PyTorchKR Papers

최신 논문

총 403편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2404.16578

Road Surface Friction Estimation for Winter Conditions Utilising General Visual Features

In below freezing winter conditions, road surface friction can greatly vary based on the mixture of snow, ice, and water on the road. Friction between the road and vehicle tyres is a critical parameter defining vehicle dynamics, and therefore road surface friction information is essential to acquire for several intelligent transportation applications, such as safe control of automated vehicles or alerting drivers of slippery road conditions. This paper explores computer vision-based evaluation of road surface friction from roadside cameras. Previous studies have extensively investigated the application of convolutional neural networks for the task of evaluating the road surface condition from images. Here, we propose a hybrid deep learning architecture, WCamNet, consisting of a pretrained visual transformer model and convolutional blocks. The motivation of the architecture is to combine general visual features provided by the transformer model, as well as finetuned feature extraction properties of the convolutional blocks. To benchmark the approach, an extensive dataset was gathered from national Finnish road infrastructure network of roadside cameras and optical road surface friction sensors. Acquired results highlight that the proposed WCamNet outperforms previous approaches in the task of predicting the road surface friction from the roadside camera images.

arXiv:2404.09707

Adaptive Patching for High-resolution Image Segmentation with Transformers

Attention-based models are proliferating in the space of image analytics, including segmentation. The standard method of feeding images to transformer encoders is to divide the images into patches and then feed the patches to the model as a linear sequence of tokens. For high-resolution images, e.g. microscopic pathology images, the quadratic compute and memory cost prohibits the use of an attention-based model, if we are to use smaller patch sizes that are favorable in segmentation. The solution is to either use custom complex multi-resolution models or approximate attention schemes. We take inspiration from Adapative Mesh Refinement (AMR) methods in HPC by adaptively patching the images, as a pre-processing step, based on the image details to reduce the number of patches being fed to the model, by orders of magnitude. This method has a negligible overhead, and works seamlessly with any attention-based model, i.e. it is a pre-processing step that can be adopted by any attention-based model without friction. We demonstrate superior segmentation quality over SoTA segmentation models for real-world pathology datasets while gaining a geomean speedup of $6.9\times$ for resolutions up to $64K^2$, on up to $2,048$ GPUs.

arXiv:2404.06017

Identifying Shopping Intent in Product QA for Proactive Recommendations

Voice assistants have become ubiquitous in smart devices allowing users to instantly access information via voice questions. While extensive research has been conducted in question answering for voice search, little attention has been paid on how to enable proactive recommendations from a voice assistant to its users. This is a highly challenging problem that often leads to user friction, mainly due to recommendations provided to the users at the wrong time. We focus on the domain of e-commerce, namely in identifying Shopping Product Questions (SPQs), where the user asking a product-related question may have an underlying shopping need. Identifying a user's shopping need allows voice assistants to enhance shopping experience by determining when to provide recommendations, such as product or deal recommendations, or proactive shopping actions recommendation. Identifying SPQs is a challenging problem and cannot be done from question text alone, and thus requires to infer latent user behavior patterns inferred from user's past shopping history. We propose features that capture the user's latent shopping behavior from their purchase history, and combine them using a novel Mixture-of-Experts (MoE) model. Our evaluation shows that the proposed approach is able to identify SPQs with a high score of F1=0.91. Furthermore, based on an online evaluation with real voice assistant users, we identify SPQs in real-time and recommend shopping actions to users to add the queried product into their shopping list. We demonstrate that we are able to accurately identify SPQs, as indicated by the significantly higher rate of added products to users' shopping lists when being prompted after SPQs vs random PQs.

arXiv:2404.04242

Physical Property Understanding from Language-Embedded Feature Fields

Can computers perceive the physical properties of objects solely through vision? Research in cognitive science and vision science has shown that humans excel at identifying materials and estimating their physical properties based purely on visual appearance. In this paper, we present a novel approach for dense prediction of the physical properties of objects using a collection of images. Inspired by how humans reason about physics through vision, we leverage large language models to propose candidate materials for each object. We then construct a language-embedded point cloud and estimate the physical properties of each 3D point using a zero-shot kernel regression approach. Our method is accurate, annotation-free, and applicable to any object in the open world. Experiments demonstrate the effectiveness of the proposed approach in various physical property reasoning tasks, such as estimating the mass of common objects, as well as other properties like friction and hardness.

