This-and-That-1.0

This&That V1.0 Model Card

<div align="center">

Project Page | Paper (ArXiv) | Code

</div>

Introduction

We propose a robot learning method for communicating, planning, and executing a wide range of tasks, dubbed This&That. We achieve robot planning for general tasks by leveraging the power of video generative models trained on internet-scale data containing rich physical and semantic context. In this work, we tackle three fundamental challenges in video-based planning: 1) unambiguous task communication with simple human instructions, 2) controllable video generation that respects user intents, and 3) translating visual planning into robot actions. We propose language-gesture conditioning to generate videos, which is both simpler and clearer than existing language-only methods, especially in complex and uncertain environments. We then suggest a behavioral cloning design that seamlessly incorporates the video plans. This&That demonstrates state-of-the-art effectiveness in addressing the above three challenges, and justifies the use of video generation vas an intermediate representation for generalizable task planning and execution.

Citation

@article{wang2024language,
  title={This\&That: Language-Gesture Controlled Video Generation for Robot Planning},
  author={Wang, Boyang and Sridhar, Nikhil and Feng, Chao and Van der Merwe, Mark and Fishman, Adam and Fazeli, Nima and Park, Jeong Joon},
  journal={arXiv preprint arXiv:2407.05530},
  year={2024}
}