用真实感重建环境训练机器人定位模型，提升室内导航精度。
Real World Robotic Exploration using Deep Neural Networks Trained in Photorealistic Reconstructed Environments
- 改进损失函数融合位置与旋转误差，增强对视觉混淆的鲁棒性。
- 定位误差降低9.64%（位置）和2.99%（姿态），达0.11m/0.89°。
- 仅需330秒拍摄图像即可训练，适合快速部署到任意室内场景。
本文改进了基于视觉信息（RGB图像）确定机器人位姿的深度神经网络方法，在不增加训练难度的前提下提升了定位性能。通过在损失函数中显式结合位置与旋转误差，增强了对感知歧义的鲁棒性。在室内场景中，相比原始网络，中位位置误差减少9.64%，中位旋转误差减少2.99%。利用摄影测量数据构建带位姿标注的数据集，使模型可在局部环境上训练，实现0.11m的位置精度和0.89度的姿态精度。该模型构成实时导航算法基础，并在TurtleBot上验证。本工作提出完整流程：仅需采集330秒内拍摄的图像，即可为任意真实室内场景构建鲁棒导航系统。
原文摘要 · Abstract (English)
In this work, an existing deep neural network approach for determining a robot's pose from visual information (RGB images) is modified, improving its localization performance without impacting its ease of training. Explicitly, the network's loss function is extended in a manner which intuitively combines the positional and rotational error in order to increase robustness to perceptual aliasing. An improvement in the localization accuracy for indoor scenes is observed: with decreases of up to 9.64% and 2.99% in the median positional and rotational error respectively, when compared to the unmodified network. Additionally, photogrammetry data is used to produce a pose-labelled dataset which allows the above model to be trained on a local environment, resulting in localization accuracies of 0.11m & 0.89 degrees. This trained model forms the basis of a navigation algorithm, which is tested in real-time on a TurtleBot (a wheeled robotic device). As such, this work introduces a full pipeline for creating a robust navigational algorithm for any given real world indoor scene; the only requirement being a collection of images from the scene, which can be captured in as little as 330 seconds of
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。