Machine Learning‐Enhanced Modular Ionic Skin for Broad‐Spectrum Multimodal Discriminability in Bidirectional Human–Robot Interaction (Adv. Mater. 42/2025)
Data-Driven Decoupled Multimodal Ionic Skin In their Research Article (DOI: 10.1002/adma.202508795), Geng Yang, Kaichen Xu, and co-workers report a machine learning-enhanced modular ionic skin capable of large-range multimodal decoupled sensing. Its outstanding performance is enabled by a synergistic sensor-algorithm optimization strategy, including hard-segment modulation of ionic gels and data-driven decoupling model. Functional validation via operator hand recognition and robotic sensing feedback underscore its potential for advanced human-robot interaction.
Authors
- Honghao Lyu (ORCID: https://orcid.org/0000-0001-8310-2990)
- Jiayan Li (ORCID: https://orcid.org/0000-0002-8521-2461)
- Kaichen Xu (ORCID: https://orcid.org/0000-0003-4957-3144)
- Mengke Wang
- Huayong Yang
- Gaoyang Pang (ORCID: https://orcid.org/0000-0002-0948-4641)
- Geng Yang (ORCID: https://orcid.org/0000-0002-8685-5426)
- Yuyao Lu (ORCID: https://orcid.org/0000-0001-9946-0469)
- Qianqian Yang (ORCID: https://orcid.org/0000-0002-0421-2954)
- Bizhi Li (ORCID: https://orcid.org/0000-0002-7774-5452)
Institutions
- The University of Sydney (AU)
- Zhejiang Lab (CN)
- Hangzhou Wanxiang Polytechnic (CN)
- Zhejiang University (CN)
Publication Details
- Journal
- Advanced Materials
- Published
- 2025-10-01
- DOI
- https://doi.org/10.1002/adma.70838
- Citations
- 5
- Primary Topic
- Advanced Sensor and Energy Harvesting Materials
- Type
- article
- Field-Weighted Citation Impact
- 3.37