用大模型自动简化杂乱场景，让机器人更聪明地抓取物品。
LENS: LLM-guided Environment Simplification for Planning and Control in Clutter
- 大模型实时分析任务进度，动态合并或删除物体来简化场景
- 在多种复杂场景中提升经典规划与控制算法性能
- 无需人工设计，可直接接入现有机器人系统
尽管通用机器人操作取得进展，现实中的多物体杂乱环境仍难以处理。问题复杂度随物体数量、碰撞和不可预测的接触物理而上升，且存在干扰物与任务模糊性。当前有效场景抽象依赖大量特定任务的手动工程，难以扩展且难以调整。本文提出 LENS：一种即插即用的解决方案，可在现有规划与控制框架上自动生成场景与任务相关的动态抽象。LENS 通过闭合环路，根据任务进展合并（如堆叠物体）或剪枝（如远距离物体）场景实体，生成去杂乱的抽象表示。这些动态、任务相关的抽象具有高度适应性且易于使用。实验表明，LENS 在多种高度杂乱的操作场景中，提升了经典规划、基于模型的控制以及视觉-语言-动作模型的表现。项目网站：https://lens-2026.github.io/。
原文摘要 · Abstract (English)
Despite recent advances in general-purpose robotic manipulation, real-world multi-object clutter remains challenging to handle for today's prevalent approaches. The problem scales in complexity due to more objects and collisions, more unpredictable contact physics, distractors, and task ambiguity. Bridging this gap to real-world deployment requires effective scene abstractions; yet today, producing such abstractions requires extensive task-specific manual engineering, which does not scale. These abstractions are costly to generate and difficult to adjust or fine-tune. We instead propose a plug-and-play fix to automatically generate scene-specific, task-specific, adaptively updating abstractions on top of existing planning and control stacks. LLM-guided Environment Simplification (LENS) produces a de-cluttered abstracted scene representation by merging (e.g., stacked objects) or pruning (e.g., distant objects) scene entities in a closed loop in response to task progress. These dynamic, task-relevant abstractions are versatile and easy to use. In our experiments, we show that LENS improves classical planning, model-based control, and a vision-language-action model, across a diverse set of highly cluttered manipulation scenes. Project website: https://lens-2026.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。