融合深度不确定性，实现高精度实时立体建图与定位
Uncertainty-Aware Visual-Inertial SLAM with Volumetric Occupancy Mapping
- 用深度神经网络预测深度及不确定性，融合多基线视觉信息
- 不确定性传播至占据概率与子地图对齐，提升全局一致性
- 支持机器人规划的实时体积占据建图，性能超越现有方法
本文提出一种紧耦合的视觉惯性同时定位与建图方法，融合稀疏重投影误差、惯性测量单元预积分和相对位姿因子，以及稠密体积占据映射。深度预测来自深度神经网络，以全概率方式融合。方法严格考虑不确定性：首先，不仅使用机器人双目相机的深度与不确定性预测，还进一步概率融合运动双目技术，在多种基线范围内提供深度信息，显著提升建图精度。其次，预测的深度不确定性不仅传播至占据概率，还进入生成的稠密子地图间的对齐因子，进入概率非线性最小二乘估计器。该子地图表示在大尺度下保持全局几何一致性。方法在两个基准数据集上充分评估，定位与建图精度超过现有最先进水平，同时提供可直接用于下游机器人规划与控制的实时体积占据信息。
原文摘要 · Abstract (English)
We propose visual-inertial simultaneous localization and mapping that tightly couples sparse reprojection errors, inertial measurement unit pre-integrals, and relative pose factors with dense volumetric occupancy mapping. Hereby depth predictions from a deep neural network are fused in a fully probabilistic manner. Specifically, our method is rigorously uncertainty-aware: first, we use depth and uncertainty predictions from a deep network not only from the robot's stereo rig, but we further probabilistically fuse motion stereo that provides depth information across a range of baselines, therefore drastically increasing mapping accuracy. Next, predicted and fused depth uncertainty propagates not only into occupancy probabilities but also into alignment factors between generated dense submaps that enter the probabilistic nonlinear least squares estimator. This submap representation offers globally consistent geometry at scale. Our method is thoroughly evaluated in two benchmark datasets, resulting in localization and mapping accuracy that exceeds the state of the art, while simultaneously offering volumetric occupancy directly usable for downstream robotic planning and control in real-time.
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。