Relative Distance Information Research Articles

Bilinear Distance Feature Network for Semantic Segmentation in PowerLine Corridor Point Clouds

Semantic segmentation of target objects in power transmission line corridor point cloud scenes is a crucial step in powerline tree barrier detection. The massive quantity, disordered distribution, and non-uniformity of point clouds in power transmission line corridor scenes pose significant challenges for feature extraction. Previous studies have often overlooked the core utilization of spatial information, limiting the network’s ability to understand complex geometric shapes. To overcome this limitation, this paper focuses on enhancing the deep expression of spatial geometric information in segmentation networks and proposes a method called BDF-Net to improve RandLA-Net. For each input 3D point cloud data, BDF-Net first encodes the relative coordinates and relative distance information into spatial geometric feature representations through the Spatial Information Encoding block to capture the local spatial structure of the point cloud data. Subsequently, the Bilinear Pooling block effectively combines the feature information of the point cloud with the spatial geometric representation by leveraging its bilinear interaction capability thus learning more discriminative local feature descriptors. The Global Feature Extraction block captures the global structure information in the point cloud data by using the ratio between the point position and the relative position, so as to enhance the semantic understanding ability of the network. In order to verify the performance of BDF-Net, this paper constructs a dataset, PPCD, for the point cloud scenario of transmission line corridors and conducts detailed experiments on it. The experimental results show that BDF-Net achieves significant performance improvements in various evaluation metrics, specifically achieving an OA of 97.16%, a mIoU of 77.48%, and a mAcc of 87.6%, which are 3.03%, 16.23%, and 18.44% higher than RandLA-Net, respectively. Moreover, comparisons with other state-of-the-art methods also verify the superiority of BDF-Net in point cloud semantic segmentation tasks.

Simulated annealing-particle swarm optimization initial orbit determination method for too-short-arcs

The initial orbit determination (IOD) of a non-cooperative satellite through space-based optical angle-only measurement data is a fundamental task. However, due to the lack of relative distance information of the targets, traditional methods have problems with poor accuracy and robustness in orbit determination results. The application of particle swarm optimization algorithm for IOD under optical too-short-arcs (TSA) measurement data has achieved good results. However, there is still a problem of convergence to local extremum. This article proposes a simulated annealing-particle swarm optimization (SA-PSO) hierarchical algorithm, which combines the efficient searchability of particle swarm optimization with the fine searchability of simulated annealing algorithm to achieve robust and precise optimization of non-cooperative targets orbit elements. The experimental results show the SA-PSO algorithm significantly improves the accuracy of orbit elements prediction compared to the particle swarm optimization algorithm and proves its effectiveness.

Joint extraction of biomedical overlapping triples through feature partition encoding

Entities and relations extraction are the key tasks in the construction of biomedical knowledge graph, which play an important role in the biomedical artificial intelligence. However, extraction of entities and relations from biomedical texts is challenging because of the overlapping triples problem. The previous approaches typically divided the task into two separate sub-tasks. However, these methods failed to address the error propagation problem. Recent methods have been proposed to perform both sub-tasks simultaneously. Nonetheless, most current methods still encounter issues related to imbalanced interactions and independent features. In this paper, we propose a novel method based on feature partition encoding and relative positional embedding to joint extract biomedical entity and relation triples simultaneously. Compared to previous work, our method shows exceptional accurate in extracting entities and relations, while efficiently tackling the challenge of overlapping triples in biomedical texts. Our work has two contributions. Firstly, our method divides the features into task-specific and shared parts through entity, relation and sharing partitions at the encoding stage. And the encoded features will be aggregated according to the subsequent tasks. Secondly, we introduce a relative positional embedding method to capture the relative distance information between token pairs. In this way, our method can effectively deal with the sub-tasks interactions problem and improve entities and relations extraction. The experimental results show that our method improves the F1 scores of relations extraction by 3.2%, 2.1%, 3.4%, and 2.8% on four biomedical datasets, respectively.

