RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Long, Zijun, Killick, George, McCreadie, Richard, Camarasa, Gerardo Aragon
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913240934514688
author Long, Zijun
Killick, George
McCreadie, Richard
Camarasa, Gerardo Aragon
author_facet Long, Zijun
Killick, George
McCreadie, Richard
Camarasa, Gerardo Aragon
contents Robotic vision applications often necessitate a wide range of visual perception tasks, such as object detection, segmentation, and identification. While there have been substantial advances in these individual tasks, integrating specialized models into a unified vision pipeline presents significant engineering challenges and costs. Recently, Multimodal Large Language Models (MLLMs) have emerged as novel backbones for various downstream tasks. We argue that leveraging the pre-training capabilities of MLLMs enables the creation of a simplified framework, thus mitigating the need for task-specific encoders. Specifically, the large-scale pretrained knowledge in MLLMs allows for easier fine-tuning to downstream robotic vision tasks and yields superior performance. We introduce the RoboLLM framework, equipped with a BEiT-3 backbone, to address all visual perception tasks in the ARMBench challenge-a large-scale robotic manipulation dataset about real-world warehouse scenarios. RoboLLM not only outperforms existing baselines but also substantially reduces the engineering burden associated with model selection and tuning. The source code is publicly available at https://github.com/longkukuhi/armbench.
format Preprint
id arxiv_https___arxiv_org_abs_2310_10221
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models
Long, Zijun
Killick, George
McCreadie, Richard
Camarasa, Gerardo Aragon
Robotics
Computer Vision and Pattern Recognition
Robotic vision applications often necessitate a wide range of visual perception tasks, such as object detection, segmentation, and identification. While there have been substantial advances in these individual tasks, integrating specialized models into a unified vision pipeline presents significant engineering challenges and costs. Recently, Multimodal Large Language Models (MLLMs) have emerged as novel backbones for various downstream tasks. We argue that leveraging the pre-training capabilities of MLLMs enables the creation of a simplified framework, thus mitigating the need for task-specific encoders. Specifically, the large-scale pretrained knowledge in MLLMs allows for easier fine-tuning to downstream robotic vision tasks and yields superior performance. We introduce the RoboLLM framework, equipped with a BEiT-3 backbone, to address all visual perception tasks in the ARMBench challenge-a large-scale robotic manipulation dataset about real-world warehouse scenarios. RoboLLM not only outperforms existing baselines but also substantially reduces the engineering burden associated with model selection and tuning. The source code is publicly available at https://github.com/longkukuhi/armbench.
title RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.10221