English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This study presents a control framework leveraging vision language models(VLMs) for multiple tasks and robots. Notably, existing control methods usingVLMs have achieved high performance in various tasks and robots in the trainingenvironment. However, these methods incur high costs for learning controlpolicies for tasks and robots other than those in the training environment.Considering the application of industrial and household robots, learning innovel environments where robots are introduced is challenging. To address thisissue, we propose a control framework that does not require learning controlpolicies. Our framework combines the vision-language CLIP model with arandomized control. CLIP computes the similarity between images and texts byembedding them in the feature space. This study employs CLIP to compute thesimilarity between camera images and text representing the target state. In ourmethod, the robot is controlled by a randomized controller that simultaneouslyexplores and increases the similarity gradients. Moreover, we fine-tune theCLIP to improve the performance of the proposed method. Consequently, weconfirm the effectiveness of our approach through a multitask simulation and areal robot experiment using a two-wheeled robot and robot arm.

CLIP feature-based randomized control using images and text for multiple tasks and robots