通过漂移模型实现滚动预测控制
Receding-Horizon Control via Drifting Models
AI总结：
本文提出Drifting MPC框架，结合漂移生成模型与未知动态下的滚动规划，从离线轨迹数据中学习最优轨迹分布，提升轨迹生成效率和性能。
摘要：
我们研究了在系统动态未知且无法通过代理模型模拟轨迹的情况下轨迹优化问题。当有离线轨迹数据时，智能体可通过分布匹配直接学习轨迹生成器。然而，这种方法仅能恢复数据集中的行为分布，一般不产生最小化期望成本标准的模型。本文提出Drifting MPC，一种离线轨迹优化框架，结合漂移生成模型与未知动态下的滚动规划。Drifting MPC的目标是从离线轨迹数据中学习一个轨迹条件分布，该分布既受数据支持又偏向最优计划。我们证明，Drifting MPC学习的分布是唯一解，该解在最优性与接近离线先验之间进行权衡。实验表明，Drifting MPC能生成近最优轨迹，同时保持漂移模型的一步推理效率，并显著减少生成时间，相比基于扩散的基线方法。
英文摘要：
We study the problem of trajectory optimization in settings where the system dynamics are unknown and it is not possible to simulate trajectories through a surrogate model. When an offline dataset of trajectories is available, an agent could directly learn a trajectory generator by distribution matching. However, this approach only recovers the behavior distribution in the dataset, and does not in general produce a model that minimizes a desired cost criterion. In this work, we propose Drifting MPC, an offline trajectory optimization framework that combines drifting generative models with receding-horizon planning under unknown dynamics. The goal of Drifting MPC is to learn, from an offline dataset of trajectories, a conditional distribution over trajectories that is both supported by the data and biased toward optimal plans. We show that the resulting distribution learned by Drifting MPC is the unique solution of an objective that trades off optimality with closeness to the offline prior. Empirically, we show that Drifting MPC can generate near-optimal trajectories while retaining the one-step inference efficiency of drifting models and substantially reducing generation time relative to diffusion-based baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