DeepMatcher: A deep transformer-based network for robust and accurate local feature matching

Local feature matching constitutes the cornerstone of multiple computer vision applications (e.g., 3D reconstruction and long-term visual localization), and has been successfully resolved by detector-free methods. To further improve the matching performance, more recent research has focused on designing sophisticated architectures but endures additional computational overhead. In this study, with a different perspective from previous studies, we aim to develop a deep and compact matching network to improve performance while reducing computing cost. The key insight is that a local feature matcher with deep layers can capture more human-intuitive and simpler-to-match features. To this end, we propose DeepMatcher, a deep transformer-based network that tackles the inherent obstacles of not being able to build a deep local feature matcher with current methods. DeepMatcher consists of: (1) a local feature extractor (LFE), (2) a feature-transition module (FTM), (3) a slimming transformer (SlimFormer), (4) a coarse matches module (CMM), and (5) a fine matches module (FMM). The LFE is utilized to generate dense keypoints with enriched features from the images. We then introduce the FTM to ensure a smooth transition of feature scopes from LFE to the subsequent SlimFormer because of their different receptive fields. Subsequently, we develop SlimFormer dedicated to DeepMatcher, which leverages vector-based attention to model the relevance among all keypoints, enabling the network to construct a deep Transformer architecture with less computational cost. Relative position encoding is applied to each SlimFormer to explicitly disclose the relative distance information, thereby improving the representation of the keypoints. A layer-scale strategy is also employed in each SlimFormer to enable the network to adaptively assimilate message exchange, thus endowing it to simulate human behavior, in which humans can acquire different matching cues each time they scan an image pair. By interleaving the self- and cross-SlimFormers multiple times, DeepMatcher can easily establish pixel-wise dense matches at the coarse level using the CMM. Finally, we consider match refinement as a combination of classification and regression problems and design an FMM to predict confidence and offset concurrently, thus generating robust and accurate matches. Compared with our baseline LoFTR in indoor/outdoor pose estimation, DeepMatcher surpasses it by 3.32%/2.91% in AUC@5∘. Besides, DeepMatcher and DeepMatcher-L significantly reduce computational cost and only consume 77.89% and 92.46% GFLOPs of LoFTR. Large DeepMatcher considerably outperforms state-of-the-art methods on several benchmarks, including outdoor pose estimation (MegaDepth dataset), indoor pose estimation (ScanNet dataset), homography estimation (HPatches dataset), and image matching (HPatches dataset), demonstrating the superior matching capability of a deep local feature matcher.

Weight Factor Graph Co-Location Method for UAV Formation Based on Navigation Performance Evaluation

At present, multiple unmanned aerial vehicles (UAVs) collaboration have attracted people’s more and more attention. The abundant relative distance information in UAV cooperative network can be employed to further improve UAV’s positioning accuracy. However, the traditional distance-based cooperative localization (CL) algorithm does not consider the performance of cooperative navigation information. Cooperative information with poor navigation performance will affect follower UAV’s state estimation accuracy. Thus, this paper proposes a weight factor graph CL method based on navigation performance evaluation. A novel navigation performance evaluation strategy based on Fisher information and relative entropy is proposed. The distance observations and cooperative nodes’ positions with higher estimation accuracy and contribution are selected to estimate follower UAV’s position. Considering the difference contributions of the selected cooperative information to follower UAV’s state estimation, we employ the information weight processing to achieve higher state estimation accuracy. Based on the selected cooperative information and weight coefficient, a multi-UAVs cooperative optimization graph model based on navigation performance is constructed. The global optimization cost function is constructed using relative distance constraints from the current time to historical time in the sliding window. The global optimal navigation solution of follower UAV is achieved using iterative weighted least squares method. Simulation and experiment results show that the proposed navigation performance evaluation strategy can effectively screen cooperative information with higher estimation accuracy and contribution for CL. Using the selected high-quality cooperative information, the system computational complexity is reduced without significantly affecting system positioning accuracy.

Subgraph Learning for Topological Geolocalization with Graph Neural Networks.

One of the challenges of spatial cognition, such as self-localization and navigation, is to develop an efficient learning approach capable of mimicking human ability. This paper proposes a novel approach for topological geolocalization on the map using motion trajectory and graph neural networks. Specifically, our learning method learns an embedding of the motion trajectory encoded as a path subgraph where the node and edge represent turning direction and relative distance information by training a graph neural network. We formulate the subgraph learning as a multi-class classification problem in which the output node IDs are interpreted as the object's location on the map. After training using three map datasets with small, medium, and large sizes, the node localization tests on simulated trajectories generated from the map show 93.61%, 95.33%, and 87.50% accuracy, respectively. We also demonstrate similar accuracy for our approach on actual trajectories generated by visual-inertial odometry. The key benefits of our approach are as follows: (1) we take advantage of the powerful graph-modeling ability of neural graph networks, (2) it only requires a map in the form of a 2D graph, and (3) it only requires an affordable sensor that generates relative motion trajectory.

