[3O1-OS-16b] OS-16

[3O1-OS-16b-02] Task Success Prediction on Large-Scale Object Manipulation Datasets Based on Multimodal LLMs and Vision-Language Foundation Models

〇Daichi Saito¹, Motonari Kambara¹, Katsuyuki Kuyo¹, Komei Sugiura¹ (1. Keio University)

Keywords:Manipulator, Object Manipulation, Vision-and-Language, Multimodal LLM, Success Prediction

For enhancing model performance in object manipulation tasks, high-performance prediction mechanisms for task success are crucial. However, existing methods are still insufficient in performance. Moreover, existing prediction mechanisms are designed to address only specific tasks, making it challenging to accommodate a diverse range of tasks. Therefore, our study aims to develop a task success prediction mechanism that can handle multiple object manipulation tasks. A key novelty of the proposed method is the introduction of the λ-Representation, which preserves all types of visual features: visual charactaristics such as colors and shapes; features aligned with natural language; features structured through natural language. For the experiments, we newly built datasets for task success prediction in object manipulation tasks based on the RT-1 dataset and VLMbench. The results show that the proposed method outperforms all baseline methods in accuracy.