Latent Action Pretraining from Videos
- URL: http://arxiv.org/abs/2410.11758v1
- Date: Tue, 15 Oct 2024 16:28:09 GMT
- Title: Latent Action Pretraining from Videos
- Authors: Seonghyeon Ye, Joel Jang, Byeongguk Jeon, Sejune Joo, Jianwei Yang, Baolin Peng, Ajay Mandlekar, Reuben Tan, Yu-Wei Chao, Bill Yuchen Lin, Lars Liden, Kimin Lee, Jianfeng Gao, Luke Zettlemoyer, Dieter Fox, Minjoon Seo,
- Abstract summary: We introduce Latent Action Pretraining for general Action models (LAPA)
LAPA is an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels.
We propose a method to learn from internet-scale videos that do not have robot action labels.
- Score: 156.88613023078778
- License:
- Abstract: We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require action labels typically collected by human teleoperators during pretraining, which significantly limits possible data sources and scale. In this work, we propose a method to learn from internet-scale videos that do not have robot action labels. We first train an action quantization model leveraging VQ-VAE-based objective to learn discrete latent actions between image frames, then pretrain a latent VLA model to predict these latent actions from observations and task descriptions, and finally finetune the VLA on small-scale robot manipulation data to map from latent to robot actions. Experimental results demonstrate that our method significantly outperforms existing techniques that train robot manipulation policies from large-scale videos. Furthermore, it outperforms the state-of-the-art VLA model trained with robotic action labels on real-world manipulation tasks that require language conditioning, generalization to unseen objects, and semantic generalization to unseen instructions. Training only on human manipulation videos also shows positive transfer, opening up the potential for leveraging web-scale data for robotics foundation model.
Related papers
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model [45.03115608632622]
spatial understanding is the keypoint in robot manipulation.
We propose SpatialVLA to explore effective spatial representations for the robot foundation model.
We show the proposed Adaptive Action Grids offer a new and effective way to fine-tune the pre-trained SpatialVLA model for new simulation and real-world setups.
arXiv Detail & Related papers (2025-01-27T07:34:33Z) - FAST: Efficient Action Tokenization for Vision-Language-Action Models [98.15494168962563]
We propose a new compression-based tokenization scheme for robot actions, based on the discrete cosine transform.
Based on FAST, we release FAST+, a universal robot action tokenizer, trained on 1M real robot action trajectories.
arXiv Detail & Related papers (2025-01-16T18:57:04Z) - KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data [45.25288643161976]
We propose Keypoint Affordance Learning from Imagined Environments (KALIE) for robotic control in a scalable manner.
Instead of directly producing motor commands, KALIE controls the robot by predicting point-based affordance representations.
We demonstrate that KALIE can learn to robustly solve new manipulation tasks with unseen objects given only 50 example data points.
arXiv Detail & Related papers (2024-09-21T08:45:16Z) - LLaRA: Supercharging Robot Learning Data for Vision-Language Policy [56.505551117094534]
We introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations.
First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets.
We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control.
arXiv Detail & Related papers (2024-06-28T17:59:12Z) - Exploring Visual Pre-training for Robot Manipulation: Datasets, Models
and Methods [14.780597545674157]
We investigate the effects of visual pre-training strategies on robot manipulation tasks from three fundamental perspectives.
We propose a visual pre-training scheme for robot manipulation termed Vi-PRoM, which combines self-supervised learning and supervised learning.
arXiv Detail & Related papers (2023-08-07T14:24:52Z) - RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic
Control [140.48218261864153]
We study how vision-language models trained on Internet-scale data can be incorporated directly into end-to-end robotic control.
Our approach leads to performant robotic policies and enables RT-2 to obtain a range of emergent capabilities from Internet-scale training.
arXiv Detail & Related papers (2023-07-28T21:18:02Z) - Visual Affordance Prediction for Guiding Robot Exploration [56.17795036091848]
We develop an approach for learning visual affordances for guiding robot exploration.
We use a Transformer-based model to learn a conditional distribution in the latent embedding space of a VQ-VAE.
We show how the trained affordance model can be used for guiding exploration by acting as a goal-sampling distribution, during visual goal-conditioned policy learning in robotic manipulation.
arXiv Detail & Related papers (2023-05-28T17:53:09Z) - Learning Video-Conditioned Policies for Unseen Manipulation Tasks [83.2240629060453]
Video-conditioned Policy learning maps human demonstrations of previously unseen tasks to robot manipulation skills.
We learn our policy to generate appropriate actions given current scene observations and a video of the target task.
We validate our approach on a set of challenging multi-task robot manipulation environments and outperform state of the art.
arXiv Detail & Related papers (2023-05-10T16:25:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.