IEA-GNN: Anchor-aware graph neural network fused with information entropy for node classification and link prediction

Graph neural networks are essential in mining complex relationships in graphs. However, most methods ignore the global location information of nodes and the discrepancy between symmetrically located nodes, resulting in the inability to distinguish between nodes with homogeneous network neighborhoods. We propose an Anchor-aware Graph Neural Network fused with Information Entropy (IEA-GNN) to capture the global location information of nodes in the graph. IEA-GNN first calculates the information entropy of nodes and constructs candidate sets of anchors. We define the calculation method of the distance from any node to the anchor points and incorporate the relative distance information between nodes at initialization. The nonlinear distance-weighted aggregation learning strategy based on the anchor points of candidate sets is used to obtain the nodes' feature information, which can be captured more effectively by fusing the global location information to the node representation with the selected anchor points. Selecting anchor points based on information entropy avoid the aggregation of anchor points in the graph, highlighting the positional differences between nodes and making it easier to distinguish homogeneous neighborhood nodes. Experimental results of node classification and link prediction on five datasets show that IEA-GNN outperforms the baseline model.

Research on the improvement of the LaneGCN trajectory prediction algorithm

Abstract The LaneGCN proposed by Uber has achieved good performance in trajectory prediction, but it has shortcomings in capturing long range information, expressing road information and modelling the strong and weak relationships of interaction between actors. In this paper, the LaneGCN is improved from three parts. Firstly, multi-scale long short-term memory is introduced to encode multi-scale trajectory information. Secondly, relative distance information is added to enhance the spatial expressive capacity of the model in the process of road information encoding. Finally, we build a weighted interaction model based on Graph Attention Networks in the process of road information encoding. In order to verify the performance of the improved model, ablation and comparison experiments are designed in this paper. The results showed that all the evaluation metrics are lower than the LaneGCN and the overall performance of the model is improved.

Multimobile Robot Cooperative Localization Using Ultrawideband Sensor and GPU Acceleration

To tackle the poor localization accuracy of multimobile robots caused by non-line-of-sight (NLOS) errors in a complex indoor environment and to meet the real-time requirement, this article proposes a multimobile robot cooperative localization system using ultrawideband (UWB) sensor and GPU hardware acceleration. First, a UWB multinode ranging network is established to obtain the relative distance information between robots and anchors. Then, the line-of-sight (LOS) and NLOS errors in distance information are effectively mitigated by using the proposed UWB ranging error mitigation algorithm based on the Bayesian filter. A cooperative particle filter (PF) localization algorithm based on the Gibbs sampling is designed to estimate the position information of each robot at any time. Finally, in order to improve the real-time performance of the collaborative localization system, a parallel Gibbs collaborative localization algorithm that can be accelerated by GPU is proposed considering the characteristics of GPU hardware and CUDA programming model. The experimental results of three TurtleBot2 mobile robots in real scene show that the proposed multimobile robot cooperative localization system using UWB technology can estimate the position information of each robot robustly and accurately, and the localization accuracy is superior to that of the popular extended Kalman filter (EKF) and PF algorithms. It is shown through further evaluations that the proposed parallel algorithm achieves about 3.2 times acceleration effect in the scenarios of three mobile robots. The speed gain is found more significant with more robots, which substantially improves the real-time performance of the cooperative localization system. In the test with seven mobile robots, the speedup is as high as 11.9, that is, the execution time of the algorithm is only 8.39% of that of the original algorithm. Note to Practitioners—The purpose of this article is to improve the accuracy and real-time indoor multimobile robot cooperative localization, but the method proposed in this article is also applicable to outdoor multimobile robot cooperative localization. The existing methods for indoor cooperative localization of mobile robots usually use Bluetooth, infrared, RFID, and other technologies to establish a wireless sensor network (WSN) and then combine Karman filter or particle filter (PF) to achieve cooperative localization, which is difficult to achieve low-cost and high-precision real-time localization. In this article, a new method of cooperative localization is proposed, which uses ultrawideband (UWB) ranging network with high penetration and high precision to obtain accurate distance information, then weakens NLOS error by the Bayesian filtering to further improve the accuracy of distance information, and, finally, uses a novel cooperative localization approach to realize fast and high-precision indoor multimobile robot localization. In addition, by redesigning the collaborative localization algorithm in parallel, the real-time performance of the algorithm is improved while ensuring high accuracy. The collaborative localization experiment of three mobile robots in the real scene shows that the proposed algorithm can effectively improve the localization accuracy, and the real-time performance of collaborative localization is significantly improved. However, the algorithm still has some limitations when mitigating UWB ranging errors in highly obstructed environments, and the algorithm parallelization framework can be further improved for higher real-time performance. In the future, we will further improve the robustness of cooperative localization and apply this algorithm to cooperative control of multiple mobile robots, such as formation control and cooperative search.

