Saved in:
Bibliographic Details
Main Authors: Wang, Boyang, Sridhar, Nikhil, Feng, Chao, Van der Merwe, Mark, Fishman, Adam, Fazeli, Nima, Park, Jeong Joon
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.05530
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Clear, interpretable instructions are invaluable when attempting any complex task. Good instructions help to clarify the task and even anticipate the steps needed to solve it. In this work, we propose a robot learning framework for communicating, planning, and executing a wide range of tasks, dubbed This&That. This&That solves general tasks by leveraging video generative models, which, through training on internet-scale data, contain 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 intent, and 3) translating visual plans into robot actions. This&That uses language-gesture conditioning to generate video predictions, as a succinct and unambiguous alternative to existing language-only methods, especially in complex and uncertain environments. These video predictions are then fed into a behavior cloning architecture dubbed Diffusion Video to Action (DiVA), which outperforms prior state-of-the-art behavior cloning and video-based planning methods by substantial margins.