Teaching Robots to Say 'I Don't Know' : SENTINEL for Uncertainty-Aware SLAM
教机器人说‘我不知道’:用于不确定性感知SLAM的SENTINEL
机构 * University of California, Berkeley(加州大学伯克利分校) ; Stanford University(斯坦福大学)
AI总结 提出SENTINEL框架,通过几何扫描统计和跨模态深度一致性为低成本2D LiDAR提供无训练、无标签的可靠性评分,拒绝损坏扫描并回退到轮式里程计,防止SLAM无声损坏。
Comments 6 pages, 10 figures, 3 tables, This paper was accepted at Uncertainty in Open-World Robotics Workshop in conjunction with Internation conference of robotics and automation (ICRA 2026)