Exploiting upper-limb functional principal components for human-like motion generation of anthropomorphic robots.
Giuseppe Averta, Cosimo Della Santina, Gaetano Valenza and 2 others
PMID 32404174WHAT IT FOUND
A new robot control method uses human movement data to generate smooth, human-like arm motions.
Simulations show it can avoid obstacles using just one to three motion components, but it has not been tested on patients or in clinical rehabilitation settings.
Key findings
01The method generates human-like trajectories by combining a small number of functional components extracted from human movement data.
02In simulations, the algorithm successfully generated smooth trajectories that avoided obstacles without colliding with them.
03The generated movements exhibited human-like characteristics, such as bell-shaped velocity profiles and low jerk values.
STILL TO COME
How it was doneWhat they found
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
This is a simulation study; the method has not been tested on real physical robots. No patients were included; the movement data came from 33 healthy subjects. The study did not test the method in a clinical rehabilitation context or with assistive devices. The optimization method is local and may not always find the globally best solution, though this was not the primary focus.
Declared interests
The authors declare no competing interests. The work was supported by non-U.S. government funding.
The easy way to misread this
Do not interpret this as evidence that this technology is ready for clinical use. The results are from computer simulations using healthy movement data, not from trials with patients or physical rehabilitation devices.