bank for enhanced sensitivity. Servo control technology ensures robust target tracking by fully utilising appearance information and motion characteristics, even in occluded scenarios. Comprehensive testing on the OTB100 dataset validates the system's effectiveness in addressing target tracking challenges in diverse crowded environments, affirming algorithm robustness.

Resilient motion planning and control, without prior knowledge of disturbances, are crucial to ensure the safe and robust flight of quadrotors. The development of a motion planning and control architecture for quadrotors, considering both internal and external disturbances (i.e., motor damages and suspended payloads), is addressed. Firstly, the authors introduce the use of exponential functions to formulate trajectory planning. This choice is driven by its ability to predict thrust responses with minimal computational overhead. Additionally, a reachability analysis is incorporated for error dynamics resulting from multiple disturbances. This analysis sits at the interface between the planner and controller, contributing to the generation of more robust and safe spatial–temporal trajectories. Lastly, the authors employ a cascade controller, with the assistance of internal and external loop observers, to further enhance resilience and compensate the disturbances. The authors’ benchmark experiments demonstrate the effectiveness of the proposed strategy in enhancing flight safety, particularly when confronted with motor damages and payload disturbances.

In various fields, knowledge distillation (KD) techniques that combine vision transformers (ViTs) and convolutional neural networks (CNNs) as a hybrid teacher have shown remarkable results in classification. However, in the realm of remote sensing images (RSIs), existing KD research studies are not only scarce but also lack competitiveness. This issue significantly impedes the deployment of the notable advantages of ViTs and CNNs. To tackle this, the authors introduce a novel hybrid-model KD approach named HMKD-Net, which comprises a CNN-ViT ensemble teacher and a CNN student. Contrary to popular opinion, the authors posit that the sparsity in RSI data distribution limits the effectiveness and efficiency of hybrid-model knowledge transfer. As a solution, a simple yet innovative method to handle variances during the KD phase is suggested, leading to substantial enhancements in the effectiveness and efficiency of hybrid knowledge transfer. The authors assessed the performance of HMKD-Net on three RSI datasets. The findings indicate that HMKD-Net significantly outperforms other cutting-edge methods while maintaining a significantly smaller size. Specifically, HMKD-Net exceeds other KD-based methods with a maximum accuracy improvement of 22.8% across various datasets. As ablation experiments indicated, HMKD-Net has cut down on time expenses by about 80% in the KD process. This research study validates that the hybrid-model KD technique can be more effective and efficient if the data distribution sparsity in RSIs is well handled.

Bird flocking is a paradigmatic case of self-organised collective behaviours in biology. Stereo camera systems are employed to observe flocks of starlings, jackdaws, and chimney swifts, mainly on a spot-fixed basis. A portable non-fixed stereo vision-based flocking observation system, namely FlockSeer, is developed by the authors for observing more species of bird flocks within field scenarios. The portable flocking observer, FlockSeer, responds to the challenges in extrinsic calibration, camera synchronisation and field movability compared to existing spot-fixed observing systems. A measurement and sensor fusion approach is utilised for rapid calibration, and a light-based synchronisation approach is used to simplify hardware configuration. FlockSeer has been implemented and tested across six cities in three provinces and has accomplished diverse flock-tracking tasks, accumulating behavioural data of four species, including egrets, with up to 300 resolvable trajectories. The authors reconstructed the trajectories of a flock of egrets under disturbed conditions to verify the practicality and reliability. In addition, we analysed the accuracy of identifying nearest neighbours, and then examined the similarity between the trajectories and the Couzin model. Experimental results demonstrate that the developed flocking observing system is highly portable, more convenient and swift to deploy in wetland-like or coast-like fields. Its observation process is reliable and practical and can effectively support the study of understanding and modelling of bird flocking behaviours.

With the development of deep learning and federated learning (FL), federated intrusion detection systems (IDSs) based on deep learning have played a significant role in securing industrial control systems (ICSs). However, adversarial attacks on ICSs may compromise the ability of deep learning-based IDSs to accurately detect cyberattacks, leading to serious consequences. Moreover, in the process of generating adversarial samples, the selection of replacement models lacks an effective method, which may not fully expose the vulnerabilities of the models. The authors first propose an automated FL-based method to generate adversarial samples in ICSs, called AFL-GAS, which uses the principle of transfer attack and fully considers the importance of replacement models during the process of adversarial sample generation. In the proposed AFL-GAS method, a lightweight neural architecture search method is developed to find the optimised replacement model composed of a combination of four lightweight basic blocks. Then, to enhance the adversarial robustness, the authors propose a multi-objective neural architecture search-based IDS method against adversarial attacks in ICSs, called MoNAS-IDSAA, by considering both classification performance on regular samples and adversarial robustness simultaneously. The experimental results on three widely used intrusion detection datasets in ICSs, such as secure water treatment (SWaT), Water Distribution, and Power System Attack, demonstrate that the proposed AFL-GAS method has obvious advantages in evasion rate and lightweight compared with other four methods. Besides, the proposed MoNAS-IDSAA method not only has a better classification performance, but also has obvious advantages in model adversarial robustness compared with one manually designed federated adversarial learning-based IDS method.