arXiv:2404.02234공식 코드 · Papers with Code

Deep Neural Networks with 3D Point Clouds for Empirical Friction Measurements in Hydrodynamic Flood Models

Friction is one of the cruxes of hydrodynamic modeling; flood conditions are highly sensitive to the Friction Factors (FFs) used to calculate momentum losses. However, empirical FFs are challenging to measure because they require laboratory experiments. Flood models often rely on surrogate observations (such as land use) to estimate FFs, introducing uncertainty. This research presents a laboratory-trained Deep Neural Network (DNN), trained using flume experiments with data augmentation techniques, to measure Manning's n based on Point Cloud data. The DNN was deployed on real-world lidar Point Clouds to directly measure Manning's n under regulatory and extreme storm events, showing improved prediction capabilities in both 1D and 2D hydrodynamic models. For 1D models, the lidar values decreased differences with regulatory models for in-channel water depth when compared to land cover values. For 1D/2D coupled models, the lidar values produced better agreement with flood extents measured from airborne imagery, while better matching flood insurance claim data for Hurricane Harvey. In both 1D and 1D/2D coupled models, lidar resulted in better agreement with validation gauges. For these reasons, the lidar measurements of Manning's n were found to improve both regulatory models and forecasts for extreme storm events, while simultaneously providing a pathway to standardize the measurement of FFs. Changing FFs significantly affected fluvial and pluvial flood models, while surge flooding was generally unaffected. Downstream flow conditions were found to change the importance of FFs to fluvial models, advancing the literature of friction in flood models. This research introduces a reliable, repeatable, and readily-accessible avenue to measure high-resolution FFs based on 3D point clouds, improving flood prediction, and removing uncertainty from hydrodynamic modeling.

arXiv:2403.19946

A Peg-in-hole Task Strategy for Holes in Concrete

A method that enables an industrial robot to accomplish the peg-in-hole task for holes in concrete is proposed. The proposed method involves slightly detaching the peg from the wall, when moving between search positions, to avoid the negative influence of the concrete's high friction coefficient. It uses a deep neural network (DNN), trained via reinforcement learning, to effectively find holes with variable shape and surface finish (due to the brittle nature of concrete) without analytical modeling or control parameter tuning. The method uses displacement of the peg toward the wall surface, in addition to force and torque, as one of the inputs of the DNN. Since the displacement increases as the peg gets closer to the hole (due to the chamfered shape of holes in concrete), it is a useful parameter for inputting in the DNN. The proposed method was evaluated by training the DNN on a hole 500 times and attempting to find 12 unknown holes. The results of the evaluation show the DNN enabled a robot to find the unknown holes with average success rate of 96.1% and average execution time of 12.5 seconds. Additional evaluations with random initial positions and a different type of peg demonstrate the trained DNN can generalize well to different conditions. Analyses of the influence of the peg displacement input showed the success rate of the DNN is increased by utilizing this parameter. These results validate the proposed method in terms of its effectiveness and applicability to the construction industry.

arXiv:2403.19546공식 코드 · Papers with Code

Croissant: A Metadata Format for ML-Ready Datasets

Data is a critical resource for machine learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that creates a shared representation across ML tools, frameworks, and platforms. Croissant makes datasets more discoverable, portable, and interoperable, thereby addressing significant challenges in ML data management. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, enabling easy loading into the most commonly-used ML frameworks, regardless of where the data is stored. Our initial evaluation by human raters shows that Croissant metadata is readable, understandable, complete, yet concise.

arXiv:2403.15446

Shape Sensing for Continuum Robotics using Optoelectronic Sensors with Convex Reflectors

Three-dimensional shape sensing in soft and continuum robotics is a crucial aspect for stable actuation and control in fields such as Minimally Invasive surgery, as the estimation of complex curvatures while using continuum robotic tools is required to manipulate through fragile paths. This challenge has been addressed using a range of different sensing techniques, for example, Fibre Bragg grating (FBG) technology, inertial measurement unit (IMU) sensor networks or stretch sensors. Previously, an optics-based method, using optoelectronic sensors was explored, offering a simple and cost-effective solution for shape sensing in a flexible tendon-actuated manipulator in two orientations. This was based on proximity-modulated angle estimation and has been the basis for the shape-sensing method addressed in this paper. The improved and miniaturized technique demonstrated in this paper is based on the use of a spherically shaped reflector with optoelectronic sensors integrated into a tendon actuated robotic manipulator. Upgraded sensing capability is achieved using optimization of the spherical reflector shape in terms of sensor range and resolution, and improved calibration is achieved through the integration of spherical bearings for friction-free motion. Shape estimation is achieved in two orientations upon calibration of sensors, with a maximum Root Mean Square Error (RMS) of 3.37{\deg}.

