Robotic Applications of Pre-Trained Vision-Language Models to Various Recognition Behaviors

TL;DR

This paper reviews methods for applying pre-trained vision-language models to robotic recognition tasks, emphasizing flexible, non-retraining approaches to enhance robot understanding and broaden application scope.

Contribution

It categorizes and summarizes five methods to utilize vision-language models in robotics without retraining, enabling diverse recognition behaviors.

Findings

Effective methods for state recognition, object recognition, and more.

Enhanced flexibility and applicability of vision-language models in robotics.

Potential for new robotic applications using these methods.

Abstract

In recent years, a number of models that learn the relations between vision and language from large datasets have been released. These models perform a variety of tasks, such as answering questions about images, retrieving sentences that best correspond to images, and finding regions in images that correspond to phrases. Although there are some examples, the connection between these pre-trained vision-language models and robotics is still weak. If they are directly connected to robot motions, they lose their versatility due to the embodiment of the robot and the difficulty of data collection, and become inapplicable to a wide range of bodies and situations. Therefore, in this study, we categorize and summarize the methods to utilize the pre-trained vision-language models flexibly and easily in a way that the robot can understand, without directly connecting them to robot motions. We discuss how to use these models for robot motion selection and motion planning without re-training the models. We consider five types of methods to extract information understandable for robots, and show the results of state recognition, object recognition, affordance recognition, relation recognition, and anomaly detection based on the combination of these five methods. We expect that this study will add flexibility and ease-of-use, as well as new applications, to the recognition behavior of existing robots.