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.

翻译：我们提出SLS^2框架，一种通过鲁棒模型预测控制（MPC）在学习的潜世界模型中实现基于像素的安全反馈运动规划方法。该方法训练一个具有紧凑马尔可夫潜状态的动作条件联合嵌入世界模型，通过学习的潜动力学实现高效基于梯度的轨迹优化。针对潜状态预测不完美时真实系统的安全保障问题，我们采用共形预测为GPU加速的系统级综合（SLS）鲁棒MPC方案提供校准的潜误差边界和鲁棒潜空间约束集。进一步地，我们学习并共形化一个潜约束检查器，使SLS规划器能在闭环执行期间施加概率安全约束。在基于视觉的控制任务上，该方法在目标到达性能和安全性方面均优于基线方法——包括潜世界模型和安全规划基线。