让机器人通过移动物体解锁路径，实现零样本持续导航
CoReLIN: Constraint-based Reasoning for Zero-shot Lifelong Interactive Navigation
- 基于场景图与约束推理，决定移什么、放哪、往哪走
- 在ProcTHOR-10k上比基线高16%的长期效率得分
- 适合需要持续交互与环境适应的智能机器人任务
传统机器人导航假设起点到目标间无阻碍路径。但在真实环境中，杂物可能堵死所有通路。本文提出「持续交互导航」任务：具备操作能力的移动机器人需移动障碍物以开辟路径，并完成一系列物品放置任务。由于环境改变会持续存在，当前决策影响未来可导航性与任务难度。我们提出CoReLIN，一种由大模型驱动的约束式推理框架，结合主动感知。CoReLIN基于结构化场景图判断应移动的物体、放置位置及下一步探索方向，由标准运动规划器执行可靠的导航与操作动作。为评估长时序行为，引入两个新指标——长期效率得分（LES），综合成功度、执行效率与环境优化程度，由“杂物代价”衡量。在ProcTHOR-10k数据集上，CoReLIN在标准指标与LES上均优于最佳基线16%，并成功迁移到真实硬件平台。
原文摘要 · Abstract (English)
Robot navigation typically assumes an obstacle-free path exists between start and goal. In real environments, however, clutter may block all routes. We introduce Lifelong Interactive Navigation, where a mobile robot with manipulation capabilities must move objects to forge paths and complete sequential object-placement tasks. Because environment modifications persist, decisions impact future navigability and task difficulty. We propose CoReLIN, an LLM-driven constraint-based reasoning framework with active perception. CoReLIN reasons over a structured scene graph to decide which objects to relocate, where to place them, and where to explore next. A standard motion planner executes reliable navigation and manipulation primitives. To evaluate long-horizon behavior, we introduce 2 new metrics - Long-term Efficiency Score (LES), a unified metric capturing success, execution efficiency, environment optimality, captured by Price of Clutter. In ProcTHOR-10k, CoReLIN outperforms best baseline by 16% under standard metrics and LES, and transfers to real-world hardware.
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。