arXiv:2403.14194

Event-triggered Boundary Control of Mixed-autonomy Traffic

Control problems of mixed-autonomy traffic systems that consist of both human-driven vehicles (HV) and autonomous vehicles (AV), have gained increasing attention. This paper focuses on suppressing traffic oscillations in the mixed-autonomy traffic system using boundary control design. The mixed traffic dynamics are described by 4 x 4 hyperbolic partial differential equations (PDEs), governing the propagation of four waves of traffic, including the density of HV, the density of AV, the friction between the two vehicle classes from driving interactions and the averaged velocity. We propose an event-triggered boundary control design since control signals of the traffic light on ramp or the varying speed limit cannot be continuously updated. We apply the event-triggered mechanism for a PDE backstepping controller and obtain a dynamic triggering condition. Lyapunov analysis is performed to prove the exponential stability of the closed-loop system with the event-triggered controller. Numerical simulation demonstrates the efficiency of the proposed event-trigger control design. We analyzed how the car-following spacing of AV affects the event-triggering mechanism of the control input in mixed-autonomy traffic.

arXiv:2403.14172

Lane level joint control of off-ramp and main line speed guidance on expressway in rainy weather

In the upstream of the exit ramp of the expressway, the speed limit difference leads to a significant deceleration of the vehicle in the area adjacent to the off-ramp. The friction coefficient of the road surface decreases under rainy weather, and the above deceleration process can easily lead to sideslip and rollover of the vehicle. Dynamic speed guidance is an effective way to improve the status quo. Currently, there is an emerging trend to utilize I2V technology and high-precision map technology for lane level speed guidance control. This paper presents an optimized joint control strategy for main line-off-ramp speed guidance, which can adjust the guidance speed in real time according to the rainfall intensity. At the same time, this paper designs a progressive deceleration strategy, which works together with the speed guidance control to ensure the safe deceleration of vehicles. The simulation results show that the proposed control strategy outperforms the fixed speed limit control in terms of improving the total traveled time (TTT), total traveled distance (TTD) and standard deviation of speed (SD). Sensitivity analysis shows that the proposed control strategy can improve performance with the increase of the compliance rate of drivers. The speed guidance control method established in this paper can improve the vehicle operation efficiency in the off-ramp area of the expressway and reduce the speed difference of each vehicle in rainy weather, which guarantee the safety of expressway driving in the rainy day.

arXiv:2403.11237

FORCE: Physics-aware Human-object Interaction

Interactions between human and objects are influenced not only by the object's pose and shape, but also by physical attributes such as object mass and surface friction. They introduce important motion nuances that are essential for diversity and realism. Despite advancements in recent human-object interaction methods, this aspect has been overlooked. Generating nuanced human motion presents two challenges. First, it is non-trivial to learn from multi-modal human and object information derived from both the physical and non-physical attributes. Second, there exists no dataset capturing nuanced human interactions with objects of varying physical properties, hampering model development. This work addresses the gap by introducing the FORCE model, an approach for synthesizing diverse, nuanced human-object interactions by modeling physical attributes. Our key insight is that human motion is dictated by the interrelation between the force exerted by the human and the perceived resistance. Guided by a novel intuitive physics encoding, the model captures the interplay between human force and resistance. Experiments also demonstrate incorporating human force facilitates learning multi-class motion. Accompanying our model, we contribute a dataset, which features diverse, different-styled motion through interactions with varying resistances.

