This paper develops an adaptive digital autopilot for a fixed-wing aircraft and compares its performance with a fixed-gain autopilot. The adaptive digital autopilot is constructed by augmenting the autopilot architecture implemented in PX4 flight stack with adaptive digital control laws that are updated using the retrospective cost adaptive control algorithm. In order to investigate the performance of the adaptive digital autopilot, the default gains of the fixed-gain autopilot are scaled down to degrade its performance. This scenario provides a venue for determining the ability of the adaptive digital autopilot to compensate for the detuned fixed-gain autopilot. Next, the performance of the adaptive autopilot is examined under failure conditions by simulating a scenario where one of the control surfaces is assumed to be stuck at an unknown angular position. The adaptive digital autopilot is tested in simulation, and the resulting performance improvements are examined.
This paper proposes a method to automatically detect the key feature parts in a CAD of commercial TV and monitor using a deep neural network. We developed a deep learning pipeline that can detect the injection parts such as hook, boss, undercut and press parts such as DPS, Embo-Screwless, Embo-Burring, and EMBO in the 2D CAD drawing images. We first cropped the drawing to a specific size for the training efficiency of a deep neural network. Then, we use Cascade R-CNN to find the position of injection and press parts and use Resnet-50 to predict the orientation of the parts. Finally, we convert the position of the parts found through the cropped image to the position of the original image. As a result, we obtained detection accuracy of injection and press parts with 84.1% in AP (Average Precision), 91.2% in AR(Average Recall), 72.0% in AP, 87.0% in AR, and orientation accuracy of injection and press parts with 94.4% and 92.0%, which can facilitate the faster design in industrial product design.
This paper deals with multipath-based positioning and tracking in off-body channels. An analysis of the effects introduced by the human body and the implications on positioning and tracking is presented based on channel measurements obtained in an indoor scenario. It shows the influence of the radio signal bandwidth on the human body induced field of view (FOV) and the number of multipath components (MPCs) detected and estimated by a deterministic maximum likelihood (ML) algorithm. A multipath-based positioning and tracking algorithm is proposed that associates these estimated MPC parameters with floor plan features and exploits a human body-dependent FOV function. The proposed algorithm is able to provide accurate position estimates even for an off-body radio channel in a multipath-prone environment with the signal bandwidth found to be a limiting factor.
As a critical task for large-scale commercial recommender systems, reranking has shown the potential of improving recommendation results by uncovering mutual influence among items. Reranking rearranges items in the initial ranking lists from the previous ranking stage to better meet users' demands. However, rather than considering the context of initial lists as most existing methods do, an ideal reranking algorithm should consider the counterfactual context -- the position and the alignment of the items in the reranked lists. In this work, we propose a novel pairwise reranking framework, Context-aware Reranking with Utility Maximization for recommendation (CRUM), which maximizes the overall utility after reranking efficiently. Specifically, we first design a utility-oriented evaluator, which applies Bi-LSTM and graph attention mechanism to estimate the listwise utility via the counterfactual context modeling. Then, under the guidance of the evaluator, we propose a pairwise reranker model to find the most suitable position for each item by swapping misplaced item pairs. Extensive experiments on two benchmark datasets and a proprietary real-world dataset demonstrate that CRUM significantly outperforms the state-of-the-art models in terms of both relevance-based metrics and utility-based metrics.
Ultrasound Elastography aims to determine the mechanical properties of the tissue by monitoring tissue deformation due to internal or external forces. Tissue deformations are estimated from ultrasound radio frequency (RF) signals and are often referred to as time delay estimation (TDE). Given two RF frames I1 and I2, we can compute a displacement image which shows the change in the position of each sample in I1 to a new position in I2. Two important challenges in TDE include high computational complexity and the difficulty in choosing suitable RF frames. Selecting suitable frames is of high importance because many pairs of RF frames either do not have acceptable deformation for extracting informative strain images or are decorrelated and deformation cannot be reliably estimated. Herein, we introduce a method that learns 12 displacement modes in quasi-static elastography by performing Principal Component Analysis (PCA) on displacement fields of a large training database. In the inference stage, we use dynamic programming (DP) to compute an initial displacement estimate of around 1% of the samples, and then decompose this sparse displacement into a linear combination of the 12 displacement modes. Our method assumes that the displacement of the whole image could also be described by this linear combination of principal components. We then use the GLobal Ultrasound Elastography (GLUE) method to fine-tune the result yielding the exact displacement image. Our method, which we call PCA-GLUE, is more than 10 times faster than DP in calculating the initial displacement map while giving the same result. Our second contribution in this paper is determining the suitability of the frame pair I1 and I2 for strain estimation, which we achieve by using the weight vector that we calculated for PCA-GLUE as an input to a multi-layer perceptron (MLP) classifier.
