The authors generated a dataset of stable whole-body grasps, categorized by contact mode: left arm, both arms or right arm.
Humanoid repositions bulky objects using its arms and torso
A learned controller transferred from simulation to a Unitree G1, enabling contact-rich object handoffs, carrying and placement.
Big Tech
Conor Mc Gartoll · An Dang · Pranay Thangeda · Arjun Gupta · Carolina Higuera · Nima Fazeli · +2 more
Amazon · University of California, San Diego · University of Michigan
Research Digest··3 min read
Thread:Robot Manipulation Policies
Mc Gartoll and colleagues introduce Whole-Body Dexterity, a framework that treats a humanoid’s arms and torso as coordinated contact surfaces rather than relying only on its hands.
Why this paper
From Amazon and 2 others · Part of Robot Manipulation Policies, now 25 papers
In one line
A humanoid robot can reposition objects using its entire body, not just hands, after training in simulation.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§