Spatialvla 4b 224 Pt

🚀 SpatialVLA

SpatialVLA is a spatial-enhanced vision-language-action model trained on 1.1 million real robot episodes. The code, based purely on HuggingFace, is concise and offers efficient performance. All SpatialVLA checkpoints and our training codebase are released under an MIT License. For full details, please read our paper and visit our project page.

🚀 Quick Start

SpatialVLA relies solely on HuggingFace Transformers 🤗, making deployment extremely easy. If your environment supports transformers >= 4.47.0, you can directly use the following code to load the model and perform inference (requires 8.5GB of GPU memory).

import torch
from PIL import Image
from transformers import AutoModel, AutoProcessor

model_name_or_path="IPEC-COMMUNITY/spatialvla-4b-224-pt"
processor = AutoProcessor.from_pretrained(model_name_or_path, trust_remote_code=True)

model = AutoModel.from_pretrained(model_name_or_path, trust_remote_code=True, torch_dtype=torch.bfloat16).eval().cuda()

image = Image.open("example.png").convert("RGB")
prompt = "What action should the robot take to pick the cup?"
inputs = processor(images=[image], text=prompt, return_tensors="pt")
generation_outputs = model.predict_action(inputs)

actions = processor.decode_actions(generation_outputs, unnorm_key="bridge_orig/1.0.0")
print(actions)

✨ Features

• Spatial Enhancement: Trained on 1.1 million real robot episodes, SpatialVLA is a spatial-enhanced vision-language-action model.
• Easy Deployment: Relying solely on HuggingFace Transformers, it simplifies the deployment process.
• MIT License: All checkpoints and the training codebase are released under an MIT License.

📦 Installation

If you want to use the model for fine-tuning or pre-training, you need to clone the official repository first.

git clone https://github.com/SpatialVLA/SpatialVLA.git

Then, install the required packages and download the model from the Hugging Face model hub. The VLM backbone of SpatialVLA is PaLiGemma2, which requires transformers >= 4.47.0. Hence, create a Python environment with Python >= 3.10.

conda create -n spatialvla python=3.10
conda activate spatialvla

Install packages from the requirements.txt file. Note that we use a customised dlimp to support seed setting for reproducibility. If you encounter any problems, please manually install dlimp from dlimp_custom.

pip install -r requirements.txt

Train from Scratch

SpatialVLA is pre-trained with 1.1 million real-robot demonstrations from the OXE and RH20T dataset on a cluster of 64 A100 GPUs for about 10 days, using a batch size of 2048. You can pre-train the model from scratch using the following command.

# torchrun
bash scripts/spatialvla_4b_pretrain/torchrun_pretrain.sh

# or in a slurm cluster
bash scripts/spatialvla_4b_pretrain/slurm_pretrain.sh

Fine-tuning

Most of our fine-tuning experiments are conducted using LoRA on 4 or 8 A100 GPUs. You can use the following scripts for full-parameter or LoRA fine-tuning. For real-world experiments with small datasets, we prefer using LoRA for fine-tuning.

# full fine-tuning
bash scripts/spatialvla_4b_finetune/finetune_full.sh

# LoRA fine-tuning
bash scripts/spatialvla_4b_finetune/finetune_lora.sh

📚 Documentation

Model Details

Model Description

Uses

Direct Use

The provided code snippet shows how to load the model and perform inference directly.

Out-of-Scope Use

SpatialVLA models do not zero-shot generalize to new (unseen) robot embodiments, or setups that are not represented in the pretraining mix. In these cases, we suggest collecting a dataset of demonstrations on the desired setup and fine-tuning the SpatialVLA models.

🔧 Technical Details

Evaluation

• SimplerEnv evaluation on Google Robot tasks: | Model | Visual Matching - Pick Coke Can | Visual Matching - Move Near | Visual Matching - Open/Close Drawer | Visual Matching - #Average | Variant Aggregation - Pick Coke Can | Variant Aggregation - Move Near | Variant Aggregation - Open/Close Drawer | Variant Aggregation - #Average | | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | | RT-1 (Begin) | 2.7% | 5.0% | 13.9% | 6.8% | 2.2% | 4.0% | 6.9% | 4.2% | | RT-1 (15%) | 71.0% | 35.4% | 56.5% | 60.2% | 81.3% | 44.6% | 26.7% | 56.2% | | RT-1 (Converged) | 85.7% | 44.2% | 73.0% | 74.6% | 89.8% | 50.0% | 32.3% | 63.3% | | HPT | 56.0% | 60.0% | 24.0% | 46.0% | -- | -- | 31.0% | 45.0% | | TraceVLA | 28.0% | 53.7% | 57.0% | 42.0% | 60.0% | 56.4% | 29.4% | 39.6% | | RT-1-X | 56.7% | 31.7% | 59.7% | 53.4% | 49.0% | 32.3% | 35.3% | 64.3% | | RT-2-X | 78.7% | 77.9% | 25.0% | 60.7% | 82.3% | 79.2% | -- | -- | | Octo-Base | 17.0% | 4.2% | 22.7% | 16.8% | 0.6% | 3.1% | 1.1% | 1.1% | | OpenVLA | 16.3% | 46.2% | 35.6% | 27.7% | 54.5% | 47.7% | 17.7% | 39.8% | | RoboVLM (zero-shot) | 72.7% | 66.3% | 26.8% | 56.3% | 68.3% | 56.0% | 8.5% | 46.3% | | RoboVLM (fine-tuning) | 77.3% | 61.7% | 43.5% | 63.4% | 75.6% | 60.0% | 10.6% | 51.3% | | SpatialVLA (zero-shot) | 81.0% | 69.6% | 59.3% | 71.9% | 89.5% | 71.7% | 36.2% | 68.8% | | SpatialVLA (fine-tuning) | 86.0% | 77.9% | 57.4% | 75.1% | 88.0% | 72.7% | 41.8% | 70.7% |

