Event
HKU trains dual-arm robot using 538.9 hours of human data
1 reports · 1 sources
The MMLab team at the University of Hong Kong proposes EgoWild2Dex, which uses 538.9 hours of unscripted human first-person manipulation data to train a dual-arm dexterous robot, requiring less than 1 hour of real-robot data per downstream task. The team reports an average success rate of 96.7% on three long-horizon tasks: unpacking a parcel, securing ornaments with a hot-melt glue gun, and making cold drinks.
Report timeline
- HKU's EgoWild2Dex trains dual-arm robot on 538.9 hours of "extremely dirty" human data, with under 1 hour of real-robot data
The University of Hong Kong's MMLab team proposes EgoWild2Dex, which directly trains a dual-arm dexterous robot on 538.9 hours of unscripted human first-person manipulation data, using under 1 hour of real-robot data per downstream task; across three long-horizon tasks—unpacking a parcel, fixing ornaments with a hot glue gun, and making a cold drink—the average success rate is 96.7%.
机器之心 · 微信公众号 ·