Digital twinJanus: One Agent, Two Roles for Digital Twin Construction and Network OrchestrationarXiv API — полнотекстовый поиск "digital twin" · 3dModellingStochastic MPC robust to errors in disturbance statisticsarXiv — Systems and Control (eess.SY) · 3dModellingРоман Венедиктов («Эмерджентные мультиагентные системы»): «Сегодня сам факт использования ИИ стал обычной частью корпоративной ИТ-среды»spbIT · 3dDigital twinA High-Fidelity Cardiac Digital Twin for Assessing Rate-Dependent Responses: A Comparative Multi-scale Study of TT2 and Tomek Models in Stratified 3D VentriclesarXiv API — полнотекстовый поиск "digital twin" · 3dForecastingAdaptive clustering for robust distributed MPC of coupled multi-agent systemsarXiv — Systems and Control (eess.SY) · 3dForecastingNeural approximation of NMPC without expert demonstrationsarXiv — Systems and Control (eess.SY) · 3dAssets & dataAn operational model for a trusted data space in vocational educationarXiv — Computers and Society (cs.CY) · 3dModellingАгентная система для тех, кто вкатывается: собираем агента поддержки от одного файла до Temporal, саги и circuit breakerХабр · 4dDigital twinOnline digital twin: data assimilation and control in a mean-field formulationarXiv — Systems and Control (eess.SY) · 4dDigital twinSurvey of digital twin networks for 6G: architecture, technologies and AI controlarXiv — Systems and Control (eess.SY) · 4dDigital twin5G NR neural receiver trained on corridor digital twin dataarXiv API — полнотекстовый поиск "digital twin" · 4dForecastingSampling-based MPC unified as a single sequential Monte Carlo algorithmarXiv — Systems and Control (eess.SY) · 4d
Digital twin speeds up reinforcement learning for lab robots
US & West ·
TwinBridge builds digital twins from 3D Gaussian splatting and physics simulation to supply policy initialization and dense visual rewards for real-world online learning of a laboratory robot. Simulator task events and geometric progress yield rewards for pretraining, distilled into a visual reward model and combined with execution history during human-in-the-loop refinement.
Why it matters
It shows a practical way to transfer knowledge from simulation to a real system while reducing the need for costly real-world runs.
Original headline
TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics
Next-generation wireless networks are increasingly large-scale, heterogeneous, and dynamic, posing significant challenges to network modeling and control. Digital twins offer a promising solution, but existing approaches typically rely on static models and decouple twin construction from network…
Cardiac digital twins (CDTs) provide a computational platform for personalized cardiac modeling, but their predictive behavior depends strongly on the selected ionic model and the representation of transmural electrophysiological heterogeneity.