Currently, unmanned automation studies are underway to minimize the loss rate of rebar production and the time and accuracy of calibration when producing defective products in the cutting process of processing rebar factories. In this paper, we propose a method to detect and track rebar endpoint images entering the machine vision camera based on YOLO (You Only Look Once)v3, and to predict rebar endpoint in advance with sin exponential regression of acquired coordinates. The proposed method solves the problem of large prediction error rates for frame locations where rebar endpoints are far away in OPPDet (Object Position Prediction Detect) models, which prepredict rebar endpoints with improved results showing 0.23 to 0.52% less error rates at sin exponential regression prediction points.
In sequence-based predictions, conventionally an input sequence is represented by a multiple sequence alignment (MSA) or a representation derived from MSA, such as a position-specific scoring matrix. Recently, inspired by the development in natural language processing, several applications of sequence embedding have been observed. Here, we review different approaches of protein sequence embeddings and their applications including protein contact prediction, secondary structure, prediction, and function prediction.
Position-aided beam selection methods have been shown to be an effective approach to achieve high beamforming gain while limiting the overhead and latency of initial access in millimeter wave (mmWave) communications. Most research in the area, however, has focused on vehicular applications, where the orientation of the user terminal (UT) is mostly fixed at each position of the environment. This paper proposes a location- and orientation-based beam selection method to enable context information (CI)-based beam alignment in applications where the UT can take arbitrary orientation at each location. We propose three different network structures, with different amounts of trainable parameters that can be used with different training dataset sizes. A professional 3-dimensional ray tracing tool is used to generate datasets for an IEEE standard indoor scenario. Numerical results show the proposed networks outperform a CI-aided benchmark such as the generalized inverse fingerprinting (GIFP) method as well as hierarchical beam search as a non-CI-based approach. Moreover, compared to the GIFP method, the proposed deep learning-based beam selection shows higher robustness to different line-of-sight blockage probability in the training and test datasets and lower sensitivity to inaccuracies in the position and orientation information.
It is well known that the conventional quadrotor is an under-actuated MIMO system. The number of the inputs is less than the degree of freedom. One approach in controlling this non-holonomic system is feedback linearization. In the frequently cited (305 times) application, the yaw and the position are selected as the controlled variables. It is reported that no singularity is found in their delta matrix, making it possible to apply the inversion within a wide range. However, we find the ignored singular zone within the range of interest. The unreported singular area can cause the failure in the controller design. This paper visualizes this uninvertible area and details the deduction process.
Formation control (FC) of multi-agent plays a critical role in a wide variety of fields. In the absence of absolute positioning, agents in FC systems rely on relative position measurements with respect to their neighbors. In distributed filter design literature, relative observation models are comparatively unexplored, and in FC literature, uncertainty models are rarely considered. In this article, we aim to bridge the gap between these domains, by exploring distributed filters tailored for relative FC of swarms. We propose statistically robust data models for tracking relative positions of agents in a FC network, and subsequently propose optimal Kalman filters for both centralized and distributed scenarios. Our simulations highlight the benefits of these estimators, and we identify future research directions based on our proposed framework.
This paper considers the problem of controlling a quadrotor to go through a window and land on a planar target, the landing pad, using an Image-Based Visual Servo (IBVS) controller that relies on sensing information from two on-board cameras and an IMU. The maneuver is divided into two stages: crossing the window and landing on the pad. For the first stage, a control law is proposed that guarantees that the vehicle will not collide with the wall containing the window and will go through the window with non-zero velocity along the direction orthogonal to the window, keeping at all times a safety distance with respect to the window edges. For the landing stage, the proposed control law ensures that the vehicle achieves a smooth touchdown, keeping at all time a positive height above the plane containing the landing pad. For control purposes, the centroid vectors provided by the combination of the spherical image measurements of a collection of landmarks (corners) for both the window and the landing pad are used as position measurement. The translational optical flow relative to the wall, window edges, and landing plane is used as velocity cue. To achieve the proposed objective, no direct measurements nor explicit estimate of position or velocity are required. Simulation and experimental results are provided to illustrate the performance of the presented controller.
Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based approach for feature-preserving point cloud filtering. Unlike normal based techniques, our method does not require the normal information. The core idea is to first design a similarity metric to search the non-local similar patches of a queried local patch. We then map the non-local similar patches into a canonical space and aggregate the non-local information. The aggregated outcome (i.e. coordinate) will be inversely mapped into the original space. Our method is simple yet effective. Extensive experiments validate our method, and show that it generally outperforms position based methods (deep learning and non-learning), and generates better or comparable outcomes to normal based techniques (deep learning and non-learning).
