Improve model card: Add tags, links, abstract, and usage

README.md

@@ -1,3 +1,69 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: robotics
+library_name: jax
+---
+
+# AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies
+
+This repository contains model checkpoints and code for **AimBot**, a lightweight visual augmentation technique designed to improve visuomotor policy learning in robotic manipulation.
+
+## Paper Abstract
+
+In this paper, we propose AimBot, a lightweight visual augmentation technique that provides explicit spatial cues to improve visuomotor policy learning in robotic manipulation. AimBot overlays shooting lines and scope reticles onto multi-view RGB images, offering auxiliary visual guidance that encodes the end-effector's state. The overlays are computed from depth images, camera extrinsics, and the current end-effector pose, explicitly conveying spatial relationships between the gripper and objects in the scene. AimBot incurs minimal computational overhead (less than 1 ms) and requires no changes to model architectures, as it simply replaces original RGB images with augmented counterparts. Despite its simplicity, our results show that AimBot consistently improves the performance of various visuomotor policies in both simulation and real-world settings, highlighting the benefits of spatially grounded visual feedback.
+
+## Links
+
+*   **Paper:** [AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies](https://huggingface.co/papers/2508.08113)
+*   **Project Page:** [https://aimbot-reticle.github.io/](https://aimbot-reticle.github.io/)
+*   **Code Repository:** [https://github.com/aimbot-reticle/AimBot-Pi0](https://github.com/aimbot-reticle/AimBot-Pi0)
+
+## Usage
+
+You can run inference with the pre-trained AimBot models using the `openpi` package.
+
+First, ensure you have the necessary environment setup and dependencies installed as described in the [official GitHub repository's installation guide](https://github.com/aimbot-reticle/AimBot-Pi0#install).
+
+Here's an example of how to load a trained policy and run inference:
+
+```python
+from openpi.training import config
+from openpi.policies import policy_config
+from openpi.shared import download
+
+# Example: Load the pi0_fast_droid model.
+# Adjust 'pi0_fast_droid' and checkpoint_dir to your specific model/checkpoint.
+config = config.get_config("pi0_fast_droid")
+checkpoint_dir = download.maybe_download("s3://openpi-assets/checkpoints/pi0_fast_droid")
+
+# Create a trained policy.
+policy = policy_config.create_trained_policy(config, checkpoint_dir)
+
+# Prepare your observation data.
+# Replace '...' with actual image tensors (e.g., from PIL.Image or numpy arrays)
+# and other required observation keys (e.g., proprioception, language prompts).
+example = {
+    "observation/exterior_image_1_left": ..., # Placeholder for image data
+    "observation/wrist_image_left": ...,   # Placeholder for image data
+    # ... other observation keys as required by the model, e.g., "prompt": "pick up the fork"
+}
+
+# Run inference to get action predictions.
+action_chunk = policy.infer(example)["actions"]
+print("Inferred actions:", action_chunk)
+```
+
+For more detailed instructions on installation, running simulation/real-world experiments, and fine-tuning, please refer to the [official GitHub repository](https://github.com/aimbot-reticle/AimBot-Pi0).
+
+## Citation
+
+If you find this work helpful, please consider citing our paper:
+
+```bibtex
+@article{aimbot,
+  title={AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies},
+  author={Dai, Yinpei and Lee, Jayjun and et al},
+  journal={CoRL},
+  year={2025},
+}
+```