1,615 Hits in 4.8 sec

A Spectral Learning Approach to Range-Only SLAM [article]

Byron Boots, Geoffrey J. Gordon
2012 arXiv   pre-print
We present a novel spectral learning algorithm for simultaneous localization and mapping (SLAM) from range data with known correspondences.  ...  can cause severe errors in EKFs and EIFs, and to a lesser extent MHT, particularly for the highly non-Gaussian posteriors encountered in range-only SLAM.  ...  Finally, we demonstrate that our spectral approach to SLAM beats other state-of-the-art SLAM approaches on real-world range-only SLAM problems.  ... 
arXiv:1207.2491v1 fatcat:747jknsjrbf3hhxxgqsoewiwzy

A Spectral Learning Approach to Range-Only SLAM

Byron Boots, Geoffrey J. Gordon
We present a novel spectral learning algorithm for simultaneous localization and mapping (SLAM) from range data with known correspondences.  ...  Compared with popular batch optimization or multiple-hypothesis tracking (MHT) methods for range-only SLAM, our spectral approach o↵ers guaranteed low computational requirements and good tracking performance  ...  Inspired by SfM, we reformulate range-only SLAM problem in a similar way in Section 3, and then similarly solve the problem with a spectral learning algorithm.  ... 
doi:10.1184/r1/6475436 fatcat:pkci57j7onawhckqcmt6s24kmu

The Early-type Stars from LAMOST survey: Atmospheric parameters [article]

YanJun Guo, Bo Zhang, Chao Liu, Jiao Li, JiangDan Li, LuQian Wang, ZhiCun Liu, YongHui Hou, ZhanWen Han, XueFei Chen
2021 arXiv   pre-print
We apply two consistency tests to verify this machine learning method and compare stellar labels given by SLAM with that in literature for several objects having high-resolution spectra.  ...  Here we report our work on adopting the data-driven technique Stellar LAbel Machine (SLAM) with the non-LTE TLUSTY synthetic spectra as the training dataset to estimate the stellar parameters of LAMOST  ...  Guoshoujing Telescope (the Large Sky Area Multi-Object Fiber Spectroscopic Telescope LAMOST) is a National Major Scientific Project built by the Chinese  ... 
arXiv:2110.06246v1 fatcat:evcx3yyvhva2nf5msuui2b3al4

Affinity and Penalty Jointly Constrained Spectral Clustering With All-Compatibility, Flexibility, and Robustness

Pengjiang Qian, Yizhang Jiang, Shitong Wang, Kuan-Hao Su, Jun Wang, Lingzhi Hu, Raymond F. Muzic
2017 IEEE Transactions on Neural Networks and Learning Systems  
Finally, both TI-APJCSC and TII-APJCSC demonstrate strong robustness, not only to the number of pairwise constraints but also to the parameter for affinity measurement.  ...  The existing, semisupervised, spectral clustering approaches have two major drawbacks, i.e., either they cannot cope with multiple categories of supervision or they sometimes exhibit unstable effectiveness  ...  Acknowledgment The authors would like to thank B. Hami from MA, USA, for the editorial assistance in the preparation of this paper.  ... 
doi:10.1109/tnnls.2015.2511179 pmid:26915134 pmcid:PMC4990515 fatcat:kcdils5wczfmvffegccqllv34e

Deriving the stellar labels of LAMOST spectra with Stellar LAbel Machine (SLAM) [article]

Bo Zhang and Chao Liu and Li-Cai Deng
2019 arXiv   pre-print
Thanks to the capability to model highly non-linear problems with SVR, SLAM generally can derive stellar labels over a wide range of spectral types.  ...  To illustrate this capability, we test the performance of SLAM on stars ranging from Teff∼4000 to ∼8000 K trained on LAMOST spectra and stellar labels.  ...  Taking advantages of the non-parametric nature of SVR, SLAM is able to fit multi-dimensional and highly non-linear relationship between the fluxes and stellar labels, which is very different from The Cannon  ... 
arXiv:1908.08677v2 fatcat:cvppcmg6xbg2lb7eipmahallhm

