AI 中文总结
DRAM是一种即插即用的固定大小记忆模块，利用门控Delta规则线性注意力为预训练机器人策略提供长时程记忆，无需修改架构或重训骨干，实验证明其优于短上下文基线和替代记忆设计。
AI 中文摘要
机器人操作本质上依赖于历史状态，然而大多数预训练机器人策略仅基于当前观测或短时间窗口进行条件化。为这类策略配备长期记忆仍然具有挑战性：现有方法要么向骨干网络输入多帧观测窗口，这大幅增加了推理成本；要么依赖预定义的语义特征，这限制了任务通用性，并且可能需要重新训练骨干网络以适应记忆。我们提出了DRAM（Delta规则递归联想记忆），一种即插即用的记忆模块，可附加到广泛的预训练机器人策略上，赋予其长时程记忆能力，无需修改架构或重新训练骨干网络，仅需对记忆模块和动作专家进行任务特定的后训练。DRAM使用门控Delta规则线性注意力维护一个固定大小的联想记忆，其更新规则经过修改，可并行整合每帧内的所有令牌。一种与架构无关的读出机制将历史上下文整合到不同策略架构的动作预测中。实验表明，DRAM在冻结的预训练策略上持续优于短上下文基线和替代的紧凑记忆设计，验证了其作为在骨干网络冻结情况下训练的固定大小、事后记忆模块的有效性。
英文摘要
Robotic manipulation is inherently history-dependent, yet most pretrained robotic policies condition on only the current observation or a short temporal window. Equipping such policies with long-term memory remains challenging: existing approaches either feed the backbone multi-frame observation windows, which substantially increase inference cost, or rely on pre-defined semantic features, which limit task generality and may also require the retraining of the backbone to adapt to the memory. We introduce DRAM (Delta-rule Recurrent Associative Memory), a plug-and-play memory module that can be attached to a wide range of pretrained robotic policies, endowing them with long-horizon memory without architectural modification or backbone retraining, requiring only task-specific post-training of the memory module and action expert. DRAM maintains a fixed-size associative memory using gated delta-rule linear attention, with a modified update that incorporates all tokens within each frame in parallel. An architecture-agnostic readout integrates historical context into action prediction across different policy architectures. Experiments show that DRAM consistently improves frozen pretrained policies over short-context baselines and alternative compact memory designs, validating its effectiveness as a fixed-size, post-hoc memory module trained with the backbone frozen.
