metadata
pipeline_tag: robotics
WSA₁: A 3D-Centric World-Spatial-Action Model for Generalizable Robot Control
WSA₁ is an embodied foundation model that introduces World-Spatial-Action modeling to unify instruction-aligned 2D visual planning, action-conditioned 3D world modeling, and 3D-aware action generation.
- Paper: WSA₁: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control
- Project Page: https://zaleni.github.io/WSA1/
- Repository: https://github.com/zaleni/WSA
Overview
WSA₁ learns a shared 2D-3D latent space that connects instruction-aligned visual planning, action-conditioned 3D world prediction, and 3D-aware action generation. It delivers high manipulation performance across simulation environments (such as RoboTwin 2.0 and LIBERO) and real-world robot control tasks.
For environment setup, pretraining, fine-tuning, and evaluation workflows, please refer to the official GitHub repository.