让机器人通过在线尝试自动优化记忆，避免重复做已完任务。
OnEvoMemory: Evolving Memory through Online Robot Rollouts for Pretrained Robot Policies
- 用成功/失败的在线试错动态调整记忆内容
- 在长任务中使基线策略成功率提升显著
- 适合需要持续记忆的复杂机器人操作场景
长时序机器人操作需要策略跟踪已完成的子任务和关键交互事件。但现有记忆机制严重依赖外部模型或预设更新规则。为此，我们提出OnEvoMemory，一种基于价值引导的记忆模块，用于预训练机器人策略。它维护近期上下文、高价值经验及显著状态转移，并学习从轨迹结果中判断哪些经验应保留。离线演示初始化记忆先验，而成功与失败的在线回放则进一步优化记忆选择，帮助策略识别任务阶段切换并避免重复执行已完成子任务。在多个长时序操作基准测试中，OnEvoMemory通过离线初始化与在线记忆演化双重方式，显著提升了基础VLA策略的性能。
原文摘要 · Abstract (English)
Long-horizon robot manipulation requires policies to track completed subtasks and critical interaction events. However, existing memory mechanisms heavily rely on external models or predefined update rules. To address this, we propose OnEvoMemory, a value-guided memory module for pretrained robot policies. It maintains recent context, high-value experiences, and salient transitions, while learning which experiences should be retained from trajectory outcomes. Offline demonstrations initialize the memory prior, whereas successful and unsuccessful online rollouts refine memory selection, helping the policy recognize task-stage transitions and avoid repeating completed subtasks. Experiments on long-horizon manipulation benchmarks show that OnEvoMemory improves the performance of the base VLA policy through both offline initialization and online memory evolution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。