The rapid development of Uncrewed Aerial Vehicles (UAVs) and their unique vantage points present both new opportunities and challenges for person Re-Identification (ReID). Uncertain rotations and scale variations of targets in UAV images, coupled with complex environmental factors, hinder existing methods from extracting robust feature representations. Some methods either make minor modifications to the traditional model architecture or apply simple image rotations but still fail to effectively address the challenges of UAV person ReID. To overcome these limitations, we propose a novel Data Augmentation and Rotation Invariance (DARI) algorithm. First, rotation-invariant convolution is introduced to adaptively extract features, mitigating the uncertainty caused by target rotation. Second, a refined data augmentation correction strategy is employed to reduce noise interference by increasing the richness of global features at different stages. Additionally, considering that multiple features of the same identity should yield consistent recognition result, invariant constraints are designed to enhance the clustering effect. We conducted extensive experiments on both UAV and fixed-camera datasets. The results on PRAI-1581 demonstrate a 5.6% and 6.1% improvement in mAP and Rank-1, respectively, compared to baseline. These findings highlight the model’s effectiveness in addressing the challenges of UAV ReID, demonstrating its robustness and superiority.

Large Language Models (LLMs) have been widely utilized to perform complex robotic tasks. However, handling external disturbances during tasks is still an open challenge. This paper proposes a novel method to achieve robotic adaptive tasks based on LLMs and Behavior Trees (BTs). It utilizes ChatGPT to reason the descriptive steps of tasks. In order to enable ChatGPT to understand the environment, semantic maps are constructed by an object recognition algorithm. Then, we design a Parser module based on Bidirectional Encoder Representations from Transformers (BERT) to parse these steps into initial BTs. Subsequently, a BTs Update algorithm is proposed to expand the initial BTs dynamically to control robots to perform adaptive tasks. Different from other LLM-based methods for complex robotic tasks, our method outputs variable BTs that can add and execute new actions according to environmental changes, which is robust to external disturbances. Our method is validated with simulation in different practical scenarios.

Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms of generalization. Although masked image modeling (MIM) has achieved noteworthy advancements across various high-level tasks (e.g., classification, detection etc.). In this work, we take on a novel perspective to investigate its capabilities in terms of quality- and aesthetics-awareness. To this end, we propose Quality- and aesthetics-aware pretraining (QPT V2), the first pretraining framework based on MIM that offers a unified solution to quality and aesthetics assessment. To perceive the high-level semantics and fine-grained details, pretraining data is curated. To comprehensively encompass quality- and aesthetics-related factors, degradation is introduced. To capture multi-scale quality and aesthetic information, model structure is modified. Extensive experimental results on 11 downstream benchmarks clearly show the superior performance of QPT V2 in comparison with current state-of-the-art approaches and other pretraining paradigms. Code and models will be released at https://github.com/KeiChiTse/QPT-V2.

Intelligent reflecting surface (IRS) has recently gained significant academic interest as a prospective contender for improving wireless communication system coverage and spectral efficiency. This paper investigates a robust beamforming design of an IRS-aided dual-functional radar-communication (DFRC) system in the presence of channel uncertainty, as opposed to the idealistic assumption of perfect channel state information (CSI) in the existing literature. The optimization is carried out by minimizing the transmit power while ensuring the detection performance and the achievable rate of the user meets the quality of service (QoS) requirement, which turns out to be a non-convex and intractable problem. To circumvent this issue, we alternatively update the transmit beamforming vector and the phase shifts at the IRS using the block coordinate descent (BCD) algorithm. Afterwards, the resulting two sub-problems can be efficiently solved with the help of approximation and transformation techniques. Simulation results have validated the convergence and effectiveness of the proposed algorithm.

