Results 171 to 180 of about 442,345 (289)

Data‐Driven Bulldozer Blade Control for Autonomous Terrain Leveling

open access: yesAdvanced Robotics Research, EarlyView.
A simulation‐driven framework for autonomous bulldozer leveling is presented, combining high‐fidelity terramechanics simulation with a neural‐network‐based reduced‐order model. Gradient‐based optimization enables efficient, low‐level blade control that balances leveling quality and operation time.
Harry Zhang   +5 more
wiley   +1 more source

Introducing PNEUMA: A Hybrid Soft Pneumatic Fabric Bidirectional Actuation Module for Wearable Robotics

open access: yesAdvanced Robotics Research, EarlyView.
This study presents a soft pneumatic fabric bidirectional actuation module (PNEUMA) capable of generating high torque in both bending directions within a single integrated architecture. PNEUMA achieves up to 50 Nm with reduced inflation volume and a lightweight design.
Odysseas Simatos   +2 more
wiley   +1 more source

Stiffness‐Programmable Origami Robots With Tendon‐Driven Actuation via Multimaterial 3D Printing

open access: yesAdvanced Robotics Research, EarlyView.
Motion diversity is achieved in a tendon‐driven origami robot through programmable stiffness rather than modified actuation. Multimaterial 3D printing embeds soft creases, modular inserts redirect identical tendon inputs into distinct behaviors, and variable‐stiffness inserts enable real‐time switching.
Elisha Lerner, Jianguo Zhao
wiley   +1 more source

WorMa: An Undulatory Robot With Center of Mass Regulation via Internal Fluid Redistribution for Amphibious Locomotion

open access: yesAdvanced Robotics Research, EarlyView.
WorMa is an amphibious undulatory robot that uses Center of Mass redistribution as the sole terrain adaptation mechanism. This mechanism is based on internal fluid mass redistribution through a pump‐driven latex balloon system that creates three profiles: head‐biased, balanced, and tail‐biased.
Daniil Filimonov, Nana Obayashi
wiley   +1 more source

Bio‐Inspired Object Retrieval via Proximity‐Guided Adaptive Thigmotactic Exploration and Neuromorphic Recognition

open access: yesAdvanced Robotics Research, EarlyView.
Sparse active‐infrared proximity sensing is coupled to an adaptive thigmotactic controller for camera‐inaccessible object retrieval. After grasping, receptor‐informed encoding transforms force, temperature, and wrist force–torque signals into spike trains for spiking neural network recognition.
Fengyi Wang, Nitish Thakor, Gordon Cheng
wiley   +1 more source

Home - About - Disclaimer - Privacy