让机器人在动态环境中精准导航，靠的是会自我修正的智能感知系统。
Learning to Evolve: Multi-modal Interactive Fields for Robust Humanoid Navigation in Dynamic Environments
- 构建多模态交互场，融合感知与适应，实现动态环境下的稳定记忆
- 真实办公室测试中重定位成功率从12%提升至94%，内存减少91.4%
- 适合需要高可靠导航的仿人机器人研发与部署场景
仿人机器人在动态环境中实现安全、面向操作的导航，需具备在步态引起的感知畸变、环境变化及交互级几何安全约束下仍可靠的场景记忆。现有语义地图与场景图系统难以直接应用，因其常假设相机轨迹稳定、环境静态或物体几何粗糙。本文提出多模态交互场（MIF），一种面向仿人机器人的系统，整合了置信度感知的语义3D高斯泼溅、差异触发的空间记忆更新，以及闭环感知-适应管道内的任务驱动几何重建。MIF耦合三个场：抗不确定性3DGS外观场抑制步态导致的模糊，空间场维持拓扑记忆，几何场支持操作前的交互姿态安全（IPS）。引入差异检测得分以区分步态引起的伪阳性变化与持久变化，仅更新局部不一致区域。在真实动态办公室环境中的Unitree-G1机器人上，相比静态场景图记忆，MIF将非静态环境下的重定位成功率从12%提升至94%，并通过特征蒸馏将语义记忆占用减少91.4%，支持实际在线运行。项目页与代码：https://ziya-jiang.github.io/MIF-homepage/
原文摘要 · Abstract (English)
Safe manipulation-oriented navigation for humanoid robots requires scene memory that remains reliable under locomotion-induced perceptual distortion, environmental changes, and interaction-level geometric safety constraints. Existing semantic mapping and scene-graph systems are difficult to deploy directly in this setting because they often assume stable camera trajectories, static environments, or coarse object geometry. We introduce the Multi-modal Interactive Field (MIF), a humanoid-oriented system that integrates confidence-aware semantic 3D Gaussian Splatting, discrepancy-triggered spatial memory updates, and task-driven geometric reconstruction within a closed-loop perception-adaptation pipeline. MIF couples three fields: an uncertainty-aware 3DGS Appearance Field that suppresses gait-induced blur, a Spatial Field that maintains topological memory, and a Geometry Field that supports Interaction Pose Safety (IPS) before manipulation. A discrepancy detection score is introduced to separate locomotion-induced false-positive changes from persistent changes and updates only locally inconsistent regions. On a Unitree-G1 humanoid in a real dynamic office, MIF improves relocation success in non-static environments from 12% to 94% compared with static scene-graph memory, while reducing semantic memory footprint by 91.4% through feature distillation for practical online operation. Project page and code: https://ziya-jiang.github.io/MIF-homepage/
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。