arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.00436cs.ROcs.CV
收藏

基于多层对齐表示的开放词汇操作任务成功预测

Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations

Keio University(庆应义塾大学)

Miyu Goko, Motonari Kambara, Daichi Saito, Seitaro Otsuki, Komei Sugiura

AI总结:

本文提出Contrastive λ-Repformer,通过融合局部图像、自然语言对齐及语言结构化特征构建多层对齐表示,在RT-1和真实机器人数据上实现开放词汇操作任务成功预测,准确率比代表性MLLM模型提升8.66个百分点。

摘要:

在本研究中,我们考虑基于操作前后的指令语句和第一人称图像,预测机械臂开放词汇操作任务成功的问题。包括多模态大语言模型(MLLMs)在内的传统方法,往往无法恰当理解物体的详细特征和/或物体位置的细微变化。我们提出Contrastive λ-Repformer,通过将图像与指令语句对齐来预测桌面操作任务的成功。我们的方法将以下三类关键特征整合到一个多层对齐表示中:保留局部图像信息的特征;与自然语言对齐的特征;以及通过自然语言结构化的特征。这使得模型能够通过观察两幅图像之间表示的差异来关注重要变化。我们在基于大规模标准数据集RT-1数据集以及物理机器人平台的数据集上评估了Contrastive λ-Repformer。结果表明,我们的方法优于包括MLLMs在内的现有方法。与代表性的基于MLLM的模型相比,我们最佳模型的准确率提高了8.66个百分点。

英文摘要:

In this study, we consider the problem of predicting task success for open-vocabulary manipulation by a manipulator, based on instruction sentences and egocentric images before and after manipulation. Conventional approaches, including multimodal large language models (MLLMs), often fail to appropriately understand detailed characteristics of objects and/or subtle changes in the position of objects. We propose Contrastive $λ$-Repformer, which predicts task success for table-top manipulation tasks by aligning images with instruction sentences. Our method integrates the following three key types of features into a multi-level aligned representation: features that preserve local image information; features aligned with natural language; and features structured through natural language. This allows the model to focus on important changes by looking at the differences in the representation between two images. We evaluate Contrastive $λ$-Repformer on a dataset based on a large-scale standard dataset, the RT-1 dataset, and on a physical robot platform. The results show that our approach outperformed existing approaches including MLLMs. Our best model achieved an improvement of 8.66 points in accuracy compared to the representative MLLM-based model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