让机器人通过回顾历史互动，智能选择最优操作方案。
Learn from What We HAVE: History-Aware VErifier that Reasons about Past Interactions Online
- 用无条件扩散模型生成多个动作候选，再由历史感知验证器筛选最佳动作。
- 在模拟与真实环境中，对可动部件、多模式门等复杂场景提升操作成功率。
- 适合需要安全决策的机器人交互任务，尤其在视觉模糊时表现更优。
我们提出一种新型历史感知验证器（HAVE），通过利用过往交互信息来消解在线环境中的不确定性。机器人常遇视觉模糊物体，其操作结果在物理交互前难以确定。尽管生成模型理论上可适应此类模糊性，但实际中即使结合动作历史仍表现不佳。为此，我们显式分离动作生成与验证：使用无条件扩散模型生成多个候选动作，再由历史感知验证器基于过往交互推理选择最有望成功的动作。理论分析表明，引入验证器能显著提升期望动作质量。在包含可动部件、多模态门和不规则抓取等复杂场景的多组模拟与真实世界实验中，本方法均优于基线，验证了其有效性。
原文摘要 · Abstract (English)
We introduce a novel History-Aware VErifier (HAVE) to disambiguate uncertain scenarios online by leveraging past interactions. Robots frequently encounter visually ambiguous objects whose manipulation outcomes remain uncertain until physically interacted with. While generative models alone could theoretically adapt to such ambiguity, in practice they obtain suboptimal performance in ambiguous cases, even when conditioned on action history. To address this, we propose explicitly decoupling action generation from verification: we use an unconditional diffusion-based generator to propose multiple candidate actions and employ our history-aware verifier to select the most promising action by reasoning about past interactions. Through theoretical analysis, we demonstrate that employing a verifier significantly improves expected action quality. Empirical evaluations and analysis across multiple simulated and real-world environments including articulated objects, multi-modal doors, and uneven object pick-up confirm the effectiveness of our method and improvements over baselines. Our project website is available at: https://liy1shu.github.io/HAVE_CoRL25/
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。