Article

RoboEvolve: A Planner-Simulator Co-Evolution Framework for Robotic Manipulation

RoboEvolve couples a VLM planner and a VGM simulator into a mutually reinforcing co-evolutionary loop, bootstrapped from unlabeled seed images to alleviate manipulation data scarcity. Experiments show it raises the base planner by 30 absolute points and improves simulator success by 48% on average, surpassing fully supervised baselines with only 500 unlabeled seed images and reducing initial reinforcement learning data by 50 times.

Part of the event: RoboEvolve Releases v2, Extending to World-Action Models

This page provides a summary and source link only.