用类脑记忆机制让机器人导航更懂长期路径规划
BIT-Nav: Brain-Inspired Trajectory Memory for Embodied Navigation
- 模仿海马体编码方式，用双向GRU学习动作与位姿序列
- 在100+步长的导航任务中，成功率提升12.3%（从68.5%到80.8%）
- 仅增加一个记忆令牌，适合部署在轻量级视觉语言模型中
具身导航中的视觉语言模型依赖从不断增长的轨迹历史中选取固定数量的帧。随着任务延长，这种选择变得越来越稀疏，但先前研究显示将帧数从8增加到64并未带来精度提升，表明瓶颈不在帧的数量，而在表示本身。稀疏帧选择无法捕捉长期推理所需的结构化行为信号：转向模式、累积位移和路径拓扑。我们提出BIT-Nav（脑启发式轨迹记忆用于导航），一种为冻结的视觉语言模型导航流程添加紧凑可学习轨迹记忆的框架。受海马体路径整合机制启发，空间经验被压缩为结构化的情景痕迹，而非原始感官重放。BIT-Nav通过多正例InfoNCE对比目标，在共享相同行为意图的轨迹前缀上训练双向GRU编码器，处理动作和相对位姿序列。所得嵌入通过轻量MLP投影至VLM标记空间，并作为单个记忆标记在每个决策步骤注入，使模型在不增加令牌成本的前提下，始终获得结构化运动历史的条件信息。
原文摘要 · Abstract (English)
Vision-Language Models (VLMs) for embodied navigation rely on selecting a fixed number of frames from a growing trajectory history. As episodes extend, this selection grows increasingly sparse, yet prior work shows no accuracy gain when scaling from 8 to 64 frames, suggesting the bottleneck is not frame quantity but the representation itself. Sparse frame selection cannot capture the structured behavioral signal that long-horizon reasoning requires: turning patterns, cumulative displacement, and path topology. We introduce BIT-Nav (Brain-Inspired Trajectory Memory for Navigation), a framework that augments frozen VLM navigation pipelines with a compact learned trajectory memory. Motivated by hippocampal path integration, where spatial experience is compressed into structured episodic traces rather than stored as raw sensory replay, BIT-Nav trains a Bi-GRU encoder over action and relative pose sequences via a multi-positive InfoNCE contrastive objective on trajectory prefixes sharing the same behavioral intent. The resulting embedding is projected into the VLM token space via a lightweight MLP and injected as a single memory token at each decision step, conditioning the model on structured motion history at constant token cost regardless of episode length
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。