CHORD: Contact-Guided Dexterous Manipulation
NVIDIA Isaac's CHORD teaches robots dexterous, two-handed manipulation by learning from human demonstrations.
Start Your Physical AI Journey with Us
A curated selection of research shaping physical AI
NVIDIA Isaac's CHORD teaches robots dexterous, two-handed manipulation by learning from human demonstrations.
UC Berkeley, NVIDIA, and Stanford give robots a sense of touch, boosting success on delicate two-handed manipulation tasks.
USC’s DUET teaches a Dexmate Vega and a second robot to collaborate by watching pairs of humans work together.
Dexmate and Carnegie Mellon turn one demonstration into a full training dataset, teaching robots to recover from mistakes.
Amazon FAR fine-tunes behavior cloning with lightweight off-policy RL on Dexmate's Vega for real-world dexterous manipulation.