{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:02Z","timestamp":1781534522004,"version":"3.54.5"},"reference-count":46,"publisher":"ASME International","issue":"10","license":[{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/100000084","name":"Directorate for Engineering","doi-asserted-by":"publisher","award":["2048020"],"award-info":[{"award-number":["2048020"]}],"id":[{"id":"10.13039\/100000084","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>A swarm of robots working together promises efficient solutions toward searching for signal sources in hazard localization and search-and-rescue applications. An effective class of such swarm search algorithms is one that constructs, progressively refines, and uses a belief model of the signal environment. These algorithms however risk becoming too computationally burdensome for real-time or onboard decentralized implementation as the size of the swarm or mission duration increases. Other applications that involve collecting an increasing amount of spatially distributed data and building belief models thereof to make decisions face this risk as well. To alleviate this risk, this article presents a new learning-based down-sampling approach applied to a notable search algorithm called Bayes-Swarm, which uses a Gaussian process model of the signal environment. The proposed down-sampling approach involves three key elements: (1) a new abstraction of the input encoding visited locations and the down-sampled data, (2) a probabilistic loss function based on Sinkhorn distance to capture the down-sampling performance, and (3) a convolutional neural network (CNN) to perform this down-sampling. These elements enable learning a generalized way to down-sample observations without requiring expensive simulations of the swarm search process. The new Bayes-Swarm implementation with the CNN-based down-sampling (CNN-Bayes-Swarm) is found to be agnostic to increasing dataset size unlike the original Bayes-Swarm, without significant compromise in search completion time. CNN-Bayes-Swarm also outperforms other baseline down-samplers in terms of search performance and computing costs considered together.<\/jats:p>","DOI":"10.1115\/1.4069191","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T13:39:08Z","timestamp":1752845948000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":1,"title":["Learning-Based Real-Time Down-Sampling for Scalable Decentralized Decision-Making in Bayes-Swarm Search"],"prefix":"10.1115","volume":"25","author":[{"given":"Aditya","family":"Bhatt","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01y64my43","id-type":"ROR","asserted-by":"publisher"}],"name":"University at Buffalo Department of Mechanical and Aerospace Engineering, , , \u00a0","place":["Buffalo, NY, 14260"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jhoel","family":"Witter","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01y64my43","id-type":"ROR","asserted-by":"publisher"}],"name":"University at Buffalo Department of Mechanical and Aerospace Engineering, , , \u00a0","place":["Buffalo, NY, 14260"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prajit","family":"KrisshnaKumar","sequence":"additional","affiliation":[{"name":"University at Buffalo Department of Mechanical and Aerospace Engineering, , , \u00a0","place":["Buffalo, NY, 14260"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve","family":"Paul","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01y64my43","id-type":"ROR","asserted-by":"publisher"}],"name":"University at Buffalo Department of Mechanical and Aerospace Engineering, , , \u00a0","place":["Buffalo, NY, 14260"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Souma","family":"Chowdhury","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01y64my43","id-type":"ROR","asserted-by":"publisher"}],"name":"University at Buffalo Department of Mechanical and Aerospace Engineering, , , \u00a0","place":["Buffalo, NY, 14260"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"issue":"1","key":"2025081809140673000_CIT0001","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.dt.2013.03.001","article-title":"Research Advance in Swarm Robotics","volume":"9","author":"Tan","year":"2013","journal-title":"Defence Technol."},{"key":"2025081809140673000_CIT0002","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/978-3-642-00644-9_21","volume-title":"Distributed Autonomous Robotic Systems 8","author":"Lochmatter","year":"2009"},{"key":"2025081809140673000_CIT0003","first-page":"83","article-title":"Learning Robot Swarm Tactics Over Complex Adversarial Environments","author":"Behjat","year":"2021"},{"key":"2025081809140673000_CIT0004","first-page":"455","article-title":"A Multi-Robot Control Policy for Information Gathering in the Presence of Unknown Hazards","author":"Schwager","year":"2017"},{"key":"2025081809140673000_CIT0005","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.robot.2018.11.014","article-title":"Odor Source Localization Algorithms on Mobile Robots: A Review and Future Outlook","volume":"112","author":"Chen","year":"2019","journal-title":"Rob. Auton. Syst."