arXiv subjects

Zhenyu Wei

Publications and source records attributed to Zhenyu Wei.

27 records · Page 2Linked to original sources

arXiv2024

A camera system for real-time optical calibration of water-based neutrino telescopes

Calibrating the optical properties within the detection medium of a neutrino telescope is crucial for determining its angular resolution and energy scale. For the next generation of neutrino telescopes planned to be constructed in deep water, such as the TRopIcal DEep-sea Neutrino Telescope (TRIDENT), there are additional challenges due to the dynamic nature and potential non-uniformity of the water medium. This necessitates a real-time optical calibration system distributed throughout the large detector array. This study introduces a custom-designed CMOS camera system equipped with rapid image processing algorithms, providing a real-time optical calibration method for TRIDENT and other similar projects worldwide. In September 2021, the TRIDENT Pathfinder experiment (TRIDENT Explorer, T-REX for short) successfully deployed this camera system in the West Pacific Ocean at a depth of 3420 meters. Within 30 minutes, about 3000 images of the T-REX light source were captured, allowing for the in-situ measurement of seawater attenuation and absorption lengths under three wavelengths. This deep-sea experiment for the first time showcased a technical demonstration of a functioning camera calibration system in a dynamic neutrino telescope site, solidifying a substantial part of the calibration strategies for the future TRIDENT project.

physics.ins-det↗

arXiv2024

Enhanced Object Tracking by Self-Supervised Auxiliary Depth Estimation Learning

RGB-D tracking significantly improves the accuracy of object tracking. However, its dependency on real depth inputs and the complexity involved in multi-modal fusion limit its applicability across various scenarios. The utilization of depth information in RGB-D tracking inspired us to propose a new method, named MDETrack, which trains a tracking network with an additional capability to understand the depth of scenes, through supervised or self-supervised auxiliary Monocular Depth Estimation learning. The outputs of MDETrack's unified feature extractor are fed to the side-by-side tracking head and auxiliary depth estimation head, respectively. The auxiliary module will be discarded in inference, thus keeping the same inference speed. We evaluated our models with various training strategies on multiple datasets, and the results show an improved tracking accuracy even without real depth. Through these findings we highlight the potential of depth estimation in enhancing object tracking performance.

cs.CV↗

arXiv2023

A New Smoothing Technique for Bang-Bang Optimal Control Problems

Bang-bang control is ubiquitous for Optimal Control Problems (OCPs) where the constrained control variable appears linearly in the dynamics and cost function. Based on the Pontryagin's Minimum Principle, the indirect method is widely used to numerically solve OCPs because it enables to derive the theoretical structure of the optimal control. However, discontinuities in the bang-bang control structure may result in numerical difficulties for gradient-based indirect method. In this case, smoothing or regularization procedures are usually applied to eliminating the discontinuities of bang-bang controls. Traditional smoothing or regularization procedures generally modify the cost function by adding a term depending on a small parameter, or introducing a small error into the state equation. Those procedures may complexify the numerical algorithms or degenerate the convergence performance. To overcome these issues, we propose a bounded smooth function, called normalized L2-norm function, to approximate the sign function in terms of the switching function. The resulting optimal control is smooth and can be readily embedded into the indirect method. Then, the simplicity and improved performance of the proposed method over some existing methods are numerically demonstrated by a minimal-time oscillator problem and a minimal-fuel low-thrust trajectory optimization problem that involves many revolutions.

math.OC↗

arXiv2023

Hydrating and dehydrating dynamics process as an ion entering a carbon nanotube

Ion transport within confined environments, like nanopores and nanotubes, is pivotal for advancing a range of applications, including biosensors, seawater desalination, and energy storage devices. Existing research does not sufficiently delve into the alterations in ion hydration structure, a key element that significantly influences ion transport properties in such confined environments. Here, we report a theoretical model comprehensively considering the interplay between ions and nanotubes. By incorporating the effect of orientational competition, our model effectively predicts both the change in hydration structure and the free energy profile during an ion's transition from bulk water into a nanotube. These predictions match closely with the results from molecular dynamics simulations.

cond-mat.mes-hall↗

arXiv2023

Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning

Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data. Although avoiding the time-consuming online interactions in RL, it poses challenges for out-of-distribution (OOD) state actions and often suffers from data inefficiency for training. Despite many efforts being devoted to addressing OOD state actions, the latter (data inefficiency) receives little attention in offline RL. To address this, this paper proposes the cross-domain offline RL, which assumes offline data incorporate additional source-domain data from varying transition dynamics (environments), and expects it to contribute to the offline data efficiency. To do so, we identify a new challenge of OOD transition dynamics, beyond the common OOD state actions issue, when utilizing cross-domain offline data. Then, we propose our method BOSA, which employs two support-constrained objectives to address the above OOD issues. Through extensive experiments in the cross-domain offline RL setting, we demonstrate BOSA can greatly improve offline data efficiency: using only 10\% of the target data, BOSA could achieve {74.4\%} of the SOTA offline RL performance that uses 100\% of the target data. Additionally, we also show BOSA can be effortlessly plugged into model-based offline RL and noising data augmentation techniques (used for generating source-domain data), which naturally avoids the potential dynamics mismatch between target-domain data and newly generated source-domain data.

cs.LG↗

arXiv2023

BVIP Guiding System with Adaptability to Individual Differences

Guiding robots can not only detect close-range obstacles like other guiding tools, but also extend its range to perceive the environment when making decisions. However, most existing works over-simplified the interaction between human agents and robots, ignoring the differences between individuals, resulting in poor experiences for different users. To solve the problem, we propose a data-driven guiding system to cope with the effect brighten by individual differences. In our guiding system, we design a Human Motion Predictor (HMP) and a Robot Dynamics Model (RDM) based on deep neural network, the time convolutional network (TCN) is verified to have the best performance, to predict differences in interaction between different human agents and robots. To train our models, we collected datasets that records the interactions from different human agents. Moreover, given the predictive information of the specific user, we propose a waypoints selector that allows the robot to naturally adapt to the user's state changes, which are mainly reflected in the walking speed. We compare the performance of our models with previous works and achieve significant performance improvements. On this basis, our guiding system demonstrated good adaptability to different human agents. Our guiding system is deployed on a real quadruped robot to verify the practicability.

cs.RO↗

arXiv2023

Simulation study on the optical processes at deep-sea neutrino telescope sites

The performance of a large-scale water Cherenkov neutrino telescope relies heavily on the transparency of the surrounding water, quantified by its level of light absorption and scattering. A pathfinder experiment was carried out to measure the optical properties of deep seawater in South China Sea with light-emitting diodes (LEDs) as light sources, photon multiplier tubes (PMTs) and cameras as photon sensors. Here, we present an optical simulation program employing the Geant4 toolkit to understand the absorption and scattering processes in the deep seawater, which helps to extract the underlying optical properties from the experimental data. The simulation results are compared with the experimental data and show good agreements. We also verify the analysis methods that utilize various observables of the PMTs and the cameras with this simulation program, which can be easily adapted by other neutrino telescope pathfinder experiments and future large-scale detectors.

astro-ph.IM↗

arXiv2022

Few-shot Domain Adaptation for IMU Denoising

Different application scenarios will cause IMU to exhibit different error characteristics which will cause trouble to robot application. However, most data processing methods need to be designed for specific scenario. To solve this problem, we propose a few-shot domain adaptation method. In this work, a domain adaptation framework is considered for denoising the IMU, a reconstitution loss is designed to improve domain adaptability. In addition, in order to further improve the adaptability in the case of limited data, a few-shot training strategy is adopted. In the experiment, we quantify our method on two datasets (EuRoC and TUM-VI) and two real robots (car and quadruped robot) with three different precision IMUs. According to the experimental results, the adaptability of our framework is verified by t-SNE. In orientation results, our proposed method shows the great denoising performance.

cs.RO↗

arXiv2022

Extending the Use of MDL for High-Dimensional Problems: Variable Selection, Robust Fitting, and Additive Modeling

In the signal processing and statistics literature, the minimum description length (MDL) principle is a popular tool for choosing model complexity. Successful examples include signal denoising and variable selection in linear regression, for which the corresponding MDL solutions often enjoy consistent properties and produce very promising empirical results. This paper demonstrates that MDL can be extended naturally to the high-dimensional setting, where the number of predictors $p$ is larger than the number of observations $n$. It first considers the case of linear regression, then allows for outliers in the data, and lastly extends to the robust fitting of nonparametric additive models. Results from numerical experiments are presented to demonstrate the efficiency and effectiveness of the MDL approach.

eess.SP↗