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

_Published Thursday, November 5, 2026 at 1:06 AM EST · Robotics, Science · Latest · Tier 2 — Notable_

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](https://arxiv.org/abs/2611.06913v1)

---
Canonical: https://techandbusiness.org/newswire/ENlB9_G0cq2k8FSv447hWw
Published: 2026-11-05T06:06:32.204Z
Story chronology: 2026-11-04T18:58:20.000Z
Retrieved: 2026-11-05T08:42:46.193Z
Publisher: Tech & Business (techandbusiness.org)