Abstract The use of deep neural networks has revolutionised object tracking tasks, and Siamese trackers have emerged as a prominent technique for this purpose. Existing Siamese trackers use a fixed template or template updating technique, but it is prone to overfitting, lacks the capacity to exploit global temporal sequences, and cannot utilise multi‐layer features. As a result, it is challenging to deal with dramatic appearance changes in complicated scenarios. Siamese trackers also struggle to learn background information, which impairs their discriminative ability. Hence, two transformer‐based modules, the Spatio‐Temporal Fusion (ST) module and the Discriminative Enhancement (DE) module, are proposed to improve the performance of Siamese trackers. The ST module leverages cross‐attention to accumulate global temporal cues and generates an attention matrix with ST similarity to enhance the template's adaptability to changes in target appearance. The DE module associates semantically similar points from the template and search area, thereby generating a learnable discriminative mask to enhance the discriminative ability of the Siamese trackers. In addition, a Multi‐Layer ST module (ST + ML) was constructed, which can be integrated into Siamese trackers based on multi‐layer cross‐correlation for further improvement. The authors evaluate the proposed modules on four public datasets and show comparative performance compared to existing Siamese trackers.

3D perception of objects is critical for many real-world applications, such as autonomous cars and robots. Among them, most state-of-the-art (SOTA) 3D perception systems are based on deep learning models. Recently, the research community found that 3D object classifiers on point cloud based on deep learning are easily fooled by adversarial point cloud craft by attackers. To overcome this, adversarial defenses are considered the most effective ways to improve the robustness of deep learning models, and most adversarial defenses on point cloud are focused on input transformation. However, all previous defense methods decrease the natural accuracy, and the nature of the point cloud classifiers itself has been overlooked. To this end, in this paper, we propose a novel adversarial defense for 3D point cloud classifiers that makes full use of the nature of the point cloud classifiers. Due to the disorder of point cloud, all point cloud classifiers have the property of permutation invariant to the input point cloud. Based on this nature, we design invariant transformations defense (IT-Defense). We show that, even after accounting for obfuscated gradients, our IT-Defense is a resilient defense against SOTA 3D attacks. Moreover, IT-Defense does not hurt clean accuracy compared to previous SOTA 3D defenses. Our code will be available at: https://github.com/cuge1995/IT-Defense.

Despite the recent success of visual recognition on artificially balanced datasets, the performance degrades heavily in face of the long-tailed distribution. Existing methods typically tackle this problem by re-balancing the distribution in the data space. However, we observe that more balanced data distribution can not effectively alleviate the problem of uneven feature distribution, still leading to a heavily biased classifier. In this paper, we propose a novel re-balancing framework, Feature Re-Balancing (FeatRB), which directly re-balances the distribution in the feature space by combining the long-tailed initial features and the generated virtual features. The key ideas of FeatRB include: 1) Generating the virtual features. First, we calculate the class-wise feature mean and variance based on the past learned representations and store them in a memory bank. Then we generate virtual features based on the memory bank. And to increase the diversity of generated features, we transfer the variance from similar classes to tail classes. 2) Utilizing the generated features. We introduce a simple but effective sampling strategy, Effective Number Reversed Sampling (ENRS), to assign larger sampling probability for tail classes. 3) Updating the memory bank. We propose an updating method, Adaptive Updating (AU), which adaptively updates the memory bank in the training process to further improve the diversity. By increasing the intra-class diversity, FeatRB enlarges the spatial span for the features of tail classes. Therefore, the discriminative power of tail classes can be enhanced, and then the biased classifier can be calibrated. Extensive experiments on three widely used large-scale long-tailed datasets show that our FeatRB surpasses the current state-of-the-art methods.

For tolerating Byzantine faults of both the terminal and communication components in self-stabilizing clock synchronization, the two-dimensional self-stabilizing Byzantine-fault-tolerant clock synchronization problem is investigated and solved. By utilizing the time-triggered (TT) stage provided in the underlying networks as TT communication windows, the approximate agreement, hopping procedure, and randomized grandmasters are integrated into the overall solution. It is shown that with partitioning the communication components into 3 arbitrarily connected subnetworks, efficient synchronization can be achieved with one such subnetwork and less than 1/3 terminal components being Byzantine. Meanwhile, the desired stabilization can be reached for the specific networks in one or several seconds with high probabilities. This helps in developing various distributed hard-real-time systems with stringent time, resources, and safety requirements.

