Robotic Environmental State Recognition with Pre-Trained Vision-Language Models and Black-Box Optimization

TL;DR

This paper presents a unified approach for robotic environmental state recognition using pre-trained vision-language models and black-box optimization, enabling flexible and accurate recognition without training new neural networks.

Contribution

The study introduces a novel method combining vision-language models with black-box optimization for environmental recognition, eliminating the need for training separate models for each state.

Findings

Effective recognition of various environmental states without training new models.

Improved accuracy through text selection and weighting optimization.

Successful application on a mobile robot, Fetch.

Abstract

In order for robots to autonomously navigate and operate in diverse environments, it is essential for them to recognize the state of their environment. On the other hand, the environmental state recognition has traditionally involved distinct methods tailored to each state to be recognized. In this study, we perform a unified environmental state recognition for robots through the spoken language with pre-trained large-scale vision-language models. We apply Visual Question Answering and Image-to-Text Retrieval, which are tasks of Vision-Language Models. We show that with our method, it is possible to recognize not only whether a room door is open/closed, but also whether a transparent door is open/closed and whether water is running in a sink, without training neural networks or manual programming. In addition, the recognition accuracy can be improved by selecting appropriate texts from the set of prepared texts based on black-box optimization. For each state recognition, only the text set and its weighting need to be changed, eliminating the need to prepare multiple different models and programs, and facilitating the management of source code and computer resource. We experimentally demonstrate the effectiveness of our method and apply it to the recognition behavior on a mobile robot, Fetch.