Neural RF SLAM for unsupervised positioning and mapping with channel state information [article]

Shreya Kadambi, Arash Behboodi, Joseph B. Soriaga, Max Welling, Roohollah Amiri, Srinivas Yerramalli, Taesang Yoo
2022 arXiv   pre-print
We present a neural network architecture for jointly learning user locations and environment mapping up to isometry, in an unsupervised way, from channel state information (CSI) values with no location  ...  The neural network task is set prediction and is accordingly trained end-to-end. The proposed model learns an interpretable latent, i.e., user location, by just enforcing a physics-based decoder.  ...  Spectral system identification is used to learn dynamical system parameters such as a state space, motion model, and observation model directly.  ... 
arXiv:2203.08264v1 fatcat:zrs3ofa7v5c3tehgzo5vf6jwcy

PHROG: A Multimodal Feature for Place Recognition

Fabien Bonardi, Samia Ainouz, Rémi Boutteau, Yohan Dupuis, Xavier Savatier, Pascal Vasseur
2017 Sensors  
Author Contributions: F.B. conceived, designed and developed the proposed method and its experimental validation; All other authors contributed their expertise to validate the proposal, evaluate and question  ...  spectral ranges.  ...  Knowing what happens globally to textures across different spectral ranges, we have decided to validate the detection step itself in order to choose the best detection approach, namely corner detection  ... 
doi:10.3390/s17051167 pmid:28531101 pmcid:PMC5470912 fatcat:qqw26dbt6vcoxl2ttrbx7uybiq

Exploring the stellar rotation of early-type stars in the LAMOST Medium-Resolution Survey. I. Catalog [article]

Weijia Sun, Xiao-Wei Duan, Licai Deng, Richard de Grijs, Bo Zhang, Chao Liu
2021 arXiv   pre-print
We employed the Stellar LAbel Machine (SLAM) to derive their spectroscopic stellar parameters, drawing on Kurucz spectral synthesis models with 6000 K < T_eff < 15,000 K and -1 dex < [M/H] < 1 dex.  ...  Although this is an intrinsic caveat that comes from the MRS's narrow wavelength coverage, it only has a minor effect on estimates of the stellar rotation rates because of the decent spectral resolution  ...  The Guoshoujing Telescope (the Large Sky Area Multi-Object Fiber Spectroscopic Telescope; LAMOST) is a National Major Scientific Project built by the Chinese Academy of Sciences.  ... 
arXiv:2108.01212v2 fatcat:kkds2kcj7ngihgif7mmhu3g46a

Lifelong Map Learning for Graph-based SLAM in Static Environments

Henrik Kretzschmar, Giorgio Grisetti, Cyrill Stachniss
2010 Künstliche Intelligenz  
We present a novel approach to prune the pose graph so that it only grows when the robot acquires relevant new information about the environment in terms of expected information gain.  ...  As a result, our approach scales with the size of the environment and not with the length of the trajectory, which is an important prerequisite for lifelong map learning.  ...  Acknowledgements We would like to thank Dirk Hähnel for providing the Intel Research Lab dataset.  ... 
doi:10.1007/s13218-010-0034-2 fatcat:t4ygjusjrjejbmpmbezzcmodva

Map building without localization by dimensionality reduction techniques

Takehisa Yairi
2007 Proceedings of the 24th international conference on Machine learning - ICML '07  
Not only traditional linear PCA but also recent manifold learning techniques can be used for solving this problem.  ...  In contrast to the SLAM framework, LFMDR framework does not require localization procedures nor explicit measurement and motion models.  ...  Acknowledgments The author would like to thank T-PRIMAL (Tokyo PRobabilistic Inference and MAchine Learning) members and the ICML reviewers for valuable comments.  ... 
doi:10.1145/1273496.1273631 dblp:conf/icml/Yairi07 fatcat:x7pziojcbrbvtd2biaasndrmou

