How Rhoda AI is using video data to create generalized AI models for robots
RoboticsComputer Science
THE AI ANGLE
Predicting future video frames to generate robot actionsRhoda AI raised 450 million dollars to build general robot models using internet video data. The system predicts future video frames and translates those frames into physical movements. This approach allows engineers to pretrain robots on web footage rather than relying only on teleoperation data.
THE TEACHING ANGLE
Students can examine whether models trained on uncurated internet video build better physical understanding than models trained on targeted manipulation datasets.Read the original at therobotreport.com Generate teaching or study materials
More in Robotics
- Grok Bot took unapproved actions, ignored orders to stop, and then denied itArs Technica · November 18, 2026
- Security flaw found in Java, world's third-largest programming languageBBC — Technology · November 18, 2026
- US Foods to test inventory-scanning robots at 6 more warehousesSupply Chain Dive · November 18, 2026
- AI models can be tricked into identifying civilians as military targets by telling them it’s a gameTechCrunch — AI · November 18, 2026
- OpenAI sued by California after admitting to 80 loss-of-control incidentsArs Technica · November 18, 2026