发表机构
Nanjing University of Aeronautics and Astronautics; Tsinghua University; Nanjing University（南京航空航天大学; 清华大学; 南京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究揭示世界模型控制器在异步执行下存在动作语义不匹配，提出两种轻量级接口分别修正TD-MPC2和DreamerV3的失败模式，实验验证了诊断与修正的有效性。
AI 中文摘要
世界模型控制器依赖动作条件动力学进行预测和规划，然而实际控制系统常因通信延迟、数据包丢失、乱序和执行器缓冲而异步执行命令。我们研究异步执行如何改变世界模型控制器中假设的动作语义，而非仅将其视为外部控制扰动。通过受控干预，我们识别出两种依赖架构的失败模式：基于规划的控制器（如TD-MPC2）在想象与执行的动作序列之间存在未来动作时间线不匹配，而循环世界模型（如DreamerV3）可能将观察到的转移归因于实际未应用的命令。我们的分析表明，TD-MPC2在潜在动力学展开时需要正确的未来动作序列，而DreamerV3需要及时将每个转移归因于生成它的动作。基于这些发现，我们引入了两种轻量级执行一致性接口——面向TD-MPC2的未来序列和面向DreamerV3的应用动作反馈——在不修改预训练世界模型的情况下纠正这些不匹配。在延迟、数据包丢失、乱序、多个控制域、测量网络轨迹以及进程分离的异步栈上的实验一致支持两种诊断及相应的架构特定修正。
英文摘要
World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the action semantics assumed within world-model controllers, rather than treating it only as an external control disturbance. Through controlled interventions, we identify two architecture-dependent failure modes: planning-based controllers such as TD-MPC2 suffer from a future-action timeline mismatch between imagined and executed action sequences, while recurrent world models such as DreamerV3 can attribute observed transitions to commands that were not actually applied. Our analysis shows that TD-MPC2 requires the correct future action sequence during latent dynamics rollout, whereas DreamerV3 requires timely attribution of each transition to the action that generated it. Based on these findings, we introduce two lightweight execution-consistent interfaces, Future-Sequence for TD-MPC2 and Applied-Action Feedback for DreamerV3, that correct these mismatches without modifying the pretrained world models. Experiments across delays, packet loss, reordering, multiple control domains, measured network traces, and a process-separated asynchronous stack consistently support both diagnoses and the corresponding architecture-specific corrections.
