记住你做了什么？：学习部分可观察物体操作的行为记忆
Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation
AI总结：
针对长时域、接触式操作中的部分可观测问题，提出压缩动作记忆策略（CAMP），通过自监督学习动作历史压缩表示，隐式追踪任务进度并从失败中学习，在多个真实和仿真任务上超越现有方法。
摘要：
长时域、接触式操作本质上是部分可观测的。这是因为单一的视觉观测很少能捕捉到机器人的完整动作上下文，包括先前的尝试、交互或进度。因此，标准的视觉运动策略或视觉-语言-动作模型由于缺乏记忆，在此类任务中容易遇到困难。为了解决这个问题，我们基于机器人自身的动作历史是一个高度信息丰富、自监督信号的洞察，提出了压缩动作记忆策略（CAMP），使策略能够学习鲁棒、紧凑的历史表示。在我们的方法中，我们训练一个记忆模块来维护过去动作的压缩表示，迫使其编码机器人所有过去交互的潜在行为记忆，然后用于更好地为未来动作提供上下文。这使得我们的方法能够隐式地追踪广义任务进度，并从失败的尝试中学习，无需任何额外的监督或外部监督。我们在四个真实机器人平台和两个新的仿真基准测试（Memory-T-Bench和Memory-Manip-Bench）上评估了CAMP。通过展示相对于最先进基线的显著提升，据我们所知，CAMP是第一个仅通过学习记忆就在接触式部分可观测操作任务上取得显著成功的策略。
英文摘要：
Long horizon, contact-rich manipulation is inherently partially observable. This is as a single visual observation rarely captures a robot's full action context, including prior attempts, interactions, or progress. Consequently, standard visuomotor policies or vision-language-action models are prone to struggle in such tasks due to a lack of memory. To address this, we introduce Compressed Action Memory Policy (CAMP) based on the insight that a robot's own action history serves as a highly informative, self-supervised signal, enabling the policy to learn a robust, compact history representation. In our approach, we train a memory module to maintain a compressed representation of past actions, forcing it to encode a latent behavioral memory of all the robot's past interactions that can then be used to better contextualize future actions. This allows our approach to implicitly track generalized task progress and learn from failed attempts without any additional supervision, or external oversight. We evaluate CAMP across four real-robot setups and two novel simulation benchmarks: Memory-T-Bench and Memory-Manip-Bench. By demonstrating substantial gains over state-of-the-art baselines, CAMP is, to our knowledge, the first policy to demonstrate substantial success on contact-rich partially observable manipulation tasks purely through learned memory.
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。
