Robocasa_navigatekitchen
A pi0.5 (ฯโ.โ ) Vision-Language-Action (VLA) model, finetuned on the ROBOCASA robotic manipulation/navigation benchmark using the OpenTau training framework. This model is designed to follow natural language instructions to perform navigation tasks in a simulated kitchen environment.
For full documentation, evaluation results, and inference code, please visit the repository:
๐ https://github.com/TensorAuto/OpenTau
Model Details
Description
- Model Type: Vision-Language-Action (VLA) Model
- Base Architecture: ฯโ.โ (pi0.5) by Physical Intelligence
- Backbone: PaliGemma-3B (VLM) + Gemma-300M (Action Expert)
- Training Data: Robocasa Benchmark
- Framework: OpenTau
Architecture
The pi0.5 architecture uses a flow-matching-based policy designed for open-world generalization. It combines a Visual Language Model (VLM) for high-level semantic understanding with a smaller "action expert" model that generates continuous joint trajectories (10-step action chunks) via flow matching.
Training and Evaluation
Dataset
This model was finetuned on the Robocasa benchmark dataset. The Robocasa suite consists of human-teleoperated and mimicgen demonstrations for manipulation and navigation, covering:
- Navigate Kitchen (Atomic)
Results
Training on 100 Human demonstrations, our model achieves 97% success rate on Navigate Kitchen tasks. For detailed usage instructions, success rates, baseline comparisons, and evaluation protocols, please refer to the OpenTau GitHub Repository.