检索结果-内蒙古大学图书馆

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learning

学校读者我要写书评

暂无评论

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem w...

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Yifan Guo Zhongqiang Ren Chen Wang Flight Dynamics & Control/Hybrid Systems Lab Purdue University West Lafayette IN Robotics Institute Carnegie Mellon University Pittsburgh PA USA Department of Computer Science and Engineering Spatial AI & Robotics (SAIR) Lab University at Buffalo NY USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper considers a Min-Max Multiple Traveling Salesman Problem (MTSP), where the goal is to find a set of tours, one for each agent, to collectively visit all the cities while minimizing the length of the longest tour. Though MTSP has been widely studied, obtaining near-optimal solutions for large-scale problems is still challenging due to its NP-hardness. Recent efforts in data-driven methods face challenges of the need for hard-to-obtain supervision and issues with high variance in gradient estimations, leading to slow convergence and highly sub-optimal solutions. We address these issues by reformulating MTSP as a bilevel optimization problem, using the concept of imperative learning (IL). This involves introducing an allocation network that decomposes the MTSP into multiple single-agent traveling salesman problems (TSPs). The longest tour from these TSP solutions is then used to self-supervise the allocation network, resulting in a new self-supervised, bilevel, end-to-end learning framework, which we refer to as imperative MTSP (iMTSP). Additionally, to tackle the high-variance gradient issues during the optimization, we introduce a control variate-based gradient estimation algorithm. Our experiments showed that these innovative designs enable our gradient estimator to converge 20× faster than the advanced reinforcement learning baseline, and find up to 80% shorter tour length compared with Google OR-Tools MTSP solver, especially in large-scale problems (e.g. 1000 cities and 15 agents).

关键词： Urban areas Estimation Reinforcement learning Traveling salesman problems Internet Resource management Optimization Intelligent robots Faces Convergence

Physics Informed Deep Learning for Strain Gradient Continuum Plasticity

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tyagi, Ankit Suman, Uttam Mamajiwala, Mariya Roy, Debasish Computational Mechanics Lab Department of Civil Engineering Indian Institute of Science Bangalore India Department of Computer Science University of Sheffield United Kingdom Centre of Excellence in Advanced Mechanics of Materials Indian Institute of Science Bangalore India

We use a space-time discretization based on physics informed deep learning (PIDL) to approximate solutions of a class of rate-dependent strain gradient plasticity models. The differential equation governing the plastic flow, the so-called microforce balance for this class of yield-free plasticity models, is very stiff, often leading to numerical corruption and a consequent lack of accuracy or convergence by finite element (FE) methods. Indeed, setting up the discretized framework, especially with an elaborate meshing around the propagating plastic bands whose locations are often unknown apriori, also scales up the computational effort significantly. Taking inspiration from physics informed neural networks, we modify the loss function of a PIDL model in several novel ways to account for the balance laws, either through energetics or via the resulting PDEs once a variational scheme is applied, and the constitutive equations. The initial and the boundary conditions may either be imposed strictly by encoding them within the PIDL architecture, or enforced weakly as a part of the loss function. The flexibility in the implementation of a PIDL technique often makes for its ready interface with powerful optimization schemes, and this in turn provides for many possibilities in posing the problem. We have used freely available open-source libraries that perform fast, parallel computations on GPUs. Using numerical illustrations, we demonstrate how PIDL methods could address the computational challenges posed by strain gradient plasticity models. Also, PIDL methods offer abundant potentialities, vis-á-vis a somewhat straitjacketed and poorer approximant of FE methods, in customizing the formulation as per the problem objective. © 2024, CC BY.

关键词： Constitutive equations

CROWD-CALIBRATOR: Can Annotator Disagreement Inform Calibration in Subjective Tasks?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Khurana, Urja Nalisnick, Eric Fokkens, Antske Swayamdipta, Swabha Computational Linguistics and Text Mining Lab Vrije Universiteit Amsterdam Netherlands Department of Computer Science Johns Hopkins University United States Thomas Lord Dept. of Computer Science University of Southern California United States

Subjective tasks in NLP have been mostly relegated to objective standards, where the gold label is decided by taking the majority vote. This obfuscates annotator disagreement and the inherent uncertainty of the label. We argue that subjectivity should factor into model decisions and play a direct role via calibration under a selective prediction setting. Specifically, instead of calibrating confidence purely from the model's perspective, we calibrate models for subjective tasks based on crowd worker agreement. Our method, CROWD-CALIBRATOR, models the distance between the distribution of crowd worker labels and the model's own distribution over labels to inform whether the model should abstain from a decision. On two highly subjective tasks, hate speech detection and natural language inference, our experiments show CROWD-CALIBRATOR either outperforms or achieves competitive performance with existing selective prediction baselines. Our findings highlight the value of bringing human decision-making into model predictions. © 2024, CC BY.

