ピクセルから証明へ：並列コンフォーマルロバストMPCによる確率的に安全な潜在世界モデル制御
Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC
学習した潜在世界モデル上でロバストMPCを行い、コンフォーマル予測で誤差を校正して安全制約を課す、ピクセル入力の安全な運動計画フレームワークを提案した。
著者: Devesh Nath, Anutam Srinivasan, Haoran Yin, Ruitong Jiang, Jeffrey Fang, Glen Chou
分類: cs.RO, cs.AI, cs.CV, cs.LG, eess.SY
原文アブストラクト
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.