Results 171 to 180 of about 1,857,440 (272)

Dual‐View Representation Learning for Deployable Humanoid Whole‐Body Control

open access: yesAdvanced Intelligent Systems, EarlyView.
Humanoid robots must learn control from limited onboard sensing, although simulation provides richer training‐only states. DVP learning pairs these views of each simulated motion and aligns their latent control features inside the policy‐learning loop. This direct, deployment‐aware supervision accelerates learning while the deployed policy relies only ...
Haolin Song   +3 more
wiley   +1 more source

Single-Pixel Tactile Skin via compressive sampling. [PDF]

open access: yesCommun Eng
Slepyan A, Xing L, Zhang R, Thakor N.
europepmc   +1 more source

3D Closed‐Loop Navigation of Magnetic Microswimmers Using Vision‐Derived Depth Feedback

open access: yesAdvanced Intelligent Systems, EarlyView.
A planar magnetic microswimmer is navigated in three dimensions under a standard microscope. Image defocus supplies a real‐time depth cue, and model‐predictive control with A* planning steers the body on surfaces and in free swimming. Axial position is regulated by propulsion alone, without magnetic field gradients or extra cameras.
Yasin Cagatay Duygu   +2 more
wiley   +1 more source

Compliant Footpads Enable Terrain‐Adaptive Hopping in a Monopedal Robot

open access: yesAdvanced Intelligent Systems, EarlyView.
A lightweight compliant footpad with embedded spines lets a monopedal hopping robot keep stable ground contact. It preserves stance‐phase dynamics and enables reliable hopping on rock, sand, and ice. Monopedal hopping robots offer exceptional mobility over discontinuous terrain but require consistent foot‐ground contact to maintain stance‐phase ...
Jeeraphat Owen Kledkruemas   +3 more
wiley   +1 more source

Shape Sensing, Mapping, and Obstacle Avoidance of the Continuum Manipulator in Confined Environments

open access: yesAdvanced Intelligent Systems, EarlyView.
An integrated sensing framework combines capacitive sensors, IMU, and laser array sensor. The shape reconstruction is finished by backpropagation neural network. Accurate shape estimation (relative error of 1.04%) is maintained under a 110 g tip load, while a miniaturized VL6180X array enables local environmental reconstruction and reactive obstacle ...
Pengyuan Wang   +9 more
wiley   +1 more source

Self‐Assembled Magnetic Cilia Skin for Five‐Degree‐of‐Freedom Tactile Sensing via Hybrid Physics–Neural Decoding

open access: yesAdvanced Intelligent Systems, EarlyView.
Self‐assembled magnetic cilia convert contact‐induced deformation into spatial magnetic signals with enhanced sensitivity. A hybrid neural–physical decoder simultaneously estimates contact location and three‐axis force (5‐DoF), achieving a localization RMSE of 0.47 mm and force estimation errors below 8%.
Youngjun Ryu   +5 more
wiley   +1 more source

Reverse Haptic Alerting: Human‐Centered Intelligent Systems That Turn Chemical and Biomedical Signals Into Felt Cues

open access: yesAdvanced Intelligent Systems, EarlyView.
Wearable sensors usually warn through sight or sound, channels that become unreliable under protective equipment or in noise. Reverse haptic alerting inverts this flow: Stimuli‐responsive materials convert chemical and biological signals into cues felt through the skin, while a machine‐learned digital twin of tactile perception personalizes the body ...
Hwanhee Yoo   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy