Results 201 to 210 of about 1,645,700 (287)

Reinforcement Learning With a Low‐Cost Parallel Linkage Gripper for Static and Dynamic Planar In‐Hand Manipulation

open access: yesAdvanced Intelligent Systems, EarlyView.
Hardware‐learning co‐design combines volar‐plate‐inspired passive‐joint constraints with mechanism‐aware reinforcement learning for a low‐cost parallel‐linkage gripper. The resulting system performs quasi‐static object adjustment and dynamic pinch grasping, demonstrating reliable planar in‐hand manipulation and successful sim‐to‐real transfer. Parallel
Yanzhou Jin   +4 more
wiley   +1 more source

Miniaturized Multifunctional Valves for Intelligent Pneumatic Systems in Soft Robotics

open access: yesAdvanced Intelligent Systems, EarlyView.
Miniaturized multifunctional pneumatic valves in normally closed (NC) and normally open (NO) configurations enable reconfigurable and programmable fluidic logic—including AND, OR, NAND, and NOR gates—with/without physical replumbing. These valves integrate sensing, logic, and actuation within a unified architecture, demonstrated through an electronics ...
J. Xu   +4 more
wiley   +1 more source

PDBFS: A novel active routing protocol for prioritized delivery of safety messages in VANETs. [PDF]

open access: yesPLoS One
Shah W   +6 more
europepmc   +1 more source

Interbody Wire for Reconfigurable Robots: Bridging Integrated Morphological Reconfiguration and Distributed Wire‐Mediated Cooperation

open access: yesAdvanced Intelligent Systems, EarlyView.
TwinX shows how a single interbody wire connecting two robots can support both integrated morphological reconfiguration and distributed wire‐mediated cooperation. When the robots dock, they reconfigure into different forms for locomotion and manipulation.
Shintaro Inoue   +5 more
wiley   +1 more source

Graph Neural Network‐Based Reinforcement Learning for Decentralized Multi‐Robot Manipulation

open access: yesAdvanced Intelligent Systems, EarlyView.
Robot arms lifting a large object face a trade‐off: centralized controllers explode in parameters, while decentralized ones cannot coordinate. A GNN resolves this—each arm runs its own network but acts on the full team state, achieving centralized‐level coordination with decentralized execution. Trained across team sizes, a single policy scales to four‐
Tong Chen   +3 more
wiley   +1 more source

Home - About - Disclaimer - Privacy