Researchers at Xidian University in China have demonstrated a light-powered computing chip capable of running reinforcement ...
Perceptive Humanoid Parkour (PHP) enables a Unitree G1 humanoid robot to execute highly dynamic, long-horizon parkour behaviors using onboard perception. By composing various agil ...
Interesting Engineering on MSN
New light-based photonic chips enable robotic learning without electronic computation
Researchers have built new photonic computing chips that allow neural networks to learn using ...
Morning Overview on MSN
Mind-blowing photonic chips teach robots using light instead of electronics
Researchers report building photonic computing chips that use light pulses to train spiking neural networks on ...
Interesting Engineering on MSN
China: Xiaomi humanoid robot carries out complex nut assembly task at EV factory
Chinese technology company Xiaomi announced on March 2 that it has deployed humanoid robots ...
Image courtesy by QUE.com Not long ago, the idea of a humanoid robot folding laundry, loading a dishwasher, or making a simple meal ...
Xiaomi has announced the deployment of a humanoid robot at its electric vehicle manufacturing plant, AzerNEWS reports.
New photonic chips could improve autonomous driving technologies and enable robotic systems that learn through real-world ...
If generative AI improves what robots know, physical AI improves how they behave. One of humanoid robotics’ longest-standing problems is the ‘sim-to-real’ gap: policies that look agile in simulation ...
Xiaomi has deployed humanoid robots in its electric vehicle factory, automatically assembling complex components with a 90.2% success rate and a production cycle of 76 seconds.
Morning Overview on MSN
NASA robot heads back to US for epic Mars mission after a decade in Scotland
NASA’s humanoid robot Valkyrie is heading back to the United States after spending a decade at the University of Edinburgh in ...
AZoRobotics on MSN
New Analytical Method Makes Hybrid Soft-Rigid Robot Simulations Up to 1000× Faster
This research advances hybrid soft-rigid robot simulations, achieving up to 1000 times faster computations through analytical derivatives in the GVS framework.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results