arXiv:2403.04607공식 코드 · Papers with Code

Repelling-Attracting Hamiltonian Monte Carlo

We propose a variant of Hamiltonian Monte Carlo (HMC), called the Repelling-Attracting Hamiltonian Monte Carlo (RAHMC), for sampling from multimodal distributions. The key idea that underpins RAHMC is a departure from the conservative dynamics of Hamiltonian systems, which form the basis of traditional HMC, and turning instead to the dissipative dynamics of conformal Hamiltonian systems. In particular, RAHMC involves two stages: a mode-repelling stage to encourage the sampler to move away from regions of high probability density; and, a mode-attracting stage, which facilitates the sampler to find and settle near alternative modes. We achieve this by introducing just one additional tuning parameter -- the coefficient of friction. The proposed method adapts to the geometry of the target distribution, e.g., modes and density ridges, and can generate proposals that cross low-probability barriers with little to no computational overhead in comparison to traditional HMC. Notably, RAHMC requires no additional information about the target distribution or memory of previously visited modes. We establish the theoretical basis for RAHMC, and we discuss repelling-attracting extensions to several variants of HMC in literature. Finally, we provide a tuning-free implementation via dual-averaging, and we demonstrate its effectiveness in sampling from, both, multimodal and unimodal distributions in high dimensions.

arXiv:2403.00470

Autonomous Robotic Arm Manipulation for Planetary Missions using Causal Machine Learning

Autonomous robotic arm manipulators have the potential to make planetary exploration and in-situ resource utilization missions more time efficient and productive, as the manipulator can handle the objects itself and perform goal-specific actions. We train a manipulator to autonomously study objects of which it has no prior knowledge, such as planetary rocks. This is achieved using causal machine learning in a simulated planetary environment. Here, the manipulator interacts with objects, and classifies them based on differing causal factors. These are parameters, such as mass or friction coefficient, that causally determine the outcomes of its interactions. Through reinforcement learning, the manipulator learns to interact in ways that reveal the underlying causal factors. We show that this method works even without any prior knowledge of the objects, or any previously-collected training data. We carry out the training in planetary exploration conditions, with realistic manipulator models.

arXiv:2402.18348

Ten simple rules for collaborating with wet lab researchers for computational researchers

Computational biologists are frequently engaged in collaborative data analysis with wet lab researchers. These interdisciplinary projects, as necessary as they are to the scientific endeavour, can be surprisingly challenging due to cultural differences in operations and values. In these Ten Simple Rules guide we aim to help dry lab researchers identify sources of friction; and provide actionable tools to facilitate respectful, open, transparent and rewarding collaborations.

arXiv:2402.14423

The Universe as a Learning System

At its microscopic level, the universe follows the laws of quantum mechanics. Focusing on the quantum trajectories of particles as followed from the hydrodynamical formulation of quantum mechanics, we propose that under general requirements, quantum systems follow a disrupted version of the gradient descent model, a basic machine learning algorithm, where the learning is distorted due to the self-organizing process of the quantum system. Such a learning process is possible only when we assume dissipation, i.e., that the quantum system is open. The friction parameter determines the nonlinearity of the quantum system. We then provide an empirical demonstration of the proposed model.

arXiv:2402.14148

Data-Driven Dynamic Friction Models based on Recurrent Neural Networks

In this concise contribution, it is demonstrated that Recurrent Neural Networks (RNNs) based on Gated Recurrent Unit (GRU) architecture, possess the capability to learn the complex dynamics of rate-and-state friction (RSF) laws from synthetic data. The data employed for training the network is generated through the application of traditional RSF equations coupled with either the aging law or the slip law for state evolution. A novel aspect of this approach is the formulation of a loss function that explicitly accounts for the direct effect by means of automatic differentiation. It is found that the GRU-based RNNs effectively learns to predict changes in the friction coefficient resulting from velocity jumps (with and without noise in the target data), thereby showcasing the potential of machine learning models in capturing and simulating the physics of frictional processes. Current limitations and challenges are discussed.

arXiv:2402.12487

Explaining the emergence of land-use frontiers

Land use expansion is linked to major sustainability concerns including climate change, food security and biodiversity loss. This expansion is largely concentrated in so-called frontiers, defined here as places experiencing marked transformations due to rapid resource exploitation. Understanding the mechanisms shaping these frontiers is crucial for sustainability. Previous work focused mainly on explaining how active frontiers advance, in particular into tropical forests. Comparatively, our understanding of how frontiers emerge in territories considered marginal in terms of agricultural productivity and global market integration remains weak. We synthesize conceptual tools explaining resource and land-use frontiers, including theories of land rent and agglomeration economies, of frontiers as successive waves, spaces of territorialization, friction, and opportunities, anticipation and expectation. We then propose a new theory of frontier emergence, which identifies exogenous pushes, legacies of past waves, and actors anticipations as key mechanisms by which frontiers emerge. Processes of abnormal rent creation and capture and the built-up of agglomeration economies then constitute key mechanisms sustaining active frontiers. Finally, we discuss five implications for the governance of frontiers for sustainability. Our theory focuses on agriculture and deforestation frontiers in the tropics, but can be inspirational for other frontier processes including for extractive resources, such as minerals.

arXiv:2402.11319

Hysteresis Compensation of Flexible Continuum Manipulator using RGBD Sensing and Temporal Convolutional Network

Flexible continuum manipulators are valued for minimally invasive surgery, offering access to confined spaces through nonlinear paths. However, cable-driven manipulators face control difficulties due to hysteresis from cabling effects such as friction, elongation, and coupling. These effects are difficult to model due to nonlinearity and the difficulties become even more evident when dealing with long and coupled, multi-segmented manipulator. This paper proposes a data-driven approach based on Deep Neural Networks (DNN) to capture these nonlinear and previous states-dependent characteristics of cable actuation. We collect physical joint configurations according to command joint configurations using RGBD sensing and 7 fiducial markers to model the hysteresis of the proposed manipulator. Result on a study comparing the estimation performance of four DNN models show that the Temporal Convolution Network (TCN) demonstrates the highest predictive capability. Leveraging trained TCNs, we build a control algorithm to compensate for hysteresis. Tracking tests in task space using unseen trajectories show that the proposed control algorithm reduces the average position and orientation error by 61.39% (from 13.7mm to 5.29 mm) and 64.04% (from 31.17{\deg} to 11.21{\deg}), respectively. This result implies that the proposed calibrated controller effectively reaches the desired configurations by estimating the hysteresis of the manipulator. Applying this method in real surgical scenarios has the potential to enhance control precision and improve surgical performance.

arXiv:2402.10761

Autonomous Emergency Braking With Driver-In-The-Loop: Torque Vectoring for Active Learning

Autonomous Emergency Braking (AEB) potentially brings significant improvements in automotive safety due to its ability to autonomously prevent collisions in situations where the driver may not be able to do so. Driven by the poor performance of the state of the art in recent testing, this work provides an online solution to identify critical parameters such as the current and maximum friction coefficients. The method introduced here, namely Torque Vectoring for Active Learning (TVAL), can perform state and parameter estimation whilst following the driver's input. Importantly with less power requirements than normal driving. Our method is designed with a crucial focus on ensuring minimal disruption to the driver, allowing them to maintain full control of the vehicle. Additionally, we exploit a rain/light sensor to drive the observer resampling to maintain estimation certainty across prolonged operation. Then a scheme to modulate TVAL is introduced that considers powertrain efficiency, safety, and availability in an online fashion. Using a high-fidelity vehicle model and drive cycle we demonstrate the functionality of TVAL controller across changing road surfaces where we successfully identify the road surface whenever possible.

arXiv:2402.09442

Progress in artificial intelligence applications based on the combination of self-driven sensors and deep learning

In the era of Internet of Things, how to develop a smart sensor system with sustainable power supply, easy deployment and flexible use has become a difficult problem to be solved. The traditional power supply has problems such as frequent replacement or charging when in use, which limits the development of wearable devices. The contact-to-separate friction nanogenerator (TENG) was prepared by using polychotomy thy lene (PTFE) and aluminum (AI) foils. Human motion energy was collected by human body arrangement, and human motion posture was monitored according to the changes of output electrical signals. In 2012, Academician Wang Zhong lin and his team invented the triboelectric nanogenerator (TENG), which uses Maxwell displacement current as a driving force to directly convert mechanical stimuli into electrical signals, so it can be used as a self-driven sensor. Teng-based sensors have the advantages of simple structure and high instantaneous power density, which provides an important means for building intelligent sensor systems. At the same time, machine learning, as a technology with low cost, short development cycle, strong data processing ability and prediction ability, has a significant effect on the processing of a large number of electrical signals generated by TENG, and the combination with TENG sensors will promote the rapid development of intelligent sensor networks in the future. Therefore, this paper is based on the intelligent sound monitoring and recognition system of TENG, which has good sound recognition capability, and aims to evaluate the feasibility of the sound perception module architecture in ubiquitous sensor networks.