Researchers at Singapore University of Technology and Design developed a new machine learning approach to model underwater robot dynamics, allowing for efficient swimming in complex environments. The approach, published in IEEE-RAL, uses deep neural networks to predict required flapping motions for a set of given propulsive force targets.
SourceSingapore University of Technology and Design·JournalIEEE Robotics and Automation Letters·DateMay 11, 2022
Researchers from Harvard John A. Paulson School of Engineering and Applied Sciences have developed a single-material, single-stimuli microstructure that can outmaneuver even living cilia. These programmable structures could be used for soft robotics, biocompatible medical devices, and dynamic information encryption.
SourceHarvard John A. Paulson School of Engineering and Applied Sciences·JournalNature·DateMay 5, 2022
Developed by Prof. Qing Shi's team, SQuRo can mimic the motion of actual rats and perform various motions like crouching-to-standing, walking, crawling, and turning. It successfully passed through an irregular narrow passage and demonstrated its potential application to inspection tasks inside narrow spaces.
SourceCactus Communications·JournalIEEE Transactions on Robotics·TypeExperimental study·DateApr 18, 2022
Researchers developed a hybrid machine-learning approach combining CNN and LSTM to recognize complex hand gestures in prosthetic hands. The technique achieved far superior performance than traditional machine learning efforts, with an accuracy of over 80%, but struggled with certain pinching gestures.
SourceBeijing Institute of Technology Press Co., Ltd·JournalCyborg and Bionic Systems·TypeExperimental study·DateFeb 7, 2022
SAMSUNG T9 Portable SSD 2TB
SAMSUNG T9 Portable SSD 2TB transfers large imagery and model outputs quickly between field laptops, lab workstations, and secure archives.
A new design for thermal actuators accelerates soft robotic movement by exploiting temperature-dependent bi-stability. The structure changes shape in response to heat, allowing for rapid snapping actions. Prototypes demonstrate rapid movement capabilities, paving the way for biomedical, prosthetic, and manufacturing applications.
SourceNorth Carolina State University·JournalSoft Robotics·TypeExperimental study·DateDec 13, 2021
Researchers created a paper-like material that folds itself into new shapes in response to environmental humidity, with potential applications in self-folding envelopes and boxes. The material's ability to morph on demand could lead to the development of autonomous origami robots and other complex shapes.
SourceNanyang Technological University·JournalProceedings of the National Academy of Sciences·DateOct 18, 2021
Researchers developed electrically-driven soft valves to control hydraulic soft actuators, enabling faster and more powerful control of macro- and small-scale hydraulic actuators. The breakthrough allows for unprecedented motion control of soft robots with internal volume ranging from hundreds of microliters to tens of milliliters.
SourceHarvard John A. Paulson School of Engineering and Applied Sciences·JournalProceedings of the National Academy of Sciences·DateSep 8, 2021