The authenticated broadcast is simulated in the bounded-degree networks to provide efficient broadcast primitives for building efficient higher-layer Byzantine protocols. A general abstraction of the relay-based broadcast system is introduced, in which the properties of the relay-based broadcast primitives are generalized. With this, fault-tolerant propagation is proposed as a building block of the broadcast primitives. Meanwhile, complementary systems are proposed in complementing fault-tolerant propagation and localized communication. Analysis shows that efficient fault-tolerant propagation can be built with sufficient initiation areas. Meanwhile, by integrating fault-tolerant propagation and localized communication, efficient broadcast primitives can be built in bounded-degree networks.

To improve the overall efficiency and reliability of Byzantine protocols in large sparse networks, we propose a new system assumption for developing multi-scale fault-tolerant systems, with which several kinds of multi-scale Byzantine protocols are developed in large sparse networks with high system assumption coverage. By extending the traditional Byzantine adversary to the multi-scale adversaries, it is shown that efficient deterministic Byzantine broadcast and Byzantine agreement can be built in logarithmic-degree networks. Meanwhile, it is shown that the multi-scale adversary can make a finer trade-off between the system assumption coverage and the overall efficiency of the Byzantine protocols, especially when a small portion of the low-layer small-scale protocols are allowed to fail arbitrarily. With this, efficient Byzantine protocols can be built in large sparse networks with high system reliability.

3D object detection based on LiDAR point cloud has gained more and more attention from industry and academia. Most of the previous works are carried out on the KITTI dataset, which has the gap with real-world scenes in terms of data size and distribution. Faced with large-scale datasets, existing methods have encountered with some problems, especially in the detection of difficult targets and heading prediction. In this paper, we design an integrated framework to improve 3D object detection accuracy targeting on large-scale datasets. We explore data augmentation methods from the perspective of data-rich scenes. Two well-designed auxiliary losses are introduced into our framework to relieve the problem caused by the diversity of points density and distribution. To promote the performance of heading prediction, the existing heading classifier is replaced by our novel dual heading classifier. Experiments on the largest and most realistic 3D object detection benchmark of Waymo Open Dataset show that our integrated framework boosts the detection accuracy for a large margin.

LiDAR-based 3D object detection is important for numerous applications, such as autonomous driving and robot navigation. How to use the specialized geometric representation of point clouds, such as surface normal, to promote the performance of 3D detection is an essential but seldom explored issue. In this paper, we introduce a normal module using geometric surface normal representation to supplement existing methods using coordinate representation. We also propose an attention module for further integration. It integrates features learning from the two representations – coordinate and surface normal, so that they can make up for each other's feature space. Our framework can improve the object detection accuracy, especially for targets with complementary coordinate and surface normal features. As far as we know, we are the first work applying surface normal of LiDAR point cloud to 3D object detection, which can be easily extended to other LiDAR-based methods. Extensive experiments on the KITTI dataset demonstrate that our method boosts the performance of 3D object detection for the voxel-based methods and achieves state-of-the-art results.

The recent success of Deep Convolutional Neural Network (DCNN) for various computer vision tasks such as image recognition has already demonstrated its robust feature representation ability. However, the limitation of training database on small scale vein recognition tasks restricts its performance because the recognition result of DCNN depends heavily on the number of trainsets. This motivates the design of a Multi-Scale Deep Representation Aggregation (MSDRA) model based on a pre-trained DCNN for vein recognition. First, the multi-scale feature maps are extracted by a pre-trained DCNN model. Second, a local mean threshold approach is designed to preliminarily remove the noisy information of multi-scale feature maps and generate the selected feature maps. Third, we propose an Unsupervised Vein Information Mining (UVIM) method to localize vein information of selected feature maps for generating a binary vein information mask, and then the vein information mask is utilized to keep useful deep representation and discard the background information. Finally, the discriminative multi-scale deep representations, which are generated by using the vein information mask to aggregate multi-scale feature maps, are concatenated into the final compact feature vectors, and then a Support Vector Machine (SVM) is introduced for final recognition. Our proposed model outperforms the state-of-the-art methods on two benchmark vein databases. Moreover, an additional experiment using the subset of PolyU Palmprint database illustrates the system's generalization ability and robustness.

