Results 121 to 130 of about 9,437,008 (290)

Compliant Pneumatic Feet with Real‐Time Stiffness Adaptation for Humanoid Locomotion

Advanced Robotics Research, EarlyView.
A compliant pneumatic foot with real‐time variable stiffness enables humanoid robots to adapt to changing terrains. Using onboard vision and pressure control, the foot modulates stiffness within each gait cycle, reducing impact forces and improving balance. The design, cast in soft silicone with embedded air chambers and Kevlar wrapping, offers durable,
Irene Frizza, Hiroshi Kaminaga, Philippe Fraisse, Gentiane Venture   +3 more
wiley   +1 more source

Bayesian quantification of thermodynamic uncertainties in dense gas flows [PDF]

, 2014
A Bayesian inference methodology is developed for calibrating complex equations of state used in numerical fluid flow solvers. Precisely, the input parameters of three equations of state commonly used for modeling the thermodynamic behavior of so-called ...
CINNELLA, Paola, X. Merle, MERLE, Xavier
core   +1 more source

Gradient-Free De Novo Learning

Entropy
This technical note applies active inference to the problem of learning goal-directed behaviour from scratch, namely, de novo learning. By de novo learning, we mean discovering, directly from observations, the structure and parameters of a discrete ...
Karl Friston, Thomas Parr, Conor Heins, Lancelot Da Costa, Tommaso Salvatori, Alexander Tschantz, Magnus Koudahl, Toon Van de Maele, Christopher Buckley, Tim Verbelen   +9 more
doaj   +1 more source

Muscle Control of an Extra Robotic Digit

Advanced Robotics Research, EarlyView.
This study compares muscle‐ and movement‐based control for operating a supernumerary robotic thumb. While movement control performs better in the proposed tasks, muscle‐based (EMG) control promotes broader motor learning. The results highlight the promise and challenges of using biosignals for human augmentation, offering new insights into intuitive ...
Julien Russ, Lucy Dowdall, Francesco Cenciarelli, Kitty Goodridge, Mabel Ziman, Hristo Dimitrov, Danielle Clode, Tamar R. Makin   +7 more
wiley   +1 more source

Physics‐Embedded Neural Network: A Novel Approach to Design Polymeric Materials

Advanced Science, EarlyView.
Traditional black‐box models for polymer mechanics rely solely on data and lack physical interpretability. This work presents a physics‐embedded neural network (PENN) that integrates constitutive equations into machine learning. The approach ensures reliable stress predictions, provides interpretable parameters, and enables performance‐driven, inverse ...
Siqi Zhan, Hengheng Zhao, Haotian Wang, Zhanjie Liu, Qian Li, Weifeng Zhang, Qingsong Zhao, Liqun Zhang, Jun Liu   +8 more
wiley   +1 more source

Bayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing

Light: Science & Applications
Multi-photon polymerization is a well-established, yet actively developing, additive manufacturing technique for 3D printing on the micro/nanoscale.
Jason E. Johnson, Ishat Raihan Jamil, Liang Pan, Guang Lin, Xianfan Xu   +4 more
doaj   +1 more source

Reinforcement Learning-Based Augmentation of Data Collection for Bayesian Optimization Towards Radiation Survey and Source Localization

Journal of Nuclear Engineering
Safer and more efficient characterization of radioactive environments requires exploring intelligently, utilizing robotic systems which use smart strategies and physics-based statistical models.
Jeremy Marquardt, Leonard Lucas, Stylianos Chatzidakis   +2 more
doaj   +1 more source

ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals

Advanced Science, EarlyView.
The environmental persistence of per‐ and polyfluoroalkyl substances (PFAS) necessitates efficient remediation strategies. This study presents physics‐informed machine learning workflows that accurately predict critical degradation properties, including bond dissociation energies and polarizability.
Pranoy Ray, Andrew R. Castillo, Manoj Kolel‐Veetil, Surya R. Kalidindi   +3 more
wiley   +1 more source

Bayesian cue integration as a developmental outcome of reward mediated learning [PDF]

, 2011
Average human behavior in cue combination tasks is well predicted by Bayesian inference models. As this capability is acquired over developmental timescales, the question arises, how it is learned.
Weisswange Thomas H., Rothkopf Constantin A., Weisswange, Thomas H., Tobias Rodemann, Thomas H. Weisswange, Constantin A Rothkopf, Jochen Triesch, Triesch Jochen, Thomas H Weisswange, Rothkopf, Constantin, Constantin A. Rothkopf, Rodemann, Tobias, Triesch, Jochen, Rodemann Tobias   +13 more
core   +2 more sources

Towards interpretable drug interaction prediction via dual-stage attention and Bayesian calibration with active learning [PDF]

PeerJ Computer Science
Background Drug-drug interactions (DDIs) account for 17–23% of adverse drug reactions leading to hospitalization, with over 74,000 DDI-related events reported in the FDA Adverse Event Reporting System (FAERS) during 2023.
Rongpei Li, Yufang Zhang, Heqi Sun, Shenggeng Lin, Guihua Jia, Yitian Fang, Chen Zhang, Xiaotong Song, Jianwei Zhao, Lyubin Hu, Yajing Yuan, Xueying Mao, Jiayi Li, Aman Kaushik, Dandan An, Dongqing Wei   +15 more
doaj   +2 more sources