Engineering · Biomedical Engineering
Researchers developed an aerial robot that uses touch to refine its position and perch on structures it has not encountered before. The system succeeded in more than 99% of simulated trials and completed 26 real-world perching trials despite corrupted position estimates.
Neural networks running on low-power microcontrollers decoded surface muscle signals in real time, a requirement for wearable devices and prosthetic control. On a large-scale benchmark, the models matched or exceeded earlier accuracy with up to 5,000 times lower computational cost in resource-constrained settings.
A single ionic wearable sensor simultaneously captured the heart’s electrical signals and arterial pulse waves in a wristband. The design could support beat-to-beat blood-pressure monitoring without timing errors between separate sensors, although the reported testing was limited to daily resting conditions.
