Inertial Navigation Systems (INS) are algorithms that fuse inertial measurements of angular velocity and specific acceleration with supplementary sensors including GNSS and magnetometers to estimate the position, velocity and attitude, or extended pose, of a vehicle. The industry-standard extended Kalman filter (EKF) does not come with strong stability or robustness guarantees and can be subject to catastrophic failure. This paper exploits a Lie group symmetry of the INS dynamics to propose the first nonlinear observer for INS with error dynamics that are almost-globally asymptotically and locally exponentially stable, independently of the chosen gains. The observer is aided only by a GNSS measurement of position. As expected, the convergence guarantee depends on persistence of excitation of the vehicle's specific acceleration in the inertial frame. Simulation results demonstrate the observer's performance and its ability to converge from extreme errors in the initial state estimates.
Existing skeleton-based 3D human pose estimation methods only predict joint positions. Although the yaw and pitch of bone rotations can be derived from joint positions, the roll around the bone axis remains unresolved. We present PoseGraphNet++ (PGN++), a novel 2D-to-3D lifting Graph Convolution Network that predicts the complete human pose in 3D including joint positions and bone orientations. We employ both node and edge convolutions to utilize the joint and bone features. Our model is evaluated on multiple datasets using both position and rotation metrics. PGN++ performs on par with the state-of-the-art (SoA) on the Human3.6M benchmark. In generalization experiments, it achieves the best results in position and matches the SoA in orientation, showcasing a more balanced performance than the current SoA. PGN++ exploits the mutual relationship of joints and bones resulting in significantly \SB{improved} position predictions, as shown by our ablation results.
Rail detection is one of the key factors for intelligent train. In the paper, motivated by the anchor line-based lane detection methods, we propose a rail detection network called DALNet based on dynamic anchor line. Aiming to solve the problem that the predefined anchor line is image agnostic, we design a novel dynamic anchor line mechanism. It utilizes a dynamic anchor line generator to dynamically generate an appropriate anchor line for each rail instance based on the position and shape of the rails in the input image. These dynamically generated anchor lines can be considered as better position references to accurately localize the rails than the predefined anchor lines. In addition, we present a challenging urban rail detection dataset DL-Rail with high-quality annotations and scenario diversity. DL-Rail contains 7000 pairs of images and annotations along with scene tags, and it is expected to encourage the development of rail detection. We extensively compare DALNet with many competitive lane methods. The results show that our DALNet achieves state-of-the-art performance on our DL-Rail rail detection dataset and the popular Tusimple and LLAMAS lane detection benchmarks. The code will be released at https://github.com/Yzichen/mmLaneDet.
The recognition of abstracts is crucial for effectively locating the content and clarifying the article. Existing move recognition algorithms lack the ability to learn word position information to obtain contextual semantics. This paper proposes a novel enhanced move recognition algorithm with an improved pre-trained model and a gated network with attention mechanism for unstructured abstracts of Chinese scientific and technological papers. The proposed algorithm first performs summary data segmentation and vocabulary training. The EP-ERNIE$\_$AT-GRU framework is leveraged to incorporate word positional information, facilitating deep semantic learning and targeted feature extraction. Experimental results demonstrate that the proposed algorithm achieves 13.37$\%$ higher accuracy on the split dataset than on the original dataset and a 7.55$\%$ improvement in accuracy over the basic comparison model.
Vehicular visible light positioning (VLP) methods find relative locations of vehicles by estimating the positions of intensity-modulated head/tail lights of one vehicle (target) with respect to another (ego). Estimation is done in two steps: 1) relative bearing or range of the transmitter-receiver link is measured over the received signal on the ego side, and 2) target position is estimated based on those measurements using a geometric algorithm that expresses position coordinates in terms of the bearing-range parameters. The primary source of statistical error for these non-linear algorithms is the channel noise on the received signals that contaminates parameter measurements with varying levels of sensitivity. In this paper, we present two such geometric vehicular VLP algorithms that were previously unexplored, compare their performance with state-of-the-art algorithms over simulations, and analyze theoretical performance of all algorithms against statistical channel noise by deriving the respective Cramer-Rao lower bounds. The two newly explored algorithms do not outperform existing state-of-the-art, but we present them alongside the statistical analyses for the sake of completeness and to motivate further research in vehicular VLP. Our main finding is that direct bearing-based algorithms provide higher accuracy against noise for estimating lateral position coordinates, and range-based algorithms provide higher accuracy in the longitudinal axis due to the non-linearity of the respective geometric algorithms.
