从像素出发的可控运动规划，让机器人更安全地完成任务
Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC
- 用学习的隐空间模型和鲁棒预测控制实现像素级运动规划
- 在真实系统中实现95%以上安全率，比基线提升18%以上
- 适合需要高安全性的视觉控制场景，如自动驾驶、工业机器人
我们提出SLS^2框架，基于学习的隐空间世界模型，实现从像素出发的鲁棒反馈运动规划。通过训练条件动作的联合嵌入世界模型，采用紧凑马尔可夫隐状态，支持高效梯度优化轨迹。为确保真实系统下的安全性，结合共形预测校准隐空间误差边界，并构建鲁棒隐空间约束集，同时学习并共形化隐空间约束检查器，使SLS规划器在闭环执行中施加概率性安全约束。我们在视觉控制任务上评估该方法，结果表明其在目标达成率与安全性方面均优于基线的隐空间模型与安全规划方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。