HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 6 天前AI 评分31
HIDE 基准与 SEEK 框架：部分可观测机器人操作中的技能级记忆评测与增强
AI 导读
研究者提出 HIDE 基准，用 15 项任务评测部分可观测条件下的机器人操作记忆，涵盖重复计数、历史状态回忆与执行进度跟踪，并设置随机初始配置和需依赖先前事件才能正确决策的决策点。同时提出 SEEK 框架，组合三种互补记忆机制保留历史证据并跟踪执行状态。评测显示现有策略在 HIDE 上存在明显不足，记忆增强在仿真与真实实验中均提升任务成功率，三种机制组合取得最高平均成功率。
正文
Abstract:Recent advances in robot learning have enabled manipulation policies to perform increasingly diverse tasks and generalize across environments. However, reliable execution often depends on hidden task states that cannot be determined from current observations alone, making interaction history essential. We introduce $HIDE$, a benchmark for evaluating manipulation memory under partial observability. HIDE comprises 15 tasks covering repetition counting, historical-state recall, and execution-progress tracking, with randomized initial configurations and decision points where similar observations require different actions depending on prior events. We further propose $SEEK$, a framework combining three complementary memory mechanisms to retain historical evidence and track execution state. Evaluations reveal substantial limitations in existing policies on HIDE, while memory augmentation improves task success in both simulation and real-world experiments. Individual mechanisms benefit some tasks but can degrade others; their combination achieves the highest average success rate on HIDE among the evaluated configurations. These findings highlight the importance of maintaining internal representations of hidden task states and matching memory design to task-specific information requirements.
| Comments: | Project page: this https URL |
| Subjects: | Robotics (cs.RO) |
| Cite as: | arXiv:2609.38886 [cs.RO] |
| (or arXiv:2609.38886v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2609.38886 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yansong Shi [view email]
[v1]
Wed, 30 Sep 2026 03:35:00 UTC (5,203 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org