Besides interacting correctly with other vehicles, automated vehicles should also be able to react in a safe manner to vulnerable road users like pedestrians or cyclists. For a safe interaction between pedestrians and automated vehicles, the vehicle must be able to interpret the pedestrian's behavior. Common environment models do not contain information like body poses used to understand the pedestrian's intent. In this work, we propose an environment model that includes the position of the pedestrians as well as their pose information. We only use images from a monocular camera and the vehicle's localization data as input to our pedestrian environment model. We extract the skeletal information with a neural network human pose estimator from the image. Furthermore, we track the skeletons with a simple tracking algorithm based on the Hungarian algorithm and an ego-motion compensation. To obtain the 3D information of the position, we aggregate the data from consecutive frames in conjunction with the vehicle position. We demonstrate our pedestrian environment model on data generated with the CARLA simulator and the nuScenes dataset. Overall, we reach a relative position error of around 16% on both datasets.
We study single-image super-resolution algorithms for photons at collider experiments based on generative adversarial networks. We treat the energy depositions of simulated electromagnetic showers of photons and neutral-pion decays in a toy electromagnetic calorimeter as 2D images and we train super-resolution networks to generate images with an artificially increased resolution by a factor of four in each dimension. The generated images are able to reproduce features of the electromagnetic showers that are not obvious from the images at nominal resolution. Using the artificially-enhanced images for the reconstruction of shower-shape variables and of the position of the shower center results in significant improvements. We additionally investigate the utilization of the generated images as a pre-processing step for deep-learning photon-identification algorithms and observe improvements in the case of training samples of small size.
We present Spatial LibriSpeech, a spatial audio dataset with over 650 hours of 19-channel audio, first-order ambisonics, and optional distractor noise. Spatial LibriSpeech is designed for machine learning model training, and it includes labels for source position, speaking direction, room acoustics and geometry. Spatial LibriSpeech is generated by augmenting LibriSpeech samples with 200k+ simulated acoustic conditions across 8k+ synthetic rooms. To demonstrate the utility of our dataset, we train models on four spatial audio tasks, resulting in a median absolute error of 6.60{\deg} on 3D source localization, 0.43m on distance, 90.66ms on T30, and 2.74dB on DRR estimation. We show that the same models generalize well to widely-used evaluation datasets, e.g., obtaining a median absolute error of 12.43{\deg} on 3D source localization on TUT Sound Events 2018, and 157.32ms on T30 estimation on ACE Challenge.
We investigate radar parameter estimation and beam tracking with a hybrid digital-analog (HDA) architecture in a multi-block measurement framework using an extended target model. In the considered setup, the backscattered data signal is utilized to predict the user position in the next time slots. Specifically, a simplified maximum likelihood framework is adopted for parameter estimation, based on which a simple tracking scheme is also developed. Furthermore, the proposed framework supports adaptive transmitter beamwidth selection, whose effects on the communication performance are also studied. Finally, we verify the effectiveness of the proposed framework via numerical simulations over complex motion patterns that emulate a realistic integrated sensing and communication (ISAC) scenario.
Real-time numerical differentiation plays a crucial role in many digital control algorithms, such as PID control, which requires numerical differentiation to implement derivative action. This paper addresses the problem of numerical differentiation for real-time implementation with minimal prior information about the signal and noise using adaptive input and state estimation. Adaptive input estimation with adaptive state estimation (AIE/ASE) is based on retrospective cost input estimation, while adaptive state estimation is based on an adaptive Kalman filter in which the input-estimation error covariance and the measurement-noise covariance are updated online. The accuracy of AIE/ASE is compared numerically to several conventional numerical differentiation methods. Finally, AIE/ASE is applied to simulated vehicle position data generated from CarSim.
