LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

• URL: http://arxiv.org/abs/2406.20095v3
• Date: Thu, 30 Jan 2025 17:34:37 GMT
• Title: LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
• Authors: Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo,
• Abstract summary: 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.
• Score: 56.505551117094534
• License:
• Abstract: Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when constrained by a limited number of robot demonstrations. In this work, we introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations and enables an efficient transfer of a pretrained VLM into a powerful VLA, motivated by the success of visual instruction tuning in Computer Vision. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets, aligning robotic actions with image pixel coordinates. Further, we enhance this dataset in a self-supervised manner by defining six auxiliary tasks, without requiring any additional action annotations. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control. Through experiments across multiple simulated and real-world tasks, we demonstrate that LLaRA achieves state-of-the-art performance while preserving the generalization capabilities of large language models. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.

Related papers

• Latent Action Pretraining from Videos [156.88613023078778]
  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.
  arXiv  Detail & Related papers  (2024-10-15T16:28:09Z)
• VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model [4.557035895252272]
  Vision Language Models (VLMs) have been adopted in robotics for their capability in common sense reasoning and generalizability. In this work, we explore using VLM to interpret human demonstration videos and generate robot task planning. We named it SeeDo because it enables the VLM to ''see'' human demonstrations and explain the corresponding plans to the robot for it to ''do''
  arXiv  Detail & Related papers  (2024-10-11T13:17:52Z)
• 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)
• LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning [50.99807031490589]
  We introduce LLARVA, a model trained with a novel instruction tuning method to unify a range of robotic learning tasks, scenarios, and environments. We generate 8.5M image-visual trace pairs from the Open X-Embodiment dataset in order to pre-train our model. Experiments yield strong performance, demonstrating that LLARVA performs well compared to several contemporary baselines.
  arXiv  Detail & Related papers  (2024-06-17T17:55:29Z)
• Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks [54.60571399091711]
  Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary tasks. We present an interactive planning technique for partially observable tasks using LLMs.
  arXiv  Detail & Related papers  (2023-12-11T22:54:44Z)
• Vision-Language Foundation Models as Effective Robot Imitators [48.73027330407576]
  We derive a vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control.
  arXiv  Detail & Related papers  (2023-11-02T16:34:33Z)
• 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)

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.