Aerial imagery plays an important role in land-use planning, population analysis, precision agriculture, and unmanned aerial vehicle tasks. However, existing aerial image datasets generally suffer from the problem of inaccurate labeling, single ground truth type, and few category numbers. In this work, we implement a simulator that can simultaneously acquire diverse visual ground truth data in the virtual environment. Based on that, we collect a comprehensive Virtual AeriaL Image Dataset named VALID, consisting of 6690 high-resolution images, all annotated with panoptic segmentation on 30 categories, object detection with oriented bounding box, and binocular depth maps, collected in 6 different virtual scenes and 5 various ambient conditions (sunny, dusk, night, snow and fog). To our knowledge, VALID is the first aerial image dataset that can provide panoptic level segmentation and complete dense depth maps. We analyze the characteristics of VALID and evaluate state-of-the-art methods for multiple tasks to provide reference baselines. The experiment results demonstrate that VALID is well presented and challenging. The dataset is available at https://sites.google.com/view/valid-dataset/.

Tail-sitter unmanned aerial vehicles (UAVs) have broad application prospects since they merge advantages of both fixed-wing UAVs and rotary-wing UAVs. However, there exist great challenges in the transition maneuvers due to model un-certainties and external disturbances. Aimed at these problems, a robust transition controller based on incremental nonlinear dynamic inversion (INDI) is developed for a tail-sitter UAV in this paper. Different from existing works, the controller mainly concerns the transition pitch angle and altitude, because the altitude is more intuitive then flight speed in indicating whether a transition is successful or not. The robustness of the developed transition controller is analyzed with consideration of error terms exist in the closed-loop system, which were generally omitted in existing INDI flight control works. With some reasonable assumptions, it is proven that the tracking errors can converge into a specified neighbourhood of the origin in a finite time by choosing appropriate controller parameters. Numerical simulations demonstrate the robustness of the controller in handling model uncertainties and external disturbances.

As an extension of the conventional prescribed tracking performance constraint problem, this paper proposes a novel online tracking performance constrained control combined with the dynamic surface control (DSC) technique for a class of strict-feedback nonlinear systems with unmeasurable states and input saturation. Using fuzzy logic systems to approximate the unknown nonlinear functions, a high-gain fuzzy observer is designed for state estimation. In the development of DSC control, a serial-parallel estimation model is introduced to analyze the effect of input saturation, and a compensation term is added. To deal with the singularity problem of the prescribed performance constrained method, a novel online performance function is investigated to obtain a satisfactory tracking performance. Under the proposed control scheme, the stability and boundedness of all closed-loop signals are confirmed via Lyapunov synthesis. Finally, numerical simulation results illustrate the effectiveness of the proposed scheme.

Tail-sitter unmanned aerial vehicles (UAVs) have gained extensive popularity in recent years due to their inherent advantages of both fixed wing and rotary wing UAVs. However, these advantages are accompanied with control challenges because of two different flight regimes and drastically changing dynamics during transition flights. This paper focuses on the design of a unified controller free from cumbersome controller switchings and applicable in all attitude range for a tail-sitter with single thrust-vectored propeller. To achieve this, both thrust vectoring model and full-regime aerodynamics model are built first, after which a complete attitude dynamics model of the tail-sitter is established utilizing the quaternion attitude description to avoid the singularity problem. An adaptive controller is then derived based on a simplified model using the Lyapunov stability theory with unknown system parameters identified online by forgetting factor recursive least square (FF-RLS) method. Flight experiments are conducted to demonstrate the feasibility and effectiveness of the proposed control scheme.