},{"issue":"3","key":"2025081809140673000_CIT0006","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1109\/TRO.2012.2183069","article-title":"Simultaneous Localization of Multiple Unknown and Transient Radio Sources Using a Mobile Robot","volume":"28","author":"Song","year":"2012","journal-title":"IEEE Trans. Rob."},{"issue":"1","key":"2025081809140673000_CIT0007","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1080\/19475705.2016.1238852","article-title":"Multipurpose UAV for Search and Rescue Operations in Mountain Avalanche Events","volume":"8","author":"Silvagni","year":"2017","journal-title":"Geomatics Natural Hazards Risk"},{"key":"2025081809140673000_CIT0008","doi-asserted-by":"publisher","first-page":"191617","DOI":"10.1109\/ACCESS.2020.3030190","article-title":"Collaborative Multi-Robot Search and Rescue: Planning, Coordination, Perception, and Active Vision","volume":"8","author":"Queralta","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"2025081809140673000_CIT0009","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1002\/rob.21439","article-title":"Emergency Response to the Nuclear Accident at the Fukushima Daiichi Nuclear Power Plants Using Mobile Rescue Robots","volume":"30","author":"Nagatani","year":"2013","journal-title":"J. Field Rob."},{"key":"2025081809140673000_CIT0010","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.asoc.2019.01.023","article-title":"A Probabilistic Finite State Machine Based Strategy for Multi-Target Search Using Swarm Robotics","volume":"77","author":"Li","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"2025081809140673000_CIT0011","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1016\/j.asoc.2017.02.028","article-title":"Swarm Robotics Search & Rescue: A Novel Artificial Intelligence-Inspired Optimization Approach","volume":"57","author":"Bakhshipour","year":"2017","journal-title":"Appl. Soft Comput."},{"key":"2025081809140673000_CIT0012","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/978-3-540-89933-4_3","volume-title":"Design and Control of Intelligent Robotic Systems","author":"Krishnanand","year":"2009"},{"key":"2025081809140673000_CIT0013","first-page":"1602","article-title":"Particle Swarm Optimization for Source Localization in Environment With Obstacles","author":"Zou","year":"2014"},{"key":"2025081809140673000_CIT0014","doi-asserted-by":"publisher","first-page":"76328","DOI":"10.1109\/ACCESS.2019.2921621","article-title":"Extended PSO Based Collaborative Searching for Robotic Swarms With Practical Constraints","volume":"7","author":"Yang","year":"2019","journal-title":"IEEE Access"},{"key":"2025081809140673000_CIT0015","doi-asserted-by":"publisher","first-page":"949888","DOI":"10.3389\/fnbot.2022.949888","article-title":"Odor Source Localization of Multi-robots With Swarm Intelligence Algorithms: A Review","volume":"16","author":"Wang","year":"2022","journal-title":"Front. Neurorobot."},{"key":"2025081809140673000_CIT0016","doi-asserted-by":"publisher","first-page":"108873","DOI":"10.1016\/j.asoc.2022.108873","article-title":"A Swarm Intelligence-Based Robotic Search Algorithm Integrated With Game Theory","volume":"122","author":"Youssefi","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"2025081809140673000_CIT0017","first-page":"2359","article-title":"Cooperative Control of a Multi-Robot System for Odor Source Localization","author":"Lu","year":"2011"},{"key":"2025081809140673000_CIT0018","first-page":"1","article-title":"Convergence of Multi-agent Systems to Unknown Source of an Odor","author":"Sinha","year":"2018"},{"issue":"7","key":"2025081809140673000_CIT0019","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1002\/tee.23364","article-title":"Recent Progress and Trend of Robot Odor Source Localization","volume":"16","author":"Jing","year":"2021","journal-title":"IEEJ Trans. Electr. Electron. Eng."},{"issue":"10","key":"2025081809140673000_CIT0020","doi-asserted-by":"publisher","first-page":"105005","DOI":"10.1088\/1361-6501\/aa7d31","article-title":"Intelligent Adaptive Sampling Guided by Gaussian Process Inference","volume":"28","author":"Chen","year":"2017","journal-title":"Meas. Sci. Technol."},{"key":"2025081809140673000_CIT0021","first-page":"194","article-title":"Tumor Localization Using Automated Palpation With Gaussian Process Adaptive Sampling","author":"Garg","year":"2016"},{"key":"2025081809140673000_CIT0022","first-page":"6359","article-title":"Adaptive Sampling and Online Learning in Multi-Robot Sensor Coverage With Mixture of Gaussian Processes","author":"Luo","year":"2018"},{"issue":"5","key":"2025081809140673000_CIT0023","doi-asserted-by":"publisher","first-page":"051003","DOI":"10.1115\/1.4046587","article-title":"An Extended Bayesian Optimization Approach to Decentralized Swarm Robotic Search","volume":"20","author":"Ghassemi","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"6","key":"2025081809140673000_CIT0024","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1007\/s10514-022-10047-8","article-title":"A Penalized Batch-Bayesian Approach to Informative Path Planning for Decentralized Swarm Robotic Search","volume":"46","author":"Ghassemi","year":"2022","journal-title":"Auton. Rob."