Fine-tuned multimodal large language model for autonomous state cognition system of shape-recognition 6-bar tensegrity integrated with flexible sensors

Zebing Mao, Jianhui Wang, Jianhua Zhang, Junji Ohgi, Yanqiu Zheng, Yanhong Peng, Luyang Zhao, Qi Su, Weidi Huang, Bing Xu · 2026

Read Fine-tuned multimodal large language model for autonomous state cognition system of shape-recognition 6-bar tensegrity integrated with flexible sensors by Zebing Mao, Jianhui Wang, Jianhua Zhang, Junji Ohgi, Yanqiu Zheng, Yanhong Peng, Luyang Zhao, Qi Su, Weidi Huang, Bing Xu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13253877.txt.

Description

Zebing Mao and a large team build a self-aware tensegrity robot in a 2026 study. Tensegrity structures mix stiff bars with stretchy cables, making light, strong frames suited to rough places. Their six-bar version carries 24 flexible sensors and a fine-tuned large language model, a type of AI trained on text and images.

The system can rebuild its own shape from its sensing tendons, with no outside sensors. It sends data to an iPhone for wireless checks and uses the AI model for fault finding and plain-language answers. The authors see promise for exploration tasks where human help is far away.

Catalog record

CREATORZebing Mao, Jianhui Wang, Jianhua Zhang, Junji Ohgi, Yanqiu Zheng, Yanhong Peng, Luyang Zhao, Qi Su, Weidi Huang, Bing Xu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE44861
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13253877

Browse the full library · About the Tower of Babel