• SimplerEnv evaluation on WidowX Robot tasks: | Model | Put Spoon on Towel - Grasp Spoon | Put Spoon on Towel - Success | Put Carrot on Plate - Grasp Carrot | Put Carrot on Plate - Success | Stack Green Block on Yellow Block - Grasp Green Block | Stack Green Block on Yellow Block - Success | Put Eggplant in Yellow Basket - Grasp Eggplant | Put Eggplant in Yellow Basket - Success | #Overall Average | | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | | RT-1-X | 16.7% | 0.0% | 20.8% | 4.2% | 8.3% | 0.0% | 0.0% | 0.0% | 1.1% | | Octo-Base | 34.7% | 12.5% | 52.8% | 8.3% | 31.9% | 0.0% | 66.7% | 43.1% | 16.0% | | Octo-Small | 77.8% | 47.2% | 27.8% | 9.7% | 40.3% | 4.2% | 87.5% | 56.9% | 30.0% | | OpenVLA | 4.1% | 0.0% | 33.3% | 0.0% | 12.5% | 0.0% | 8.3% | 4.1% | 1.0% | | RoboVLM (zero-shot) | 37.5% | 20.8% | 33.3% | 25.0% | 8.3% | 8.3% | 0.0% | 0.0% | 13.5% | | RoboVLM (fine-tuning) | 54.2% | 29.2% | 25.0% | 25.0% | 45.8% | 12.5% | 58.3% | 58.3% | 31.3% | | SpatialVLA (zero-shot) | 25.0% | 20.8% | 41.7% | 20.8% | 58.3% | 25.0% | 79.2% | 70.8% | 34.4% | | SpatialVLA (fine-tuning) | 20.8% | 16.7% | 29.2% | 25.0% | 62.5% | 29.2% | 100.0% | 100.0% | 42.7% |

• LIBERO Simulation Benchmark Results: | Model | LIBERO - Spatial - SR (↑) | LIBERO - Spatial - Rank (↓) | LIBERO - Object - SR (↑) | LIBERO - Object - Rank (↓) | LIBERO - Goal - SR (↑) | LIBERO - Goal - Rank (↓) | LIBERO - Long - SR (↑) | LIBERO - Long - Rank (↓) | Average - SR (↑) | Average - Rank (↓) | | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | | Diffusion Policy from scratch | 78.3 ± 1.1% | 5 | 92.5 ± 0.7% | 1 | 68.3 ± 1.2% | 5 | 50.5 ± 1.3% | 5 | 72.4 ± 0.7% | 5 | | Octo fine - tuned | 78.9 ± 1.0% | 4 | 85.7 ± 0.9% | 4 | 84.6 ± 0.9% | 1 | 51.1 ± 1.3% | 4 | 75.1 ± 0.6% | 3 | | OpenVLA fine - tuned | 84.7 ± 0.9% | 2 | 88.4 ± 0.8% | 3 | 79.2 ± 1.0% | 2 | 53.7 ± 1.3% | 3 | 76.5 ± 0.6% | 2 | | TraceVLA fine - tuned | 84.6 ± 0.2% | 3 | 85.2 ± 0.4% | 5 | 75.1 ± 0.3% | 4 | 54.1 ± 1.0% | 2 | 74.8 ± 0.5% | 4 | | SpatialVLA fine - tuned | 88.2 ± 0.5% | 1 | 89.9 ± 0.7% | 2 | 78.6 ± 0.6% | 3 | 55.5 ± 1.0% | 1 | 78.1 ± 0.7% | 1 |

• Zero - shot Robot Control Evaluation on WidowX Robot:

• Spatial Understanding Capability Evaluation:

• Adapting to New Robot Setups on Franka Robot:

📄 License

This project is released under the MIT License.

Citation

BibTeX:

@misc{qu2025spatialvlaexploringspatialrepresentations,
      title={SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model}, 
      author={Delin Qu and Haoming Song and Qizhi Chen and Yuanqi Yao and Xinyi Ye and Yan Ding and Zhigang Wang and JiaYuan Gu and Bin Zhao and Dong Wang and Xuelong Li},
      year={2025},
      eprint={2501.15830},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2501.15830}, 
}