Cooperative Location Method for Leader-Follower UAV Formation Based on Follower UAV's Moving Vector.

The traditional leader-follower Unmanned Aerial Vehicle (UAV) formation cooperative positioning (CP) algorithm, based on relative ranging, requires at least four leader UAV positions to be known accurately, using relative distance with leader UAVs to achieve the unknown position follower UAV’s high-precision positioning. When the number of the known position leader UAVs is limited, the traditional CP algorithm is not applicable. Aiming at the minimum cooperative unit, which consists of a known position leader UAV and an unknown position follower UAV, this paper proposes a CP method based on the follower UAV’s moving vector. Considering the follower UAV can only acquire the single distance with the leader UAV at each distance-sampling period, it is difficult to determine the follower UAV’s spatial location. The follower UAV’s moving vector is used to construct position observation of the follower UAV’s inertial navigation system (INS). High-precision positioning is achieved by combining the follower UAV’s moving vector. In the process of CP, the leader UAV obtains a high-precision position by an INS/Global Positioning System (GPS) loosely integrated navigation system and transmits its position information to the follower UAV. Based on accurate modeling of the follower UAV’s INS, the position, velocity and heading observation equation of the follower UAV’s INS are constructed. The improved extended Kalman filtering is designed to estimate the state vector to improve the follower UAV’s positioning accuracy. In addition, considering that the datalink system based on radio signals may be interfered with by the external environment, it is difficult for the follower UAV to obtain relative distance information from the leader UAV in real time. In this paper, the availability of the relative distance information is judged by a two-state Markov chain. Finally, a real flight test is conducted to validate the performance of the proposed algorithm.

Cooperative augmented proportional navigation and guidance for proximity to uncooperative space targets

Navigation and proximity to non-cooperative targets have garnered the interest of both academia and industry. This paper proposes a new space operation concept that would enable two CubeSats equipped with only optical sensor to achieve autonomous and robust proximity with uncooperative satellites. This is a novel strategy for distributed spacecraft missions and applications.Because optical sensors are lightweight and therefore reduce reliance on external measurement sources, the case for their use is compelling. Designing robust guidance and control algorithm is the greatest challenge for optical sensors because relative distance information is unavailable, whereas range information is required for safe proximity. The purpose of this paper is to propose a novel concept in which two CubeSats cooperate and share angle measurement data to approach uncooperative targets despite their maneuverability.This paper introduces a new guidance scheme for proximity operations, namely cooperative augmented proportional navigation (CAPN). Modern control law is applied along line-of-sight (LOS) while classical proportional navigation is applied in the normal direction of LOS. By measuring only elevation and azimuth angles between each chaser and the target, the algorithm can account for a maneuvering target. The cooperative scheme offers estimation-based distance measurement, which enhances the observability of angle-only navigation.Target’s maneuverability and different control parameter settings have been considered in simulation scenarios. The degree of observability (DOO) is then introduced as the quantitative observability analysis metric to validate the effectiveness of the guidance scheme and precision of the estimation. The results of simulations have demonstrated that the CAPN proposed in this paper is capable of completing challenging proximity missions.

