Hybrid EEG–EMG intention decoding for real-time triggering of a lower-limb exoskeleton
Ke Wang, Wenshan Li, Danyang Ding, Lei Wang, Yue Sun, Hongbo Zhao, Weijun Gong · 2026
Read Hybrid EEG–EMG intention decoding for real-time triggering of a lower-limb exoskeleton by Ke Wang, Wenshan Li, Danyang Ding, Lei Wang, Yue Sun, Hongbo Zhao, Weijun Gong (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/pmc-13581620.txt.
Description
Wang and co-authors test a control method for a wearable leg exoskeleton that reads user intent from brain and muscle signals. Most current systems use mechanical or manual triggers, which can miss what the user means to do. The team trained a BiLSTM model on data from 50 healthy volunteers. The data paired 16-channel EEG and surface EMG from six leg muscles with hip and knee motion.
Seven new users then walked repeated 20-meter trials under EMG-only, EEG-only, and combined control. The combined mode sorted steps more accurately, reaching 91.3% on the left side. It also fired help faster, at about 0.29 seconds per step. Users rated ease of use with the QUEST 2.0 scale.
Catalog record
| CREATOR | Ke Wang, Wenshan Li, Danyang Ding, Lei Wang, Yue Sun, Hongbo Zhao, Weijun Gong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |