FoAR uses a future-contact predictor to gate force/torque features into a vision-based imitation policy and adds a reactive nudge, beating vision-only and naive fusion baselines on three real contact-rich tasks.
RT-1: Robotics Transformer for Real-World Control at Scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulation
FoAR uses a future-contact predictor to gate force/torque features into a vision-based imitation policy and adds a reactive nudge, beating vision-only and naive fusion baselines on three real contact-rich tasks.