Robot learns mobility and manipulation with just 15 minutes of training data
GordonWetzstein · x · 2026-11-04
RhodaAI showed a robot powered by its Direct Video-Action (DVA) approach completing a task requiring both mobility and manipulation after only 15 minutes of mobility data.
Stanford professor Gordon Wetzstein highlighted that mobile DVA needs remarkably little additional robot data to learn robust mobility and manipulation — a powerful example of how web-scale video pretraining makes new robot capabilities easy to learn.
More from Embodied
- OpenCV Live demos robot visual cortex with RealSense, Jetson, ROS 2 and VLMs — chrismatthieu · 2026-11-04
- Flipper One opens pre-orders ahead of Kickstarter campaign — user_7832 · 2026-11-04
- Sutton shares RL-trained robot dog preparing for lunar terrain — RichardSSutton · 2026-11-04
- Open-weight LLMs control robots zero-shot: Qwen scores 31.39 on RoboDojo, beating GPT-6 Astra — pabbeel · 2026-11-04
- Apple reportedly beta tests Apple Watch AI feature that analyzes nearby conversations — Polymarket · 2026-11-04
- Boston Dynamics rebuilt Stretch Gen 2 from 100,000 operating hours, cutting 81% of internal cabling — xmercury_one · 2026-11-04