# ForeTac: A Predictive Contact Guidance Framework for Generative Robot Policies

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/grlbui84oop4tfu04gzh0micq
- Original: https://arxiv.org/abs/2610.18118

## Summary

ForeTac is a predictive contact guidance framework for contact-rich manipulation that uses a represent-predict-evaluate-guide loop: it encodes the current tactile state, predicts future tactile latent trajectories conditioned on candidate action sequences, and evaluates each trajectory with a contact-quality objective learned from successful and failed physical interactions. At inference, gradients of this objective are backpropagated through the tactile predictor to guide action generation before execution, while all model parameters remain frozen.