},{"key":"2025081809140673000_CIT0025","first-page":"11495","article-title":"An Active Learning Based Robot Kinematic Calibration Framework Using Gaussian Processes","author":"Da\u015f","year":"2023"},{"issue":"11","key":"2025081809140673000_CIT0026","doi-asserted-by":"publisher","first-page":"6981","DOI":"10.1109\/TCSVT.2023.3270315","article-title":"Task-Oriented Compact Representation of 3D Point Clouds via A Matrix Optimization-Driven Network","volume":"33","author":"Qian","year":"2023","journal-title":"IEEE Trans. Circ. Syst. Video Tech."},{"issue":"11","key":"2025081809140673000_CIT0027","doi-asserted-by":"publisher","first-page":"4405","DOI":"10.1109\/TNNLS.2019.2957109","article-title":"When Gaussian Process Meets Big Data: A Review of Scalable GPS","volume":"31","author":"Liu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2025081809140673000_CIT0028","first-page":"1533","article-title":"Understanding Probabilistic Sparse Gaussian Process Approximations","volume":"29","author":"Bauer","year":"2016","journal-title":"Adv. Neural Inform. Process. Syst."},{"issue":"28","key":"2025081809140673000_CIT0029","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1016\/j.ifacol.2015.12.212","article-title":"Online Sparse Gaussian Process Regression Using FITC and PITC Approximations","volume":"48","author":"Bijl","year":"2015","journal-title":"IFAC-PapersOnLine"},{"key":"2025081809140673000_CIT0030","first-page":"567","article-title":"Variational Learning of Inducing Variables in Sparse Gaussian Processes","author":"Titsias","year":"2009"},{"issue":"6","key":"2025081809140673000_CIT0031","doi-asserted-by":"publisher","first-page":"e1414","DOI":"10.1002\/wics.1414","article-title":"Recent Advances in Scaling-Down Sampling Methods in Machine Learning","volume":"9","author":"ElRafey","year":"2017","journal-title":"Wiley Interdiscipl. Rev.: Comput. Stat."},{"key":"2025081809140673000_CIT0032","first-page":"188","article-title":"Informative Path Planning With Local Penalization for Decentralized and Asynchronous Swarm Robotic Search","author":"Ghassemi","year":"2019"},{"issue":"9","key":"2025081809140673000_CIT0033","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1109\/83.623193","article-title":"The Farthest Point Strategy for Progressive Image Sampling","volume":"6","author":"Eldar","year":"1997","journal-title":"IEEE Trans. Image Process."},{"key":"2025081809140673000_CIT0034","first-page":"1","article-title":"Clustering Based Downsampling and Reconstruction for Band-Limited Graph Signal","author":"Yang","year":"2016"},{"key":"2025081809140673000_CIT0035","first-page":"4716","article-title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","author":"Jain","year":"2023"},{"key":"2025081809140673000_CIT0036","first-page":"415","article-title":"Autoencoder and Its Various Variants","author":"Zhai","year":"2018"},{"key":"2025081809140673000_CIT0037","first-page":"2352","article-title":"Variational Autoencoder for Deep Learning of Images, Labels and Captions","volume":"29","author":"Pu","year":"2016","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"2025081809140673000_CIT0038","first-page":"2292","article-title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"2025081809140673000_CIT0039","first-page":"1608","article-title":"Learning Generative Models With Sinkhorn Divergences","author":"Genevay","year":"2018"},{"key":"2025081809140673000_CIT0040","first-page":"116","article-title":"Imitation Learning With Sinkhorn Distances","author":"Papagiannis","year":"2022"},{"key":"2025081809140673000_CIT0041","first-page":"5859","article-title":"Differential Properties of Sinkhorn Approximation for Learning With Wasserstein Distance","volume":"31","author":"Luise","year":"2018","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"2025081809140673000_CIT0042","first-page":"2681","article-title":"Interpolating Between Optimal Transport and MMD Using Sinkhorn Divergences","author":"Feydy","year":"2019"},{"key":"2025081809140673000_CIT0043","article-title":"Geometric Data Analysis, Beyond Convolutions","volume":"3","author":"Feydy","year":"2020","journal-title":"Appl. Math."},{"key":"2025081809140673000_CIT0044","author":"Bhatt"},{"key":"2025081809140673000_CIT0045","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139170314","volume-title":"Signal Coding and Processing","author":"Wade","year":"1994"},{"issue":"6","key":"2025081809140673000_CIT0046","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random Sample Consensus: A Paradigm for Model Fitting With Applications to Image Analysis and Automated Cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Commun. ACM"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/25\/10\/101004\/7522405\/jcise-25-1054.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/25\/10\/101004\/7522405\/jcise-25-1054.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T13:14:15Z","timestamp":1755522855000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/25\/10\/101004\/1219713\/Learning-Based-Real-Time-Down-Sampling-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":46,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4069191","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,18]]},"article-number":"101004"}}