GRADE：使用 Isaac Sim 为机器人研究生成逼真且动态的环境
GRADE: Generating Realistic And Dynamic Environments for Robotics Research with Isaac Sim
AI总结：
提出基于 NVIDIA Isaac Sim 的 GRADE 框架，通过生成逼真动态环境、收集合成数据集并训练模型以缩小仿真到现实差距，同时基准测试动态 V-SLAM 算法揭示其局限性。
摘要：
合成数据和新颖的渲染技术极大地影响了计算机视觉研究中的任务，如目标跟踪和人体姿态估计。然而，由于大多数仿真框架的局限性，包括缺乏底层软件控制和灵活性、缺乏 Robot Operating System 集成、逼真的物理效果或照片级真实感，机器人学研究在利用这些技术方面一直滞后。这阻碍了（视觉）感知研究的进展，例如在自主机器人领域，尤其是在动态环境中。例如，视觉同步定位与建图（V-SLAM）大多是在静态环境中被动开发的，并且由于逼真地模拟动态世界的困难以及巨大的仿真到现实差距，仅在少数预录制的动态数据集上进行了评估。为了应对这些挑战，我们提出了 GRADE（Generating Realistic and Dynamic Environments），这是一个基于 NVIDIA Isaac Sim 构建的高度可定制框架。我们利用 Isaac 的渲染能力和底层 API 来填充和控制仿真、收集真值数据，并测试在线和离线方法。重要的是，我们引入了一种新方法，可以在物理启用的仿真中精确重复已记录的实验，同时允许环境和仿真发生变化。接下来，我们使用飞行无人机在动态环境中收集了一个包含丰富标注视频的合成数据集。利用该数据集，我们训练了用于人类的检测和分割模型，缩小了仿真到现实的差距。最后，我们对最先进的动态 V-SLAM 算法进行了基准测试，揭示了它们较短的跟踪时间和低泛化能力。我们还首次表明，性能最佳的深度学习模型并未实现最佳的 SLAM 性能。代码和数据已在 https://grade.is.tue.mpg.de 作为开源提供。
英文摘要：
Synthetic data and novel rendering techniques have greatly influenced computer vision research in tasks like target tracking and human pose estimation. However, robotics research has lagged behind in leveraging it due to the limitations of most simulation frameworks, including the lack of low-level software control and flexibility, Robot Operating System integration, realistic physics, or photorealism. This hindered progress in (visual-)perception research, e.g. in autonomous robotics, especially in dynamic environments. Visual Simultaneous Localization and Mapping (V-SLAM), for instance, has been mostly developed passively, in static environments, and evaluated on few pre-recorded dynamic datasets due to the difficulties of realistically simulating dynamic worlds and the huge sim-to-real gap. To address these challenges, we present GRADE (Generating Realistic and Dynamic Environments), a highly customizable framework built upon NVIDIA Isaac Sim. We leverage Isaac's rendering capabilities and low-level APIs to populate and control the simulation, collect ground-truth data, and test online and offline approaches. Importantly, we introduce a new way to precisely repeat a recorded experiment within a physically enabled simulation while allowing environmental and simulation changes. Next, we collect a synthetic dataset of richly annotated videos in dynamic environments with a flying drone. Using that, we train detection and segmentation models for humans, closing the syn-to-real gap. Finally, we benchmark state-of-the-art dynamic V-SLAM algorithms, revealing their short tracking times and low generalization capabilities. We also show for the first time that the top-performing deep learning models do not achieve the best SLAM performance. Code and data are provided as open-source at https://grade.is.tue.mpg.de.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
