Autonomous Exploration, Reconstruction, and Surveillance of 3D Environments Aided by Deep Learning
Autonomous Exploration, Reconstruction, and Surveillance of 3D Environments Aided by Deep Learning
复制标题
DOI：
10.1109/icra.2019.8794426
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Louis Ly;Y. Tsai
中科院分区：
文献类型：
--
作者：
Louis Ly;Y. Tsai
我们提出了一个贪婪和监督学习方法的可行性为基础的探索，重建和监视。使用水平集表示，我们训练卷积神经网络来确定最大化可见性的Vantage位置。我们表明，这种方法大大降低了在线计算成本，并确定了一个小的Vantage点，解决了这个问题。这使我们能够有效地生成复杂3D环境的高分辨率和拓扑准确的地图。与传统的下一个最佳视图和基于前沿的策略不同，该方法在评估潜在Vantage点的同时考虑了几何先验。虽然现有的深度学习方法专注于避障和本地导航，但我们的方法旨在为更全局的探索问题找到接近最优的解决方案。我们在2D和3D城市环境中进行了逼真的模拟。
We propose a greedy and supervised learning approach for visibility-based exploration, reconstruction and surveillance. Using a level set representation, we train a convolutional neural network to determine vantage points that maximize visibility. We show that this method drastically reduces the on-line computational cost and determines a small set of vantage points that solve the problem. This enables us to efficiently produce highly-resolved and topologically accurate maps of complex 3D environments. Unlike traditional next-best-view and frontier-based strategies, the proposed method accounts for geometric priors while evaluating potential vantage points. While existing deep learning approaches focus on obstacle avoidance and local navigation, our method aims at finding near-optimal solutions to the more global exploration problem. We present realistic simulations on 2D and 3D urban environments.