We introduce DeSCo, a scalable neural deep subgraph counting pipeline, designed to accurately predict both the count and occurrence position of queries on target graphs post single training. Firstly, DeSCo uses a novel canonical partition and divides the large target graph into small neighborhood graphs, greatly reducing the count variation while guaranteeing no missing or double-counting. Secondly, neighborhood counting uses an expressive subgraph-based heterogeneous graph neural network to accurately count in each neighborhood. Finally, gossip propagation propagates neighborhood counts with learnable gates to harness the inductive biases of motif counts. DeSCo is evaluated on eight real-world datasets from various domains. It outperforms state-of-the-art neural methods with 137x improvement in the mean squared error of count prediction, while maintaining the polynomial runtime complexity. Our open source project is at https://github.com/fuvty/DeSCo.
Navigation in Global Positioning Systems (GPS)-denied environments requires robust estimators reliant on fusion of inertial sensors able to estimate rigid-body's orientation, position, and linear velocity. Ultra-wideband (UWB) and Inertial Measurement Unit (IMU) represent low-cost measurement technology that can be utilized for successful Inertial Navigation. This paper presents a nonlinear deterministic navigation observer in a continuous form that directly employs UWB and IMU measurements. The estimator is developed on the extended Special Euclidean Group $\mathbb{SE}_{2}\left(3\right)$ and ensures exponential convergence of the closed loop error signals starting from almost any initial condition. The discrete version of the proposed observer is tested using a publicly available real-world dataset of a drone flight. Keywords: Ultra-wideband, Inertial measurement unit, Sensor Fusion, Positioning system, GPS-denied navigation.
Much of the recent discourse within the ML community has been centered around Large Language Models (LLMs), their functionality and potential -- yet not only do we not have a working definition of LLMs, but much of this discourse relies on claims and assumptions that are worth re-examining. We contribute a definition of LLMs, critically examine five common claims regarding their properties (including 'emergent properties'), and conclude with suggestions for future research directions and their framing.
Due to the high mobility and easy deployment, unmanned aerial vehicles (UAVs) have attracted much attention in the field of wireless communication and positioning. To meet the challenges of lack of infrastructure coverage, uncertain sensor position and large amount of sensing data collection in wireless sensor network (WSN), this paper presents an efficient joint data collection and sensor positioning scheme for WSN supported by multiple UAVs. Specifically, a UAV is set as the main UAV to collect data, and other UAVs are used as auxiliary UAVs for sensor positioning using time difference of arrival (TDoA). A mixed-integer non-convex optimization problem with uncertain sensor position is established. The goal is to minimize the average positioning error of all sensors by jointly optimizing the UAV trajectories, sensor transmission schedule and positioning observation points (POPs). To solve this optimization model, the original problem is decomposed into two sub-problems based on the path discrete method. Firstly, the block coordinate descent (BCD) and successive convex approximation (SCA) techniques are applied to iteratively optimize the trajectory of the main UAV and the sensor transmission schedule, so as to maximize the minimum amount of data uploaded by the sensor. Then, based on the trajectory of the main UAV, a particle swarm optimization (PSO)-based algorithm is designed to optimize the POPs of UAVs. Finally, the spline curve is applied to generate the trajectories of auxiliary UAVs. The simulation results show that the proposed scheme can meet the requirements of data collection and has a good positioning performance.
Transformer-based visual trackers have demonstrated significant progress owing to their superior modeling capabilities. However, existing trackers are hampered by low speed, limiting their applicability on devices with limited computational power. To alleviate this problem, we propose HiT, a new family of efficient tracking models that can run at high speed on different devices while retaining high performance. The central idea of HiT is the Bridge Module, which bridges the gap between modern lightweight transformers and the tracking framework. The Bridge Module incorporates the high-level information of deep features into the shallow large-resolution features. In this way, it produces better features for the tracking head. We also propose a novel dual-image position encoding technique that simultaneously encodes the position information of both the search region and template images. The HiT model achieves promising speed with competitive performance. For instance, it runs at 61 frames per second (fps) on the Nvidia Jetson AGX edge device. Furthermore, HiT attains 64.6% AUC on the LaSOT benchmark, surpassing all previous efficient trackers.
