Shanghai researchers record 100 hours with a wearable rig to train robots
A team from Shanghai AI Laboratory and two universities built a wearable rig that captures body motion, hands and touch for robots to learn from.
Researchers had a person wear a camera, sensors and gloves while working. They want robots to learn from those moves. So far it works only inside a computer.
Hype check
The noise matches the real change.
Our editorial opinion, based on the sources below. How we score
Your call: hype or real?
Real = it will matter in daily use. Hype = louder than it is. One vote, and it can’t be changed.
Our view and readers’ views are opinions, not statements of fact about a product.
Why it matters
Robots need lots of data on how people move. This rig gathers it from the wearer's own point of view.
Watch: this is how robots may one day learn our work.
The details
- The team is from Shanghai AI Laboratory, Zhejiang University and Shanghai Jiao Tong University; the dataset is called EgoExplorer.
- The rig has a head-mounted GoPro HERO13, five VIVE trackers and gloves for finger motion and touch.
- The researchers recorded 100 hours, mostly professional tasks, with video, body motion and touch.
- Body-point error fell 71.9% against the strongest baseline.
- Training ran only in simulation on a Unitree G1; this is an early preprint, not yet peer-reviewed.
Receipts
One trusted outlet reports it. Not confirmed yet. Open the sources and check us.
Written with the help of AI tools and checked against the sources above. How we work
See a mistake? Tell us and we’ll fix it.