关键词： Prediction models

Fast Spatial Reasoning of Implicit 3D Maps through Explicit Near-Far Sampling Range Prediction

学校读者我要写书评

暂无评论

Fast Spatial Reasoning of Implicit 3D Maps through Explicit ...

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Chaerin Min Sehyun Cha Changhee Won Jongwoo Lim Department of Computer Science Brown University Advanced Robotics Lab. CTO Division LG Electronics MultiplEYE Co. Ltd Department of Mechanical Engineering Seoul National University

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

3D mapping is critical for many robotics applications, such as autonomous navigation and object manipulation. Recently, deep implicit mapping approaches have received much attention for their compactness and ability to represent fine-grained details. However, without explicit guidance, such implicit representations are often cumbersome for searching the full range on the rays to find the object surfaces. As a result, several approaches, including hierarchical sampling, occupancy grids, and zero-level set baking, have been proposed to improve sampling where costly forward passes of the neural network should be performed. However, hierarchical sampling is still suboptimal in that it requires uniform coarse samples. Discrete occupancy grids of Instant NGP and zero-level sets of various baking methods are less suitable for large and noisy real *** this paper, we present a novel framework for adaptively predicting the near-far range for sampling the query positions of the deep implicit map. For this purpose, the truncated signed distance grid for the map is pre-constructed and used to provide hints for near-far prediction during rendering. In addition, our recovery algorithm automatically detects failed near-far predictions and recovers only those rays by directly using the implicit map. We conduct extensive experiments on a synthetic dataset, a public real dataset, and a real dataset captured by our multi-camera robot system. The experimental results show that our algorithm achieves the same rendering quality with surprisingly fewer samples compared to the existing methods, which means that the robot can reason about the image and depth properties of the scene much faster. Finally, a thorough analysis of the sample distribution along the rays is provided to give a better understanding of our method’s strong efficiency, adaptability, and robustness. https://***/TSDF-sampling/

关键词： Three-dimensional displays Neural networks Rendering (computer graphics) Prediction algorithms Search problems Robustness Cognition Noise measurement Intelligent robots Synthetic data

Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pataki, Zador Altillawi, Mohammad Kanakis, Menelaos Pautrat, Rémi Shen, Fengyi Liu, Ziyuan Van Gool, Luc Pollefeys, Marc The Computer Vision and Geometry Lab Department of Computer Science ETH Zurich Switzerland The Computer Vision Center CVC-Barcelona The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Computer Vision Lab Department Electrical Engineering ETH Zurich Switzerland The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Center for Processing Speech and Images KU Leuven The Computer Vision Lab ETH Zurich Switzerland

Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured across long-term visual domain variations, such as different seasonal and daytime variations. In this paper, our first contribution is a benchmark to investigate the performance impact of long-term variations on visual localization. We conduct a thorough analysis of the performance of current state-of-the-art feature extraction networks under various domain changes and find a significant performance gap between intra- and cross-domain localization. We investigate different methods to close this gap by improving the supervision of modern feature extractor networks. We propose a novel data-centric method, Implicit Cross-Domain Correspondences (iCDC). iCDC represents the same environment with multiple Neural Radiance Fields, each fitting the scene under individual visual domains. It utilizes the underlying 3D representations to generate accurate correspondences across different long-term visual conditions. Our proposed method enhances cross-domain localization performance, significantly reducing the performance gap. When evaluated on popular long-term localization benchmarks, our trained networks consistently outperform existing methods. This work serves as a substantial stride toward more robust visual localization pipelines for long-term deployments, and opens up research avenues in the development of long-term invariant descriptors. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature extraction

FDA-approved Levophed as an alternative multitargeted therapeutic against cervical cancer transferase, cell cycle, and regulatory proteins

学校读者我要写书评

暂无评论

computers in Biology and Medicine 2025年 191卷 110163-110163页

作者： Bano, Nagmi Ahmad, Shaban Gupta, Dinesh Raza, Khalid Translational Bioinformatics Group International Centre for Genetic Engineering and Biotechnology New Delhi 110067 India Computational Intelligence and Bioinformatics Lab Department of Computer Science Jamia Millia Islamia New Delhi 110025 India

Despite the availability of Pap tests and HPV vaccines, Cervical Cancer continues to be a significant factor contributing to women's deaths. It poses severe consequences to women's health. The disease's severity lies in its potential to progress silently in its early stages, mainly detected in its advanced stage, and clinical treatment is challenging due to drug resistance. This study aims to identify multitargeted lead molecules based on the interactome of Cervical Cancer-related crucial genes, which can help develop drug-resistant therapies. We have considered 9 crucial Cervical Cancer genes, namely BUBR1, CCNB1, FEN1, MAD2, MCM10, MCM6, ITGB8, POLE, and TPX2, to perform gene network analysis and Gene Ontology enrichment studies to identify the potential hub genes and their role. Further, we performed multitarget screening using multisampling algorithms HTVS, SP, and XP to screen the protein products of the 9 genes for their binding affinity for the FDA-approved drugs library. The binding affinities of the compounds were evaluated using MM\GBSA that identified multitargeted potential inhibitor as a Levophed for Cervical Cancer, and the docking results showed a range of MM/GBSA scores, varying from −8.35 to −5.38 kcal/mol for docking, and −43.41 to −19.37 kcal/mol for MM/GBSA scoring. The protein residues that interact the most with Levophed are ALA, THR, ILE, ASN, GLY, ASP, LEU, LYS, VAL, GLN, PRO, CYS, GLU, and TYR. The pharmacokinetic properties and WaterMap computations also support the idea that the compound can potentially become a drug candidate. Furthermore, all 9 complexes were simulated for 100ns, resulting in cumulative deviation and fluctuation of © 2025 Elsevier Ltd

关键词： Lung cancer

Breaking Isometric Ties and Introducing Priors in Gromov-Wasserstein Distances 27

学校读者我要写书评

暂无评论

Breaking Isometric Ties and Introducing Priors in Gromov-Was...

27th International Conference on Artificial Intelligence and Statistics, AISTATS 2024

作者： Demetci, Pinar Tran, Quang Huy Redko, Ievgen Singh, Ritambhara Eric and Wendy Schmidt Center 1 Broad Institute of MIT and Harvard United States Université Bretagne-Sud IRISA CMAP Ecole Polytechnique IP Paris France Paris Noah’s Ark Lab Huawei Technologies France Department of Computer Science Center for Computational Molecular Biology Brown University United States

Gromov-Wasserstein distance has many applications in machine learning due to its ability to compare measures across metric spaces and its invariance to isometric transformations. However, in certain applications, this invariant property can be too flexible, thus undesirable. Moreover, the Gromov-Wasserstein distance solely considers pairwise sample similarities in input datasets, disregarding the raw feature representations. We propose a new optimal transport formulation, called Augmented Gromov-Wasserstein (AGW), that allows for some control over the level of rigidity to transformations. It also incorporates feature alignments, enabling us to better leverage prior knowledge on the input data for improved performance. We first present theoretical insights into the proposed method. We then demonstrate its usefulness for single-cell multi-omic alignment tasks and heterogeneous domain adaptation in machine learning. Copyright 2024 by the author(s).

关键词： Machine learning

ORBSLAM3-Enhanced Autonomous Toy Drones: Pioneering Indoor Exploration

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tukan, Murad Fares, Fares Grufinkle, Yotam Talmor, Ido Mualem, Loay Braverman, Vladimir Feldman, Dan DataHeroes Israel The Robotics and Big Data lab University of Haifa Haifa Israel The Computer Science Department University of Haifa Haifa Israel The Computer Science Department Rice University HoustonTX United States

Navigating toy drones through uncharted GPS-denied indoor spaces poses significant difficulties due to their reliance on GPS for location determination. In such circumstances, the necessity for achieving proper navigation is a primary concern. In response to this formidable challenge, we introduce a real-time autonomous indoor exploration system tailored for drones equipped with a monocular RGB camera. Our system utilizes ORB-SLAM3, a state-of-the-art vision feature-based SLAM, to handle both the localization of toy drones and the mapping of unmapped indoor terrains. Aside from the practicability of ORB-SLAM3, the generated maps are represented as sparse point clouds, making them prone to the presence of outlier data. To address this challenge, we propose an outlier removal algorithm with provable guarantees. Furthermore, our system incorporates a novel exit detection algorithm, ensuring continuous exploration by the toy drone throughout the unfamiliar indoor environment. We also transform the sparse point to ensure proper path planning using existing path planners. To validate the efficacy and efficiency of our proposed system, we conducted offline and real-time experiments on the autonomous exploration of indoor spaces. The results from these endeavors demonstrate the effectiveness of our methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Drones

TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wen, Junjie Zhu, Yichen Li, Jinming Zhu, Minjie Wu, Kun Xu, Zhiyuan Liu, Ning Cheng, Ran Shen, Chaomin Peng, Yaxin Feng, Feifei Tang, Jian School of Computer Science East China Normal University China Midea Group AI Lab China Department of Computer Science Shanghai University China Syracuse University United States Beijing Innovation Center of Humanoid Robotics China

Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for pre-training stage. Our framework incorporates two essential components to build TinyVLA: (1) initializing the policy backbone with robust, high-speed multimodal models, and (2) integrating a diffusion policy decoder during fine-tuning to enable precise robot actions. We conducted extensive evaluations of TinyVLA in both simulation and on real robots, demonstrating that our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance. Additionally, TinyVLA exhibits strong generalization capabilities across various dimensions, including language instructions, novel objects, unseen positions, changes in object appearance, background variations, and environmental shifts, often matching or exceeding the performance of OpenVLA. We believe that TinyVLA offers an interesting perspective on utilizing pre-trained multimodal models for policy learning. Our project is at https://***. © 2024, CC BY.

关键词： Visual languages