In this paper, we propose a new pipeline of training a monocular UAV to fly a collision-free trajectory along the dense forest trail. As gathering high-precision images in the real world is expensive and the off-the-shelf dataset has some deficiencies, we collect a new dense forest trail dataset in a variety of simulated environment in Unreal Engine. Then we formulate visual perception of forests as a classification problem. A ResNet-18 model is trained to decide the moving direction frame by frame. To transfer the learned strategy to the real world, we construct a ResNet-18 adaptation model via multi-kernel maximum mean discrepancies to leverage the relevant labelled data and alleviate the discrepancy between simulated and real environment. Simulation and real-world flight with a variety of appearance and environment changes are both tested. The ResNet-18 adaptation and its variant model achieve the best result of 84.08% accuracy in reality.

Unmanned aerial vehicle (UAV) has become more and more widely adopted in military, commercial, scientific, recreational, agricultural fields. To build a practicable UAV system, one crucial problem is to design an efficient, high-certainty and realtime communication system for UAV, where the time-triggered network [1] is mostly used to replace the traditional event-triggered network. As for the base node of the UAV network, Field-Programmable Gate Array (FPGA) is usually used for its great computing power, excellent programming flexibility, and cost-efficient expense [2]. Therefore, the network system in this paper is also implemented based on FPGA using the time-triggered mechanism for UAV.

This paper presents the development and hovering control of a tailsitter unmanned aerial vehicle (UAV) that merges long endurance and vertical takeoff and landing (VTOL) abilities. The designed tailsitter contains one flying-wing with two motors and two elevons. Vehicle aerodynamics and a six-degrees-of-freedom (6-DOF) model are especially developed for the tailsitter. To achieve a good performance in outdoor stationary hovering and accurate vertical flying, the active disturbance rejection control (ADRC) for attitude controller is proposed. With signals from extended state observer (ESO) and tracking differentiator (TD), ADRC decouples the system model into a controllable chain of integrators. Based on the decoupled system dynamics, the motion of tailsitter can be easily handled by developed position controller. Experimental results are presented to corroborate the effectiveness of the controller in disturbance rejection.

This paper discusses the design and control methods of a thrust-vectored tailsitter that combines the advantages of both fixed wing and rotary wing systems. Separable takeoff bracket and controllable forward landing are implemented to reduce the flight weight and mitigate the effects of crosswinds. A six-degrees-of-freedom model especially for this tailsitter is then proposed to describe the dynamics of the whole system. Attitude representation based on horizontal /vertical Euler angles is presented to avoid the problem of singularity. Attitude and altitude controllers that switch between horizontal and vertical modes are used. In these controllers linear/constant acceleration approximation and filtered feed-forward acceleration algorithm are implemented. Effectiveness and reliability of the proposed control methods are demonstrated and evaluated by experimental results of the whole flight envelope.

This paper focuses on the design, modelling and hovering control of a tail-sitter with single thrust-vectored propeller which possesses the inherent advantages of both fixed wing and rotary wing unmanned aerial vehicles (UAVs). The developed tail-sitter requires only the same number of actuators as a normal fixed wing aircraft and achieves attitude control through deflections of the thrust-vectored propeller and ailerons. Thrust vectoring is realized by mounting a simple gimbal mechanism beneath the propeller motor. Both the thrust vector model and aerodynamics model are established, which leads to a complete nonlinear model of the tail-sitter in hovering state. Quaternion is applied for attitude description to avoid the singularity problem and improve computation efficiency. Through reasonable assumptions, a simplified model of the tail-sitter is obtained, based on which a backstepping controller is designed using the Lyapunov stability theory. Experimental results are presented to demonstrate the effectiveness of the proposed control scheme.

