发表机构
POSTECH; KAIST（POSTECH; 韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ACID框架，通过逆动力学模型引入循环行动一致性约束，改进基于世界模型的决策时规划，在多种任务中提升规划效果并降低计算成本。
AI 中文摘要
基于行动条件世界模型的决策时规划已成为具身控制的一种流行范式。然而，标准规划成本仅根据预测的终端状态与目标的接近程度来评判候选行动，而未检查中间过渡的可实现性——预测轨迹可能看起来令人信服，而环境实际 rollout 却偏离该轨迹。在本文中，我们提出 ACID，一种决策时规划框架，引入了循环行动一致性：由逆动力学模型从预测过渡中反向推断出的行动应恢复被条件化的行动。我们通过一个尺度不变的自适应权重将此逐步骤残差纳入规划成本。在四个行动条件世界模型和六个任务（涵盖刚体和可变形操作、关节控制以及视觉导航）上，ACID 一致地改进了规划，并以显著更少的规划计算量达到了基线的准确性。
英文摘要
Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close its predicted terminal state lies to the goal, leaving the realizability of the intermediate transitions unchecked--a predicted trajectory can look convincing while the environment rollout drifts away from it. In this paper, we propose ACID, a decision-time planning framework that introduces cycle action consistency: the action inferred backward from a predicted transition by an inverse dynamics model should recover the one that was conditioned on. We fold this per-step residual into the planning cost via a scale-invariant adaptive weight. Across four action-conditioned world models and eight tasks encompassing object manipulation and articulated control in simulation, visual navigation, and real-robot manipulation, ACID consistently improves planning and matches the baseline's accuracy with substantially less planning compute.
CommentsProject page: https://gawon1224.github.io/ACID/
