外观
论文arXiv 2610.1530517 天前
RM-WAM：用于长时程机器人操作的可靠记忆增强世界动作模型
原文链接：RM-WAM: Reliable Memory-Augmented World Action Models for Long-Horizon Robot Manipulation（arXiv 2610.15305 · 发布日期：2026-10-11）
RM-WAM: Reliable Memory-Augmented World Action Models for Long-Horizon Robot Manipulation
RM-WAM通过选择性利用短期视觉状态与潜在事件记忆，提升长时程机器人操作中的世界预测与动作决策，并在长时程任务实验中验证。
核心要点
- 现有WAM多依赖当前观测决策，长时程任务中相似视觉状态可能对应不同历史与阶段。
- 方法将记忆视为上下文相关的预测资源，结合短期视觉状态记忆与潜在事件记忆表示历史。
- 通过反事实记忆学习估计历史记忆效用，并用效用感知门控自适应注入世界动作骨干。
- 实验表明，在长时程任务中可靠且选择性地利用记忆具有重要作用。
验证范围与局限：验证范围为长时程任务实验，摘要未说明仿真或真机设置。
英文摘要 (Abstract)
World Action Models (WAMs) improve robotic manipulation by jointly predicting future visual states and actions, yet most existing methods make decisions primarily from the current observation. This limits their reliability in long-horizon tasks, where visually similar states may correspond to different interaction histories and task stages. Moreover, directly incorporating historical observations can introduce stale, stage-mismatched, or error-contaminated information, leading to inaccurate world prediction and accumulated closed-loop errors. We propose RM-WAM, a reliable memory-augmented World Action Model that treats memory as a context-dependent predictive resource rather than universally useful historical context. RM-WAM represents history using complementary short-term visual state memory and latent event memory, which respectively capture recent interaction dynamics and longer-term state transitions. A counterfactual memory learning scheme varies the accessible history while keeping the current inputs and prediction targets fixed, enabling the model to learn a context-dependent utility estimate for historical memory. Based on this estimate, a utility-aware gating mechanism adaptively controls memory injection into the world-action backbone. Experiments demonstrate that RM-WAM highlights the importance of reliable and selective memory utilization in long-horizon tasks.
作者：Miao Cui, Junhao Yu, Ping Liu, Ning Yang, Xuhua Chen, He Zheng, Xiaodong Wang, Tao Zhang
来源
本页事实对应的公开页面，以原文为准。