This paper sustains the position that the time has come for thinking of learning machines that conquer visual skills in a truly human-like context, where a few human-like object supervisions are given by vocal interactions and pointing aids only. This likely requires new foundations on computational processes of vision with the final purpose of involving machines in tasks of visual description by living in their own visual environment under simple man-machine linguistic interactions. The challenge consists of developing machines that learn to see without needing to handle visual databases. This might open the doors to a truly orthogonal competitive track concerning deep learning technologies for vision which does not rely on the accumulation of huge visual databases.
We explore online inductive transfer learning, with a feature representation transfer from a radial basis function network formed of Gaussian mixture model hidden processing units to a direct, recurrent reinforcement learning agent. This agent is put to work in an experiment, trading the major spot market currency pairs, where we accurately account for transaction and funding costs. These sources of profit and loss, including the price trends that occur in the currency markets, are made available to the agent via a quadratic utility, who learns to target a position directly. We improve upon earlier work by targeting a risk position in an online transfer learning context. Our agent achieves an annualised portfolio information ratio of 0.52 with a compound return of 9.3\%, net of execution and funding cost, over a 7-year test set; this is despite forcing the model to trade at the close of the trading day at 5 pm EST when trading costs are statistically the most expensive.
This paper introduces a run-and-tumble model with self-reinforcing directionality and rests. We derive a single governing hyperbolic partial differential equation for the probability density of random walk position, from which we obtain the second moment in the long time limit. We find the criteria for the transition between superdiffusion and diffusion caused by the addition of a rest state. The emergence of superdiffusion depends on both the parameter representing the strength of self-reinforcement and the ratio between mean running and resting times. The mean running time must be at least $2/3$ of the mean resting time for superdiffusion to be possible. Monte Carlo simulations validate this theoretical result. This work demonstrates the possibility of extending the telegrapher's (or Cattaneo) equation by adding self-reinforcing directionality so that superdiffusion occurs even when rests are introduced.
Pre-trained language models (LMs) have recently gained attention for their potential as an alternative to (or proxy for) explicit knowledge bases (KBs). In this position paper, we examine this hypothesis, identify strengths and limitations of both LMs and KBs, and discuss the complementary nature of the two paradigms. In particular, we offer qualitative arguments that latent LMs are not suitable as a substitute for explicit KBs, but could play a major role for augmenting and curating KBs.
This paper introduces k-splits, an improved hierarchical algorithm based on k-means to cluster data without prior knowledge of the number of clusters. K-splits starts from a small number of clusters and uses the most significant data distribution axis to split these clusters incrementally into better fits if needed. Accuracy and speed are two main advantages of the proposed method. We experiment on six synthetic benchmark datasets plus two real-world datasets MNIST and Fashion-MNIST, to prove that our algorithm has excellent accuracy in finding the correct number of clusters under different conditions. We also show that k-splits is faster than similar methods and can even be faster than the standard k-means in lower dimensions. Finally, we suggest using k-splits to uncover the exact position of centroids and then input them as initial points to the k-means algorithm to fine-tune the results.
A variety of behaviors like spatial navigation or bodily motion can be formulated as graph traversal problems through cognitive maps. We present a neural network model which can solve such tasks and is compatible with a broad range of empirical findings about the mammalian neocortex and hippocampus. The neurons and synaptic connections in the model represent structures that can result from self-organization into a cognitive map via Hebbian learning, i.e. into a graph in which each neuron represents a point of some abstract task-relevant manifold and the recurrent connections encode a distance metric on the manifold. Graph traversal problems are solved by wave-like activation patterns which travel through the recurrent network and guide a localized peak of activity onto a path from some starting position to a target state.
In this position paper, we discuss recent applications of simulation approaches for recommender systems tasks. In particular, we describe how they were used to analyze the problem of misinformation spreading and understand which data characteristics affect the performance of recommendation algorithms more significantly. We also present potential lines of future work where simulation methods could advance the work in the recommendation community.
Power systems are large scale cyber-physical critical infrastructure that form the basis of modern society. The reliability and resilience of the grid is dependent on the correct functioning of related subsystems, including computing, communications, and control. The integration is widespread and has a profound impact on the operation, reliability, and efficiency of the grid. Technologies comprising these infrastructure can expose new sources of threats. Mapping these threats to their grid resilience impacts to stop them early requires a timely and detailed view of the entire cyber-physical system. Grid resilience must therefore be seen and addressed as a cyber-physical systems problem. This short position paper presents several key preliminaries, supported with evidence from experience, to enable cyber-physical situational awareness and intrusion response through a cyber-physical energy management system.