Reliable formation control in real-world multi-agent systems is challenging due to the concurrent need to meet performance specifications, enforce safety constraints, and respect actuator limitations. While prescribed performance control (PPC) ensures bounded error evolution via predefined performance functions, incorporating safety and input constraints within this framework remains nontrivial. This paper develops a modular decoupled control architecture that integrates PPC and control barrier function (CBF) to enforce performance and safety. The fixed performance bound limitation in PPC control is overcome through the introduction of an auxiliary system that adaptively adjusts performance functions, thereby effectively enabling the quantification of performance degradation due to constraints while avoiding control singularities. To further mitigate conflicts between safety and performance, an online trajectory optimization module is designed to generate smooth and collision-free reference trajectories. The proposed approach is validated on a team of Crazyflie quadrotors navigating obstacle environments, demonstrating safe and accurate formation tracking under stringent constraints.

The aim of this study is to investigate the problem of cooperative multi-robot variation parameter design for dynamic formation maneuvers with bearing constraints. Notably, scaling and translation are relatively economical bearing-preserving motions in terms of formation changes. Typically, the variation parameters, i.e., the desired scaling size and translation vector, are designed offline a priori, and it is often challenging to dynamically generate the desired formation in response to a changing ambient environment. This paper proposes an online distributed design method to determine the variation parameters of an entire formation. First, local variation policies are generated by the proposed high-order control barrier functions based on received local excitations from the environment. Subsequently, using the distributed average tracking technique, consensus filters are employed to integrate various local variation policies in a weighted-average manner, which ensures that the bearing is maintained in dynamic formation maneuvers. Finally, numerical simulations and experiments are conducted to demonstrate the effectiveness of the proposed method.Note to Practitioners—This paper is motivated by the neglect of the research on the automatic co-adjustment of the formation variation parameters in most existing formation control schemes, which rely on fixed and pre-defined desired variation parameters (scaling size and translation vector). To address this limitation, this paper suggests an online distributed design method to determine the variation parameters of an entire formation in dynamic ambient environments. The proposed method consists of three parts: 1) By considering received local excitations from the environment as perturbations to asymptotically stable virtual systems, unconstrained local variation policies are generated. 2) By employing high-order control barrier functions, we solve the bounded magnitude constraints for distributed average tracking (DAT) algorithms and the minimum scale constraint for collision avoidance, leading to the generation of constrained local variation policies. 3) By using DAT algorithms, all robots can cooperatively obtain a uniform variation parameter, which is exactly the weighted average of the constrained local variation policies. This ensures that the bearing is maintained in dynamic formation maneuvers. Therefore, the proposed method can be deployed to multi-robot systems in a distributed manner. Finally, numerical simulations and experiments are conducted to demonstrate the feasibility of the proposed method and its potential in industrial applications.

TheSixdegrees of freedom 6DoF pose estimation of texture-less objects provides a spatial understanding of industrial scenes and is the basis for accurate object manipulation. Recent studies have shown that the introduction of known model information and initial poses helps CNNs-based methods achieve better performance in complex scenes. However, the mapping from image space to pose space learned by neural networks is dimensionally lifting. Due to the lack of depth information, it is difficult for neural networks to capture local clues on texture-less surfaces and directly regress the relative 3-D translation and 3-D rotation. Instead, we propose a novel framework named REG-Net, which transforms the 6DoF pose estimation task into a 2-D keypoint registration problem. The proposed network first encodes regional prior information using multi-representation, utilizes the globally-consistent offset attention module to align 2-D keypoint features in a long range, and then estimates offsets and potential regions of keypoints. The proposed regional PnP simultaneously adjusts the keypoint locations in a short range and outputs the pose. This framework compresses the learning space of the network from 3-D to 2-D. Extensive experiments on two benchmark datasets demonstrate the robustness and accuracy of REG-Net. We further demonstrate the effectiveness of REG-Net in the reflective industrial part grasping applications.

Pose estimation is an essential technology for industrial robots to perform precise gripping and assembly. The state-of-the-art deep learning-based approach uses an indirect strategy, i.e., first finding local correspondence between the 2-D image and 3-D model, and then using the perspective-n-point and RANSAC methods to calculate the poses of ordinary objects. However, the metal parts in industry are reflective and textureless, making it difficult to identify distinguishable point features to establish 2-D–3-D correspondences. To address this problem, in this article, we propose a novel deep learning based two-stage method for pose estimation of reflective textureless metal parts, which accurately estimates the target pose using monocular red green blue (RGB) images. Since contours play an important role in both keypoints prediction and pose estimation stages, our method is named ContourPose. First, an additional contour decoder is adopted to implicitly constrain the keypoints prediction in the former stage, which improves the accuracy of the keypoints prediction. Then, the predicted contour of the previous stage is taken as geometric prior that is used to iteratively solve for the optimal pose. Experiments indicate that the proposed approach for reflective textureless metal parts has a significant improvement over the state-of-the-art approaches.