Human-object interaction detection with depth-augmented clues

Human object interaction (HOI) detection aims to localize and classify triplets of human, object and relationship from a given image. Different from previous methods that only extract vision information in RGB images, we propose a Depth-augmented Relationship Reasoning (DRR) method that focuses on the RGB images and corresponding depth messages simultaneously. Rethinking principles of photography, we argue that RGB images discard spatial depth carrying third dimension relative distance information between instances. In light of this, we beforehand estimate the depth information for each image, yielding a corresponding depth map. Then we leverage multiple representations encoded by depth information and RGB images to enrich semantic interpretation. Subsequently, we explore a hierarchical attention strategy to fuse these semantic representations and further generate depth-augmented features, being used to reason about fine-grained human-object interactions. Extensive experiments on the benchmark datasets V-COCO, HICO-DET and HCVRD verify the effectiveness of our method and demonstrate the importance of spatial depth information for HOI.

Investigation of optical texture properties as relative distance information for monocular guidance of reaching

Reaches guided using monocular versus binocular vision have been found to be equally fast and accurate only when optical texture was available projected from a support surface across which the reach was performed. We now investigate what property of optical texture elements is used to perceive relative distance: image width, image height, or image shape. Participants performed reaches to match target distances. Targets appeared on a textured surface on the left and participants reached to place their hand at target distance along a surface on the right. A perturbation discriminated which texture property was being used. The righthand surface was higher than the lefthand one by either 2, 4 or 6 cm. Participants should overshoot if they matched texture image width at the target, undershoot if they matched image shape, and undershoot far distances and, depending on the overall eye height, overshoot near distances if they matched image height. In Experiment 1, participants reached by moving a joystick to control a hand avatar in a virtual environment display. Their eye height was 15 cm. For each texture property, distances were predicted from the viewing geometry. Results ruled out image width in favor of image height or shape. In Experiment 2, participants at a 50 cm eye height reached in an actual environment with the same manipulations. Results supported use of image shape (or foreshortening), consistent with findings of texture properties used in slant perception. We discuss implications for models of visually guided reaching.

A Distance Increment Smoothing Method and Its Application on the Detection of NLOS in the Cooperative Positioning.

The wide use of cooperative missions using multiple unmanned platforms has made relative distance information an essential factor for cooperative positioning and formation control. Reducing the range error effectively in real time has become the main technical challenge. We present a new method to deal with ranging errors based on the distance increment (DI). The DI calculated by dead reckoning is used to smooth the DI obtained by the cooperative positioning, and the smoothed DI is then used to detect and estimate the non-line-of-sight (NLOS) error as well as to smooth the observed values containing random noise in the filtering process. Simulation and experimental results show that the relative accuracy of NLOS estimation is 8.17%, with the maximum random error reduced by 40.27%. The algorithm weakens the influence of NLOS and random errors on the measurement distance, thus improving the relative distance precision and enhancing the stability and reliability of cooperative positioning.

Formation control of unmanned underwater vehicles using local sensing means in absence of follower position information

Formation control is one of the essential problems in multi-unmanned underwater vehicle (UUV) coordination. In this article, a practically oriented UUV formation control structure and method are proposed for the problem of large communication in leader–follower approach. To solve the problem of large communication in multi-UUVs, local sensing means of acoustic positioning is used to provide the real relative distance and angle information for the follower UUV. So, only a small amount of state information of the leader UUV needs to be sent to the follower UUV by acoustic communication. Then, the formation control structure in absence of follower position information is proposed. In this control structure, only the relative distance and angle, as well as velocity and heading of the leader UUV, are used for the formation controller design of the follower UUV. Backstepping and Lyapunov methods are used to design the formation controller without position information of the follower UUV. Two formation configurations of rectangle and triangle with five UUVs are simulated to verify the effectiveness of the method proposed. The simulation results show that the follower UUV can successfully constitute and maintain the desired formation by controlling each real relative distance and angle.

