This is a repository containing the code for the paper Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation.
We have provided the instructions for installation and data collection and code execution at the respective links.
We have made the data used for Point Policy publicly available here.
If you find this work useful, please cite the paper using the following bibtex:
@article{haldar2025point,
title={Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation},
author={Haldar, Siddhant and Pinto, Lerrel},
journal={arXiv preprint arXiv:2502.20391},
year={2025}
}
We welcome any queries, comments or discussions on the paper. Please feel free to open an issue on this repository or reach out to siddhanthaldar@nyu.edu.