aiqbench analysis
This research introduces SLS^2, a framework that integrates robust model predictive control with conformal prediction to ensure safety in vision-based robotic systems using learned latent world models. By calibrating error bounds within the latent space, the method achieves probabilistic guarantees for physical execution while maintaining efficient gradient-based optimization. The work advances the intersection of machine learning and robotics by addressing critical reliability challenges inherent in deploying autonomous agents from raw pixels.
Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC
arXiv:2606.15594v1 Announce Type: cross Abstract: We present SLS^2, a framework for safe feedback motion planning from pixels using robust model predictive control (MPC) in learned latent world models. Our approach trains an action-conditioned joint-embedding world model with compact Markovian latent states, enabling efficient gradient-based trajectory optimization through learned latent dynamics. To enforce safety for the true system despite imperfect latent predictions, we inform a GPU-accelerated system level synthesis (SLS) robust MPC scheme with conformal prediction to obtain calibrated latent error bounds and robust latent-space constraint sets. We further learn and conformalize a latent constraint checker, allowing the SLS planner to impose probabilistic safety constraints during closed-loop execution. We evaluate our method on vision-based control tasks, where it improves both goal-reaching performance and safety over latent world-model and safe-planning baselines.
Abstract:We present SLS^2, a framework for safe feedback motion planning from pixels using robust model predictive control (MPC) in learned latent world models. Our approach trains an action-conditioned joint-embedding world model with compact Markovian latent states, enabling efficient gradient-based trajectory optimization through learned latent dynamics. To enforce safety for the true system despite imperfect latent predictions, we inform a GPU-accelerated system level synthesis (SLS) robust MPC scheme with conformal prediction to obtain calibrated latent error bounds and robust latent-space constraint sets. We further learn and conformalize a latent constraint checker, allowing the SLS planner to impose probabilistic safety constraints during closed-loop execution. We evaluate our method on vision-based control tasks, where it improves both goal-reaching performance and safety over latent world-model and safe-planning baselines.
Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Systems and Control (eess.SY)
arXiv:2606.15594 [cs.RO]
(or arXiv:2606.15594v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.15594 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 157 words
Related coverage
[AINews] High Taste Testers Ep. 1
Latent Space · Oct 17, 2026
[AINews] Claude Fable/Mythos 5.1: new SOTA model, 75% cache price cut but 70% more output tokens
Latent Space · Sep 2, 2026
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
News
Quantum Computing Report · Jul 25, 2026