Examples of understanding and generation by Dynin-Robotics. (IMAGE)

Seoul National University College of Engineering

Examples of understanding and generation by Dynin-Robotics.

Caption

Results showing prediction of the next scene based on the current scene and robot action (top), generation of the target scene after task completion according to a user instruction (middle), and a textual description of the task performed based on video of the task (bottom).

Credit

© Seoul National University College of Engineering

Usage Restrictions

For news use only. Must credit "Seoul National University College of Engineering". Not for commercial use.

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.