Share story
Robotics Science

Robot planning preprint reports 34.6% shorter pick-and-drop cycles

Researchers report that their cuRoboV2-Fast motion planner completed robot pick-and-drop cycles in a mean 5.93 seconds, 34.6% shorter than cuRoboV2, in a stereo-camera-based deployment on YAM. The preprint describes a GPU-accelerated system that plans collision-free movements while accounting for payload and motor torque limits. With a 3 kg payload, the planner achieved a mean planning time of 4.4 milliseconds on an RTX 5090, 14.7x faster than cuRoboV2. It combines trajectory optimization with a separate step that adjusts traversal speed under sampled velocity, acceleration, jerk and torque constraints.
Sources
arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30
Published by Tech & Business, a media brand covering technology and business. This story was sourced from arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30 and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
Infrastructure Products
Infrastructure Products

Microsoft declines option to expand Nscale Texas data center contract

Microsoft has rejected an option to more than double its Texas data center contract with Nscale, the Financial Times reported, citing sources. The decision is a setback for the startup as it pursues ambitions for a $35B initial public offering.

Techmeme
Robotics AI
Robotics AI

Preprint finds robot policies can improve across tasks during deployment

Researchers report that generalist robot policies can improve across diverse tasks through reinforcement learning during deployment, including gains on tasks excluded from that training.

arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30