BAT-WAM: Bridging Action and Touch in World-Action Models for Dexterous Hands
BAT-WAM: Bridging Action and Touch in World-Action Models for Dexterous Hands
This research presents BAT-WAM, a framework designed to bridge visual, joint-state, and tactile representations for world action models (WAMs) aimed at enhancing dexterous manipulation.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
valuation protocol, BAT-WAM reduces the root mean squared error (RMSE) of tactile reconstruction by 34.73% under fully masked conditions and 38.84% under partially masked conditions, relative to an image-conditioned HandTouch checkpoint. For future tactile prediction conditioned on target-time RGB and historical actions, it reduces mean RMSE by 85.56% relative to OpenWAM with HandTouch. Real-robot experiments further
Open source S4
show that BAT-WAM consistently outperforms related WAM baselines in dexterous manipulation. Generalization experiments on unseen objects and scenes also demonstrate substantial improvements over baseline models. These findings support joint modeling of visual context, hand state, and touch as a representation approach for multimodal WAMs.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org