SOURCE-LINKED INTELLIGENCE

Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Accurate tactile forecasts need not improve force-constrained control. We study a 652,157-parameter action-conditioned visuotactile world model with matched behavior cloning, policy learning in imagination, independent reactive implicit Q-learning, and model-assisted force feedback. A fixed protocol executes 34 policies on 120 fresh MuJoCo environments spanning geometry and physical-parameter shifts, plus 324 independently replayed action branches on 12 additional ID environments. Visuotactile dynamics reduce force action-effect MAE from 0.413 N for persistence to 0.338 N. Model-assisted feedb

Read original source ↗ Open in workspace

recordType

paper

region

Global