A Hybrid Inverse Kinematics Framework for Biomimetic Redundancy Resolution in 7-DoF Humanoid Arms
Yapeng Shi, Zhen Chen, Ivan Mokiets, Songhao Piao, Teng Zhang, Lianzhao Zhang · 2026
Read A Hybrid Inverse Kinematics Framework for Biomimetic Redundancy Resolution in 7-DoF Humanoid Arms by Yapeng Shi, Zhen Chen, Ivan Mokiets, Songhao Piao, Teng Zhang, Lianzhao Zhang (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-13296688.txt.
Description
Yapeng Shi and colleagues teach a seven-jointed humanoid arm to choose natural postures while it moves, in a 2026 robotics paper. Extra joints give the arm many ways to reach the same hand position, and most look robotic rather than human. Operators first guided the arm through a wearable exoskeleton, recording the postures people actually prefer.
A small neural network learned to predict a key elbow-angle measure from each target hand pose. That prediction steers the solver toward human-like configurations without losing tracking accuracy. Tests in simulation and on a real robot showed better posture quality and lower energy use than fixed strategies. Prediction was fast enough for real-time control loops.
Catalog record
| CREATOR | Yapeng Shi, Zhen Chen, Ivan Mokiets, Songhao Piao, Teng Zhang, Lianzhao Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 72 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |