Open Models Almanac
Methodsdata curationdata mixture & curriculum

specific method · filed under data curation

Cross-embodiment robot training

Combining data from different robot embodiments to train or transfer a shared model across robot types.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See data mixture & curriculum for the methods filed beside it.

Also called Cross-embodiment data transfer, cross-embodiment transfer, cross-embodiment training.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Physical Intelligence

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2

π0.5

Physical Intelligenceadopted2 sources

cross-embodiment transfer and diverse data co-training are critical for generalization across a range of tasks

useddata curationin π0.5
1 more from this model

we employ cross-embodiment training [10], where data from many robot types is combined into the same model.

usedunclearin π0Physical Intelligence
↑