Enhanced hyperpolarized chemical shift imaging based on a priori segmented information

Gil Farkash, Stefan Markovic, Mihajlo Novakovic, Lucio Frydman
2019 Magnetic Resonance in Medicine  
The purpose of the study was to develop an approach for improving the resolution and sensitivity of hyperpolarized 13 C MRSI based on a priori anatomical information derived from featured, water-based  ...  We are grateful to Dr. Nava Nevo (WIS) for initial help in preparing and handling the animals, to Dr. Tangi Roussel (Neurospin) for Paravision programming assistance, and to Drs.  ...  Figure 7 shows results from the MRSI study reported as #2 in Supporting Information Figure S2 , only this time focusing on the spectral range corresponding to the 13 C1-alanine being metabolically produced  ... 
doi:10.1002/mrm.27631 pmid:30652358 fatcat:zt675qsxk5g7dkn634v3gai5vu

Review of seakeeping criteria for container ship sustainable speed calculation in rough weather [chapter]

L Mudronja, P Vidan, J Parunov
2014 Maritime Technology and Engineering  
Seakeeping criteria considered in the study are slamming, deck wetness, and vertical acceleration at bow.  ...  Sea states describing rough weather are given for North Atlantic sea environment according to the IACS recommendation Note No.34.  ...  Example is bowflare slamming that appears on container ships which is totally different from bottom slamming and requires other approach to determining criteria.  ... 
doi:10.1201/b17494-142 fatcat:ufrdjp74nrfa7ofwmhk7u7uume

Undelayed 3D RO-SLAM based on Gaussian-mixture and reduced spherical parametrization

Felipe R. Fabresse, Fernando Caballero, Ivan Maza, Anibal Ollero
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
This paper presents an undelayed range-only simultaneous localization and mapping (RO-SLAM) based on the Extended Kalman filter.  ...  The paper proposes a state vector parametrization based on Gaussian-Mixture to cope with the multi-modal nature of range-only measurements and a reduced spherical parametrization of the range sensor positions  ...  INTRODUCTION Range-only simultaneous localization and mapping (RO-SLAM) is an emerging application that aims to localize a mobile system at the same time it maps the position of a set of range sensors.  ... 
doi:10.1109/iros.2013.6696556 dblp:conf/iros/FabresseCMO13 fatcat:a7clxzoazrhm7nstbwq5bs6pyq

Good Feature Selection for Least Squares Pose Optimization in VO/VSLAM [article]

Yipu Zhao, Patricio A. Vela
2019 arXiv   pre-print
Integrating Max-logDet feature selection into a state-of-the-art visual SLAM system leads to accuracy improvements with low overhead, as demonstrated via evaluation on a public benchmark.  ...  Unlike existing feature selection works that are focused on efficiency only, our method significantly improves the accuracy of pose tracking, while introducing little overhead.  ...  Submatrix selection with spectral preservation has been extensively studied in the fields of computational theory and machine learning [20] , [21] , for which several matrix-revealing metrics exist to  ... 
arXiv:1905.07807v1 fatcat:imx5gsojfbdapiy5bls4s4jrnu

Information-theoretic compression of pose graphs for laser-based SLAM

Henrik Kretzschmar, Cyrill Stachniss
2012 The international journal of robotics research  
Our approach estimates the mutual information between the laser measurements and the map to discard the measurements that are expected to provide only a small amount of information.  ...  To maintain a sparse pose graph that allows for efficient map optimization, our approach applies an approximate marginalization technique that is based on Chow-Liu trees.  ...  We would like to thank Giorgio Grisetti and Maximilian Beinhofer for fruitful discussions. Furthermore, we thank Dirk Hähnel for providing the FHW and the Intel Research Lab datasets.  ... 
doi:10.1177/0278364912455072 fatcat:x4vr67jnfnc6rgqsd4q6fib2hu
« Previous Showing results 1 — 15 out of 1,615 results