FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation
About
Force signals provide critical interaction cues for contact-rich robotic manipulation. However, existing methods mostly use force as an additional observation modality, without fully exploiting its role in modeling future interaction dynamics or guiding execution-time feedback correction. In this paper, we propose FAWAM, a force-aware world action model that incorporates force information at three levels: perception, prediction, and closed-loop execution. FAWAM first encodes historical 6-axis force/torque signals to modulate action generation, then jointly predicts future actions and end-effector wrenches to explicitly model contact evolution. It further introduces a residual correction module that uses the predicted wrench trajectory as an execution-time reference to refine actions online based on real-time force feedback. Real-world experiments across multiple contact-rich tasks show that FAWAM improves the average success rate by 36.25% over vision-only baselines and 21.25% over existing force-aware baselines, demonstrating the effectiveness of our force-aware framework for robust contact-rich manipulation.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Cucumber Peeling | Real-world visuo-tactile dataset | Success Rate19 | 10 | |
| Aggregate Robotic Manipulation | Real-world | Average Success Rate85 | 6 | |
| Erase Board | Real-world | Success Rate75 | 6 | |
| Pivot Box | Real-world | Success Rate17 | 6 | |
| Wipe Vase | Real-world | Success Rate85 | 6 |