Hyperspectral anomaly detection can detect pixels which differ from the background in the hyperspectral images (HSIs). Deep learning (DL) has been applied in this field due to its ability to learn features. Nevertheless, the present DL-based anomaly detection algorithms take single pixel as input which do not utilize the spatial information. For the widely used push-broom scanners, the utilization of spatial information in sequence data may make features more distinct. Line-wise SAFL is proposed to learn more intrinsic features for HSI anomaly detection, which combines the Adversarial Autoencoder (AAE) with the Long Short Term Memory network (LSTM). The Line-wise SAFL maps sequence data to a low-dimensional space obeying Gaussian distribution which make detection result more accurate. Finally, Reed-Xiaoli (RX) anomaly detector are applied on the latent feature. The experiments show that proposed method can achieves high detection rate with a low false alarm rate, which outperforms other methods.

A major obstacle in digital projector technology is that images projected onto nonideal surfaces with large depth variances can easily become blurred. In this article, present a method to overcome projection defocus for projection surfaces that inevitably have complex shapes and large depth variances. The proposed method has two main advantages over traditional methods. First, an edge-intensification-based defocus compensation algorithm is proposed to manipulate the input image to compensate for its projection defocus before blurring occurs. Unlike previous time-consuming compensation algorithms, the proposed algorithm has very high efficiency, as it is noniterative and open loop. Second, a sinusoidal-projection-based estimation method is proposed to reduce kernel estimation errors on complex surface types. Unlike previous methods limited to specific surface types, the proposed method can provide consistently good kernel estimation results even for discontinuous and textured (nonpure white) projection surfaces. Hence, the proposed method can be applied to a wider range of applicable surfaces. These two contributions are demonstrated through extensive experiments and compared with the state-of-the-art methods.

Image compression is an intensively studied subject in computer vision. The deep generative model, especially generative adversarial networks (GANs), is a popular new direction for this subject. In this study, the authors propose a new compression method based on a generative model and focus on its application by GANs. The decoder in the proposed method is modified from the GAN generator model, which can produce visually real‐like synthetic images. It is one of the two models in GANs, which is trained through a two‐players' contest game. The encoder is an optimisation algorithm called backpropagation‐to‐the‐input, which derives from an image inpainting algorithm based on generative models. In the proposed method, the authors turn the encoding process into an optimisation task to search for optimal encoded representations. Compared with traditional methods, the proposed method can compress images from certain domains into extremely small and shape‐fixed encoded space but still retain better visual representations. It is easy and convenient to apply without any retraining or additional modification to the generative models.

Here, the authors present multistage estimation model embedding with structured pose prior (SPP), a novel coarse‐to‐fine framework for real‐time 3D hand estimation from single depth image. Authors’ main contributions can be summarised as follows: (i) The authors proposed SPP to enforce constraints of canonical hand pose instead of original hand pose. (ii) The authors are the first to adopt under‐complete stacked denoising auto‐encoder (SDA) to construct pose prior by mapping canonical hand pose to latent representation. In the case of enforcing constraints of canonical hand pose, the authors empirically validate that under‐complete SDA outperforms over‐complete SDA in improving the hand estimation accuracy. (iii) The authors propose candidate keypoints patches (CKP) as intermediate data to conduct further hand pose refinement. Experimental evaluation on two publically available datasets shows that authors’ model is competitive both in accuracy and computation time. Especially, authors’ method placed first in the location of palm key‐point on both two datasets, and the high accuracy of hand palm key‐point plays an important role in many applications, such as that manipulator can grasp objects to specific coordinates with the guiding of human hand palm.

Traffic forecasting is increasingly taking on an important role in many intelligent transportation systems (ITS) applications. However, prediction is typically performed for individual road segments and prediction horizons. In this study, we focus on the problem of collective prediction for multiple road segments and prediction-horizons. To this end, we develop various matrix and tensor based models by applying partial least squares (PLS), higher order partial least squares (HO-PLS) and N-way partial least squares (N-PLS). These models can simultaneously forecast traffic conditions for multiple road segments and prediction-horizons. Moreover, they can also perform the task of feature selection efficiently. We analyze the performance of these models by performing multi-horizon prediction for an urban subnetwork in Singapore.

An illumination-invariant background model for detecting objects in dynamic scenes is proposed. It is robust in the cases of sudden illumination fluctuation as well as burst moving background. Unlike previous works, it distinguishes objects from a dynamic background using co-occurrence character between a target pixel and its supporting pixels in the form of multiple pixel pairs. Experiments used several challenging datasets that proved the robust performance of object detection in various environments.

In this paper, we present a novel robust technique for background subtraction in different complex conditions (e.g. sudden illumination changes, swaying leaves, and camera vibrations). Unlike the previous works, the proposed method utilizes multiple point pairs that exhibit a stable statistical intensity relationship as a background model. The intensity difference between pixels of the pair is much more stable than the intensity of a single pixel, especially in varying environments. Furthermore, our proposed method focuses more on the history of global spatial correlations between pixels than on the history of any given pixel or local spatial correlations. we also adopt an adapted judgement criterion to ensure our method displays well in real-time detection. The approach has been compared with the state of the art on videos from several challenging datasets (PETS, Wallflower, and i-Lids), demonstrating that superior object detection is achieved.