The colour-enhanced point cloud map is increasingly being employed in fields such as robotics, 3D reconstruction and virtual reality. The authors propose ER-Mapping (Extrinsic Robust coloured Mapping system using residual evaluation and selection). ER-Mapping consists of two components: the simultaneous localisation and mapping (SLAM) subsystem and the colouring subsystem. The SLAM subsystem reconstructs the geometric structure, where it employs a dynamic threshold-based residual selection in LiDAR-inertial odometry to improve mapping accuracy. On the other hand, the colouring subsystem focuses on recovering texture information from input images and innovatively utilises 3D–2D feature selection and optimisation methods, eliminating the need for strict hardware time synchronisation and highly accurate extrinsic parameters. Experiments were conducted in both indoor and outdoor environments. The results demonstrate that our system can enhance accuracy, reduce computational costs and achieve extrinsic robustness.

In nature, various animal groups like bird flocks display proficient collective navigation achieved by maintaining high consistency and cohesion simultaneously. Both metric and topological interactions have been explored to ensure high consistency among groups. The topological interactions found in bird flocks are more cohesive than metric interactions against external perturbations, especially the spatially balanced topological interaction (SBTI). However, it is revealed that in complex environments, pursuing cohesion via existing interactions compromises consistency. The authors introduce an innovative solution, assemble topological interaction, to address this challenge. Contrasting with static interaction rules, the new interaction empowers individuals with self-awareness to adapt to the complex environment by switching between interactions through visual cues. Most individuals employ high-consistency k-nearest topological interaction when not facing splitting threats. In the presence of such threats, some switch to the high-cohesion SBTI to avert splitting. The assemble topological interaction thus transcends the limit of the trade-off between consistency and cohesion. In addition, by comparing groups with varying degrees of these two features, the authors demonstrate that group effects are vital for efficient navigation led by a minority of informed agents. Finally, the real-world drone-swarm experiments validate the applicability of the proposed interaction to artificial robotic collectives.

Single-image rain removal is an important problem in the field of computer vision aimed at recovering clean images from rainy images. In recent years, data-driven convolutional neural network (CNN)-based rain removal methods have achieved significant results, but most of them cannot fully focus on the contextual information in rain-containing images, which leads to the failure of recovering some of the background details of the images that have been corrupted due to the aggregation of rain streaks. With the success of Transformer-based models in the field of computer vision, global features can be easily acquired to better help recover details in the background of an image. However, Transformer-based models often require a large number of parameters during the training process, which makes the training process very difficult and makes it difficult to apply them to specific devices for execution in reality. The authors propose a Recursive Attention Collaboration Network, which consists of a recursive Swin-transformer block (STB) and a CNN-based feature fusion block. The authors designed the Recursively Integrate Transformer Block (RITB), which consists of several STBs recursively connected, that can effectively reduce the number of parameters of the model. The final part of the module can integrate the local information from the STBs. The authors also design the Feature Enhancement Block, which can better recover the details of the background information corrupted by rain streaks of different density shapes through the features passed from the RITB. Experiments show that the proposed network has an effective rain removal effect on both synthetic and real datasets and has fewer model parameters than other mainstream methods.

Bagging is an essential skill that humans perform in their daily activities. However, deformable objects, such as bags, are complex for robots to manipulate. A learning-based framework that enables robots to learn bagging is presented. The novelty of this framework is its ability to learn and perform bagging without relying on simulations. The learning process is accomplished through a reinforcement learning (RL) algorithm introduced and designed to find the best grasping points of the bag based on a set of compact state representations. The framework utilises a set of primitive actions and represents the task in five states. In our experiments, the framework reached 60% and 80% success rates after around 3 h of training in the real world when starting the bagging task from folded and unfolded states, respectively. Finally, the authors test the trained RL model with eight more bags of different sizes to evaluate its generalisability.

The authors propose a distributed field mapping algorithm that drives a team of robots to explore and learn an unknown scalar field using a Gaussian Process (GP). The authors’ strategy arises by balancing exploration objectives between areas of high error and high variance. As computing high error regions is impossible since the scalar field is unknown, a bio-inspired approach known as Speeding-Up and Slowing-Down is leveraged to track the gradient of the GP error. This approach achieves global field-learning convergence and is shown to be resistant to poor hyperparameter tuning of the GP. This approach is validated in simulations and experiments using 2D wheeled robots and 2D flying miniature autonomous blimps.