Dual-sliding mode approach for separated fault detection and tolerant control for functional safety of longitudinal autonomous driving

This paper describes model-based separated fault detection and fault tolerant control of longitudinal autonomous driving using dual-sliding mode observer for functional safety. Internal and environment sensors such as camera or radar are required to measure the acceleration information of the subject vehicle and the relative distance and velocity information between the preceding and subject vehicles in longitudinal autonomous driving. In order to detect the independent fault of each sensor, a dual-sliding mode observer (SMO) is used for fault reconstruction under the assumption that V2V (Vehicle to Vehicle) communication for vehicle driving state is available. The each SMO reconstructs the expected fault in sensor based on discontinuous injection term used for converging output error to zero. Based on the reconstructed fault by each SMO, faults are detected using threshold approach. When the fault is detected, the reconstructed fault is used for fault tolerant control by subtracting to faulty data. The proposed fault detection (FD) and fault tolerant control (FTC) algorithms were evaluated using actual driving data and a three-dimensional (3D) vehicle model with a linear quadratic regulator for following control. The evaluation results are presented and analyzed with regard to fault reconstruction, detection, and tolerant control in four cases wherein two types of faults were applied.

Research on infrared passive ranging algorithm based on unscented Kalman filter and modified spherical coordinates

Target range detection is one of the key technologies for intelligent unmanned vehicle to work reliably and efficiently. Infrared passive ranging can estimate the relative distance information of the target in real time by measuring the angle information with noise. It has many advantages such as low cost, good real-time performance and so on, which has a good application prospect in the range detection. In this paper, the mathematical model of infrared passive ranging of intelligent unmanned vehicle based on modified spherical coordinates (MSC) is established, and the algorithm flow based on unscented Kalman filter (UKF) is given. Finally, the simulation experiment and analysis are carried out. The results show that: in the problem of target range detection of intelligent unmanned vehicle, the method adopted has high ranging accuracy and good stability.

Size-Distance Scaling With Absolute and Relative Auditory Distance Information.

In the dynamic 3D space, it is critical for survival to perceive size of an object and rescale it with distance from an observer. Humans can perceive distance via not only vision but also audition, which plays an important role in the localization of objects, especially in visually ambiguous environments. However, whether and how auditory distance information contributes to visual size perception is not well understood. To address this issue, we investigated the efficiency of size-distance scaling by using auditory distance information that was conveyed by binaurally recorded auditory stimuli. We examined the effects of absolute distance information of a single sound sequence (Experiment 1) and relative distance information between two sound sequences (Experiment 2) on visual size estimation performances in darkened and well-lit environments. We demonstrated that humans could perform size-distance disambiguation by using auditory distance information even in darkness. Curiously, relative distance information was more efficient in size-distance scaling than absolute distance information, suggesting a high reliance on relative auditory distance information in our visual spatial experiences. The results highlight a benefit of audiovisual interaction for size-distance processing and calibration of external events under visually degraded situations.

Leader-Follower Mobile Robots Control Based on Light Source Detection

This paper deals with the leader-following control of multiple autonomous mobile robots based on a new sensing method. In this method, we have mounted a light source on the leader robot and installed a photovoltaic sensor at the front end of the follower robot. The photovoltaic sensor consisting of seven micro solar modules acts as a light sensor for the follower robot which helps it to move in accordance with the leader robot by detecting the light source of the leader robot. From the relative angle measurement and ultrasonic measurement of the relative distance, angle offset and distance information between leader robot and follower robot can be estimated. Then, based on an intuitive control method for angle steering proposed in this paper, the follower robot can be controlled smoothly to achieve leader following purpose. The new leader-following control method could overcome the disadvantages of other existing formation control methods. The experimental results show that the leader following based on light source tracking is a comparatively efficient, accurate, and cost-effective method.

Collision avoidance cooperative attack with multiple pursuers based on bearing-only measurements

This paper provides a novel collisions avoidance cooperative attack method for multiple pursuers system based on bearing-only measurements. In the cooperative attack problem, the control algorithm must drive all of the attackers to converge to the desired position (target). However, the traditional consensus protocol based on the relative position information may cause the intervehicle collisions before the attackers can hit the target. To solve this issue, a distributed cooperative consensus control algorithm is proposed. Under this algorithm the potential collisions are proved to be avoided while the pursuers can achieve the final attack. Further more, considering the relative distance information is unavailable for some types of the pursuers to get, a control algorithm based on bearing-only measurements is proposed by referencing the distributed localization algorithm used in the sensors network. The advantages of this method are summed up as fully distributed, collisions avoidance, and bearing-only measurements. Finally, the effectiveness of the results is illustrated by numerical simulation.