Layered architectures have been widely used in robot systems. The majority of them implement planning and execution functions in separate layers. However, there still lacks a straightforward way to transit high-level tasks in the planning layer to the low-level motor commands in the execution layer. In order to tackle this challenge, we propose a novel approach to ground the manipulator primitive tasks to robot low-level actions using large language models (LLMs). We designed a program-function-like prompt based on the task frame formalism. In this way, we enable LLMs to generate position/force set-points for hybrid control. Evaluations over several state-of-the-art LLMs are provided.
Large Language Models (LLMs) have taken Knowledge Representation -- and the world -- by storm. This inflection point marks a shift from explicit knowledge representation to a renewed focus on the hybrid representation of both explicit knowledge and parametric knowledge. In this position paper, we will discuss some of the common debate points within the community on LLMs (parametric knowledge) and Knowledge Graphs (explicit knowledge) and speculate on opportunities and visions that the renewed focus brings, as well as related research topics and challenges.
Detecting dental diseases through panoramic X-rays images is a standard procedure for dentists. Normally, a dentist need to identify diseases and find the infected teeth. While numerous machine learning models adopting this two-step procedure have been developed, there has not been an end-to-end model that can identify teeth and their associated diseases at the same time. To fill the gap, we develop YOLOrtho, a unified framework for teeth enumeration and dental disease detection. We develop our model on Dentex Challenge 2023 data, which consists of three distinct types of annotated data. The first part is labeled with quadrant, and the second part is labeled with quadrant and enumeration and the third part is labeled with quadrant, enumeration and disease. To further improve detection, we make use of Tufts Dental public dataset. To fully utilize the data and learn both teeth detection and disease identification simultaneously, we formulate diseases as attributes attached to their corresponding teeth. Due to the nature of position relation in teeth enumeration, We replace convolution layer with CoordConv in our model to provide more position information for the model. We also adjust the model architecture and insert one more upsampling layer in FPN in favor of large object detection. Finally, we propose a post-process strategy for teeth layout that corrects teeth enumeration based on linear sum assignment. Results from experiments show that our model exceeds large Diffusion-based model.
Background-Induced Text2Image (BIT2I) aims to generate foreground content according to the text on the given background image. Most studies focus on generating high-quality foreground content, although they ignore the relationship between the two contents. In this study, we analyzed a novel Background-Aware Text2Image (BAT2I) task in which the generated content matches the input background. We proposed a Background-Aware Text to Image synthesis and manipulation Network (BATINet), which contains two key components: Position Detect Network (PDN) and Harmonize Network (HN). The PDN detects the most plausible position of the text-relevant object in the background image. The HN harmonizes the generated content referring to background style information. Finally, we reconstructed the generation network, which consists of the multi-GAN and attention module to match more user preferences. Moreover, we can apply BATINet to text-guided image manipulation. It solves the most challenging task of manipulating the shape of an object. We demonstrated through qualitative and quantitative evaluations on the CUB dataset that the proposed model outperforms other state-of-the-art methods.
Global Navigation Satellite System (GNSS) is pervasive in navigation and positioning applications, where precise position and time referencing estimations are required. Conventional methods for GNSS positioning involve a two-step process, where intermediate measurements such as Doppler shift and time delay of received GNSS signals are computed and then used to solve for the receiver's position. Alternatively, Direct Position Estimation (DPE) was proposed to infer the position directly from the sampled signal without intermediate variables, yielding to superior levels of sensitivity and operation under challenging environments. However, the positioning resilience of DPE method is still under the threat of various interferences. Robust Interference Mitigation (RIM) processing has been studied and proved to be efficient against various interference in conventional two-step positioning (2SP) methods, and therefore worthy to be explored regarding its potential to enhance DPE. This article extends DPE methodology by incorporating RIM strategies that address the increasing need to protect GNSS receivers against intentional or unintentional interferences, such as jamming signals, which can deny GNSS-based positioning. RIM, which leverages robust statistics, was shown to provide competitive results in two-step approaches and is here employed in a high-sensitivity DPE framework with successful results. The article also provides a quantification of the loss of efficiency of using RIM when no interference is present and validates the proposed methodology on relevant interference cases, while the approach can be used to mitigate other common interference signals.