This paper focused on the aerodynamic modeling for hypersonic flight vehicles, taking into account the scramjet effects on aerodynamics. A methodology was proposed for aerodynamic modeling in this case. First, aerodynamic models were identified at each Mach number with the scramjet engine off. Then, the differences between aerodynamics with engine on and those with engine off were modeled to describe the scramjet effects on aerodynamics. Stepwise regression was applied to determine model structures and model parameters were estimated by using the least squares method. The flight simulation platform was constructed by applying the aerodynamic database to conduct flight tests. Multi-sine and multi-step inputs were designed for control surface perturbations to perform specific maneuvers to excite the hypersonic vehicle sufficiently. Simulation results were presented to demonstrate the validity of the proposed aerodynamic models.

This paper focuses on identification of systems with rate saturation nonlinearity, considering measurement and process noises. A methodology is proposed to estimate the parameters of linear dynamics along with the upper and lower limits of rate saturation, using only system input and output. The methodology consists of four correlative parts which sequentially are choosing sine sweep signal with appropriate amplitude and frequency as input to excite the system sufficiently, designing a Kalman filter based on the constant rate model to obtain rate optimal estimation, suggesting a window scanning and filtrating method which deals with rate estimation to identify rate saturation limits, and applying the bias compensation recursive least squares with valid input and output data filtrated by the estimated rate limits to identify linear dynamics. Simulation results of a position servo system with rate saturation are presented to illustrate the validity of the proposed technique.

The prop-hanging control of the fixed-wing aircraft can enable the vehicle to improve the cruise performance and hover ability. The prop-hanging control of the thrust vector vehicle would be a challenging problem, for the reason that it is a system with properties of inherent instability, coupling, non-linearity and non-minimum phase characteristics. To deal with these complex problems, a hybrid Nonlinear Dynamic Inversion (NDI) method is proposed in this paper. Inspired by NDI, Incremental NDI and angular acceleration feedback control methods, the hybrid NDI method includes three parts: feedforward control, proportional control and logical integral control, which can enable the system to have a rapid response in the transient phase and a satisfactory performance in the steady state. A numerical simulation is conducted to test the performance and the robustness of the proposed control method, and a Hardware-in-the-loop simulation is also conducted to check the practicability and effectiveness in the actual application. Simulation results show that the proposed control method can effectively improve system robustness and is practical.

The optimal state estimation problem for sampled-data systems with randomly sampled and delayed measurements is addressed in this paper. An optimal filter is presented first for the sampled-data system with randomly sampled and delay-free measurements from multiple sensors. The filter, which has been proved to be optimal in the sense of minimum estimation variance, updates the state estimation once new measurements are available. The result is applicable to a wide range of sampling cases of which the corresponding state estimation procedures are formulated separately. Discrete-time equivalent of the filter is also derived rigorously which makes it feasible for computer implementation. Furthermore, we extend the optimal filter and develop a sliding time window estimator through the measurement reorganization technique to deal with the situation of delayed measurements. Monte-Carlo simulations are carried out to demonstrate the effectiveness of the proposed approach.

The external disturbances together with endogenous unknown dynamics need to be concerned eternally in control problems. And the inverted pendulum problem is one of the most essential and classical problems in control engineering. In this paper, the cascaded linear Active Disturbance Rejection Control (ADRC) method is proposed to stabilize the pendulum around its unstable equilibrium and track the desired position with disturbance and measurement noise. Simulation results justify the effectiveness and robustness, and offer a better performance against external disturbances in comparison with the common PID & linear quadratic regulator (LQR) method.

This paper seeks to model the Integrated Modular Avionics (IMA) using Architectural Analysis and Design Language (AADL). In particular, the mechanism to describe the dynamic reconfiguration of multimodal system is presented. By translating the AADL model into Time Petri Net (TPN), some real-time and logical properties (deadlock, reach ability, missed deadline) of reconfiguration could be checked. The analysis results could then be used to adjust the design of software at the early stage of system development and ensure that the reconfiguration of IMA meets the real-time constraints.