外观
论文arXiv 2609.304951 个月前
面向动态环境中高效安全导航的记忆感知多传感器感知
原文链接：Memory-Aware Multi-Sensor Perception for Efficient and Safe Navigation in Dynamic Environments（arXiv 2609.30495 · 发布日期：2026-09-24）
Memory-Aware Multi-Sensor Perception for Efficient and Safe Navigation in Dynamic Environments
提出融合LiDAR与RGB感知、在线距离场表示学习和阶段自适应MCBF-QP的导航框架，并在复杂室内外环境验证。
核心要点
- 面向未知环境自主导航，需兼顾有效感知、持久环境表示、避碰与朝目标推进。
- 框架融合LiDAR和RGB感知，学习在线距离场表示，并采用阶段自适应MCBF-QP控制。
- 方法可持久表示静态设施并跟踪动态障碍，使控制器利用已观测几何绕障。
- 实验显示在复杂室内外环境中提升导航效率和到达目标表现，同时保持避碰。
验证范围与局限：验证范围为复杂室内外环境中的狭窄通道和动态障碍物周边导航。
英文摘要 (Abstract)
Autonomous navigation in previously unseen environments requires effective perception, persistent environmental representation, and collision avoidance while maintaining progress toward a goal. Existing perception-based methods often rely on prior maps or short-horizon observations, limiting their ability to exploit previously observed structure. We propose a memory-aware multi-sensor navigation framework that integrates LiDAR and RGB perception, online distance-field representation learning, and a stage-adaptive Modulated Control Barrier Function Quadratic Program (MCBF-QP). The framework persistently represents static infrastructure while tracking dynamic obstacles, enabling the MCBF-QP controller to exploit previously observed geometry for obstacle circumvention and adapt its safety constraints and guidance to local conditions. Experiments in complex indoor and outdoor environments demonstrate improved navigation efficiency and goal-reaching performance while maintaining collision avoidance in narrow passages and around dynamic obstacles.
作者：Jiahuan Li, Yifan Xue, Yifei Li, Shubhodeep Shiv Aditya, Nadia Figueroa
来源
本页事实对应的公开页面，以原文为准。