用可学习记忆增强机器人长时序操作能力，解决复杂任务中的非马尔可夫问题。
Beyond Short-Horizon: VQ-Memory for Robust Long-Horizon Manipulation in Non-Markovian Simulation Benchmarks
- 设计基于LLM的规则生成框架，构建含多阶段推理的长时序操作任务
- 引入向量量化记忆模块，实现对过往状态的轻量级、高鲁棒性编码
- 适用于需长期规划的复杂物体操作，尤其适合视觉-语言-动作模型
真实机器人数据采集成本高昂，促使仿真成为可扩展的评估与数据生成平台。然而现有基准多集中于简单操作任务（如拾取放置），难以体现真实任务的非马尔可夫特性及复杂机械交互。为此，我们提出RuleSafe——一个基于可扩展的LLM辅助仿真框架构建的关节物体操作基准。该基准包含具有多种解锁机制（如钥匙锁、密码锁、逻辑锁）的安全箱，需不同阶段的推理与操作策略。这些由LLM生成的规则构造出非马尔可夫且长时序的任务，要求时间建模与记忆推理。我们进一步提出VQ-Memory，一种紧凑且结构化的时序表示，利用向量量化变分自编码器（VQ-VAEs）将过去本体感知状态编码为离散潜在标记。该表示在过滤低层噪声的同时保留高层任务阶段上下文，为现有视觉-语言-动作模型（VLA）提供轻量但鲁棒的时间线索。大量实验表明，VQ-Memory在先进VLA模型与扩散策略上均显著提升长时序规划性能，增强对未见配置的泛化能力，并降低计算开销。项目主页：vqmemory.github.io
原文摘要 · Abstract (English)
The high cost of collecting real-robot data has made robotic simulation a scalable platform for both evaluation and data generation. Yet most existing benchmarks concentrate on simple manipulation tasks such as pick-and-place, failing to capture the non-Markovian characteristics of real-world tasks and the complexity of articulated object interactions. To address this limitation, we present RuleSafe, a new articulated manipulation benchmark built upon a scalable LLM-aided simulation framework. RuleSafe features safes with diverse unlocking mechanisms, such as key locks, password locks, and logic locks, which require different multi-stage reasoning and manipulation strategies. These LLM-generated rules produce non-Markovian and long-horizon tasks that require temporal modeling and memory-based reasoning. We further propose VQ-Memory, a compact and structured temporal representation that uses vector-quantized variational autoencoders (VQ-VAEs) to encode past proprioceptive states into discrete latent tokens. This representation filters low-level noise while preserving high-level task-phase context, providing lightweight yet robust temporal cues that are compatible with existing Vision-Language-Action models (VLA). Extensive experiments on state-of-the-art VLA models and diffusion policies show that VQ-Memory consistently improves long-horizon planning, enhances generalization to unseen configurations, and enables more efficient manipulation with reduced computational cost. Project page: vqmemory.github.io
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。